[www-releases] r275092 - Add 3.8.1 documentation
Tom Stellard via llvm-commits
llvm-commits at lists.llvm.org
Mon Jul 11 12:36:15 PDT 2016
Added: www-releases/trunk/3.8.1/docs/tutorial/LangImpl6.html
URL: http://llvm.org/viewvc/llvm-project/www-releases/trunk/3.8.1/docs/tutorial/LangImpl6.html?rev=275092&view=auto
==============================================================================
--- www-releases/trunk/3.8.1/docs/tutorial/LangImpl6.html (added)
+++ www-releases/trunk/3.8.1/docs/tutorial/LangImpl6.html Mon Jul 11 14:36:11 2016
@@ -0,0 +1,1878 @@
+
+<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN"
+ "http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd">
+
+
+<html xmlns="http://www.w3.org/1999/xhtml">
+ <head>
+ <meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
+
+ <title>6. Kaleidoscope: Extending the Language: User-defined Operators — LLVM 3.8 documentation</title>
+
+ <link rel="stylesheet" href="../_static/llvm-theme.css" type="text/css" />
+ <link rel="stylesheet" href="../_static/pygments.css" type="text/css" />
+
+ <script type="text/javascript">
+ var DOCUMENTATION_OPTIONS = {
+ URL_ROOT: '../',
+ VERSION: '3.8',
+ COLLAPSE_INDEX: false,
+ FILE_SUFFIX: '.html',
+ HAS_SOURCE: true
+ };
+ </script>
+ <script type="text/javascript" src="../_static/jquery.js"></script>
+ <script type="text/javascript" src="../_static/underscore.js"></script>
+ <script type="text/javascript" src="../_static/doctools.js"></script>
+ <link rel="top" title="LLVM 3.8 documentation" href="../index.html" />
+ <link rel="up" title="LLVM Tutorial: Table of Contents" href="index.html" />
+ <link rel="next" title="7. Kaleidoscope: Extending the Language: Mutable Variables" href="LangImpl7.html" />
+ <link rel="prev" title="5. Kaleidoscope: Extending the Language: Control Flow" href="LangImpl5.html" />
+<style type="text/css">
+ table.right { float: right; margin-left: 20px; }
+ table.right td { border: 1px solid #ccc; }
+</style>
+
+ </head>
+ <body>
+<div class="logo">
+ <a href="../index.html">
+ <img src="../_static/logo.png"
+ alt="LLVM Logo" width="250" height="88"/></a>
+</div>
+
+ <div class="related">
+ <h3>Navigation</h3>
+ <ul>
+ <li class="right" style="margin-right: 10px">
+ <a href="../genindex.html" title="General Index"
+ accesskey="I">index</a></li>
+ <li class="right" >
+ <a href="LangImpl7.html" title="7. Kaleidoscope: Extending the Language: Mutable Variables"
+ accesskey="N">next</a> |</li>
+ <li class="right" >
+ <a href="LangImpl5.html" title="5. Kaleidoscope: Extending the Language: Control Flow"
+ accesskey="P">previous</a> |</li>
+ <li><a href="http://llvm.org/">LLVM Home</a> | </li>
+ <li><a href="../index.html">Documentation</a>»</li>
+
+ <li><a href="index.html" accesskey="U">LLVM Tutorial: Table of Contents</a> »</li>
+ </ul>
+ </div>
+
+
+ <div class="document">
+ <div class="documentwrapper">
+ <div class="body">
+
+ <div class="section" id="kaleidoscope-extending-the-language-user-defined-operators">
+<h1>6. Kaleidoscope: Extending the Language: User-defined Operators<a class="headerlink" href="#kaleidoscope-extending-the-language-user-defined-operators" title="Permalink to this headline">¶</a></h1>
+<div class="contents local topic" id="contents">
+<ul class="simple">
+<li><a class="reference internal" href="#chapter-6-introduction" id="id1">Chapter 6 Introduction</a></li>
+<li><a class="reference internal" href="#user-defined-operators-the-idea" id="id2">User-defined Operators: the Idea</a></li>
+<li><a class="reference internal" href="#user-defined-binary-operators" id="id3">User-defined Binary Operators</a></li>
+<li><a class="reference internal" href="#user-defined-unary-operators" id="id4">User-defined Unary Operators</a></li>
+<li><a class="reference internal" href="#kicking-the-tires" id="id5">Kicking the Tires</a></li>
+<li><a class="reference internal" href="#full-code-listing" id="id6">Full Code Listing</a></li>
+</ul>
+</div>
+<div class="section" id="chapter-6-introduction">
+<h2><a class="toc-backref" href="#id1">6.1. Chapter 6 Introduction</a><a class="headerlink" href="#chapter-6-introduction" title="Permalink to this headline">¶</a></h2>
+<p>Welcome to Chapter 6 of the “<a class="reference external" href="index.html">Implementing a language with
+LLVM</a>” tutorial. At this point in our tutorial, we now
+have a fully functional language that is fairly minimal, but also
+useful. There is still one big problem with it, however. Our language
+doesn’t have many useful operators (like division, logical negation, or
+even any comparisons besides less-than).</p>
+<p>This chapter of the tutorial takes a wild digression into adding
+user-defined operators to the simple and beautiful Kaleidoscope
+language. This digression now gives us a simple and ugly language in
+some ways, but also a powerful one at the same time. One of the great
+things about creating your own language is that you get to decide what
+is good or bad. In this tutorial we’ll assume that it is okay to use
+this as a way to show some interesting parsing techniques.</p>
+<p>At the end of this tutorial, we’ll run through an example Kaleidoscope
+application that <a class="reference external" href="#kicking-the-tires">renders the Mandelbrot set</a>. This gives an
+example of what you can build with Kaleidoscope and its feature set.</p>
+</div>
+<div class="section" id="user-defined-operators-the-idea">
+<h2><a class="toc-backref" href="#id2">6.2. User-defined Operators: the Idea</a><a class="headerlink" href="#user-defined-operators-the-idea" title="Permalink to this headline">¶</a></h2>
+<p>The “operator overloading” that we will add to Kaleidoscope is more
+general than languages like C++. In C++, you are only allowed to
+redefine existing operators: you can’t programatically change the
+grammar, introduce new operators, change precedence levels, etc. In this
+chapter, we will add this capability to Kaleidoscope, which will let the
+user round out the set of operators that are supported.</p>
+<p>The point of going into user-defined operators in a tutorial like this
+is to show the power and flexibility of using a hand-written parser.
+Thus far, the parser we have been implementing uses recursive descent
+for most parts of the grammar and operator precedence parsing for the
+expressions. See <a class="reference external" href="LangImpl2.html">Chapter 2</a> for details. Without
+using operator precedence parsing, it would be very difficult to allow
+the programmer to introduce new operators into the grammar: the grammar
+is dynamically extensible as the JIT runs.</p>
+<p>The two specific features we’ll add are programmable unary operators
+(right now, Kaleidoscope has no unary operators at all) as well as
+binary operators. An example of this is:</p>
+<div class="highlight-python"><div class="highlight"><pre># Logical unary not.
+def unary!(v)
+ if v then
+ 0
+ else
+ 1;
+
+# Define > with the same precedence as <.
+def binary> 10 (LHS RHS)
+ RHS < LHS;
+
+# Binary "logical or", (note that it does not "short circuit")
+def binary| 5 (LHS RHS)
+ if LHS then
+ 1
+ else if RHS then
+ 1
+ else
+ 0;
+
+# Define = with slightly lower precedence than relationals.
+def binary= 9 (LHS RHS)
+ !(LHS < RHS | LHS > RHS);
+</pre></div>
+</div>
+<p>Many languages aspire to being able to implement their standard runtime
+library in the language itself. In Kaleidoscope, we can implement
+significant parts of the language in the library!</p>
+<p>We will break down implementation of these features into two parts:
+implementing support for user-defined binary operators and adding unary
+operators.</p>
+</div>
+<div class="section" id="user-defined-binary-operators">
+<h2><a class="toc-backref" href="#id3">6.3. User-defined Binary Operators</a><a class="headerlink" href="#user-defined-binary-operators" title="Permalink to this headline">¶</a></h2>
+<p>Adding support for user-defined binary operators is pretty simple with
+our current framework. We’ll first add support for the unary/binary
+keywords:</p>
+<div class="highlight-c++"><div class="highlight"><pre><span class="k">enum</span> <span class="n">Token</span> <span class="p">{</span>
+ <span class="p">...</span>
+ <span class="c1">// operators</span>
+ <span class="n">tok_binary</span> <span class="o">=</span> <span class="o">-</span><span class="mi">11</span><span class="p">,</span>
+ <span class="n">tok_unary</span> <span class="o">=</span> <span class="o">-</span><span class="mi">12</span>
+<span class="p">};</span>
+<span class="p">...</span>
+<span class="k">static</span> <span class="kt">int</span> <span class="n">gettok</span><span class="p">()</span> <span class="p">{</span>
+<span class="p">...</span>
+ <span class="k">if</span> <span class="p">(</span><span class="n">IdentifierStr</span> <span class="o">==</span> <span class="s">"for"</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">tok_for</span><span class="p">;</span>
+ <span class="k">if</span> <span class="p">(</span><span class="n">IdentifierStr</span> <span class="o">==</span> <span class="s">"in"</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">tok_in</span><span class="p">;</span>
+ <span class="k">if</span> <span class="p">(</span><span class="n">IdentifierStr</span> <span class="o">==</span> <span class="s">"binary"</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">tok_binary</span><span class="p">;</span>
+ <span class="k">if</span> <span class="p">(</span><span class="n">IdentifierStr</span> <span class="o">==</span> <span class="s">"unary"</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">tok_unary</span><span class="p">;</span>
+ <span class="k">return</span> <span class="n">tok_identifier</span><span class="p">;</span>
+</pre></div>
+</div>
+<p>This just adds lexer support for the unary and binary keywords, like we
+did in <a class="reference external" href="LangImpl5.html#lexer-extensions-for-if-then-else">previous chapters</a>. One nice thing
+about our current AST, is that we represent binary operators with full
+generalisation by using their ASCII code as the opcode. For our extended
+operators, we’ll use this same representation, so we don’t need any new
+AST or parser support.</p>
+<p>On the other hand, we have to be able to represent the definitions of
+these new operators, in the “def binary| 5” part of the function
+definition. In our grammar so far, the “name” for the function
+definition is parsed as the “prototype” production and into the
+<tt class="docutils literal"><span class="pre">PrototypeAST</span></tt> AST node. To represent our new user-defined operators
+as prototypes, we have to extend the <tt class="docutils literal"><span class="pre">PrototypeAST</span></tt> AST node like
+this:</p>
+<div class="highlight-c++"><div class="highlight"><pre><span class="c1">/// PrototypeAST - This class represents the "prototype" for a function,</span>
+<span class="c1">/// which captures its argument names as well as if it is an operator.</span>
+<span class="k">class</span> <span class="nc">PrototypeAST</span> <span class="p">{</span>
+ <span class="n">std</span><span class="o">::</span><span class="n">string</span> <span class="n">Name</span><span class="p">;</span>
+ <span class="n">std</span><span class="o">::</span><span class="n">vector</span><span class="o"><</span><span class="n">std</span><span class="o">::</span><span class="n">string</span><span class="o">></span> <span class="n">Args</span><span class="p">;</span>
+ <span class="kt">bool</span> <span class="n">IsOperator</span><span class="p">;</span>
+ <span class="kt">unsigned</span> <span class="n">Precedence</span><span class="p">;</span> <span class="c1">// Precedence if a binary op.</span>
+
+<span class="nl">public:</span>
+ <span class="n">PrototypeAST</span><span class="p">(</span><span class="k">const</span> <span class="n">std</span><span class="o">::</span><span class="n">string</span> <span class="o">&</span><span class="n">name</span><span class="p">,</span> <span class="n">std</span><span class="o">::</span><span class="n">vector</span><span class="o"><</span><span class="n">std</span><span class="o">::</span><span class="n">string</span><span class="o">></span> <span class="n">Args</span><span class="p">,</span>
+ <span class="kt">bool</span> <span class="n">IsOperator</span> <span class="o">=</span> <span class="nb">false</span><span class="p">,</span> <span class="kt">unsigned</span> <span class="n">Prec</span> <span class="o">=</span> <span class="mi">0</span><span class="p">)</span>
+ <span class="o">:</span> <span class="n">Name</span><span class="p">(</span><span class="n">name</span><span class="p">),</span> <span class="n">Args</span><span class="p">(</span><span class="n">std</span><span class="o">::</span><span class="n">move</span><span class="p">(</span><span class="n">Args</span><span class="p">)),</span> <span class="n">IsOperator</span><span class="p">(</span><span class="n">IsOperator</span><span class="p">),</span>
+ <span class="n">Precedence</span><span class="p">(</span><span class="n">Prec</span><span class="p">)</span> <span class="p">{}</span>
+
+ <span class="kt">bool</span> <span class="n">isUnaryOp</span><span class="p">()</span> <span class="k">const</span> <span class="p">{</span> <span class="k">return</span> <span class="n">IsOperator</span> <span class="o">&&</span> <span class="n">Args</span><span class="p">.</span><span class="n">size</span><span class="p">()</span> <span class="o">==</span> <span class="mi">1</span><span class="p">;</span> <span class="p">}</span>
+ <span class="kt">bool</span> <span class="n">isBinaryOp</span><span class="p">()</span> <span class="k">const</span> <span class="p">{</span> <span class="k">return</span> <span class="n">IsOperator</span> <span class="o">&&</span> <span class="n">Args</span><span class="p">.</span><span class="n">size</span><span class="p">()</span> <span class="o">==</span> <span class="mi">2</span><span class="p">;</span> <span class="p">}</span>
+
+ <span class="kt">char</span> <span class="n">getOperatorName</span><span class="p">()</span> <span class="k">const</span> <span class="p">{</span>
+ <span class="n">assert</span><span class="p">(</span><span class="n">isUnaryOp</span><span class="p">()</span> <span class="o">||</span> <span class="n">isBinaryOp</span><span class="p">());</span>
+ <span class="k">return</span> <span class="n">Name</span><span class="p">[</span><span class="n">Name</span><span class="p">.</span><span class="n">size</span><span class="p">()</span><span class="o">-</span><span class="mi">1</span><span class="p">];</span>
+ <span class="p">}</span>
+
+ <span class="kt">unsigned</span> <span class="n">getBinaryPrecedence</span><span class="p">()</span> <span class="k">const</span> <span class="p">{</span> <span class="k">return</span> <span class="n">Precedence</span><span class="p">;</span> <span class="p">}</span>
+
+ <span class="n">Function</span> <span class="o">*</span><span class="n">codegen</span><span class="p">();</span>
+<span class="p">};</span>
+</pre></div>
+</div>
+<p>Basically, in addition to knowing a name for the prototype, we now keep
+track of whether it was an operator, and if it was, what precedence
+level the operator is at. The precedence is only used for binary
+operators (as you’ll see below, it just doesn’t apply for unary
+operators). Now that we have a way to represent the prototype for a
+user-defined operator, we need to parse it:</p>
+<div class="highlight-c++"><div class="highlight"><pre><span class="c1">/// prototype</span>
+<span class="c1">/// ::= id '(' id* ')'</span>
+<span class="c1">/// ::= binary LETTER number? (id, id)</span>
+<span class="k">static</span> <span class="n">std</span><span class="o">::</span><span class="n">unique_ptr</span><span class="o"><</span><span class="n">PrototypeAST</span><span class="o">></span> <span class="n">ParsePrototype</span><span class="p">()</span> <span class="p">{</span>
+ <span class="n">std</span><span class="o">::</span><span class="n">string</span> <span class="n">FnName</span><span class="p">;</span>
+
+ <span class="kt">unsigned</span> <span class="n">Kind</span> <span class="o">=</span> <span class="mi">0</span><span class="p">;</span> <span class="c1">// 0 = identifier, 1 = unary, 2 = binary.</span>
+ <span class="kt">unsigned</span> <span class="n">BinaryPrecedence</span> <span class="o">=</span> <span class="mi">30</span><span class="p">;</span>
+
+ <span class="k">switch</span> <span class="p">(</span><span class="n">CurTok</span><span class="p">)</span> <span class="p">{</span>
+ <span class="nl">default:</span>
+ <span class="k">return</span> <span class="n">ErrorP</span><span class="p">(</span><span class="s">"Expected function name in prototype"</span><span class="p">);</span>
+ <span class="k">case</span> <span class="n">tok_identifier</span>:
+ <span class="n">FnName</span> <span class="o">=</span> <span class="n">IdentifierStr</span><span class="p">;</span>
+ <span class="n">Kind</span> <span class="o">=</span> <span class="mi">0</span><span class="p">;</span>
+ <span class="n">getNextToken</span><span class="p">();</span>
+ <span class="k">break</span><span class="p">;</span>
+ <span class="k">case</span> <span class="n">tok_binary</span>:
+ <span class="n">getNextToken</span><span class="p">();</span>
+ <span class="k">if</span> <span class="p">(</span><span class="o">!</span><span class="n">isascii</span><span class="p">(</span><span class="n">CurTok</span><span class="p">))</span>
+ <span class="k">return</span> <span class="n">ErrorP</span><span class="p">(</span><span class="s">"Expected binary operator"</span><span class="p">);</span>
+ <span class="n">FnName</span> <span class="o">=</span> <span class="s">"binary"</span><span class="p">;</span>
+ <span class="n">FnName</span> <span class="o">+=</span> <span class="p">(</span><span class="kt">char</span><span class="p">)</span><span class="n">CurTok</span><span class="p">;</span>
+ <span class="n">Kind</span> <span class="o">=</span> <span class="mi">2</span><span class="p">;</span>
+ <span class="n">getNextToken</span><span class="p">();</span>
+
+ <span class="c1">// Read the precedence if present.</span>
+ <span class="k">if</span> <span class="p">(</span><span class="n">CurTok</span> <span class="o">==</span> <span class="n">tok_number</span><span class="p">)</span> <span class="p">{</span>
+ <span class="k">if</span> <span class="p">(</span><span class="n">NumVal</span> <span class="o"><</span> <span class="mi">1</span> <span class="o">||</span> <span class="n">NumVal</span> <span class="o">></span> <span class="mi">100</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">ErrorP</span><span class="p">(</span><span class="s">"Invalid precedecnce: must be 1..100"</span><span class="p">);</span>
+ <span class="n">BinaryPrecedence</span> <span class="o">=</span> <span class="p">(</span><span class="kt">unsigned</span><span class="p">)</span><span class="n">NumVal</span><span class="p">;</span>
+ <span class="n">getNextToken</span><span class="p">();</span>
+ <span class="p">}</span>
+ <span class="k">break</span><span class="p">;</span>
+ <span class="p">}</span>
+
+ <span class="k">if</span> <span class="p">(</span><span class="n">CurTok</span> <span class="o">!=</span> <span class="sc">'('</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">ErrorP</span><span class="p">(</span><span class="s">"Expected '(' in prototype"</span><span class="p">);</span>
+
+ <span class="n">std</span><span class="o">::</span><span class="n">vector</span><span class="o"><</span><span class="n">std</span><span class="o">::</span><span class="n">string</span><span class="o">></span> <span class="n">ArgNames</span><span class="p">;</span>
+ <span class="k">while</span> <span class="p">(</span><span class="n">getNextToken</span><span class="p">()</span> <span class="o">==</span> <span class="n">tok_identifier</span><span class="p">)</span>
+ <span class="n">ArgNames</span><span class="p">.</span><span class="n">push_back</span><span class="p">(</span><span class="n">IdentifierStr</span><span class="p">);</span>
+ <span class="k">if</span> <span class="p">(</span><span class="n">CurTok</span> <span class="o">!=</span> <span class="sc">')'</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">ErrorP</span><span class="p">(</span><span class="s">"Expected ')' in prototype"</span><span class="p">);</span>
+
+ <span class="c1">// success.</span>
+ <span class="n">getNextToken</span><span class="p">();</span> <span class="c1">// eat ')'.</span>
+
+ <span class="c1">// Verify right number of names for operator.</span>
+ <span class="k">if</span> <span class="p">(</span><span class="n">Kind</span> <span class="o">&&</span> <span class="n">ArgNames</span><span class="p">.</span><span class="n">size</span><span class="p">()</span> <span class="o">!=</span> <span class="n">Kind</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">ErrorP</span><span class="p">(</span><span class="s">"Invalid number of operands for operator"</span><span class="p">);</span>
+
+ <span class="k">return</span> <span class="n">llvm</span><span class="o">::</span><span class="n">make_unique</span><span class="o"><</span><span class="n">PrototypeAST</span><span class="o">></span><span class="p">(</span><span class="n">FnName</span><span class="p">,</span> <span class="n">std</span><span class="o">::</span><span class="n">move</span><span class="p">(</span><span class="n">ArgNames</span><span class="p">),</span> <span class="n">Kind</span> <span class="o">!=</span> <span class="mi">0</span><span class="p">,</span>
+ <span class="n">BinaryPrecedence</span><span class="p">);</span>
+<span class="p">}</span>
+</pre></div>
+</div>
+<p>This is all fairly straightforward parsing code, and we have already
+seen a lot of similar code in the past. One interesting part about the
+code above is the couple lines that set up <tt class="docutils literal"><span class="pre">FnName</span></tt> for binary
+operators. This builds names like “binary@” for a newly defined “@”
+operator. This then takes advantage of the fact that symbol names in the
+LLVM symbol table are allowed to have any character in them, including
+embedded nul characters.</p>
+<p>The next interesting thing to add, is codegen support for these binary
+operators. Given our current structure, this is a simple addition of a
+default case for our existing binary operator node:</p>
+<div class="highlight-c++"><div class="highlight"><pre><span class="n">Value</span> <span class="o">*</span><span class="n">BinaryExprAST</span><span class="o">::</span><span class="n">codegen</span><span class="p">()</span> <span class="p">{</span>
+ <span class="n">Value</span> <span class="o">*</span><span class="n">L</span> <span class="o">=</span> <span class="n">LHS</span><span class="o">-></span><span class="n">codegen</span><span class="p">();</span>
+ <span class="n">Value</span> <span class="o">*</span><span class="n">R</span> <span class="o">=</span> <span class="n">RHS</span><span class="o">-></span><span class="n">codegen</span><span class="p">();</span>
+ <span class="k">if</span> <span class="p">(</span><span class="o">!</span><span class="n">L</span> <span class="o">||</span> <span class="o">!</span><span class="n">R</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">nullptr</span><span class="p">;</span>
+
+ <span class="k">switch</span> <span class="p">(</span><span class="n">Op</span><span class="p">)</span> <span class="p">{</span>
+ <span class="k">case</span> <span class="sc">'+'</span>:
+ <span class="k">return</span> <span class="n">Builder</span><span class="p">.</span><span class="n">CreateFAdd</span><span class="p">(</span><span class="n">L</span><span class="p">,</span> <span class="n">R</span><span class="p">,</span> <span class="s">"addtmp"</span><span class="p">);</span>
+ <span class="k">case</span> <span class="sc">'-'</span>:
+ <span class="k">return</span> <span class="n">Builder</span><span class="p">.</span><span class="n">CreateFSub</span><span class="p">(</span><span class="n">L</span><span class="p">,</span> <span class="n">R</span><span class="p">,</span> <span class="s">"subtmp"</span><span class="p">);</span>
+ <span class="k">case</span> <span class="sc">'*'</span>:
+ <span class="k">return</span> <span class="n">Builder</span><span class="p">.</span><span class="n">CreateFMul</span><span class="p">(</span><span class="n">L</span><span class="p">,</span> <span class="n">R</span><span class="p">,</span> <span class="s">"multmp"</span><span class="p">);</span>
+ <span class="k">case</span> <span class="sc">'<'</span>:
+ <span class="n">L</span> <span class="o">=</span> <span class="n">Builder</span><span class="p">.</span><span class="n">CreateFCmpULT</span><span class="p">(</span><span class="n">L</span><span class="p">,</span> <span class="n">R</span><span class="p">,</span> <span class="s">"cmptmp"</span><span class="p">);</span>
+ <span class="c1">// Convert bool 0/1 to double 0.0 or 1.0</span>
+ <span class="k">return</span> <span class="n">Builder</span><span class="p">.</span><span class="n">CreateUIToFP</span><span class="p">(</span><span class="n">L</span><span class="p">,</span> <span class="n">Type</span><span class="o">::</span><span class="n">getDoubleTy</span><span class="p">(</span><span class="n">getGlobalContext</span><span class="p">()),</span>
+ <span class="s">"booltmp"</span><span class="p">);</span>
+ <span class="nl">default:</span>
+ <span class="k">break</span><span class="p">;</span>
+ <span class="p">}</span>
+
+ <span class="c1">// If it wasn't a builtin binary operator, it must be a user defined one. Emit</span>
+ <span class="c1">// a call to it.</span>
+ <span class="n">Function</span> <span class="o">*</span><span class="n">F</span> <span class="o">=</span> <span class="n">TheModule</span><span class="o">-></span><span class="n">getFunction</span><span class="p">(</span><span class="n">std</span><span class="o">::</span><span class="n">string</span><span class="p">(</span><span class="s">"binary"</span><span class="p">)</span> <span class="o">+</span> <span class="n">Op</span><span class="p">);</span>
+ <span class="n">assert</span><span class="p">(</span><span class="n">F</span> <span class="o">&&</span> <span class="s">"binary operator not found!"</span><span class="p">);</span>
+
+ <span class="n">Value</span> <span class="o">*</span><span class="n">Ops</span><span class="p">[</span><span class="mi">2</span><span class="p">]</span> <span class="o">=</span> <span class="p">{</span> <span class="n">L</span><span class="p">,</span> <span class="n">R</span> <span class="p">};</span>
+ <span class="k">return</span> <span class="n">Builder</span><span class="p">.</span><span class="n">CreateCall</span><span class="p">(</span><span class="n">F</span><span class="p">,</span> <span class="n">Ops</span><span class="p">,</span> <span class="s">"binop"</span><span class="p">);</span>
+<span class="p">}</span>
+</pre></div>
+</div>
+<p>As you can see above, the new code is actually really simple. It just
+does a lookup for the appropriate operator in the symbol table and
+generates a function call to it. Since user-defined operators are just
+built as normal functions (because the “prototype” boils down to a
+function with the right name) everything falls into place.</p>
+<p>The final piece of code we are missing, is a bit of top-level magic:</p>
+<div class="highlight-c++"><div class="highlight"><pre><span class="n">Function</span> <span class="o">*</span><span class="n">FunctionAST</span><span class="o">::</span><span class="n">codegen</span><span class="p">()</span> <span class="p">{</span>
+ <span class="n">NamedValues</span><span class="p">.</span><span class="n">clear</span><span class="p">();</span>
+
+ <span class="n">Function</span> <span class="o">*</span><span class="n">TheFunction</span> <span class="o">=</span> <span class="n">Proto</span><span class="o">-></span><span class="n">codegen</span><span class="p">();</span>
+ <span class="k">if</span> <span class="p">(</span><span class="o">!</span><span class="n">TheFunction</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">nullptr</span><span class="p">;</span>
+
+ <span class="c1">// If this is an operator, install it.</span>
+ <span class="k">if</span> <span class="p">(</span><span class="n">Proto</span><span class="o">-></span><span class="n">isBinaryOp</span><span class="p">())</span>
+ <span class="n">BinopPrecedence</span><span class="p">[</span><span class="n">Proto</span><span class="o">-></span><span class="n">getOperatorName</span><span class="p">()]</span> <span class="o">=</span> <span class="n">Proto</span><span class="o">-></span><span class="n">getBinaryPrecedence</span><span class="p">();</span>
+
+ <span class="c1">// Create a new basic block to start insertion into.</span>
+ <span class="n">BasicBlock</span> <span class="o">*</span><span class="n">BB</span> <span class="o">=</span> <span class="n">BasicBlock</span><span class="o">::</span><span class="n">Create</span><span class="p">(</span><span class="n">getGlobalContext</span><span class="p">(),</span> <span class="s">"entry"</span><span class="p">,</span> <span class="n">TheFunction</span><span class="p">);</span>
+ <span class="n">Builder</span><span class="p">.</span><span class="n">SetInsertPoint</span><span class="p">(</span><span class="n">BB</span><span class="p">);</span>
+
+ <span class="k">if</span> <span class="p">(</span><span class="n">Value</span> <span class="o">*</span><span class="n">RetVal</span> <span class="o">=</span> <span class="n">Body</span><span class="o">-></span><span class="n">codegen</span><span class="p">())</span> <span class="p">{</span>
+ <span class="p">...</span>
+</pre></div>
+</div>
+<p>Basically, before codegening a function, if it is a user-defined
+operator, we register it in the precedence table. This allows the binary
+operator parsing logic we already have in place to handle it. Since we
+are working on a fully-general operator precedence parser, this is all
+we need to do to “extend the grammar”.</p>
+<p>Now we have useful user-defined binary operators. This builds a lot on
+the previous framework we built for other operators. Adding unary
+operators is a bit more challenging, because we don’t have any framework
+for it yet - lets see what it takes.</p>
+</div>
+<div class="section" id="user-defined-unary-operators">
+<h2><a class="toc-backref" href="#id4">6.4. User-defined Unary Operators</a><a class="headerlink" href="#user-defined-unary-operators" title="Permalink to this headline">¶</a></h2>
+<p>Since we don’t currently support unary operators in the Kaleidoscope
+language, we’ll need to add everything to support them. Above, we added
+simple support for the ‘unary’ keyword to the lexer. In addition to
+that, we need an AST node:</p>
+<div class="highlight-c++"><div class="highlight"><pre><span class="c1">/// UnaryExprAST - Expression class for a unary operator.</span>
+<span class="k">class</span> <span class="nc">UnaryExprAST</span> <span class="o">:</span> <span class="k">public</span> <span class="n">ExprAST</span> <span class="p">{</span>
+ <span class="kt">char</span> <span class="n">Opcode</span><span class="p">;</span>
+ <span class="n">std</span><span class="o">::</span><span class="n">unique_ptr</span><span class="o"><</span><span class="n">ExprAST</span><span class="o">></span> <span class="n">Operand</span><span class="p">;</span>
+
+<span class="nl">public:</span>
+ <span class="n">UnaryExprAST</span><span class="p">(</span><span class="kt">char</span> <span class="n">Opcode</span><span class="p">,</span> <span class="n">std</span><span class="o">::</span><span class="n">unique_ptr</span><span class="o"><</span><span class="n">ExprAST</span><span class="o">></span> <span class="n">Operand</span><span class="p">)</span>
+ <span class="o">:</span> <span class="n">Opcode</span><span class="p">(</span><span class="n">Opcode</span><span class="p">),</span> <span class="n">Operand</span><span class="p">(</span><span class="n">std</span><span class="o">::</span><span class="n">move</span><span class="p">(</span><span class="n">Operand</span><span class="p">))</span> <span class="p">{}</span>
+ <span class="k">virtual</span> <span class="n">Value</span> <span class="o">*</span><span class="n">codegen</span><span class="p">();</span>
+<span class="p">};</span>
+</pre></div>
+</div>
+<p>This AST node is very simple and obvious by now. It directly mirrors the
+binary operator AST node, except that it only has one child. With this,
+we need to add the parsing logic. Parsing a unary operator is pretty
+simple: we’ll add a new function to do it:</p>
+<div class="highlight-c++"><div class="highlight"><pre><span class="c1">/// unary</span>
+<span class="c1">/// ::= primary</span>
+<span class="c1">/// ::= '!' unary</span>
+<span class="k">static</span> <span class="n">std</span><span class="o">::</span><span class="n">unique_ptr</span><span class="o"><</span><span class="n">ExprAST</span><span class="o">></span> <span class="n">ParseUnary</span><span class="p">()</span> <span class="p">{</span>
+ <span class="c1">// If the current token is not an operator, it must be a primary expr.</span>
+ <span class="k">if</span> <span class="p">(</span><span class="o">!</span><span class="n">isascii</span><span class="p">(</span><span class="n">CurTok</span><span class="p">)</span> <span class="o">||</span> <span class="n">CurTok</span> <span class="o">==</span> <span class="sc">'('</span> <span class="o">||</span> <span class="n">CurTok</span> <span class="o">==</span> <span class="sc">','</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">ParsePrimary</span><span class="p">();</span>
+
+ <span class="c1">// If this is a unary operator, read it.</span>
+ <span class="kt">int</span> <span class="n">Opc</span> <span class="o">=</span> <span class="n">CurTok</span><span class="p">;</span>
+ <span class="n">getNextToken</span><span class="p">();</span>
+ <span class="k">if</span> <span class="p">(</span><span class="k">auto</span> <span class="n">Operand</span> <span class="o">=</span> <span class="n">ParseUnary</span><span class="p">())</span>
+ <span class="k">return</span> <span class="n">llvm</span><span class="o">::</span><span class="n">unique_ptr</span><span class="o"><</span><span class="n">UnaryExprAST</span><span class="o">></span><span class="p">(</span><span class="n">Opc</span><span class="p">,</span> <span class="n">std</span><span class="o">::</span><span class="n">move</span><span class="p">(</span><span class="n">Operand</span><span class="p">));</span>
+ <span class="k">return</span> <span class="n">nullptr</span><span class="p">;</span>
+<span class="p">}</span>
+</pre></div>
+</div>
+<p>The grammar we add is pretty straightforward here. If we see a unary
+operator when parsing a primary operator, we eat the operator as a
+prefix and parse the remaining piece as another unary operator. This
+allows us to handle multiple unary operators (e.g. ”!!x”). Note that
+unary operators can’t have ambiguous parses like binary operators can,
+so there is no need for precedence information.</p>
+<p>The problem with this function, is that we need to call ParseUnary from
+somewhere. To do this, we change previous callers of ParsePrimary to
+call ParseUnary instead:</p>
+<div class="highlight-c++"><div class="highlight"><pre><span class="c1">/// binoprhs</span>
+<span class="c1">/// ::= ('+' unary)*</span>
+<span class="k">static</span> <span class="n">std</span><span class="o">::</span><span class="n">unique_ptr</span><span class="o"><</span><span class="n">ExprAST</span><span class="o">></span> <span class="n">ParseBinOpRHS</span><span class="p">(</span><span class="kt">int</span> <span class="n">ExprPrec</span><span class="p">,</span>
+ <span class="n">std</span><span class="o">::</span><span class="n">unique_ptr</span><span class="o"><</span><span class="n">ExprAST</span><span class="o">></span> <span class="n">LHS</span><span class="p">)</span> <span class="p">{</span>
+ <span class="p">...</span>
+ <span class="c1">// Parse the unary expression after the binary operator.</span>
+ <span class="k">auto</span> <span class="n">RHS</span> <span class="o">=</span> <span class="n">ParseUnary</span><span class="p">();</span>
+ <span class="k">if</span> <span class="p">(</span><span class="o">!</span><span class="n">RHS</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">nullptr</span><span class="p">;</span>
+ <span class="p">...</span>
+<span class="p">}</span>
+<span class="c1">/// expression</span>
+<span class="c1">/// ::= unary binoprhs</span>
+<span class="c1">///</span>
+<span class="k">static</span> <span class="n">std</span><span class="o">::</span><span class="n">unique_ptr</span><span class="o"><</span><span class="n">ExprAST</span><span class="o">></span> <span class="n">ParseExpression</span><span class="p">()</span> <span class="p">{</span>
+ <span class="k">auto</span> <span class="n">LHS</span> <span class="o">=</span> <span class="n">ParseUnary</span><span class="p">();</span>
+ <span class="k">if</span> <span class="p">(</span><span class="o">!</span><span class="n">LHS</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">nullptr</span><span class="p">;</span>
+
+ <span class="k">return</span> <span class="nf">ParseBinOpRHS</span><span class="p">(</span><span class="mi">0</span><span class="p">,</span> <span class="n">std</span><span class="o">::</span><span class="n">move</span><span class="p">(</span><span class="n">LHS</span><span class="p">));</span>
+<span class="p">}</span>
+</pre></div>
+</div>
+<p>With these two simple changes, we are now able to parse unary operators
+and build the AST for them. Next up, we need to add parser support for
+prototypes, to parse the unary operator prototype. We extend the binary
+operator code above with:</p>
+<div class="highlight-c++"><div class="highlight"><pre><span class="c1">/// prototype</span>
+<span class="c1">/// ::= id '(' id* ')'</span>
+<span class="c1">/// ::= binary LETTER number? (id, id)</span>
+<span class="c1">/// ::= unary LETTER (id)</span>
+<span class="k">static</span> <span class="n">std</span><span class="o">::</span><span class="n">unique_ptr</span><span class="o"><</span><span class="n">PrototypeAST</span><span class="o">></span> <span class="n">ParsePrototype</span><span class="p">()</span> <span class="p">{</span>
+ <span class="n">std</span><span class="o">::</span><span class="n">string</span> <span class="n">FnName</span><span class="p">;</span>
+
+ <span class="kt">unsigned</span> <span class="n">Kind</span> <span class="o">=</span> <span class="mi">0</span><span class="p">;</span> <span class="c1">// 0 = identifier, 1 = unary, 2 = binary.</span>
+ <span class="kt">unsigned</span> <span class="n">BinaryPrecedence</span> <span class="o">=</span> <span class="mi">30</span><span class="p">;</span>
+
+ <span class="k">switch</span> <span class="p">(</span><span class="n">CurTok</span><span class="p">)</span> <span class="p">{</span>
+ <span class="nl">default:</span>
+ <span class="k">return</span> <span class="n">ErrorP</span><span class="p">(</span><span class="s">"Expected function name in prototype"</span><span class="p">);</span>
+ <span class="k">case</span> <span class="n">tok_identifier</span>:
+ <span class="n">FnName</span> <span class="o">=</span> <span class="n">IdentifierStr</span><span class="p">;</span>
+ <span class="n">Kind</span> <span class="o">=</span> <span class="mi">0</span><span class="p">;</span>
+ <span class="n">getNextToken</span><span class="p">();</span>
+ <span class="k">break</span><span class="p">;</span>
+ <span class="k">case</span> <span class="n">tok_unary</span>:
+ <span class="n">getNextToken</span><span class="p">();</span>
+ <span class="k">if</span> <span class="p">(</span><span class="o">!</span><span class="n">isascii</span><span class="p">(</span><span class="n">CurTok</span><span class="p">))</span>
+ <span class="k">return</span> <span class="n">ErrorP</span><span class="p">(</span><span class="s">"Expected unary operator"</span><span class="p">);</span>
+ <span class="n">FnName</span> <span class="o">=</span> <span class="s">"unary"</span><span class="p">;</span>
+ <span class="n">FnName</span> <span class="o">+=</span> <span class="p">(</span><span class="kt">char</span><span class="p">)</span><span class="n">CurTok</span><span class="p">;</span>
+ <span class="n">Kind</span> <span class="o">=</span> <span class="mi">1</span><span class="p">;</span>
+ <span class="n">getNextToken</span><span class="p">();</span>
+ <span class="k">break</span><span class="p">;</span>
+ <span class="k">case</span> <span class="n">tok_binary</span>:
+ <span class="p">...</span>
+</pre></div>
+</div>
+<p>As with binary operators, we name unary operators with a name that
+includes the operator character. This assists us at code generation
+time. Speaking of, the final piece we need to add is codegen support for
+unary operators. It looks like this:</p>
+<div class="highlight-c++"><div class="highlight"><pre><span class="n">Value</span> <span class="o">*</span><span class="n">UnaryExprAST</span><span class="o">::</span><span class="n">codegen</span><span class="p">()</span> <span class="p">{</span>
+ <span class="n">Value</span> <span class="o">*</span><span class="n">OperandV</span> <span class="o">=</span> <span class="n">Operand</span><span class="o">-></span><span class="n">codegen</span><span class="p">();</span>
+ <span class="k">if</span> <span class="p">(</span><span class="o">!</span><span class="n">OperandV</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">nullptr</span><span class="p">;</span>
+
+ <span class="n">Function</span> <span class="o">*</span><span class="n">F</span> <span class="o">=</span> <span class="n">TheModule</span><span class="o">-></span><span class="n">getFunction</span><span class="p">(</span><span class="n">std</span><span class="o">::</span><span class="n">string</span><span class="p">(</span><span class="s">"unary"</span><span class="p">)</span><span class="o">+</span><span class="n">Opcode</span><span class="p">);</span>
+ <span class="k">if</span> <span class="p">(</span><span class="o">!</span><span class="n">F</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">ErrorV</span><span class="p">(</span><span class="s">"Unknown unary operator"</span><span class="p">);</span>
+
+ <span class="k">return</span> <span class="n">Builder</span><span class="p">.</span><span class="n">CreateCall</span><span class="p">(</span><span class="n">F</span><span class="p">,</span> <span class="n">OperandV</span><span class="p">,</span> <span class="s">"unop"</span><span class="p">);</span>
+<span class="p">}</span>
+</pre></div>
+</div>
+<p>This code is similar to, but simpler than, the code for binary
+operators. It is simpler primarily because it doesn’t need to handle any
+predefined operators.</p>
+</div>
+<div class="section" id="kicking-the-tires">
+<h2><a class="toc-backref" href="#id5">6.5. Kicking the Tires</a><a class="headerlink" href="#kicking-the-tires" title="Permalink to this headline">¶</a></h2>
+<p>It is somewhat hard to believe, but with a few simple extensions we’ve
+covered in the last chapters, we have grown a real-ish language. With
+this, we can do a lot of interesting things, including I/O, math, and a
+bunch of other things. For example, we can now add a nice sequencing
+operator (printd is defined to print out the specified value and a
+newline):</p>
+<div class="highlight-python"><div class="highlight"><pre>ready> extern printd(x);
+Read extern:
+declare double @printd(double)
+
+ready> def binary : 1 (x y) 0; # Low-precedence operator that ignores operands.
+..
+ready> printd(123) : printd(456) : printd(789);
+123.000000
+456.000000
+789.000000
+Evaluated to 0.000000
+</pre></div>
+</div>
+<p>We can also define a bunch of other “primitive” operations, such as:</p>
+<div class="highlight-python"><div class="highlight"><pre># Logical unary not.
+def unary!(v)
+ if v then
+ 0
+ else
+ 1;
+
+# Unary negate.
+def unary-(v)
+ 0-v;
+
+# Define > with the same precedence as <.
+def binary> 10 (LHS RHS)
+ RHS < LHS;
+
+# Binary logical or, which does not short circuit.
+def binary| 5 (LHS RHS)
+ if LHS then
+ 1
+ else if RHS then
+ 1
+ else
+ 0;
+
+# Binary logical and, which does not short circuit.
+def binary& 6 (LHS RHS)
+ if !LHS then
+ 0
+ else
+ !!RHS;
+
+# Define = with slightly lower precedence than relationals.
+def binary = 9 (LHS RHS)
+ !(LHS < RHS | LHS > RHS);
+
+# Define ':' for sequencing: as a low-precedence operator that ignores operands
+# and just returns the RHS.
+def binary : 1 (x y) y;
+</pre></div>
+</div>
+<p>Given the previous if/then/else support, we can also define interesting
+functions for I/O. For example, the following prints out a character
+whose “density” reflects the value passed in: the lower the value, the
+denser the character:</p>
+<div class="highlight-python"><div class="highlight"><pre>ready>
+
+extern putchard(char)
+def printdensity(d)
+ if d > 8 then
+ putchard(32) # ' '
+ else if d > 4 then
+ putchard(46) # '.'
+ else if d > 2 then
+ putchard(43) # '+'
+ else
+ putchard(42); # '*'
+...
+ready> printdensity(1): printdensity(2): printdensity(3):
+ printdensity(4): printdensity(5): printdensity(9):
+ putchard(10);
+**++.
+Evaluated to 0.000000
+</pre></div>
+</div>
+<p>Based on these simple primitive operations, we can start to define more
+interesting things. For example, here’s a little function that solves
+for the number of iterations it takes a function in the complex plane to
+converge:</p>
+<div class="highlight-python"><div class="highlight"><pre># Determine whether the specific location diverges.
+# Solve for z = z^2 + c in the complex plane.
+def mandleconverger(real imag iters creal cimag)
+ if iters > 255 | (real*real + imag*imag > 4) then
+ iters
+ else
+ mandleconverger(real*real - imag*imag + creal,
+ 2*real*imag + cimag,
+ iters+1, creal, cimag);
+
+# Return the number of iterations required for the iteration to escape
+def mandleconverge(real imag)
+ mandleconverger(real, imag, 0, real, imag);
+</pre></div>
+</div>
+<p>This “<tt class="docutils literal"><span class="pre">z</span> <span class="pre">=</span> <span class="pre">z2</span> <span class="pre">+</span> <span class="pre">c</span></tt>” function is a beautiful little creature that is
+the basis for computation of the <a class="reference external" href="http://en.wikipedia.org/wiki/Mandelbrot_set">Mandelbrot
+Set</a>. Our
+<tt class="docutils literal"><span class="pre">mandelconverge</span></tt> function returns the number of iterations that it
+takes for a complex orbit to escape, saturating to 255. This is not a
+very useful function by itself, but if you plot its value over a
+two-dimensional plane, you can see the Mandelbrot set. Given that we are
+limited to using putchard here, our amazing graphical output is limited,
+but we can whip together something using the density plotter above:</p>
+<div class="highlight-python"><div class="highlight"><pre># Compute and plot the mandlebrot set with the specified 2 dimensional range
+# info.
+def mandelhelp(xmin xmax xstep ymin ymax ystep)
+ for y = ymin, y < ymax, ystep in (
+ (for x = xmin, x < xmax, xstep in
+ printdensity(mandleconverge(x,y)))
+ : putchard(10)
+ )
+
+# mandel - This is a convenient helper function for plotting the mandelbrot set
+# from the specified position with the specified Magnification.
+def mandel(realstart imagstart realmag imagmag)
+ mandelhelp(realstart, realstart+realmag*78, realmag,
+ imagstart, imagstart+imagmag*40, imagmag);
+</pre></div>
+</div>
+<p>Given this, we can try plotting out the mandlebrot set! Lets try it out:</p>
+<div class="highlight-python"><div class="highlight"><pre>ready> mandel(-2.3, -1.3, 0.05, 0.07);
+*******************************+++++++++++*************************************
+*************************+++++++++++++++++++++++*******************************
+**********************+++++++++++++++++++++++++++++****************************
+*******************+++++++++++++++++++++.. ...++++++++*************************
+*****************++++++++++++++++++++++.... ...+++++++++***********************
+***************+++++++++++++++++++++++..... ...+++++++++*********************
+**************+++++++++++++++++++++++.... ....+++++++++********************
+*************++++++++++++++++++++++...... .....++++++++*******************
+************+++++++++++++++++++++....... .......+++++++******************
+***********+++++++++++++++++++.... ... .+++++++*****************
+**********+++++++++++++++++....... .+++++++****************
+*********++++++++++++++........... ...+++++++***************
+********++++++++++++............ ...++++++++**************
+********++++++++++... .......... .++++++++**************
+*******+++++++++..... .+++++++++*************
+*******++++++++...... ..+++++++++*************
+*******++++++....... ..+++++++++*************
+*******+++++...... ..+++++++++*************
+*******.... .... ...+++++++++*************
+*******.... . ...+++++++++*************
+*******+++++...... ...+++++++++*************
+*******++++++....... ..+++++++++*************
+*******++++++++...... .+++++++++*************
+*******+++++++++..... ..+++++++++*************
+********++++++++++... .......... .++++++++**************
+********++++++++++++............ ...++++++++**************
+*********++++++++++++++.......... ...+++++++***************
+**********++++++++++++++++........ .+++++++****************
+**********++++++++++++++++++++.... ... ..+++++++****************
+***********++++++++++++++++++++++....... .......++++++++*****************
+************+++++++++++++++++++++++...... ......++++++++******************
+**************+++++++++++++++++++++++.... ....++++++++********************
+***************+++++++++++++++++++++++..... ...+++++++++*********************
+*****************++++++++++++++++++++++.... ...++++++++***********************
+*******************+++++++++++++++++++++......++++++++*************************
+*********************++++++++++++++++++++++.++++++++***************************
+*************************+++++++++++++++++++++++*******************************
+******************************+++++++++++++************************************
+*******************************************************************************
+*******************************************************************************
+*******************************************************************************
+Evaluated to 0.000000
+ready> mandel(-2, -1, 0.02, 0.04);
+**************************+++++++++++++++++++++++++++++++++++++++++++++++++++++
+***********************++++++++++++++++++++++++++++++++++++++++++++++++++++++++
+*********************+++++++++++++++++++++++++++++++++++++++++++++++++++++++++.
+*******************+++++++++++++++++++++++++++++++++++++++++++++++++++++++++...
+*****************+++++++++++++++++++++++++++++++++++++++++++++++++++++++++.....
+***************++++++++++++++++++++++++++++++++++++++++++++++++++++++++........
+**************++++++++++++++++++++++++++++++++++++++++++++++++++++++...........
+************+++++++++++++++++++++++++++++++++++++++++++++++++++++..............
+***********++++++++++++++++++++++++++++++++++++++++++++++++++........ .
+**********++++++++++++++++++++++++++++++++++++++++++++++.............
+********+++++++++++++++++++++++++++++++++++++++++++..................
+*******+++++++++++++++++++++++++++++++++++++++.......................
+******+++++++++++++++++++++++++++++++++++...........................
+*****++++++++++++++++++++++++++++++++............................
+*****++++++++++++++++++++++++++++...............................
+****++++++++++++++++++++++++++...... .........................
+***++++++++++++++++++++++++......... ...... ...........
+***++++++++++++++++++++++............
+**+++++++++++++++++++++..............
+**+++++++++++++++++++................
+*++++++++++++++++++.................
+*++++++++++++++++............ ...
+*++++++++++++++..............
+*+++....++++................
+*.......... ...........
+*
+*.......... ...........
+*+++....++++................
+*++++++++++++++..............
+*++++++++++++++++............ ...
+*++++++++++++++++++.................
+**+++++++++++++++++++................
+**+++++++++++++++++++++..............
+***++++++++++++++++++++++............
+***++++++++++++++++++++++++......... ...... ...........
+****++++++++++++++++++++++++++...... .........................
+*****++++++++++++++++++++++++++++...............................
+*****++++++++++++++++++++++++++++++++............................
+******+++++++++++++++++++++++++++++++++++...........................
+*******+++++++++++++++++++++++++++++++++++++++.......................
+********+++++++++++++++++++++++++++++++++++++++++++..................
+Evaluated to 0.000000
+ready> mandel(-0.9, -1.4, 0.02, 0.03);
+*******************************************************************************
+*******************************************************************************
+*******************************************************************************
+**********+++++++++++++++++++++************************************************
+*+++++++++++++++++++++++++++++++++++++++***************************************
++++++++++++++++++++++++++++++++++++++++++++++**********************************
+++++++++++++++++++++++++++++++++++++++++++++++++++*****************************
+++++++++++++++++++++++++++++++++++++++++++++++++++++++*************************
++++++++++++++++++++++++++++++++++++++++++++++++++++++++++**********************
++++++++++++++++++++++++++++++++++.........++++++++++++++++++*******************
++++++++++++++++++++++++++++++++.... ......+++++++++++++++++++****************
++++++++++++++++++++++++++++++....... ........+++++++++++++++++++**************
+++++++++++++++++++++++++++++........ ........++++++++++++++++++++************
++++++++++++++++++++++++++++......... .. ...+++++++++++++++++++++**********
+++++++++++++++++++++++++++........... ....++++++++++++++++++++++********
+++++++++++++++++++++++++............. .......++++++++++++++++++++++******
++++++++++++++++++++++++............. ........+++++++++++++++++++++++****
+++++++++++++++++++++++........... ..........++++++++++++++++++++++***
+++++++++++++++++++++........... .........++++++++++++++++++++++*
+++++++++++++++++++............ ...........++++++++++++++++++++
+++++++++++++++++............... .............++++++++++++++++++
+++++++++++++++................. ...............++++++++++++++++
+++++++++++++.................. .................++++++++++++++
++++++++++.................. .................+++++++++++++
+++++++........ . ......... ..++++++++++++
+++............ ...... ....++++++++++
+.............. ...++++++++++
+.............. ....+++++++++
+.............. .....++++++++
+............. ......++++++++
+........... .......++++++++
+......... ........+++++++
+......... ........+++++++
+......... ....+++++++
+........ ...+++++++
+....... ...+++++++
+ ....+++++++
+ .....+++++++
+ ....+++++++
+ ....+++++++
+ ....+++++++
+Evaluated to 0.000000
+ready> ^D
+</pre></div>
+</div>
+<p>At this point, you may be starting to realize that Kaleidoscope is a
+real and powerful language. It may not be self-similar :), but it can be
+used to plot things that are!</p>
+<p>With this, we conclude the “adding user-defined operators” chapter of
+the tutorial. We have successfully augmented our language, adding the
+ability to extend the language in the library, and we have shown how
+this can be used to build a simple but interesting end-user application
+in Kaleidoscope. At this point, Kaleidoscope can build a variety of
+applications that are functional and can call functions with
+side-effects, but it can’t actually define and mutate a variable itself.</p>
+<p>Strikingly, variable mutation is an important feature of some languages,
+and it is not at all obvious how to <a class="reference external" href="LangImpl7.html">add support for mutable
+variables</a> without having to add an “SSA construction”
+phase to your front-end. In the next chapter, we will describe how you
+can add variable mutation without building SSA in your front-end.</p>
+</div>
+<div class="section" id="full-code-listing">
+<h2><a class="toc-backref" href="#id6">6.6. Full Code Listing</a><a class="headerlink" href="#full-code-listing" title="Permalink to this headline">¶</a></h2>
+<p>Here is the complete code listing for our running example, enhanced with
+the if/then/else and for expressions.. To build this example, use:</p>
+<div class="highlight-bash"><div class="highlight"><pre><span class="c"># Compile</span>
+clang++ -g toy.cpp <span class="sb">`</span>llvm-config --cxxflags --ldflags --system-libs --libs core mcjit native<span class="sb">`</span> -O3 -o toy
+<span class="c"># Run</span>
+./toy
+</pre></div>
+</div>
+<p>On some platforms, you will need to specify -rdynamic or
+-Wl,–export-dynamic when linking. This ensures that symbols defined in
+the main executable are exported to the dynamic linker and so are
+available for symbol resolution at run time. This is not needed if you
+compile your support code into a shared library, although doing that
+will cause problems on Windows.</p>
+<p>Here is the code:</p>
+<div class="highlight-c++"><div class="highlight"><pre><span class="cp">#include "llvm/ADT/STLExtras.h"</span>
+<span class="cp">#include "llvm/Analysis/Passes.h"</span>
+<span class="cp">#include "llvm/IR/IRBuilder.h"</span>
+<span class="cp">#include "llvm/IR/LLVMContext.h"</span>
+<span class="cp">#include "llvm/IR/LegacyPassManager.h"</span>
+<span class="cp">#include "llvm/IR/Module.h"</span>
+<span class="cp">#include "llvm/IR/Verifier.h"</span>
+<span class="cp">#include "llvm/Support/TargetSelect.h"</span>
+<span class="cp">#include "llvm/Transforms/Scalar.h"</span>
+<span class="cp">#include <cctype></span>
+<span class="cp">#include <cstdio></span>
+<span class="cp">#include <map></span>
+<span class="cp">#include <string></span>
+<span class="cp">#include <vector></span>
+<span class="cp">#include "../include/KaleidoscopeJIT.h"</span>
+
+<span class="k">using</span> <span class="k">namespace</span> <span class="n">llvm</span><span class="p">;</span>
+<span class="k">using</span> <span class="k">namespace</span> <span class="n">llvm</span><span class="o">::</span><span class="n">orc</span><span class="p">;</span>
+
+<span class="c1">//===----------------------------------------------------------------------===//</span>
+<span class="c1">// Lexer</span>
+<span class="c1">//===----------------------------------------------------------------------===//</span>
+
+<span class="c1">// The lexer returns tokens [0-255] if it is an unknown character, otherwise one</span>
+<span class="c1">// of these for known things.</span>
+<span class="k">enum</span> <span class="n">Token</span> <span class="p">{</span>
+ <span class="n">tok_eof</span> <span class="o">=</span> <span class="o">-</span><span class="mi">1</span><span class="p">,</span>
+
+ <span class="c1">// commands</span>
+ <span class="n">tok_def</span> <span class="o">=</span> <span class="o">-</span><span class="mi">2</span><span class="p">,</span>
+ <span class="n">tok_extern</span> <span class="o">=</span> <span class="o">-</span><span class="mi">3</span><span class="p">,</span>
+
+ <span class="c1">// primary</span>
+ <span class="n">tok_identifier</span> <span class="o">=</span> <span class="o">-</span><span class="mi">4</span><span class="p">,</span>
+ <span class="n">tok_number</span> <span class="o">=</span> <span class="o">-</span><span class="mi">5</span><span class="p">,</span>
+
+ <span class="c1">// control</span>
+ <span class="n">tok_if</span> <span class="o">=</span> <span class="o">-</span><span class="mi">6</span><span class="p">,</span>
+ <span class="n">tok_then</span> <span class="o">=</span> <span class="o">-</span><span class="mi">7</span><span class="p">,</span>
+ <span class="n">tok_else</span> <span class="o">=</span> <span class="o">-</span><span class="mi">8</span><span class="p">,</span>
+ <span class="n">tok_for</span> <span class="o">=</span> <span class="o">-</span><span class="mi">9</span><span class="p">,</span>
+ <span class="n">tok_in</span> <span class="o">=</span> <span class="o">-</span><span class="mi">10</span><span class="p">,</span>
+
+ <span class="c1">// operators</span>
+ <span class="n">tok_binary</span> <span class="o">=</span> <span class="o">-</span><span class="mi">11</span><span class="p">,</span>
+ <span class="n">tok_unary</span> <span class="o">=</span> <span class="o">-</span><span class="mi">12</span>
+<span class="p">};</span>
+
+<span class="k">static</span> <span class="n">std</span><span class="o">::</span><span class="n">string</span> <span class="n">IdentifierStr</span><span class="p">;</span> <span class="c1">// Filled in if tok_identifier</span>
+<span class="k">static</span> <span class="kt">double</span> <span class="n">NumVal</span><span class="p">;</span> <span class="c1">// Filled in if tok_number</span>
+
+<span class="c1">/// gettok - Return the next token from standard input.</span>
+<span class="k">static</span> <span class="kt">int</span> <span class="nf">gettok</span><span class="p">()</span> <span class="p">{</span>
+ <span class="k">static</span> <span class="kt">int</span> <span class="n">LastChar</span> <span class="o">=</span> <span class="sc">' '</span><span class="p">;</span>
+
+ <span class="c1">// Skip any whitespace.</span>
+ <span class="k">while</span> <span class="p">(</span><span class="n">isspace</span><span class="p">(</span><span class="n">LastChar</span><span class="p">))</span>
+ <span class="n">LastChar</span> <span class="o">=</span> <span class="n">getchar</span><span class="p">();</span>
+
+ <span class="k">if</span> <span class="p">(</span><span class="n">isalpha</span><span class="p">(</span><span class="n">LastChar</span><span class="p">))</span> <span class="p">{</span> <span class="c1">// identifier: [a-zA-Z][a-zA-Z0-9]*</span>
+ <span class="n">IdentifierStr</span> <span class="o">=</span> <span class="n">LastChar</span><span class="p">;</span>
+ <span class="k">while</span> <span class="p">(</span><span class="n">isalnum</span><span class="p">((</span><span class="n">LastChar</span> <span class="o">=</span> <span class="n">getchar</span><span class="p">())))</span>
+ <span class="n">IdentifierStr</span> <span class="o">+=</span> <span class="n">LastChar</span><span class="p">;</span>
+
+ <span class="k">if</span> <span class="p">(</span><span class="n">IdentifierStr</span> <span class="o">==</span> <span class="s">"def"</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">tok_def</span><span class="p">;</span>
+ <span class="k">if</span> <span class="p">(</span><span class="n">IdentifierStr</span> <span class="o">==</span> <span class="s">"extern"</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">tok_extern</span><span class="p">;</span>
+ <span class="k">if</span> <span class="p">(</span><span class="n">IdentifierStr</span> <span class="o">==</span> <span class="s">"if"</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">tok_if</span><span class="p">;</span>
+ <span class="k">if</span> <span class="p">(</span><span class="n">IdentifierStr</span> <span class="o">==</span> <span class="s">"then"</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">tok_then</span><span class="p">;</span>
+ <span class="k">if</span> <span class="p">(</span><span class="n">IdentifierStr</span> <span class="o">==</span> <span class="s">"else"</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">tok_else</span><span class="p">;</span>
+ <span class="k">if</span> <span class="p">(</span><span class="n">IdentifierStr</span> <span class="o">==</span> <span class="s">"for"</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">tok_for</span><span class="p">;</span>
+ <span class="k">if</span> <span class="p">(</span><span class="n">IdentifierStr</span> <span class="o">==</span> <span class="s">"in"</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">tok_in</span><span class="p">;</span>
+ <span class="k">if</span> <span class="p">(</span><span class="n">IdentifierStr</span> <span class="o">==</span> <span class="s">"binary"</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">tok_binary</span><span class="p">;</span>
+ <span class="k">if</span> <span class="p">(</span><span class="n">IdentifierStr</span> <span class="o">==</span> <span class="s">"unary"</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">tok_unary</span><span class="p">;</span>
+ <span class="k">return</span> <span class="n">tok_identifier</span><span class="p">;</span>
+ <span class="p">}</span>
+
+ <span class="k">if</span> <span class="p">(</span><span class="n">isdigit</span><span class="p">(</span><span class="n">LastChar</span><span class="p">)</span> <span class="o">||</span> <span class="n">LastChar</span> <span class="o">==</span> <span class="sc">'.'</span><span class="p">)</span> <span class="p">{</span> <span class="c1">// Number: [0-9.]+</span>
+ <span class="n">std</span><span class="o">::</span><span class="n">string</span> <span class="n">NumStr</span><span class="p">;</span>
+ <span class="k">do</span> <span class="p">{</span>
+ <span class="n">NumStr</span> <span class="o">+=</span> <span class="n">LastChar</span><span class="p">;</span>
+ <span class="n">LastChar</span> <span class="o">=</span> <span class="n">getchar</span><span class="p">();</span>
+ <span class="p">}</span> <span class="k">while</span> <span class="p">(</span><span class="n">isdigit</span><span class="p">(</span><span class="n">LastChar</span><span class="p">)</span> <span class="o">||</span> <span class="n">LastChar</span> <span class="o">==</span> <span class="sc">'.'</span><span class="p">);</span>
+
+ <span class="n">NumVal</span> <span class="o">=</span> <span class="n">strtod</span><span class="p">(</span><span class="n">NumStr</span><span class="p">.</span><span class="n">c_str</span><span class="p">(),</span> <span class="n">nullptr</span><span class="p">);</span>
+ <span class="k">return</span> <span class="n">tok_number</span><span class="p">;</span>
+ <span class="p">}</span>
+
+ <span class="k">if</span> <span class="p">(</span><span class="n">LastChar</span> <span class="o">==</span> <span class="sc">'#'</span><span class="p">)</span> <span class="p">{</span>
+ <span class="c1">// Comment until end of line.</span>
+ <span class="k">do</span>
+ <span class="n">LastChar</span> <span class="o">=</span> <span class="n">getchar</span><span class="p">();</span>
+ <span class="k">while</span> <span class="p">(</span><span class="n">LastChar</span> <span class="o">!=</span> <span class="n">EOF</span> <span class="o">&&</span> <span class="n">LastChar</span> <span class="o">!=</span> <span class="sc">'\n'</span> <span class="o">&&</span> <span class="n">LastChar</span> <span class="o">!=</span> <span class="sc">'\r'</span><span class="p">);</span>
+
+ <span class="k">if</span> <span class="p">(</span><span class="n">LastChar</span> <span class="o">!=</span> <span class="n">EOF</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">gettok</span><span class="p">();</span>
+ <span class="p">}</span>
+
+ <span class="c1">// Check for end of file. Don't eat the EOF.</span>
+ <span class="k">if</span> <span class="p">(</span><span class="n">LastChar</span> <span class="o">==</span> <span class="n">EOF</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">tok_eof</span><span class="p">;</span>
+
+ <span class="c1">// Otherwise, just return the character as its ascii value.</span>
+ <span class="kt">int</span> <span class="n">ThisChar</span> <span class="o">=</span> <span class="n">LastChar</span><span class="p">;</span>
+ <span class="n">LastChar</span> <span class="o">=</span> <span class="n">getchar</span><span class="p">();</span>
+ <span class="k">return</span> <span class="n">ThisChar</span><span class="p">;</span>
+<span class="p">}</span>
+
+<span class="c1">//===----------------------------------------------------------------------===//</span>
+<span class="c1">// Abstract Syntax Tree (aka Parse Tree)</span>
+<span class="c1">//===----------------------------------------------------------------------===//</span>
+<span class="k">namespace</span> <span class="p">{</span>
+<span class="c1">/// ExprAST - Base class for all expression nodes.</span>
+<span class="k">class</span> <span class="nc">ExprAST</span> <span class="p">{</span>
+<span class="nl">public:</span>
+ <span class="k">virtual</span> <span class="o">~</span><span class="n">ExprAST</span><span class="p">()</span> <span class="p">{}</span>
+ <span class="k">virtual</span> <span class="n">Value</span> <span class="o">*</span><span class="n">codegen</span><span class="p">()</span> <span class="o">=</span> <span class="mi">0</span><span class="p">;</span>
+<span class="p">};</span>
+
+<span class="c1">/// NumberExprAST - Expression class for numeric literals like "1.0".</span>
+<span class="k">class</span> <span class="nc">NumberExprAST</span> <span class="o">:</span> <span class="k">public</span> <span class="n">ExprAST</span> <span class="p">{</span>
+ <span class="kt">double</span> <span class="n">Val</span><span class="p">;</span>
+
+<span class="nl">public:</span>
+ <span class="n">NumberExprAST</span><span class="p">(</span><span class="kt">double</span> <span class="n">Val</span><span class="p">)</span> <span class="o">:</span> <span class="n">Val</span><span class="p">(</span><span class="n">Val</span><span class="p">)</span> <span class="p">{}</span>
+ <span class="n">Value</span> <span class="o">*</span><span class="n">codegen</span><span class="p">()</span> <span class="n">override</span><span class="p">;</span>
+<span class="p">};</span>
+
+<span class="c1">/// VariableExprAST - Expression class for referencing a variable, like "a".</span>
+<span class="k">class</span> <span class="nc">VariableExprAST</span> <span class="o">:</span> <span class="k">public</span> <span class="n">ExprAST</span> <span class="p">{</span>
+ <span class="n">std</span><span class="o">::</span><span class="n">string</span> <span class="n">Name</span><span class="p">;</span>
+
+<span class="nl">public:</span>
+ <span class="n">VariableExprAST</span><span class="p">(</span><span class="k">const</span> <span class="n">std</span><span class="o">::</span><span class="n">string</span> <span class="o">&</span><span class="n">Name</span><span class="p">)</span> <span class="o">:</span> <span class="n">Name</span><span class="p">(</span><span class="n">Name</span><span class="p">)</span> <span class="p">{}</span>
+ <span class="n">Value</span> <span class="o">*</span><span class="n">codegen</span><span class="p">()</span> <span class="n">override</span><span class="p">;</span>
+<span class="p">};</span>
+
+<span class="c1">/// UnaryExprAST - Expression class for a unary operator.</span>
+<span class="k">class</span> <span class="nc">UnaryExprAST</span> <span class="o">:</span> <span class="k">public</span> <span class="n">ExprAST</span> <span class="p">{</span>
+ <span class="kt">char</span> <span class="n">Opcode</span><span class="p">;</span>
+ <span class="n">std</span><span class="o">::</span><span class="n">unique_ptr</span><span class="o"><</span><span class="n">ExprAST</span><span class="o">></span> <span class="n">Operand</span><span class="p">;</span>
+
+<span class="nl">public:</span>
+ <span class="n">UnaryExprAST</span><span class="p">(</span><span class="kt">char</span> <span class="n">Opcode</span><span class="p">,</span> <span class="n">std</span><span class="o">::</span><span class="n">unique_ptr</span><span class="o"><</span><span class="n">ExprAST</span><span class="o">></span> <span class="n">Operand</span><span class="p">)</span>
+ <span class="o">:</span> <span class="n">Opcode</span><span class="p">(</span><span class="n">Opcode</span><span class="p">),</span> <span class="n">Operand</span><span class="p">(</span><span class="n">std</span><span class="o">::</span><span class="n">move</span><span class="p">(</span><span class="n">Operand</span><span class="p">))</span> <span class="p">{}</span>
+ <span class="n">Value</span> <span class="o">*</span><span class="n">codegen</span><span class="p">()</span> <span class="n">override</span><span class="p">;</span>
+<span class="p">};</span>
+
+<span class="c1">/// BinaryExprAST - Expression class for a binary operator.</span>
+<span class="k">class</span> <span class="nc">BinaryExprAST</span> <span class="o">:</span> <span class="k">public</span> <span class="n">ExprAST</span> <span class="p">{</span>
+ <span class="kt">char</span> <span class="n">Op</span><span class="p">;</span>
+ <span class="n">std</span><span class="o">::</span><span class="n">unique_ptr</span><span class="o"><</span><span class="n">ExprAST</span><span class="o">></span> <span class="n">LHS</span><span class="p">,</span> <span class="n">RHS</span><span class="p">;</span>
+
+<span class="nl">public:</span>
+ <span class="n">BinaryExprAST</span><span class="p">(</span><span class="kt">char</span> <span class="n">Op</span><span class="p">,</span> <span class="n">std</span><span class="o">::</span><span class="n">unique_ptr</span><span class="o"><</span><span class="n">ExprAST</span><span class="o">></span> <span class="n">LHS</span><span class="p">,</span>
+ <span class="n">std</span><span class="o">::</span><span class="n">unique_ptr</span><span class="o"><</span><span class="n">ExprAST</span><span class="o">></span> <span class="n">RHS</span><span class="p">)</span>
+ <span class="o">:</span> <span class="n">Op</span><span class="p">(</span><span class="n">Op</span><span class="p">),</span> <span class="n">LHS</span><span class="p">(</span><span class="n">std</span><span class="o">::</span><span class="n">move</span><span class="p">(</span><span class="n">LHS</span><span class="p">)),</span> <span class="n">RHS</span><span class="p">(</span><span class="n">std</span><span class="o">::</span><span class="n">move</span><span class="p">(</span><span class="n">RHS</span><span class="p">))</span> <span class="p">{}</span>
+ <span class="n">Value</span> <span class="o">*</span><span class="n">codegen</span><span class="p">()</span> <span class="n">override</span><span class="p">;</span>
+<span class="p">};</span>
+
+<span class="c1">/// CallExprAST - Expression class for function calls.</span>
+<span class="k">class</span> <span class="nc">CallExprAST</span> <span class="o">:</span> <span class="k">public</span> <span class="n">ExprAST</span> <span class="p">{</span>
+ <span class="n">std</span><span class="o">::</span><span class="n">string</span> <span class="n">Callee</span><span class="p">;</span>
+ <span class="n">std</span><span class="o">::</span><span class="n">vector</span><span class="o"><</span><span class="n">std</span><span class="o">::</span><span class="n">unique_ptr</span><span class="o"><</span><span class="n">ExprAST</span><span class="o">>></span> <span class="n">Args</span><span class="p">;</span>
+
+<span class="nl">public:</span>
+ <span class="n">CallExprAST</span><span class="p">(</span><span class="k">const</span> <span class="n">std</span><span class="o">::</span><span class="n">string</span> <span class="o">&</span><span class="n">Callee</span><span class="p">,</span>
+ <span class="n">std</span><span class="o">::</span><span class="n">vector</span><span class="o"><</span><span class="n">std</span><span class="o">::</span><span class="n">unique_ptr</span><span class="o"><</span><span class="n">ExprAST</span><span class="o">>></span> <span class="n">Args</span><span class="p">)</span>
+ <span class="o">:</span> <span class="n">Callee</span><span class="p">(</span><span class="n">Callee</span><span class="p">),</span> <span class="n">Args</span><span class="p">(</span><span class="n">std</span><span class="o">::</span><span class="n">move</span><span class="p">(</span><span class="n">Args</span><span class="p">))</span> <span class="p">{}</span>
+ <span class="n">Value</span> <span class="o">*</span><span class="n">codegen</span><span class="p">()</span> <span class="n">override</span><span class="p">;</span>
+<span class="p">};</span>
+
+<span class="c1">/// IfExprAST - Expression class for if/then/else.</span>
+<span class="k">class</span> <span class="nc">IfExprAST</span> <span class="o">:</span> <span class="k">public</span> <span class="n">ExprAST</span> <span class="p">{</span>
+ <span class="n">std</span><span class="o">::</span><span class="n">unique_ptr</span><span class="o"><</span><span class="n">ExprAST</span><span class="o">></span> <span class="n">Cond</span><span class="p">,</span> <span class="n">Then</span><span class="p">,</span> <span class="n">Else</span><span class="p">;</span>
+
+<span class="nl">public:</span>
+ <span class="n">IfExprAST</span><span class="p">(</span><span class="n">std</span><span class="o">::</span><span class="n">unique_ptr</span><span class="o"><</span><span class="n">ExprAST</span><span class="o">></span> <span class="n">Cond</span><span class="p">,</span> <span class="n">std</span><span class="o">::</span><span class="n">unique_ptr</span><span class="o"><</span><span class="n">ExprAST</span><span class="o">></span> <span class="n">Then</span><span class="p">,</span>
+ <span class="n">std</span><span class="o">::</span><span class="n">unique_ptr</span><span class="o"><</span><span class="n">ExprAST</span><span class="o">></span> <span class="n">Else</span><span class="p">)</span>
+ <span class="o">:</span> <span class="n">Cond</span><span class="p">(</span><span class="n">std</span><span class="o">::</span><span class="n">move</span><span class="p">(</span><span class="n">Cond</span><span class="p">)),</span> <span class="n">Then</span><span class="p">(</span><span class="n">std</span><span class="o">::</span><span class="n">move</span><span class="p">(</span><span class="n">Then</span><span class="p">)),</span> <span class="n">Else</span><span class="p">(</span><span class="n">std</span><span class="o">::</span><span class="n">move</span><span class="p">(</span><span class="n">Else</span><span class="p">))</span> <span class="p">{}</span>
+ <span class="n">Value</span> <span class="o">*</span><span class="n">codegen</span><span class="p">()</span> <span class="n">override</span><span class="p">;</span>
+<span class="p">};</span>
+
+<span class="c1">/// ForExprAST - Expression class for for/in.</span>
+<span class="k">class</span> <span class="nc">ForExprAST</span> <span class="o">:</span> <span class="k">public</span> <span class="n">ExprAST</span> <span class="p">{</span>
+ <span class="n">std</span><span class="o">::</span><span class="n">string</span> <span class="n">VarName</span><span class="p">;</span>
+ <span class="n">std</span><span class="o">::</span><span class="n">unique_ptr</span><span class="o"><</span><span class="n">ExprAST</span><span class="o">></span> <span class="n">Start</span><span class="p">,</span> <span class="n">End</span><span class="p">,</span> <span class="n">Step</span><span class="p">,</span> <span class="n">Body</span><span class="p">;</span>
+
+<span class="nl">public:</span>
+ <span class="n">ForExprAST</span><span class="p">(</span><span class="k">const</span> <span class="n">std</span><span class="o">::</span><span class="n">string</span> <span class="o">&</span><span class="n">VarName</span><span class="p">,</span> <span class="n">std</span><span class="o">::</span><span class="n">unique_ptr</span><span class="o"><</span><span class="n">ExprAST</span><span class="o">></span> <span class="n">Start</span><span class="p">,</span>
+ <span class="n">std</span><span class="o">::</span><span class="n">unique_ptr</span><span class="o"><</span><span class="n">ExprAST</span><span class="o">></span> <span class="n">End</span><span class="p">,</span> <span class="n">std</span><span class="o">::</span><span class="n">unique_ptr</span><span class="o"><</span><span class="n">ExprAST</span><span class="o">></span> <span class="n">Step</span><span class="p">,</span>
+ <span class="n">std</span><span class="o">::</span><span class="n">unique_ptr</span><span class="o"><</span><span class="n">ExprAST</span><span class="o">></span> <span class="n">Body</span><span class="p">)</span>
+ <span class="o">:</span> <span class="n">VarName</span><span class="p">(</span><span class="n">VarName</span><span class="p">),</span> <span class="n">Start</span><span class="p">(</span><span class="n">std</span><span class="o">::</span><span class="n">move</span><span class="p">(</span><span class="n">Start</span><span class="p">)),</span> <span class="n">End</span><span class="p">(</span><span class="n">std</span><span class="o">::</span><span class="n">move</span><span class="p">(</span><span class="n">End</span><span class="p">)),</span>
+ <span class="n">Step</span><span class="p">(</span><span class="n">std</span><span class="o">::</span><span class="n">move</span><span class="p">(</span><span class="n">Step</span><span class="p">)),</span> <span class="n">Body</span><span class="p">(</span><span class="n">std</span><span class="o">::</span><span class="n">move</span><span class="p">(</span><span class="n">Body</span><span class="p">))</span> <span class="p">{}</span>
+ <span class="n">Value</span> <span class="o">*</span><span class="n">codegen</span><span class="p">()</span> <span class="n">override</span><span class="p">;</span>
+<span class="p">};</span>
+
+<span class="c1">/// PrototypeAST - This class represents the "prototype" for a function,</span>
+<span class="c1">/// which captures its name, and its argument names (thus implicitly the number</span>
+<span class="c1">/// of arguments the function takes), as well as if it is an operator.</span>
+<span class="k">class</span> <span class="nc">PrototypeAST</span> <span class="p">{</span>
+ <span class="n">std</span><span class="o">::</span><span class="n">string</span> <span class="n">Name</span><span class="p">;</span>
+ <span class="n">std</span><span class="o">::</span><span class="n">vector</span><span class="o"><</span><span class="n">std</span><span class="o">::</span><span class="n">string</span><span class="o">></span> <span class="n">Args</span><span class="p">;</span>
+ <span class="kt">bool</span> <span class="n">IsOperator</span><span class="p">;</span>
+ <span class="kt">unsigned</span> <span class="n">Precedence</span><span class="p">;</span> <span class="c1">// Precedence if a binary op.</span>
+
+<span class="nl">public:</span>
+ <span class="n">PrototypeAST</span><span class="p">(</span><span class="k">const</span> <span class="n">std</span><span class="o">::</span><span class="n">string</span> <span class="o">&</span><span class="n">Name</span><span class="p">,</span> <span class="n">std</span><span class="o">::</span><span class="n">vector</span><span class="o"><</span><span class="n">std</span><span class="o">::</span><span class="n">string</span><span class="o">></span> <span class="n">Args</span><span class="p">,</span>
+ <span class="kt">bool</span> <span class="n">IsOperator</span> <span class="o">=</span> <span class="nb">false</span><span class="p">,</span> <span class="kt">unsigned</span> <span class="n">Prec</span> <span class="o">=</span> <span class="mi">0</span><span class="p">)</span>
+ <span class="o">:</span> <span class="n">Name</span><span class="p">(</span><span class="n">Name</span><span class="p">),</span> <span class="n">Args</span><span class="p">(</span><span class="n">std</span><span class="o">::</span><span class="n">move</span><span class="p">(</span><span class="n">Args</span><span class="p">)),</span> <span class="n">IsOperator</span><span class="p">(</span><span class="n">IsOperator</span><span class="p">),</span>
+ <span class="n">Precedence</span><span class="p">(</span><span class="n">Prec</span><span class="p">)</span> <span class="p">{}</span>
+ <span class="n">Function</span> <span class="o">*</span><span class="n">codegen</span><span class="p">();</span>
+ <span class="k">const</span> <span class="n">std</span><span class="o">::</span><span class="n">string</span> <span class="o">&</span><span class="n">getName</span><span class="p">()</span> <span class="k">const</span> <span class="p">{</span> <span class="k">return</span> <span class="n">Name</span><span class="p">;</span> <span class="p">}</span>
+
+ <span class="kt">bool</span> <span class="n">isUnaryOp</span><span class="p">()</span> <span class="k">const</span> <span class="p">{</span> <span class="k">return</span> <span class="n">IsOperator</span> <span class="o">&&</span> <span class="n">Args</span><span class="p">.</span><span class="n">size</span><span class="p">()</span> <span class="o">==</span> <span class="mi">1</span><span class="p">;</span> <span class="p">}</span>
+ <span class="kt">bool</span> <span class="n">isBinaryOp</span><span class="p">()</span> <span class="k">const</span> <span class="p">{</span> <span class="k">return</span> <span class="n">IsOperator</span> <span class="o">&&</span> <span class="n">Args</span><span class="p">.</span><span class="n">size</span><span class="p">()</span> <span class="o">==</span> <span class="mi">2</span><span class="p">;</span> <span class="p">}</span>
+
+ <span class="kt">char</span> <span class="n">getOperatorName</span><span class="p">()</span> <span class="k">const</span> <span class="p">{</span>
+ <span class="n">assert</span><span class="p">(</span><span class="n">isUnaryOp</span><span class="p">()</span> <span class="o">||</span> <span class="n">isBinaryOp</span><span class="p">());</span>
+ <span class="k">return</span> <span class="n">Name</span><span class="p">[</span><span class="n">Name</span><span class="p">.</span><span class="n">size</span><span class="p">()</span> <span class="o">-</span> <span class="mi">1</span><span class="p">];</span>
+ <span class="p">}</span>
+
+ <span class="kt">unsigned</span> <span class="n">getBinaryPrecedence</span><span class="p">()</span> <span class="k">const</span> <span class="p">{</span> <span class="k">return</span> <span class="n">Precedence</span><span class="p">;</span> <span class="p">}</span>
+<span class="p">};</span>
+
+<span class="c1">/// FunctionAST - This class represents a function definition itself.</span>
+<span class="k">class</span> <span class="nc">FunctionAST</span> <span class="p">{</span>
+ <span class="n">std</span><span class="o">::</span><span class="n">unique_ptr</span><span class="o"><</span><span class="n">PrototypeAST</span><span class="o">></span> <span class="n">Proto</span><span class="p">;</span>
+ <span class="n">std</span><span class="o">::</span><span class="n">unique_ptr</span><span class="o"><</span><span class="n">ExprAST</span><span class="o">></span> <span class="n">Body</span><span class="p">;</span>
+
+<span class="nl">public:</span>
+ <span class="n">FunctionAST</span><span class="p">(</span><span class="n">std</span><span class="o">::</span><span class="n">unique_ptr</span><span class="o"><</span><span class="n">PrototypeAST</span><span class="o">></span> <span class="n">Proto</span><span class="p">,</span>
+ <span class="n">std</span><span class="o">::</span><span class="n">unique_ptr</span><span class="o"><</span><span class="n">ExprAST</span><span class="o">></span> <span class="n">Body</span><span class="p">)</span>
+ <span class="o">:</span> <span class="n">Proto</span><span class="p">(</span><span class="n">std</span><span class="o">::</span><span class="n">move</span><span class="p">(</span><span class="n">Proto</span><span class="p">)),</span> <span class="n">Body</span><span class="p">(</span><span class="n">std</span><span class="o">::</span><span class="n">move</span><span class="p">(</span><span class="n">Body</span><span class="p">))</span> <span class="p">{}</span>
+ <span class="n">Function</span> <span class="o">*</span><span class="n">codegen</span><span class="p">();</span>
+<span class="p">};</span>
+<span class="p">}</span> <span class="c1">// end anonymous namespace</span>
+
+<span class="c1">//===----------------------------------------------------------------------===//</span>
+<span class="c1">// Parser</span>
+<span class="c1">//===----------------------------------------------------------------------===//</span>
+
+<span class="c1">/// CurTok/getNextToken - Provide a simple token buffer. CurTok is the current</span>
+<span class="c1">/// token the parser is looking at. getNextToken reads another token from the</span>
+<span class="c1">/// lexer and updates CurTok with its results.</span>
+<span class="k">static</span> <span class="kt">int</span> <span class="n">CurTok</span><span class="p">;</span>
+<span class="k">static</span> <span class="kt">int</span> <span class="nf">getNextToken</span><span class="p">()</span> <span class="p">{</span> <span class="k">return</span> <span class="n">CurTok</span> <span class="o">=</span> <span class="n">gettok</span><span class="p">();</span> <span class="p">}</span>
+
+<span class="c1">/// BinopPrecedence - This holds the precedence for each binary operator that is</span>
+<span class="c1">/// defined.</span>
+<span class="k">static</span> <span class="n">std</span><span class="o">::</span><span class="n">map</span><span class="o"><</span><span class="kt">char</span><span class="p">,</span> <span class="kt">int</span><span class="o">></span> <span class="n">BinopPrecedence</span><span class="p">;</span>
+
+<span class="c1">/// GetTokPrecedence - Get the precedence of the pending binary operator token.</span>
+<span class="k">static</span> <span class="kt">int</span> <span class="nf">GetTokPrecedence</span><span class="p">()</span> <span class="p">{</span>
+ <span class="k">if</span> <span class="p">(</span><span class="o">!</span><span class="n">isascii</span><span class="p">(</span><span class="n">CurTok</span><span class="p">))</span>
+ <span class="k">return</span> <span class="o">-</span><span class="mi">1</span><span class="p">;</span>
+
+ <span class="c1">// Make sure it's a declared binop.</span>
+ <span class="kt">int</span> <span class="n">TokPrec</span> <span class="o">=</span> <span class="n">BinopPrecedence</span><span class="p">[</span><span class="n">CurTok</span><span class="p">];</span>
+ <span class="k">if</span> <span class="p">(</span><span class="n">TokPrec</span> <span class="o"><=</span> <span class="mi">0</span><span class="p">)</span>
+ <span class="k">return</span> <span class="o">-</span><span class="mi">1</span><span class="p">;</span>
+ <span class="k">return</span> <span class="n">TokPrec</span><span class="p">;</span>
+<span class="p">}</span>
+
+<span class="c1">/// Error* - These are little helper functions for error handling.</span>
+<span class="n">std</span><span class="o">::</span><span class="n">unique_ptr</span><span class="o"><</span><span class="n">ExprAST</span><span class="o">></span> <span class="n">Error</span><span class="p">(</span><span class="k">const</span> <span class="kt">char</span> <span class="o">*</span><span class="n">Str</span><span class="p">)</span> <span class="p">{</span>
+ <span class="n">fprintf</span><span class="p">(</span><span class="n">stderr</span><span class="p">,</span> <span class="s">"Error: %s</span><span class="se">\n</span><span class="s">"</span><span class="p">,</span> <span class="n">Str</span><span class="p">);</span>
+ <span class="k">return</span> <span class="n">nullptr</span><span class="p">;</span>
+<span class="p">}</span>
+
+<span class="n">std</span><span class="o">::</span><span class="n">unique_ptr</span><span class="o"><</span><span class="n">PrototypeAST</span><span class="o">></span> <span class="n">ErrorP</span><span class="p">(</span><span class="k">const</span> <span class="kt">char</span> <span class="o">*</span><span class="n">Str</span><span class="p">)</span> <span class="p">{</span>
+ <span class="n">Error</span><span class="p">(</span><span class="n">Str</span><span class="p">);</span>
+ <span class="k">return</span> <span class="n">nullptr</span><span class="p">;</span>
+<span class="p">}</span>
+
+<span class="k">static</span> <span class="n">std</span><span class="o">::</span><span class="n">unique_ptr</span><span class="o"><</span><span class="n">ExprAST</span><span class="o">></span> <span class="n">ParseExpression</span><span class="p">();</span>
+
+<span class="c1">/// numberexpr ::= number</span>
+<span class="k">static</span> <span class="n">std</span><span class="o">::</span><span class="n">unique_ptr</span><span class="o"><</span><span class="n">ExprAST</span><span class="o">></span> <span class="n">ParseNumberExpr</span><span class="p">()</span> <span class="p">{</span>
+ <span class="k">auto</span> <span class="n">Result</span> <span class="o">=</span> <span class="n">llvm</span><span class="o">::</span><span class="n">make_unique</span><span class="o"><</span><span class="n">NumberExprAST</span><span class="o">></span><span class="p">(</span><span class="n">NumVal</span><span class="p">);</span>
+ <span class="n">getNextToken</span><span class="p">();</span> <span class="c1">// consume the number</span>
+ <span class="k">return</span> <span class="n">std</span><span class="o">::</span><span class="n">move</span><span class="p">(</span><span class="n">Result</span><span class="p">);</span>
+<span class="p">}</span>
+
+<span class="c1">/// parenexpr ::= '(' expression ')'</span>
+<span class="k">static</span> <span class="n">std</span><span class="o">::</span><span class="n">unique_ptr</span><span class="o"><</span><span class="n">ExprAST</span><span class="o">></span> <span class="n">ParseParenExpr</span><span class="p">()</span> <span class="p">{</span>
+ <span class="n">getNextToken</span><span class="p">();</span> <span class="c1">// eat (.</span>
+ <span class="k">auto</span> <span class="n">V</span> <span class="o">=</span> <span class="n">ParseExpression</span><span class="p">();</span>
+ <span class="k">if</span> <span class="p">(</span><span class="o">!</span><span class="n">V</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">nullptr</span><span class="p">;</span>
+
+ <span class="k">if</span> <span class="p">(</span><span class="n">CurTok</span> <span class="o">!=</span> <span class="sc">')'</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">Error</span><span class="p">(</span><span class="s">"expected ')'"</span><span class="p">);</span>
+ <span class="n">getNextToken</span><span class="p">();</span> <span class="c1">// eat ).</span>
+ <span class="k">return</span> <span class="n">V</span><span class="p">;</span>
+<span class="p">}</span>
+
+<span class="c1">/// identifierexpr</span>
+<span class="c1">/// ::= identifier</span>
+<span class="c1">/// ::= identifier '(' expression* ')'</span>
+<span class="k">static</span> <span class="n">std</span><span class="o">::</span><span class="n">unique_ptr</span><span class="o"><</span><span class="n">ExprAST</span><span class="o">></span> <span class="n">ParseIdentifierExpr</span><span class="p">()</span> <span class="p">{</span>
+ <span class="n">std</span><span class="o">::</span><span class="n">string</span> <span class="n">IdName</span> <span class="o">=</span> <span class="n">IdentifierStr</span><span class="p">;</span>
+
+ <span class="n">getNextToken</span><span class="p">();</span> <span class="c1">// eat identifier.</span>
+
+ <span class="k">if</span> <span class="p">(</span><span class="n">CurTok</span> <span class="o">!=</span> <span class="sc">'('</span><span class="p">)</span> <span class="c1">// Simple variable ref.</span>
+ <span class="k">return</span> <span class="n">llvm</span><span class="o">::</span><span class="n">make_unique</span><span class="o"><</span><span class="n">VariableExprAST</span><span class="o">></span><span class="p">(</span><span class="n">IdName</span><span class="p">);</span>
+
+ <span class="c1">// Call.</span>
+ <span class="n">getNextToken</span><span class="p">();</span> <span class="c1">// eat (</span>
+ <span class="n">std</span><span class="o">::</span><span class="n">vector</span><span class="o"><</span><span class="n">std</span><span class="o">::</span><span class="n">unique_ptr</span><span class="o"><</span><span class="n">ExprAST</span><span class="o">>></span> <span class="n">Args</span><span class="p">;</span>
+ <span class="k">if</span> <span class="p">(</span><span class="n">CurTok</span> <span class="o">!=</span> <span class="sc">')'</span><span class="p">)</span> <span class="p">{</span>
+ <span class="k">while</span> <span class="p">(</span><span class="mi">1</span><span class="p">)</span> <span class="p">{</span>
+ <span class="k">if</span> <span class="p">(</span><span class="k">auto</span> <span class="n">Arg</span> <span class="o">=</span> <span class="n">ParseExpression</span><span class="p">())</span>
+ <span class="n">Args</span><span class="p">.</span><span class="n">push_back</span><span class="p">(</span><span class="n">std</span><span class="o">::</span><span class="n">move</span><span class="p">(</span><span class="n">Arg</span><span class="p">));</span>
+ <span class="k">else</span>
+ <span class="k">return</span> <span class="n">nullptr</span><span class="p">;</span>
+
+ <span class="k">if</span> <span class="p">(</span><span class="n">CurTok</span> <span class="o">==</span> <span class="sc">')'</span><span class="p">)</span>
+ <span class="k">break</span><span class="p">;</span>
+
+ <span class="k">if</span> <span class="p">(</span><span class="n">CurTok</span> <span class="o">!=</span> <span class="sc">','</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">Error</span><span class="p">(</span><span class="s">"Expected ')' or ',' in argument list"</span><span class="p">);</span>
+ <span class="n">getNextToken</span><span class="p">();</span>
+ <span class="p">}</span>
+ <span class="p">}</span>
+
+ <span class="c1">// Eat the ')'.</span>
+ <span class="n">getNextToken</span><span class="p">();</span>
+
+ <span class="k">return</span> <span class="n">llvm</span><span class="o">::</span><span class="n">make_unique</span><span class="o"><</span><span class="n">CallExprAST</span><span class="o">></span><span class="p">(</span><span class="n">IdName</span><span class="p">,</span> <span class="n">std</span><span class="o">::</span><span class="n">move</span><span class="p">(</span><span class="n">Args</span><span class="p">));</span>
+<span class="p">}</span>
+
+<span class="c1">/// ifexpr ::= 'if' expression 'then' expression 'else' expression</span>
+<span class="k">static</span> <span class="n">std</span><span class="o">::</span><span class="n">unique_ptr</span><span class="o"><</span><span class="n">ExprAST</span><span class="o">></span> <span class="n">ParseIfExpr</span><span class="p">()</span> <span class="p">{</span>
+ <span class="n">getNextToken</span><span class="p">();</span> <span class="c1">// eat the if.</span>
+
+ <span class="c1">// condition.</span>
+ <span class="k">auto</span> <span class="n">Cond</span> <span class="o">=</span> <span class="n">ParseExpression</span><span class="p">();</span>
+ <span class="k">if</span> <span class="p">(</span><span class="o">!</span><span class="n">Cond</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">nullptr</span><span class="p">;</span>
+
+ <span class="k">if</span> <span class="p">(</span><span class="n">CurTok</span> <span class="o">!=</span> <span class="n">tok_then</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">Error</span><span class="p">(</span><span class="s">"expected then"</span><span class="p">);</span>
+ <span class="n">getNextToken</span><span class="p">();</span> <span class="c1">// eat the then</span>
+
+ <span class="k">auto</span> <span class="n">Then</span> <span class="o">=</span> <span class="n">ParseExpression</span><span class="p">();</span>
+ <span class="k">if</span> <span class="p">(</span><span class="o">!</span><span class="n">Then</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">nullptr</span><span class="p">;</span>
+
+ <span class="k">if</span> <span class="p">(</span><span class="n">CurTok</span> <span class="o">!=</span> <span class="n">tok_else</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">Error</span><span class="p">(</span><span class="s">"expected else"</span><span class="p">);</span>
+
+ <span class="n">getNextToken</span><span class="p">();</span>
+
+ <span class="k">auto</span> <span class="n">Else</span> <span class="o">=</span> <span class="n">ParseExpression</span><span class="p">();</span>
+ <span class="k">if</span> <span class="p">(</span><span class="o">!</span><span class="n">Else</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">nullptr</span><span class="p">;</span>
+
+ <span class="k">return</span> <span class="n">llvm</span><span class="o">::</span><span class="n">make_unique</span><span class="o"><</span><span class="n">IfExprAST</span><span class="o">></span><span class="p">(</span><span class="n">std</span><span class="o">::</span><span class="n">move</span><span class="p">(</span><span class="n">Cond</span><span class="p">),</span> <span class="n">std</span><span class="o">::</span><span class="n">move</span><span class="p">(</span><span class="n">Then</span><span class="p">),</span>
+ <span class="n">std</span><span class="o">::</span><span class="n">move</span><span class="p">(</span><span class="n">Else</span><span class="p">));</span>
+<span class="p">}</span>
+
+<span class="c1">/// forexpr ::= 'for' identifier '=' expr ',' expr (',' expr)? 'in' expression</span>
+<span class="k">static</span> <span class="n">std</span><span class="o">::</span><span class="n">unique_ptr</span><span class="o"><</span><span class="n">ExprAST</span><span class="o">></span> <span class="n">ParseForExpr</span><span class="p">()</span> <span class="p">{</span>
+ <span class="n">getNextToken</span><span class="p">();</span> <span class="c1">// eat the for.</span>
+
+ <span class="k">if</span> <span class="p">(</span><span class="n">CurTok</span> <span class="o">!=</span> <span class="n">tok_identifier</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">Error</span><span class="p">(</span><span class="s">"expected identifier after for"</span><span class="p">);</span>
+
+ <span class="n">std</span><span class="o">::</span><span class="n">string</span> <span class="n">IdName</span> <span class="o">=</span> <span class="n">IdentifierStr</span><span class="p">;</span>
+ <span class="n">getNextToken</span><span class="p">();</span> <span class="c1">// eat identifier.</span>
+
+ <span class="k">if</span> <span class="p">(</span><span class="n">CurTok</span> <span class="o">!=</span> <span class="sc">'='</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">Error</span><span class="p">(</span><span class="s">"expected '=' after for"</span><span class="p">);</span>
+ <span class="n">getNextToken</span><span class="p">();</span> <span class="c1">// eat '='.</span>
+
+ <span class="k">auto</span> <span class="n">Start</span> <span class="o">=</span> <span class="n">ParseExpression</span><span class="p">();</span>
+ <span class="k">if</span> <span class="p">(</span><span class="o">!</span><span class="n">Start</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">nullptr</span><span class="p">;</span>
+ <span class="k">if</span> <span class="p">(</span><span class="n">CurTok</span> <span class="o">!=</span> <span class="sc">','</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">Error</span><span class="p">(</span><span class="s">"expected ',' after for start value"</span><span class="p">);</span>
+ <span class="n">getNextToken</span><span class="p">();</span>
+
+ <span class="k">auto</span> <span class="n">End</span> <span class="o">=</span> <span class="n">ParseExpression</span><span class="p">();</span>
+ <span class="k">if</span> <span class="p">(</span><span class="o">!</span><span class="n">End</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">nullptr</span><span class="p">;</span>
+
+ <span class="c1">// The step value is optional.</span>
+ <span class="n">std</span><span class="o">::</span><span class="n">unique_ptr</span><span class="o"><</span><span class="n">ExprAST</span><span class="o">></span> <span class="n">Step</span><span class="p">;</span>
+ <span class="k">if</span> <span class="p">(</span><span class="n">CurTok</span> <span class="o">==</span> <span class="sc">','</span><span class="p">)</span> <span class="p">{</span>
+ <span class="n">getNextToken</span><span class="p">();</span>
+ <span class="n">Step</span> <span class="o">=</span> <span class="n">ParseExpression</span><span class="p">();</span>
+ <span class="k">if</span> <span class="p">(</span><span class="o">!</span><span class="n">Step</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">nullptr</span><span class="p">;</span>
+ <span class="p">}</span>
+
+ <span class="k">if</span> <span class="p">(</span><span class="n">CurTok</span> <span class="o">!=</span> <span class="n">tok_in</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">Error</span><span class="p">(</span><span class="s">"expected 'in' after for"</span><span class="p">);</span>
+ <span class="n">getNextToken</span><span class="p">();</span> <span class="c1">// eat 'in'.</span>
+
+ <span class="k">auto</span> <span class="n">Body</span> <span class="o">=</span> <span class="n">ParseExpression</span><span class="p">();</span>
+ <span class="k">if</span> <span class="p">(</span><span class="o">!</span><span class="n">Body</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">nullptr</span><span class="p">;</span>
+
+ <span class="k">return</span> <span class="n">llvm</span><span class="o">::</span><span class="n">make_unique</span><span class="o"><</span><span class="n">ForExprAST</span><span class="o">></span><span class="p">(</span><span class="n">IdName</span><span class="p">,</span> <span class="n">std</span><span class="o">::</span><span class="n">move</span><span class="p">(</span><span class="n">Start</span><span class="p">),</span> <span class="n">std</span><span class="o">::</span><span class="n">move</span><span class="p">(</span><span class="n">End</span><span class="p">),</span>
+ <span class="n">std</span><span class="o">::</span><span class="n">move</span><span class="p">(</span><span class="n">Step</span><span class="p">),</span> <span class="n">std</span><span class="o">::</span><span class="n">move</span><span class="p">(</span><span class="n">Body</span><span class="p">));</span>
+<span class="p">}</span>
+
+<span class="c1">/// primary</span>
+<span class="c1">/// ::= identifierexpr</span>
+<span class="c1">/// ::= numberexpr</span>
+<span class="c1">/// ::= parenexpr</span>
+<span class="c1">/// ::= ifexpr</span>
+<span class="c1">/// ::= forexpr</span>
+<span class="k">static</span> <span class="n">std</span><span class="o">::</span><span class="n">unique_ptr</span><span class="o"><</span><span class="n">ExprAST</span><span class="o">></span> <span class="n">ParsePrimary</span><span class="p">()</span> <span class="p">{</span>
+ <span class="k">switch</span> <span class="p">(</span><span class="n">CurTok</span><span class="p">)</span> <span class="p">{</span>
+ <span class="nl">default:</span>
+ <span class="k">return</span> <span class="n">Error</span><span class="p">(</span><span class="s">"unknown token when expecting an expression"</span><span class="p">);</span>
+ <span class="k">case</span> <span class="n">tok_identifier</span>:
+ <span class="k">return</span> <span class="n">ParseIdentifierExpr</span><span class="p">();</span>
+ <span class="k">case</span> <span class="n">tok_number</span>:
+ <span class="k">return</span> <span class="n">ParseNumberExpr</span><span class="p">();</span>
+ <span class="k">case</span> <span class="sc">'('</span>:
+ <span class="k">return</span> <span class="n">ParseParenExpr</span><span class="p">();</span>
+ <span class="k">case</span> <span class="n">tok_if</span>:
+ <span class="k">return</span> <span class="n">ParseIfExpr</span><span class="p">();</span>
+ <span class="k">case</span> <span class="n">tok_for</span>:
+ <span class="k">return</span> <span class="n">ParseForExpr</span><span class="p">();</span>
+ <span class="p">}</span>
+<span class="p">}</span>
+
+<span class="c1">/// unary</span>
+<span class="c1">/// ::= primary</span>
+<span class="c1">/// ::= '!' unary</span>
+<span class="k">static</span> <span class="n">std</span><span class="o">::</span><span class="n">unique_ptr</span><span class="o"><</span><span class="n">ExprAST</span><span class="o">></span> <span class="n">ParseUnary</span><span class="p">()</span> <span class="p">{</span>
+ <span class="c1">// If the current token is not an operator, it must be a primary expr.</span>
+ <span class="k">if</span> <span class="p">(</span><span class="o">!</span><span class="n">isascii</span><span class="p">(</span><span class="n">CurTok</span><span class="p">)</span> <span class="o">||</span> <span class="n">CurTok</span> <span class="o">==</span> <span class="sc">'('</span> <span class="o">||</span> <span class="n">CurTok</span> <span class="o">==</span> <span class="sc">','</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">ParsePrimary</span><span class="p">();</span>
+
+ <span class="c1">// If this is a unary operator, read it.</span>
+ <span class="kt">int</span> <span class="n">Opc</span> <span class="o">=</span> <span class="n">CurTok</span><span class="p">;</span>
+ <span class="n">getNextToken</span><span class="p">();</span>
+ <span class="k">if</span> <span class="p">(</span><span class="k">auto</span> <span class="n">Operand</span> <span class="o">=</span> <span class="n">ParseUnary</span><span class="p">())</span>
+ <span class="k">return</span> <span class="n">llvm</span><span class="o">::</span><span class="n">make_unique</span><span class="o"><</span><span class="n">UnaryExprAST</span><span class="o">></span><span class="p">(</span><span class="n">Opc</span><span class="p">,</span> <span class="n">std</span><span class="o">::</span><span class="n">move</span><span class="p">(</span><span class="n">Operand</span><span class="p">));</span>
+ <span class="k">return</span> <span class="n">nullptr</span><span class="p">;</span>
+<span class="p">}</span>
+
+<span class="c1">/// binoprhs</span>
+<span class="c1">/// ::= ('+' unary)*</span>
+<span class="k">static</span> <span class="n">std</span><span class="o">::</span><span class="n">unique_ptr</span><span class="o"><</span><span class="n">ExprAST</span><span class="o">></span> <span class="n">ParseBinOpRHS</span><span class="p">(</span><span class="kt">int</span> <span class="n">ExprPrec</span><span class="p">,</span>
+ <span class="n">std</span><span class="o">::</span><span class="n">unique_ptr</span><span class="o"><</span><span class="n">ExprAST</span><span class="o">></span> <span class="n">LHS</span><span class="p">)</span> <span class="p">{</span>
+ <span class="c1">// If this is a binop, find its precedence.</span>
+ <span class="k">while</span> <span class="p">(</span><span class="mi">1</span><span class="p">)</span> <span class="p">{</span>
+ <span class="kt">int</span> <span class="n">TokPrec</span> <span class="o">=</span> <span class="n">GetTokPrecedence</span><span class="p">();</span>
+
+ <span class="c1">// If this is a binop that binds at least as tightly as the current binop,</span>
+ <span class="c1">// consume it, otherwise we are done.</span>
+ <span class="k">if</span> <span class="p">(</span><span class="n">TokPrec</span> <span class="o"><</span> <span class="n">ExprPrec</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">LHS</span><span class="p">;</span>
+
+ <span class="c1">// Okay, we know this is a binop.</span>
+ <span class="kt">int</span> <span class="n">BinOp</span> <span class="o">=</span> <span class="n">CurTok</span><span class="p">;</span>
+ <span class="n">getNextToken</span><span class="p">();</span> <span class="c1">// eat binop</span>
+
+ <span class="c1">// Parse the unary expression after the binary operator.</span>
+ <span class="k">auto</span> <span class="n">RHS</span> <span class="o">=</span> <span class="n">ParseUnary</span><span class="p">();</span>
+ <span class="k">if</span> <span class="p">(</span><span class="o">!</span><span class="n">RHS</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">nullptr</span><span class="p">;</span>
+
+ <span class="c1">// If BinOp binds less tightly with RHS than the operator after RHS, let</span>
+ <span class="c1">// the pending operator take RHS as its LHS.</span>
+ <span class="kt">int</span> <span class="n">NextPrec</span> <span class="o">=</span> <span class="n">GetTokPrecedence</span><span class="p">();</span>
+ <span class="k">if</span> <span class="p">(</span><span class="n">TokPrec</span> <span class="o"><</span> <span class="n">NextPrec</span><span class="p">)</span> <span class="p">{</span>
+ <span class="n">RHS</span> <span class="o">=</span> <span class="n">ParseBinOpRHS</span><span class="p">(</span><span class="n">TokPrec</span> <span class="o">+</span> <span class="mi">1</span><span class="p">,</span> <span class="n">std</span><span class="o">::</span><span class="n">move</span><span class="p">(</span><span class="n">RHS</span><span class="p">));</span>
+ <span class="k">if</span> <span class="p">(</span><span class="o">!</span><span class="n">RHS</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">nullptr</span><span class="p">;</span>
+ <span class="p">}</span>
+
+ <span class="c1">// Merge LHS/RHS.</span>
+ <span class="n">LHS</span> <span class="o">=</span>
+ <span class="n">llvm</span><span class="o">::</span><span class="n">make_unique</span><span class="o"><</span><span class="n">BinaryExprAST</span><span class="o">></span><span class="p">(</span><span class="n">BinOp</span><span class="p">,</span> <span class="n">std</span><span class="o">::</span><span class="n">move</span><span class="p">(</span><span class="n">LHS</span><span class="p">),</span> <span class="n">std</span><span class="o">::</span><span class="n">move</span><span class="p">(</span><span class="n">RHS</span><span class="p">));</span>
+ <span class="p">}</span>
+<span class="p">}</span>
+
+<span class="c1">/// expression</span>
+<span class="c1">/// ::= unary binoprhs</span>
+<span class="c1">///</span>
+<span class="k">static</span> <span class="n">std</span><span class="o">::</span><span class="n">unique_ptr</span><span class="o"><</span><span class="n">ExprAST</span><span class="o">></span> <span class="n">ParseExpression</span><span class="p">()</span> <span class="p">{</span>
+ <span class="k">auto</span> <span class="n">LHS</span> <span class="o">=</span> <span class="n">ParseUnary</span><span class="p">();</span>
+ <span class="k">if</span> <span class="p">(</span><span class="o">!</span><span class="n">LHS</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">nullptr</span><span class="p">;</span>
+
+ <span class="k">return</span> <span class="nf">ParseBinOpRHS</span><span class="p">(</span><span class="mi">0</span><span class="p">,</span> <span class="n">std</span><span class="o">::</span><span class="n">move</span><span class="p">(</span><span class="n">LHS</span><span class="p">));</span>
+<span class="p">}</span>
+
+<span class="c1">/// prototype</span>
+<span class="c1">/// ::= id '(' id* ')'</span>
+<span class="c1">/// ::= binary LETTER number? (id, id)</span>
+<span class="c1">/// ::= unary LETTER (id)</span>
+<span class="k">static</span> <span class="n">std</span><span class="o">::</span><span class="n">unique_ptr</span><span class="o"><</span><span class="n">PrototypeAST</span><span class="o">></span> <span class="n">ParsePrototype</span><span class="p">()</span> <span class="p">{</span>
+ <span class="n">std</span><span class="o">::</span><span class="n">string</span> <span class="n">FnName</span><span class="p">;</span>
+
+ <span class="kt">unsigned</span> <span class="n">Kind</span> <span class="o">=</span> <span class="mi">0</span><span class="p">;</span> <span class="c1">// 0 = identifier, 1 = unary, 2 = binary.</span>
+ <span class="kt">unsigned</span> <span class="n">BinaryPrecedence</span> <span class="o">=</span> <span class="mi">30</span><span class="p">;</span>
+
+ <span class="k">switch</span> <span class="p">(</span><span class="n">CurTok</span><span class="p">)</span> <span class="p">{</span>
+ <span class="nl">default:</span>
+ <span class="k">return</span> <span class="n">ErrorP</span><span class="p">(</span><span class="s">"Expected function name in prototype"</span><span class="p">);</span>
+ <span class="k">case</span> <span class="n">tok_identifier</span>:
+ <span class="n">FnName</span> <span class="o">=</span> <span class="n">IdentifierStr</span><span class="p">;</span>
+ <span class="n">Kind</span> <span class="o">=</span> <span class="mi">0</span><span class="p">;</span>
+ <span class="n">getNextToken</span><span class="p">();</span>
+ <span class="k">break</span><span class="p">;</span>
+ <span class="k">case</span> <span class="n">tok_unary</span>:
+ <span class="n">getNextToken</span><span class="p">();</span>
+ <span class="k">if</span> <span class="p">(</span><span class="o">!</span><span class="n">isascii</span><span class="p">(</span><span class="n">CurTok</span><span class="p">))</span>
+ <span class="k">return</span> <span class="n">ErrorP</span><span class="p">(</span><span class="s">"Expected unary operator"</span><span class="p">);</span>
+ <span class="n">FnName</span> <span class="o">=</span> <span class="s">"unary"</span><span class="p">;</span>
+ <span class="n">FnName</span> <span class="o">+=</span> <span class="p">(</span><span class="kt">char</span><span class="p">)</span><span class="n">CurTok</span><span class="p">;</span>
+ <span class="n">Kind</span> <span class="o">=</span> <span class="mi">1</span><span class="p">;</span>
+ <span class="n">getNextToken</span><span class="p">();</span>
+ <span class="k">break</span><span class="p">;</span>
+ <span class="k">case</span> <span class="n">tok_binary</span>:
+ <span class="n">getNextToken</span><span class="p">();</span>
+ <span class="k">if</span> <span class="p">(</span><span class="o">!</span><span class="n">isascii</span><span class="p">(</span><span class="n">CurTok</span><span class="p">))</span>
+ <span class="k">return</span> <span class="n">ErrorP</span><span class="p">(</span><span class="s">"Expected binary operator"</span><span class="p">);</span>
+ <span class="n">FnName</span> <span class="o">=</span> <span class="s">"binary"</span><span class="p">;</span>
+ <span class="n">FnName</span> <span class="o">+=</span> <span class="p">(</span><span class="kt">char</span><span class="p">)</span><span class="n">CurTok</span><span class="p">;</span>
+ <span class="n">Kind</span> <span class="o">=</span> <span class="mi">2</span><span class="p">;</span>
+ <span class="n">getNextToken</span><span class="p">();</span>
+
+ <span class="c1">// Read the precedence if present.</span>
+ <span class="k">if</span> <span class="p">(</span><span class="n">CurTok</span> <span class="o">==</span> <span class="n">tok_number</span><span class="p">)</span> <span class="p">{</span>
+ <span class="k">if</span> <span class="p">(</span><span class="n">NumVal</span> <span class="o"><</span> <span class="mi">1</span> <span class="o">||</span> <span class="n">NumVal</span> <span class="o">></span> <span class="mi">100</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">ErrorP</span><span class="p">(</span><span class="s">"Invalid precedecnce: must be 1..100"</span><span class="p">);</span>
+ <span class="n">BinaryPrecedence</span> <span class="o">=</span> <span class="p">(</span><span class="kt">unsigned</span><span class="p">)</span><span class="n">NumVal</span><span class="p">;</span>
+ <span class="n">getNextToken</span><span class="p">();</span>
+ <span class="p">}</span>
+ <span class="k">break</span><span class="p">;</span>
+ <span class="p">}</span>
+
+ <span class="k">if</span> <span class="p">(</span><span class="n">CurTok</span> <span class="o">!=</span> <span class="sc">'('</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">ErrorP</span><span class="p">(</span><span class="s">"Expected '(' in prototype"</span><span class="p">);</span>
+
+ <span class="n">std</span><span class="o">::</span><span class="n">vector</span><span class="o"><</span><span class="n">std</span><span class="o">::</span><span class="n">string</span><span class="o">></span> <span class="n">ArgNames</span><span class="p">;</span>
+ <span class="k">while</span> <span class="p">(</span><span class="n">getNextToken</span><span class="p">()</span> <span class="o">==</span> <span class="n">tok_identifier</span><span class="p">)</span>
+ <span class="n">ArgNames</span><span class="p">.</span><span class="n">push_back</span><span class="p">(</span><span class="n">IdentifierStr</span><span class="p">);</span>
+ <span class="k">if</span> <span class="p">(</span><span class="n">CurTok</span> <span class="o">!=</span> <span class="sc">')'</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">ErrorP</span><span class="p">(</span><span class="s">"Expected ')' in prototype"</span><span class="p">);</span>
+
+ <span class="c1">// success.</span>
+ <span class="n">getNextToken</span><span class="p">();</span> <span class="c1">// eat ')'.</span>
+
+ <span class="c1">// Verify right number of names for operator.</span>
+ <span class="k">if</span> <span class="p">(</span><span class="n">Kind</span> <span class="o">&&</span> <span class="n">ArgNames</span><span class="p">.</span><span class="n">size</span><span class="p">()</span> <span class="o">!=</span> <span class="n">Kind</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">ErrorP</span><span class="p">(</span><span class="s">"Invalid number of operands for operator"</span><span class="p">);</span>
+
+ <span class="k">return</span> <span class="n">llvm</span><span class="o">::</span><span class="n">make_unique</span><span class="o"><</span><span class="n">PrototypeAST</span><span class="o">></span><span class="p">(</span><span class="n">FnName</span><span class="p">,</span> <span class="n">ArgNames</span><span class="p">,</span> <span class="n">Kind</span> <span class="o">!=</span> <span class="mi">0</span><span class="p">,</span>
+ <span class="n">BinaryPrecedence</span><span class="p">);</span>
+<span class="p">}</span>
+
+<span class="c1">/// definition ::= 'def' prototype expression</span>
+<span class="k">static</span> <span class="n">std</span><span class="o">::</span><span class="n">unique_ptr</span><span class="o"><</span><span class="n">FunctionAST</span><span class="o">></span> <span class="n">ParseDefinition</span><span class="p">()</span> <span class="p">{</span>
+ <span class="n">getNextToken</span><span class="p">();</span> <span class="c1">// eat def.</span>
+ <span class="k">auto</span> <span class="n">Proto</span> <span class="o">=</span> <span class="n">ParsePrototype</span><span class="p">();</span>
+ <span class="k">if</span> <span class="p">(</span><span class="o">!</span><span class="n">Proto</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">nullptr</span><span class="p">;</span>
+
+ <span class="k">if</span> <span class="p">(</span><span class="k">auto</span> <span class="n">E</span> <span class="o">=</span> <span class="n">ParseExpression</span><span class="p">())</span>
+ <span class="k">return</span> <span class="n">llvm</span><span class="o">::</span><span class="n">make_unique</span><span class="o"><</span><span class="n">FunctionAST</span><span class="o">></span><span class="p">(</span><span class="n">std</span><span class="o">::</span><span class="n">move</span><span class="p">(</span><span class="n">Proto</span><span class="p">),</span> <span class="n">std</span><span class="o">::</span><span class="n">move</span><span class="p">(</span><span class="n">E</span><span class="p">));</span>
+ <span class="k">return</span> <span class="n">nullptr</span><span class="p">;</span>
+<span class="p">}</span>
+
+<span class="c1">/// toplevelexpr ::= expression</span>
+<span class="k">static</span> <span class="n">std</span><span class="o">::</span><span class="n">unique_ptr</span><span class="o"><</span><span class="n">FunctionAST</span><span class="o">></span> <span class="n">ParseTopLevelExpr</span><span class="p">()</span> <span class="p">{</span>
+ <span class="k">if</span> <span class="p">(</span><span class="k">auto</span> <span class="n">E</span> <span class="o">=</span> <span class="n">ParseExpression</span><span class="p">())</span> <span class="p">{</span>
+ <span class="c1">// Make an anonymous proto.</span>
+ <span class="k">auto</span> <span class="n">Proto</span> <span class="o">=</span> <span class="n">llvm</span><span class="o">::</span><span class="n">make_unique</span><span class="o"><</span><span class="n">PrototypeAST</span><span class="o">></span><span class="p">(</span><span class="s">"__anon_expr"</span><span class="p">,</span>
+ <span class="n">std</span><span class="o">::</span><span class="n">vector</span><span class="o"><</span><span class="n">std</span><span class="o">::</span><span class="n">string</span><span class="o">></span><span class="p">());</span>
+ <span class="k">return</span> <span class="n">llvm</span><span class="o">::</span><span class="n">make_unique</span><span class="o"><</span><span class="n">FunctionAST</span><span class="o">></span><span class="p">(</span><span class="n">std</span><span class="o">::</span><span class="n">move</span><span class="p">(</span><span class="n">Proto</span><span class="p">),</span> <span class="n">std</span><span class="o">::</span><span class="n">move</span><span class="p">(</span><span class="n">E</span><span class="p">));</span>
+ <span class="p">}</span>
+ <span class="k">return</span> <span class="n">nullptr</span><span class="p">;</span>
+<span class="p">}</span>
+
+<span class="c1">/// external ::= 'extern' prototype</span>
+<span class="k">static</span> <span class="n">std</span><span class="o">::</span><span class="n">unique_ptr</span><span class="o"><</span><span class="n">PrototypeAST</span><span class="o">></span> <span class="n">ParseExtern</span><span class="p">()</span> <span class="p">{</span>
+ <span class="n">getNextToken</span><span class="p">();</span> <span class="c1">// eat extern.</span>
+ <span class="k">return</span> <span class="nf">ParsePrototype</span><span class="p">();</span>
+<span class="p">}</span>
+
+<span class="c1">//===----------------------------------------------------------------------===//</span>
+<span class="c1">// Code Generation</span>
+<span class="c1">//===----------------------------------------------------------------------===//</span>
+
+<span class="k">static</span> <span class="n">std</span><span class="o">::</span><span class="n">unique_ptr</span><span class="o"><</span><span class="n">Module</span><span class="o">></span> <span class="n">TheModule</span><span class="p">;</span>
+<span class="k">static</span> <span class="n">IRBuilder</span><span class="o"><></span> <span class="n">Builder</span><span class="p">(</span><span class="n">getGlobalContext</span><span class="p">());</span>
+<span class="k">static</span> <span class="n">std</span><span class="o">::</span><span class="n">map</span><span class="o"><</span><span class="n">std</span><span class="o">::</span><span class="n">string</span><span class="p">,</span> <span class="n">Value</span> <span class="o">*></span> <span class="n">NamedValues</span><span class="p">;</span>
+<span class="k">static</span> <span class="n">std</span><span class="o">::</span><span class="n">unique_ptr</span><span class="o"><</span><span class="n">legacy</span><span class="o">::</span><span class="n">FunctionPassManager</span><span class="o">></span> <span class="n">TheFPM</span><span class="p">;</span>
+<span class="k">static</span> <span class="n">std</span><span class="o">::</span><span class="n">unique_ptr</span><span class="o"><</span><span class="n">KaleidoscopeJIT</span><span class="o">></span> <span class="n">TheJIT</span><span class="p">;</span>
+<span class="k">static</span> <span class="n">std</span><span class="o">::</span><span class="n">map</span><span class="o"><</span><span class="n">std</span><span class="o">::</span><span class="n">string</span><span class="p">,</span> <span class="n">std</span><span class="o">::</span><span class="n">unique_ptr</span><span class="o"><</span><span class="n">PrototypeAST</span><span class="o">>></span> <span class="n">FunctionProtos</span><span class="p">;</span>
+
+<span class="n">Value</span> <span class="o">*</span><span class="nf">ErrorV</span><span class="p">(</span><span class="k">const</span> <span class="kt">char</span> <span class="o">*</span><span class="n">Str</span><span class="p">)</span> <span class="p">{</span>
+ <span class="n">Error</span><span class="p">(</span><span class="n">Str</span><span class="p">);</span>
+ <span class="k">return</span> <span class="n">nullptr</span><span class="p">;</span>
+<span class="p">}</span>
+
+<span class="n">Function</span> <span class="o">*</span><span class="nf">getFunction</span><span class="p">(</span><span class="n">std</span><span class="o">::</span><span class="n">string</span> <span class="n">Name</span><span class="p">)</span> <span class="p">{</span>
+ <span class="c1">// First, see if the function has already been added to the current module.</span>
+ <span class="k">if</span> <span class="p">(</span><span class="k">auto</span> <span class="o">*</span><span class="n">F</span> <span class="o">=</span> <span class="n">TheModule</span><span class="o">-></span><span class="n">getFunction</span><span class="p">(</span><span class="n">Name</span><span class="p">))</span>
+ <span class="k">return</span> <span class="n">F</span><span class="p">;</span>
+
+ <span class="c1">// If not, check whether we can codegen the declaration from some existing</span>
+ <span class="c1">// prototype.</span>
+ <span class="k">auto</span> <span class="n">FI</span> <span class="o">=</span> <span class="n">FunctionProtos</span><span class="p">.</span><span class="n">find</span><span class="p">(</span><span class="n">Name</span><span class="p">);</span>
+ <span class="k">if</span> <span class="p">(</span><span class="n">FI</span> <span class="o">!=</span> <span class="n">FunctionProtos</span><span class="p">.</span><span class="n">end</span><span class="p">())</span>
+ <span class="k">return</span> <span class="n">FI</span><span class="o">-></span><span class="n">second</span><span class="o">-></span><span class="n">codegen</span><span class="p">();</span>
+
+ <span class="c1">// If no existing prototype exists, return null.</span>
+ <span class="k">return</span> <span class="n">nullptr</span><span class="p">;</span>
+<span class="p">}</span>
+
+<span class="n">Value</span> <span class="o">*</span><span class="n">NumberExprAST</span><span class="o">::</span><span class="n">codegen</span><span class="p">()</span> <span class="p">{</span>
+ <span class="k">return</span> <span class="n">ConstantFP</span><span class="o">::</span><span class="n">get</span><span class="p">(</span><span class="n">getGlobalContext</span><span class="p">(),</span> <span class="n">APFloat</span><span class="p">(</span><span class="n">Val</span><span class="p">));</span>
+<span class="p">}</span>
+
+<span class="n">Value</span> <span class="o">*</span><span class="n">VariableExprAST</span><span class="o">::</span><span class="n">codegen</span><span class="p">()</span> <span class="p">{</span>
+ <span class="c1">// Look this variable up in the function.</span>
+ <span class="n">Value</span> <span class="o">*</span><span class="n">V</span> <span class="o">=</span> <span class="n">NamedValues</span><span class="p">[</span><span class="n">Name</span><span class="p">];</span>
+ <span class="k">if</span> <span class="p">(</span><span class="o">!</span><span class="n">V</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">ErrorV</span><span class="p">(</span><span class="s">"Unknown variable name"</span><span class="p">);</span>
+ <span class="k">return</span> <span class="n">V</span><span class="p">;</span>
+<span class="p">}</span>
+
+<span class="n">Value</span> <span class="o">*</span><span class="n">UnaryExprAST</span><span class="o">::</span><span class="n">codegen</span><span class="p">()</span> <span class="p">{</span>
+ <span class="n">Value</span> <span class="o">*</span><span class="n">OperandV</span> <span class="o">=</span> <span class="n">Operand</span><span class="o">-></span><span class="n">codegen</span><span class="p">();</span>
+ <span class="k">if</span> <span class="p">(</span><span class="o">!</span><span class="n">OperandV</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">nullptr</span><span class="p">;</span>
+
+ <span class="n">Function</span> <span class="o">*</span><span class="n">F</span> <span class="o">=</span> <span class="n">getFunction</span><span class="p">(</span><span class="n">std</span><span class="o">::</span><span class="n">string</span><span class="p">(</span><span class="s">"unary"</span><span class="p">)</span> <span class="o">+</span> <span class="n">Opcode</span><span class="p">);</span>
+ <span class="k">if</span> <span class="p">(</span><span class="o">!</span><span class="n">F</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">ErrorV</span><span class="p">(</span><span class="s">"Unknown unary operator"</span><span class="p">);</span>
+
+ <span class="k">return</span> <span class="n">Builder</span><span class="p">.</span><span class="n">CreateCall</span><span class="p">(</span><span class="n">F</span><span class="p">,</span> <span class="n">OperandV</span><span class="p">,</span> <span class="s">"unop"</span><span class="p">);</span>
+<span class="p">}</span>
+
+<span class="n">Value</span> <span class="o">*</span><span class="n">BinaryExprAST</span><span class="o">::</span><span class="n">codegen</span><span class="p">()</span> <span class="p">{</span>
+ <span class="n">Value</span> <span class="o">*</span><span class="n">L</span> <span class="o">=</span> <span class="n">LHS</span><span class="o">-></span><span class="n">codegen</span><span class="p">();</span>
+ <span class="n">Value</span> <span class="o">*</span><span class="n">R</span> <span class="o">=</span> <span class="n">RHS</span><span class="o">-></span><span class="n">codegen</span><span class="p">();</span>
+ <span class="k">if</span> <span class="p">(</span><span class="o">!</span><span class="n">L</span> <span class="o">||</span> <span class="o">!</span><span class="n">R</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">nullptr</span><span class="p">;</span>
+
+ <span class="k">switch</span> <span class="p">(</span><span class="n">Op</span><span class="p">)</span> <span class="p">{</span>
+ <span class="k">case</span> <span class="sc">'+'</span>:
+ <span class="k">return</span> <span class="n">Builder</span><span class="p">.</span><span class="n">CreateFAdd</span><span class="p">(</span><span class="n">L</span><span class="p">,</span> <span class="n">R</span><span class="p">,</span> <span class="s">"addtmp"</span><span class="p">);</span>
+ <span class="k">case</span> <span class="sc">'-'</span>:
+ <span class="k">return</span> <span class="n">Builder</span><span class="p">.</span><span class="n">CreateFSub</span><span class="p">(</span><span class="n">L</span><span class="p">,</span> <span class="n">R</span><span class="p">,</span> <span class="s">"subtmp"</span><span class="p">);</span>
+ <span class="k">case</span> <span class="sc">'*'</span>:
+ <span class="k">return</span> <span class="n">Builder</span><span class="p">.</span><span class="n">CreateFMul</span><span class="p">(</span><span class="n">L</span><span class="p">,</span> <span class="n">R</span><span class="p">,</span> <span class="s">"multmp"</span><span class="p">);</span>
+ <span class="k">case</span> <span class="sc">'<'</span>:
+ <span class="n">L</span> <span class="o">=</span> <span class="n">Builder</span><span class="p">.</span><span class="n">CreateFCmpULT</span><span class="p">(</span><span class="n">L</span><span class="p">,</span> <span class="n">R</span><span class="p">,</span> <span class="s">"cmptmp"</span><span class="p">);</span>
+ <span class="c1">// Convert bool 0/1 to double 0.0 or 1.0</span>
+ <span class="k">return</span> <span class="n">Builder</span><span class="p">.</span><span class="n">CreateUIToFP</span><span class="p">(</span><span class="n">L</span><span class="p">,</span> <span class="n">Type</span><span class="o">::</span><span class="n">getDoubleTy</span><span class="p">(</span><span class="n">getGlobalContext</span><span class="p">()),</span>
+ <span class="s">"booltmp"</span><span class="p">);</span>
+ <span class="nl">default:</span>
+ <span class="k">break</span><span class="p">;</span>
+ <span class="p">}</span>
+
+ <span class="c1">// If it wasn't a builtin binary operator, it must be a user defined one. Emit</span>
+ <span class="c1">// a call to it.</span>
+ <span class="n">Function</span> <span class="o">*</span><span class="n">F</span> <span class="o">=</span> <span class="n">getFunction</span><span class="p">(</span><span class="n">std</span><span class="o">::</span><span class="n">string</span><span class="p">(</span><span class="s">"binary"</span><span class="p">)</span> <span class="o">+</span> <span class="n">Op</span><span class="p">);</span>
+ <span class="n">assert</span><span class="p">(</span><span class="n">F</span> <span class="o">&&</span> <span class="s">"binary operator not found!"</span><span class="p">);</span>
+
+ <span class="n">Value</span> <span class="o">*</span><span class="n">Ops</span><span class="p">[]</span> <span class="o">=</span> <span class="p">{</span><span class="n">L</span><span class="p">,</span> <span class="n">R</span><span class="p">};</span>
+ <span class="k">return</span> <span class="n">Builder</span><span class="p">.</span><span class="n">CreateCall</span><span class="p">(</span><span class="n">F</span><span class="p">,</span> <span class="n">Ops</span><span class="p">,</span> <span class="s">"binop"</span><span class="p">);</span>
+<span class="p">}</span>
+
+<span class="n">Value</span> <span class="o">*</span><span class="n">CallExprAST</span><span class="o">::</span><span class="n">codegen</span><span class="p">()</span> <span class="p">{</span>
+ <span class="c1">// Look up the name in the global module table.</span>
+ <span class="n">Function</span> <span class="o">*</span><span class="n">CalleeF</span> <span class="o">=</span> <span class="n">getFunction</span><span class="p">(</span><span class="n">Callee</span><span class="p">);</span>
+ <span class="k">if</span> <span class="p">(</span><span class="o">!</span><span class="n">CalleeF</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">ErrorV</span><span class="p">(</span><span class="s">"Unknown function referenced"</span><span class="p">);</span>
+
+ <span class="c1">// If argument mismatch error.</span>
+ <span class="k">if</span> <span class="p">(</span><span class="n">CalleeF</span><span class="o">-></span><span class="n">arg_size</span><span class="p">()</span> <span class="o">!=</span> <span class="n">Args</span><span class="p">.</span><span class="n">size</span><span class="p">())</span>
+ <span class="k">return</span> <span class="n">ErrorV</span><span class="p">(</span><span class="s">"Incorrect # arguments passed"</span><span class="p">);</span>
+
+ <span class="n">std</span><span class="o">::</span><span class="n">vector</span><span class="o"><</span><span class="n">Value</span> <span class="o">*></span> <span class="n">ArgsV</span><span class="p">;</span>
+ <span class="k">for</span> <span class="p">(</span><span class="kt">unsigned</span> <span class="n">i</span> <span class="o">=</span> <span class="mi">0</span><span class="p">,</span> <span class="n">e</span> <span class="o">=</span> <span class="n">Args</span><span class="p">.</span><span class="n">size</span><span class="p">();</span> <span class="n">i</span> <span class="o">!=</span> <span class="n">e</span><span class="p">;</span> <span class="o">++</span><span class="n">i</span><span class="p">)</span> <span class="p">{</span>
+ <span class="n">ArgsV</span><span class="p">.</span><span class="n">push_back</span><span class="p">(</span><span class="n">Args</span><span class="p">[</span><span class="n">i</span><span class="p">]</span><span class="o">-></span><span class="n">codegen</span><span class="p">());</span>
+ <span class="k">if</span> <span class="p">(</span><span class="o">!</span><span class="n">ArgsV</span><span class="p">.</span><span class="n">back</span><span class="p">())</span>
+ <span class="k">return</span> <span class="n">nullptr</span><span class="p">;</span>
+ <span class="p">}</span>
+
+ <span class="k">return</span> <span class="n">Builder</span><span class="p">.</span><span class="n">CreateCall</span><span class="p">(</span><span class="n">CalleeF</span><span class="p">,</span> <span class="n">ArgsV</span><span class="p">,</span> <span class="s">"calltmp"</span><span class="p">);</span>
+<span class="p">}</span>
+
+<span class="n">Value</span> <span class="o">*</span><span class="n">IfExprAST</span><span class="o">::</span><span class="n">codegen</span><span class="p">()</span> <span class="p">{</span>
+ <span class="n">Value</span> <span class="o">*</span><span class="n">CondV</span> <span class="o">=</span> <span class="n">Cond</span><span class="o">-></span><span class="n">codegen</span><span class="p">();</span>
+ <span class="k">if</span> <span class="p">(</span><span class="o">!</span><span class="n">CondV</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">nullptr</span><span class="p">;</span>
+
+ <span class="c1">// Convert condition to a bool by comparing equal to 0.0.</span>
+ <span class="n">CondV</span> <span class="o">=</span> <span class="n">Builder</span><span class="p">.</span><span class="n">CreateFCmpONE</span><span class="p">(</span>
+ <span class="n">CondV</span><span class="p">,</span> <span class="n">ConstantFP</span><span class="o">::</span><span class="n">get</span><span class="p">(</span><span class="n">getGlobalContext</span><span class="p">(),</span> <span class="n">APFloat</span><span class="p">(</span><span class="mf">0.0</span><span class="p">)),</span> <span class="s">"ifcond"</span><span class="p">);</span>
+
+ <span class="n">Function</span> <span class="o">*</span><span class="n">TheFunction</span> <span class="o">=</span> <span class="n">Builder</span><span class="p">.</span><span class="n">GetInsertBlock</span><span class="p">()</span><span class="o">-></span><span class="n">getParent</span><span class="p">();</span>
+
+ <span class="c1">// Create blocks for the then and else cases. Insert the 'then' block at the</span>
+ <span class="c1">// end of the function.</span>
+ <span class="n">BasicBlock</span> <span class="o">*</span><span class="n">ThenBB</span> <span class="o">=</span>
+ <span class="n">BasicBlock</span><span class="o">::</span><span class="n">Create</span><span class="p">(</span><span class="n">getGlobalContext</span><span class="p">(),</span> <span class="s">"then"</span><span class="p">,</span> <span class="n">TheFunction</span><span class="p">);</span>
+ <span class="n">BasicBlock</span> <span class="o">*</span><span class="n">ElseBB</span> <span class="o">=</span> <span class="n">BasicBlock</span><span class="o">::</span><span class="n">Create</span><span class="p">(</span><span class="n">getGlobalContext</span><span class="p">(),</span> <span class="s">"else"</span><span class="p">);</span>
+ <span class="n">BasicBlock</span> <span class="o">*</span><span class="n">MergeBB</span> <span class="o">=</span> <span class="n">BasicBlock</span><span class="o">::</span><span class="n">Create</span><span class="p">(</span><span class="n">getGlobalContext</span><span class="p">(),</span> <span class="s">"ifcont"</span><span class="p">);</span>
+
+ <span class="n">Builder</span><span class="p">.</span><span class="n">CreateCondBr</span><span class="p">(</span><span class="n">CondV</span><span class="p">,</span> <span class="n">ThenBB</span><span class="p">,</span> <span class="n">ElseBB</span><span class="p">);</span>
+
+ <span class="c1">// Emit then value.</span>
+ <span class="n">Builder</span><span class="p">.</span><span class="n">SetInsertPoint</span><span class="p">(</span><span class="n">ThenBB</span><span class="p">);</span>
+
+ <span class="n">Value</span> <span class="o">*</span><span class="n">ThenV</span> <span class="o">=</span> <span class="n">Then</span><span class="o">-></span><span class="n">codegen</span><span class="p">();</span>
+ <span class="k">if</span> <span class="p">(</span><span class="o">!</span><span class="n">ThenV</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">nullptr</span><span class="p">;</span>
+
+ <span class="n">Builder</span><span class="p">.</span><span class="n">CreateBr</span><span class="p">(</span><span class="n">MergeBB</span><span class="p">);</span>
+ <span class="c1">// Codegen of 'Then' can change the current block, update ThenBB for the PHI.</span>
+ <span class="n">ThenBB</span> <span class="o">=</span> <span class="n">Builder</span><span class="p">.</span><span class="n">GetInsertBlock</span><span class="p">();</span>
+
+ <span class="c1">// Emit else block.</span>
+ <span class="n">TheFunction</span><span class="o">-></span><span class="n">getBasicBlockList</span><span class="p">().</span><span class="n">push_back</span><span class="p">(</span><span class="n">ElseBB</span><span class="p">);</span>
+ <span class="n">Builder</span><span class="p">.</span><span class="n">SetInsertPoint</span><span class="p">(</span><span class="n">ElseBB</span><span class="p">);</span>
+
+ <span class="n">Value</span> <span class="o">*</span><span class="n">ElseV</span> <span class="o">=</span> <span class="n">Else</span><span class="o">-></span><span class="n">codegen</span><span class="p">();</span>
+ <span class="k">if</span> <span class="p">(</span><span class="o">!</span><span class="n">ElseV</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">nullptr</span><span class="p">;</span>
+
+ <span class="n">Builder</span><span class="p">.</span><span class="n">CreateBr</span><span class="p">(</span><span class="n">MergeBB</span><span class="p">);</span>
+ <span class="c1">// Codegen of 'Else' can change the current block, update ElseBB for the PHI.</span>
+ <span class="n">ElseBB</span> <span class="o">=</span> <span class="n">Builder</span><span class="p">.</span><span class="n">GetInsertBlock</span><span class="p">();</span>
+
+ <span class="c1">// Emit merge block.</span>
+ <span class="n">TheFunction</span><span class="o">-></span><span class="n">getBasicBlockList</span><span class="p">().</span><span class="n">push_back</span><span class="p">(</span><span class="n">MergeBB</span><span class="p">);</span>
+ <span class="n">Builder</span><span class="p">.</span><span class="n">SetInsertPoint</span><span class="p">(</span><span class="n">MergeBB</span><span class="p">);</span>
+ <span class="n">PHINode</span> <span class="o">*</span><span class="n">PN</span> <span class="o">=</span>
+ <span class="n">Builder</span><span class="p">.</span><span class="n">CreatePHI</span><span class="p">(</span><span class="n">Type</span><span class="o">::</span><span class="n">getDoubleTy</span><span class="p">(</span><span class="n">getGlobalContext</span><span class="p">()),</span> <span class="mi">2</span><span class="p">,</span> <span class="s">"iftmp"</span><span class="p">);</span>
+
+ <span class="n">PN</span><span class="o">-></span><span class="n">addIncoming</span><span class="p">(</span><span class="n">ThenV</span><span class="p">,</span> <span class="n">ThenBB</span><span class="p">);</span>
+ <span class="n">PN</span><span class="o">-></span><span class="n">addIncoming</span><span class="p">(</span><span class="n">ElseV</span><span class="p">,</span> <span class="n">ElseBB</span><span class="p">);</span>
+ <span class="k">return</span> <span class="n">PN</span><span class="p">;</span>
+<span class="p">}</span>
+
+<span class="c1">// Output for-loop as:</span>
+<span class="c1">// ...</span>
+<span class="c1">// start = startexpr</span>
+<span class="c1">// goto loop</span>
+<span class="c1">// loop:</span>
+<span class="c1">// variable = phi [start, loopheader], [nextvariable, loopend]</span>
+<span class="c1">// ...</span>
+<span class="c1">// bodyexpr</span>
+<span class="c1">// ...</span>
+<span class="c1">// loopend:</span>
+<span class="c1">// step = stepexpr</span>
+<span class="c1">// nextvariable = variable + step</span>
+<span class="c1">// endcond = endexpr</span>
+<span class="c1">// br endcond, loop, endloop</span>
+<span class="c1">// outloop:</span>
+<span class="n">Value</span> <span class="o">*</span><span class="n">ForExprAST</span><span class="o">::</span><span class="n">codegen</span><span class="p">()</span> <span class="p">{</span>
+ <span class="c1">// Emit the start code first, without 'variable' in scope.</span>
+ <span class="n">Value</span> <span class="o">*</span><span class="n">StartVal</span> <span class="o">=</span> <span class="n">Start</span><span class="o">-></span><span class="n">codegen</span><span class="p">();</span>
+ <span class="k">if</span> <span class="p">(</span><span class="o">!</span><span class="n">StartVal</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">nullptr</span><span class="p">;</span>
+
+ <span class="c1">// Make the new basic block for the loop header, inserting after current</span>
+ <span class="c1">// block.</span>
+ <span class="n">Function</span> <span class="o">*</span><span class="n">TheFunction</span> <span class="o">=</span> <span class="n">Builder</span><span class="p">.</span><span class="n">GetInsertBlock</span><span class="p">()</span><span class="o">-></span><span class="n">getParent</span><span class="p">();</span>
+ <span class="n">BasicBlock</span> <span class="o">*</span><span class="n">PreheaderBB</span> <span class="o">=</span> <span class="n">Builder</span><span class="p">.</span><span class="n">GetInsertBlock</span><span class="p">();</span>
+ <span class="n">BasicBlock</span> <span class="o">*</span><span class="n">LoopBB</span> <span class="o">=</span>
+ <span class="n">BasicBlock</span><span class="o">::</span><span class="n">Create</span><span class="p">(</span><span class="n">getGlobalContext</span><span class="p">(),</span> <span class="s">"loop"</span><span class="p">,</span> <span class="n">TheFunction</span><span class="p">);</span>
+
+ <span class="c1">// Insert an explicit fall through from the current block to the LoopBB.</span>
+ <span class="n">Builder</span><span class="p">.</span><span class="n">CreateBr</span><span class="p">(</span><span class="n">LoopBB</span><span class="p">);</span>
+
+ <span class="c1">// Start insertion in LoopBB.</span>
+ <span class="n">Builder</span><span class="p">.</span><span class="n">SetInsertPoint</span><span class="p">(</span><span class="n">LoopBB</span><span class="p">);</span>
+
+ <span class="c1">// Start the PHI node with an entry for Start.</span>
+ <span class="n">PHINode</span> <span class="o">*</span><span class="n">Variable</span> <span class="o">=</span> <span class="n">Builder</span><span class="p">.</span><span class="n">CreatePHI</span><span class="p">(</span><span class="n">Type</span><span class="o">::</span><span class="n">getDoubleTy</span><span class="p">(</span><span class="n">getGlobalContext</span><span class="p">()),</span>
+ <span class="mi">2</span><span class="p">,</span> <span class="n">VarName</span><span class="p">.</span><span class="n">c_str</span><span class="p">());</span>
+ <span class="n">Variable</span><span class="o">-></span><span class="n">addIncoming</span><span class="p">(</span><span class="n">StartVal</span><span class="p">,</span> <span class="n">PreheaderBB</span><span class="p">);</span>
+
+ <span class="c1">// Within the loop, the variable is defined equal to the PHI node. If it</span>
+ <span class="c1">// shadows an existing variable, we have to restore it, so save it now.</span>
+ <span class="n">Value</span> <span class="o">*</span><span class="n">OldVal</span> <span class="o">=</span> <span class="n">NamedValues</span><span class="p">[</span><span class="n">VarName</span><span class="p">];</span>
+ <span class="n">NamedValues</span><span class="p">[</span><span class="n">VarName</span><span class="p">]</span> <span class="o">=</span> <span class="n">Variable</span><span class="p">;</span>
+
+ <span class="c1">// Emit the body of the loop. This, like any other expr, can change the</span>
+ <span class="c1">// current BB. Note that we ignore the value computed by the body, but don't</span>
+ <span class="c1">// allow an error.</span>
+ <span class="k">if</span> <span class="p">(</span><span class="o">!</span><span class="n">Body</span><span class="o">-></span><span class="n">codegen</span><span class="p">())</span>
+ <span class="k">return</span> <span class="n">nullptr</span><span class="p">;</span>
+
+ <span class="c1">// Emit the step value.</span>
+ <span class="n">Value</span> <span class="o">*</span><span class="n">StepVal</span> <span class="o">=</span> <span class="n">nullptr</span><span class="p">;</span>
+ <span class="k">if</span> <span class="p">(</span><span class="n">Step</span><span class="p">)</span> <span class="p">{</span>
+ <span class="n">StepVal</span> <span class="o">=</span> <span class="n">Step</span><span class="o">-></span><span class="n">codegen</span><span class="p">();</span>
+ <span class="k">if</span> <span class="p">(</span><span class="o">!</span><span class="n">StepVal</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">nullptr</span><span class="p">;</span>
+ <span class="p">}</span> <span class="k">else</span> <span class="p">{</span>
+ <span class="c1">// If not specified, use 1.0.</span>
+ <span class="n">StepVal</span> <span class="o">=</span> <span class="n">ConstantFP</span><span class="o">::</span><span class="n">get</span><span class="p">(</span><span class="n">getGlobalContext</span><span class="p">(),</span> <span class="n">APFloat</span><span class="p">(</span><span class="mf">1.0</span><span class="p">));</span>
+ <span class="p">}</span>
+
+ <span class="n">Value</span> <span class="o">*</span><span class="n">NextVar</span> <span class="o">=</span> <span class="n">Builder</span><span class="p">.</span><span class="n">CreateFAdd</span><span class="p">(</span><span class="n">Variable</span><span class="p">,</span> <span class="n">StepVal</span><span class="p">,</span> <span class="s">"nextvar"</span><span class="p">);</span>
+
+ <span class="c1">// Compute the end condition.</span>
+ <span class="n">Value</span> <span class="o">*</span><span class="n">EndCond</span> <span class="o">=</span> <span class="n">End</span><span class="o">-></span><span class="n">codegen</span><span class="p">();</span>
+ <span class="k">if</span> <span class="p">(</span><span class="o">!</span><span class="n">EndCond</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">nullptr</span><span class="p">;</span>
+
+ <span class="c1">// Convert condition to a bool by comparing equal to 0.0.</span>
+ <span class="n">EndCond</span> <span class="o">=</span> <span class="n">Builder</span><span class="p">.</span><span class="n">CreateFCmpONE</span><span class="p">(</span>
+ <span class="n">EndCond</span><span class="p">,</span> <span class="n">ConstantFP</span><span class="o">::</span><span class="n">get</span><span class="p">(</span><span class="n">getGlobalContext</span><span class="p">(),</span> <span class="n">APFloat</span><span class="p">(</span><span class="mf">0.0</span><span class="p">)),</span> <span class="s">"loopcond"</span><span class="p">);</span>
+
+ <span class="c1">// Create the "after loop" block and insert it.</span>
+ <span class="n">BasicBlock</span> <span class="o">*</span><span class="n">LoopEndBB</span> <span class="o">=</span> <span class="n">Builder</span><span class="p">.</span><span class="n">GetInsertBlock</span><span class="p">();</span>
+ <span class="n">BasicBlock</span> <span class="o">*</span><span class="n">AfterBB</span> <span class="o">=</span>
+ <span class="n">BasicBlock</span><span class="o">::</span><span class="n">Create</span><span class="p">(</span><span class="n">getGlobalContext</span><span class="p">(),</span> <span class="s">"afterloop"</span><span class="p">,</span> <span class="n">TheFunction</span><span class="p">);</span>
+
+ <span class="c1">// Insert the conditional branch into the end of LoopEndBB.</span>
+ <span class="n">Builder</span><span class="p">.</span><span class="n">CreateCondBr</span><span class="p">(</span><span class="n">EndCond</span><span class="p">,</span> <span class="n">LoopBB</span><span class="p">,</span> <span class="n">AfterBB</span><span class="p">);</span>
+
+ <span class="c1">// Any new code will be inserted in AfterBB.</span>
+ <span class="n">Builder</span><span class="p">.</span><span class="n">SetInsertPoint</span><span class="p">(</span><span class="n">AfterBB</span><span class="p">);</span>
+
+ <span class="c1">// Add a new entry to the PHI node for the backedge.</span>
+ <span class="n">Variable</span><span class="o">-></span><span class="n">addIncoming</span><span class="p">(</span><span class="n">NextVar</span><span class="p">,</span> <span class="n">LoopEndBB</span><span class="p">);</span>
+
+ <span class="c1">// Restore the unshadowed variable.</span>
+ <span class="k">if</span> <span class="p">(</span><span class="n">OldVal</span><span class="p">)</span>
+ <span class="n">NamedValues</span><span class="p">[</span><span class="n">VarName</span><span class="p">]</span> <span class="o">=</span> <span class="n">OldVal</span><span class="p">;</span>
+ <span class="k">else</span>
+ <span class="n">NamedValues</span><span class="p">.</span><span class="n">erase</span><span class="p">(</span><span class="n">VarName</span><span class="p">);</span>
+
+ <span class="c1">// for expr always returns 0.0.</span>
+ <span class="k">return</span> <span class="n">Constant</span><span class="o">::</span><span class="n">getNullValue</span><span class="p">(</span><span class="n">Type</span><span class="o">::</span><span class="n">getDoubleTy</span><span class="p">(</span><span class="n">getGlobalContext</span><span class="p">()));</span>
+<span class="p">}</span>
+
+<span class="n">Function</span> <span class="o">*</span><span class="n">PrototypeAST</span><span class="o">::</span><span class="n">codegen</span><span class="p">()</span> <span class="p">{</span>
+ <span class="c1">// Make the function type: double(double,double) etc.</span>
+ <span class="n">std</span><span class="o">::</span><span class="n">vector</span><span class="o"><</span><span class="n">Type</span> <span class="o">*></span> <span class="n">Doubles</span><span class="p">(</span><span class="n">Args</span><span class="p">.</span><span class="n">size</span><span class="p">(),</span>
+ <span class="n">Type</span><span class="o">::</span><span class="n">getDoubleTy</span><span class="p">(</span><span class="n">getGlobalContext</span><span class="p">()));</span>
+ <span class="n">FunctionType</span> <span class="o">*</span><span class="n">FT</span> <span class="o">=</span>
+ <span class="n">FunctionType</span><span class="o">::</span><span class="n">get</span><span class="p">(</span><span class="n">Type</span><span class="o">::</span><span class="n">getDoubleTy</span><span class="p">(</span><span class="n">getGlobalContext</span><span class="p">()),</span> <span class="n">Doubles</span><span class="p">,</span> <span class="nb">false</span><span class="p">);</span>
+
+ <span class="n">Function</span> <span class="o">*</span><span class="n">F</span> <span class="o">=</span>
+ <span class="n">Function</span><span class="o">::</span><span class="n">Create</span><span class="p">(</span><span class="n">FT</span><span class="p">,</span> <span class="n">Function</span><span class="o">::</span><span class="n">ExternalLinkage</span><span class="p">,</span> <span class="n">Name</span><span class="p">,</span> <span class="n">TheModule</span><span class="p">.</span><span class="n">get</span><span class="p">());</span>
+
+ <span class="c1">// Set names for all arguments.</span>
+ <span class="kt">unsigned</span> <span class="n">Idx</span> <span class="o">=</span> <span class="mi">0</span><span class="p">;</span>
+ <span class="k">for</span> <span class="p">(</span><span class="k">auto</span> <span class="o">&</span><span class="n">Arg</span> <span class="o">:</span> <span class="n">F</span><span class="o">-></span><span class="n">args</span><span class="p">())</span>
+ <span class="n">Arg</span><span class="p">.</span><span class="n">setName</span><span class="p">(</span><span class="n">Args</span><span class="p">[</span><span class="n">Idx</span><span class="o">++</span><span class="p">]);</span>
+
+ <span class="k">return</span> <span class="n">F</span><span class="p">;</span>
+<span class="p">}</span>
+
+<span class="n">Function</span> <span class="o">*</span><span class="n">FunctionAST</span><span class="o">::</span><span class="n">codegen</span><span class="p">()</span> <span class="p">{</span>
+ <span class="c1">// Transfer ownership of the prototype to the FunctionProtos map, but keep a</span>
+ <span class="c1">// reference to it for use below.</span>
+ <span class="k">auto</span> <span class="o">&</span><span class="n">P</span> <span class="o">=</span> <span class="o">*</span><span class="n">Proto</span><span class="p">;</span>
+ <span class="n">FunctionProtos</span><span class="p">[</span><span class="n">Proto</span><span class="o">-></span><span class="n">getName</span><span class="p">()]</span> <span class="o">=</span> <span class="n">std</span><span class="o">::</span><span class="n">move</span><span class="p">(</span><span class="n">Proto</span><span class="p">);</span>
+ <span class="n">Function</span> <span class="o">*</span><span class="n">TheFunction</span> <span class="o">=</span> <span class="n">getFunction</span><span class="p">(</span><span class="n">P</span><span class="p">.</span><span class="n">getName</span><span class="p">());</span>
+ <span class="k">if</span> <span class="p">(</span><span class="o">!</span><span class="n">TheFunction</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">nullptr</span><span class="p">;</span>
+
+ <span class="c1">// If this is an operator, install it.</span>
+ <span class="k">if</span> <span class="p">(</span><span class="n">P</span><span class="p">.</span><span class="n">isBinaryOp</span><span class="p">())</span>
+ <span class="n">BinopPrecedence</span><span class="p">[</span><span class="n">P</span><span class="p">.</span><span class="n">getOperatorName</span><span class="p">()]</span> <span class="o">=</span> <span class="n">P</span><span class="p">.</span><span class="n">getBinaryPrecedence</span><span class="p">();</span>
+
+ <span class="c1">// Create a new basic block to start insertion into.</span>
+ <span class="n">BasicBlock</span> <span class="o">*</span><span class="n">BB</span> <span class="o">=</span> <span class="n">BasicBlock</span><span class="o">::</span><span class="n">Create</span><span class="p">(</span><span class="n">getGlobalContext</span><span class="p">(),</span> <span class="s">"entry"</span><span class="p">,</span> <span class="n">TheFunction</span><span class="p">);</span>
+ <span class="n">Builder</span><span class="p">.</span><span class="n">SetInsertPoint</span><span class="p">(</span><span class="n">BB</span><span class="p">);</span>
+
+ <span class="c1">// Record the function arguments in the NamedValues map.</span>
+ <span class="n">NamedValues</span><span class="p">.</span><span class="n">clear</span><span class="p">();</span>
+ <span class="k">for</span> <span class="p">(</span><span class="k">auto</span> <span class="o">&</span><span class="n">Arg</span> <span class="o">:</span> <span class="n">TheFunction</span><span class="o">-></span><span class="n">args</span><span class="p">())</span>
+ <span class="n">NamedValues</span><span class="p">[</span><span class="n">Arg</span><span class="p">.</span><span class="n">getName</span><span class="p">()]</span> <span class="o">=</span> <span class="o">&</span><span class="n">Arg</span><span class="p">;</span>
+
+ <span class="k">if</span> <span class="p">(</span><span class="n">Value</span> <span class="o">*</span><span class="n">RetVal</span> <span class="o">=</span> <span class="n">Body</span><span class="o">-></span><span class="n">codegen</span><span class="p">())</span> <span class="p">{</span>
+ <span class="c1">// Finish off the function.</span>
+ <span class="n">Builder</span><span class="p">.</span><span class="n">CreateRet</span><span class="p">(</span><span class="n">RetVal</span><span class="p">);</span>
+
+ <span class="c1">// Validate the generated code, checking for consistency.</span>
+ <span class="n">verifyFunction</span><span class="p">(</span><span class="o">*</span><span class="n">TheFunction</span><span class="p">);</span>
+
+ <span class="c1">// Run the optimizer on the function.</span>
+ <span class="n">TheFPM</span><span class="o">-></span><span class="n">run</span><span class="p">(</span><span class="o">*</span><span class="n">TheFunction</span><span class="p">);</span>
+
+ <span class="k">return</span> <span class="n">TheFunction</span><span class="p">;</span>
+ <span class="p">}</span>
+
+ <span class="c1">// Error reading body, remove function.</span>
+ <span class="n">TheFunction</span><span class="o">-></span><span class="n">eraseFromParent</span><span class="p">();</span>
+
+ <span class="k">if</span> <span class="p">(</span><span class="n">P</span><span class="p">.</span><span class="n">isBinaryOp</span><span class="p">())</span>
+ <span class="n">BinopPrecedence</span><span class="p">.</span><span class="n">erase</span><span class="p">(</span><span class="n">Proto</span><span class="o">-></span><span class="n">getOperatorName</span><span class="p">());</span>
+ <span class="k">return</span> <span class="n">nullptr</span><span class="p">;</span>
+<span class="p">}</span>
+
+<span class="c1">//===----------------------------------------------------------------------===//</span>
+<span class="c1">// Top-Level parsing and JIT Driver</span>
+<span class="c1">//===----------------------------------------------------------------------===//</span>
+
+<span class="k">static</span> <span class="kt">void</span> <span class="n">InitializeModuleAndPassManager</span><span class="p">()</span> <span class="p">{</span>
+ <span class="c1">// Open a new module.</span>
+ <span class="n">TheModule</span> <span class="o">=</span> <span class="n">llvm</span><span class="o">::</span><span class="n">make_unique</span><span class="o"><</span><span class="n">Module</span><span class="o">></span><span class="p">(</span><span class="s">"my cool jit"</span><span class="p">,</span> <span class="n">getGlobalContext</span><span class="p">());</span>
+ <span class="n">TheModule</span><span class="o">-></span><span class="n">setDataLayout</span><span class="p">(</span><span class="n">TheJIT</span><span class="o">-></span><span class="n">getTargetMachine</span><span class="p">().</span><span class="n">createDataLayout</span><span class="p">());</span>
+
+ <span class="c1">// Create a new pass manager attached to it.</span>
+ <span class="n">TheFPM</span> <span class="o">=</span> <span class="n">llvm</span><span class="o">::</span><span class="n">make_unique</span><span class="o"><</span><span class="n">legacy</span><span class="o">::</span><span class="n">FunctionPassManager</span><span class="o">></span><span class="p">(</span><span class="n">TheModule</span><span class="p">.</span><span class="n">get</span><span class="p">());</span>
+
+ <span class="c1">// Do simple "peephole" optimizations and bit-twiddling optzns.</span>
+ <span class="n">TheFPM</span><span class="o">-></span><span class="n">add</span><span class="p">(</span><span class="n">createInstructionCombiningPass</span><span class="p">());</span>
+ <span class="c1">// Reassociate expressions.</span>
+ <span class="n">TheFPM</span><span class="o">-></span><span class="n">add</span><span class="p">(</span><span class="n">createReassociatePass</span><span class="p">());</span>
+ <span class="c1">// Eliminate Common SubExpressions.</span>
+ <span class="n">TheFPM</span><span class="o">-></span><span class="n">add</span><span class="p">(</span><span class="n">createGVNPass</span><span class="p">());</span>
+ <span class="c1">// Simplify the control flow graph (deleting unreachable blocks, etc).</span>
+ <span class="n">TheFPM</span><span class="o">-></span><span class="n">add</span><span class="p">(</span><span class="n">createCFGSimplificationPass</span><span class="p">());</span>
+
+ <span class="n">TheFPM</span><span class="o">-></span><span class="n">doInitialization</span><span class="p">();</span>
+<span class="p">}</span>
+
+<span class="k">static</span> <span class="kt">void</span> <span class="n">HandleDefinition</span><span class="p">()</span> <span class="p">{</span>
+ <span class="k">if</span> <span class="p">(</span><span class="k">auto</span> <span class="n">FnAST</span> <span class="o">=</span> <span class="n">ParseDefinition</span><span class="p">())</span> <span class="p">{</span>
+ <span class="k">if</span> <span class="p">(</span><span class="k">auto</span> <span class="o">*</span><span class="n">FnIR</span> <span class="o">=</span> <span class="n">FnAST</span><span class="o">-></span><span class="n">codegen</span><span class="p">())</span> <span class="p">{</span>
+ <span class="n">fprintf</span><span class="p">(</span><span class="n">stderr</span><span class="p">,</span> <span class="s">"Read function definition:"</span><span class="p">);</span>
+ <span class="n">FnIR</span><span class="o">-></span><span class="n">dump</span><span class="p">();</span>
+ <span class="n">TheJIT</span><span class="o">-></span><span class="n">addModule</span><span class="p">(</span><span class="n">std</span><span class="o">::</span><span class="n">move</span><span class="p">(</span><span class="n">TheModule</span><span class="p">));</span>
+ <span class="n">InitializeModuleAndPassManager</span><span class="p">();</span>
+ <span class="p">}</span>
+ <span class="p">}</span> <span class="k">else</span> <span class="p">{</span>
+ <span class="c1">// Skip token for error recovery.</span>
+ <span class="n">getNextToken</span><span class="p">();</span>
+ <span class="p">}</span>
+<span class="p">}</span>
+
+<span class="k">static</span> <span class="kt">void</span> <span class="n">HandleExtern</span><span class="p">()</span> <span class="p">{</span>
+ <span class="k">if</span> <span class="p">(</span><span class="k">auto</span> <span class="n">ProtoAST</span> <span class="o">=</span> <span class="n">ParseExtern</span><span class="p">())</span> <span class="p">{</span>
+ <span class="k">if</span> <span class="p">(</span><span class="k">auto</span> <span class="o">*</span><span class="n">FnIR</span> <span class="o">=</span> <span class="n">ProtoAST</span><span class="o">-></span><span class="n">codegen</span><span class="p">())</span> <span class="p">{</span>
+ <span class="n">fprintf</span><span class="p">(</span><span class="n">stderr</span><span class="p">,</span> <span class="s">"Read extern: "</span><span class="p">);</span>
+ <span class="n">FnIR</span><span class="o">-></span><span class="n">dump</span><span class="p">();</span>
+ <span class="n">FunctionProtos</span><span class="p">[</span><span class="n">ProtoAST</span><span class="o">-></span><span class="n">getName</span><span class="p">()]</span> <span class="o">=</span> <span class="n">std</span><span class="o">::</span><span class="n">move</span><span class="p">(</span><span class="n">ProtoAST</span><span class="p">);</span>
+ <span class="p">}</span>
+ <span class="p">}</span> <span class="k">else</span> <span class="p">{</span>
+ <span class="c1">// Skip token for error recovery.</span>
+ <span class="n">getNextToken</span><span class="p">();</span>
+ <span class="p">}</span>
+<span class="p">}</span>
+
+<span class="k">static</span> <span class="kt">void</span> <span class="n">HandleTopLevelExpression</span><span class="p">()</span> <span class="p">{</span>
+ <span class="c1">// Evaluate a top-level expression into an anonymous function.</span>
+ <span class="k">if</span> <span class="p">(</span><span class="k">auto</span> <span class="n">FnAST</span> <span class="o">=</span> <span class="n">ParseTopLevelExpr</span><span class="p">())</span> <span class="p">{</span>
+ <span class="k">if</span> <span class="p">(</span><span class="n">FnAST</span><span class="o">-></span><span class="n">codegen</span><span class="p">())</span> <span class="p">{</span>
+
+ <span class="c1">// JIT the module containing the anonymous expression, keeping a handle so</span>
+ <span class="c1">// we can free it later.</span>
+ <span class="k">auto</span> <span class="n">H</span> <span class="o">=</span> <span class="n">TheJIT</span><span class="o">-></span><span class="n">addModule</span><span class="p">(</span><span class="n">std</span><span class="o">::</span><span class="n">move</span><span class="p">(</span><span class="n">TheModule</span><span class="p">));</span>
+ <span class="n">InitializeModuleAndPassManager</span><span class="p">();</span>
+
+ <span class="c1">// Search the JIT for the __anon_expr symbol.</span>
+ <span class="k">auto</span> <span class="n">ExprSymbol</span> <span class="o">=</span> <span class="n">TheJIT</span><span class="o">-></span><span class="n">findSymbol</span><span class="p">(</span><span class="s">"__anon_expr"</span><span class="p">);</span>
+ <span class="n">assert</span><span class="p">(</span><span class="n">ExprSymbol</span> <span class="o">&&</span> <span class="s">"Function not found"</span><span class="p">);</span>
+
+ <span class="c1">// Get the symbol's address and cast it to the right type (takes no</span>
+ <span class="c1">// arguments, returns a double) so we can call it as a native function.</span>
+ <span class="kt">double</span> <span class="p">(</span><span class="o">*</span><span class="n">FP</span><span class="p">)()</span> <span class="o">=</span> <span class="p">(</span><span class="kt">double</span> <span class="p">(</span><span class="o">*</span><span class="p">)())(</span><span class="kt">intptr_t</span><span class="p">)</span><span class="n">ExprSymbol</span><span class="p">.</span><span class="n">getAddress</span><span class="p">();</span>
+ <span class="n">fprintf</span><span class="p">(</span><span class="n">stderr</span><span class="p">,</span> <span class="s">"Evaluated to %f</span><span class="se">\n</span><span class="s">"</span><span class="p">,</span> <span class="n">FP</span><span class="p">());</span>
+
+ <span class="c1">// Delete the anonymous expression module from the JIT.</span>
+ <span class="n">TheJIT</span><span class="o">-></span><span class="n">removeModule</span><span class="p">(</span><span class="n">H</span><span class="p">);</span>
+ <span class="p">}</span>
+ <span class="p">}</span> <span class="k">else</span> <span class="p">{</span>
+ <span class="c1">// Skip token for error recovery.</span>
+ <span class="n">getNextToken</span><span class="p">();</span>
+ <span class="p">}</span>
+<span class="p">}</span>
+
+<span class="c1">/// top ::= definition | external | expression | ';'</span>
+<span class="k">static</span> <span class="kt">void</span> <span class="n">MainLoop</span><span class="p">()</span> <span class="p">{</span>
+ <span class="k">while</span> <span class="p">(</span><span class="mi">1</span><span class="p">)</span> <span class="p">{</span>
+ <span class="n">fprintf</span><span class="p">(</span><span class="n">stderr</span><span class="p">,</span> <span class="s">"ready> "</span><span class="p">);</span>
+ <span class="k">switch</span> <span class="p">(</span><span class="n">CurTok</span><span class="p">)</span> <span class="p">{</span>
+ <span class="k">case</span> <span class="n">tok_eof</span>:
+ <span class="k">return</span><span class="p">;</span>
+ <span class="k">case</span> <span class="sc">';'</span>: <span class="c1">// ignore top-level semicolons.</span>
+ <span class="n">getNextToken</span><span class="p">();</span>
+ <span class="k">break</span><span class="p">;</span>
+ <span class="k">case</span> <span class="n">tok_def</span>:
+ <span class="n">HandleDefinition</span><span class="p">();</span>
+ <span class="k">break</span><span class="p">;</span>
+ <span class="k">case</span> <span class="n">tok_extern</span>:
+ <span class="n">HandleExtern</span><span class="p">();</span>
+ <span class="k">break</span><span class="p">;</span>
+ <span class="nl">default:</span>
+ <span class="n">HandleTopLevelExpression</span><span class="p">();</span>
+ <span class="k">break</span><span class="p">;</span>
+ <span class="p">}</span>
+ <span class="p">}</span>
+<span class="p">}</span>
+
+<span class="c1">//===----------------------------------------------------------------------===//</span>
+<span class="c1">// "Library" functions that can be "extern'd" from user code.</span>
+<span class="c1">//===----------------------------------------------------------------------===//</span>
+
+<span class="c1">/// putchard - putchar that takes a double and returns 0.</span>
+<span class="k">extern</span> <span class="s">"C"</span> <span class="kt">double</span> <span class="n">putchard</span><span class="p">(</span><span class="kt">double</span> <span class="n">X</span><span class="p">)</span> <span class="p">{</span>
+ <span class="n">fputc</span><span class="p">((</span><span class="kt">char</span><span class="p">)</span><span class="n">X</span><span class="p">,</span> <span class="n">stderr</span><span class="p">);</span>
+ <span class="k">return</span> <span class="mi">0</span><span class="p">;</span>
+<span class="p">}</span>
+
+<span class="c1">/// printd - printf that takes a double prints it as "%f\n", returning 0.</span>
+<span class="k">extern</span> <span class="s">"C"</span> <span class="kt">double</span> <span class="n">printd</span><span class="p">(</span><span class="kt">double</span> <span class="n">X</span><span class="p">)</span> <span class="p">{</span>
+ <span class="n">fprintf</span><span class="p">(</span><span class="n">stderr</span><span class="p">,</span> <span class="s">"%f</span><span class="se">\n</span><span class="s">"</span><span class="p">,</span> <span class="n">X</span><span class="p">);</span>
+ <span class="k">return</span> <span class="mi">0</span><span class="p">;</span>
+<span class="p">}</span>
+
+<span class="c1">//===----------------------------------------------------------------------===//</span>
+<span class="c1">// Main driver code.</span>
+<span class="c1">//===----------------------------------------------------------------------===//</span>
+
+<span class="kt">int</span> <span class="n">main</span><span class="p">()</span> <span class="p">{</span>
+ <span class="n">InitializeNativeTarget</span><span class="p">();</span>
+ <span class="n">InitializeNativeTargetAsmPrinter</span><span class="p">();</span>
+ <span class="n">InitializeNativeTargetAsmParser</span><span class="p">();</span>
+
+ <span class="c1">// Install standard binary operators.</span>
+ <span class="c1">// 1 is lowest precedence.</span>
+ <span class="n">BinopPrecedence</span><span class="p">[</span><span class="sc">'<'</span><span class="p">]</span> <span class="o">=</span> <span class="mi">10</span><span class="p">;</span>
+ <span class="n">BinopPrecedence</span><span class="p">[</span><span class="sc">'+'</span><span class="p">]</span> <span class="o">=</span> <span class="mi">20</span><span class="p">;</span>
+ <span class="n">BinopPrecedence</span><span class="p">[</span><span class="sc">'-'</span><span class="p">]</span> <span class="o">=</span> <span class="mi">20</span><span class="p">;</span>
+ <span class="n">BinopPrecedence</span><span class="p">[</span><span class="sc">'*'</span><span class="p">]</span> <span class="o">=</span> <span class="mi">40</span><span class="p">;</span> <span class="c1">// highest.</span>
+
+ <span class="c1">// Prime the first token.</span>
+ <span class="n">fprintf</span><span class="p">(</span><span class="n">stderr</span><span class="p">,</span> <span class="s">"ready> "</span><span class="p">);</span>
+ <span class="n">getNextToken</span><span class="p">();</span>
+
+ <span class="n">TheJIT</span> <span class="o">=</span> <span class="n">llvm</span><span class="o">::</span><span class="n">make_unique</span><span class="o"><</span><span class="n">KaleidoscopeJIT</span><span class="o">></span><span class="p">();</span>
+
+ <span class="n">InitializeModuleAndPassManager</span><span class="p">();</span>
+
+ <span class="c1">// Run the main "interpreter loop" now.</span>
+ <span class="n">MainLoop</span><span class="p">();</span>
+
+ <span class="k">return</span> <span class="mi">0</span><span class="p">;</span>
+<span class="p">}</span>
+</pre></div>
+</div>
+<p><a class="reference external" href="LangImpl7.html">Next: Extending the language: mutable variables / SSA
+construction</a></p>
+</div>
+</div>
+
+
+ </div>
+ </div>
+ <div class="clearer"></div>
+ </div>
+ <div class="related">
+ <h3>Navigation</h3>
+ <ul>
+ <li class="right" style="margin-right: 10px">
+ <a href="../genindex.html" title="General Index"
+ >index</a></li>
+ <li class="right" >
+ <a href="LangImpl7.html" title="7. Kaleidoscope: Extending the Language: Mutable Variables"
+ >next</a> |</li>
+ <li class="right" >
+ <a href="LangImpl5.html" title="5. Kaleidoscope: Extending the Language: Control Flow"
+ >previous</a> |</li>
+ <li><a href="http://llvm.org/">LLVM Home</a> | </li>
+ <li><a href="../index.html">Documentation</a>»</li>
+
+ <li><a href="index.html" >LLVM Tutorial: Table of Contents</a> »</li>
+ </ul>
+ </div>
+ <div class="footer">
+ © Copyright 2003-2016, LLVM Project.
+ Last updated on 2016-07-11.
+ Created using <a href="http://sphinx-doc.org/">Sphinx</a> 1.2.2.
+ </div>
+ </body>
+</html>
\ No newline at end of file
Added: www-releases/trunk/3.8.1/docs/tutorial/LangImpl7.html
URL: http://llvm.org/viewvc/llvm-project/www-releases/trunk/3.8.1/docs/tutorial/LangImpl7.html?rev=275092&view=auto
==============================================================================
--- www-releases/trunk/3.8.1/docs/tutorial/LangImpl7.html (added)
+++ www-releases/trunk/3.8.1/docs/tutorial/LangImpl7.html Mon Jul 11 14:36:11 2016
@@ -0,0 +1,2131 @@
+
+<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN"
+ "http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd">
+
+
+<html xmlns="http://www.w3.org/1999/xhtml">
+ <head>
+ <meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
+
+ <title>7. Kaleidoscope: Extending the Language: Mutable Variables — LLVM 3.8 documentation</title>
+
+ <link rel="stylesheet" href="../_static/llvm-theme.css" type="text/css" />
+ <link rel="stylesheet" href="../_static/pygments.css" type="text/css" />
+
+ <script type="text/javascript">
+ var DOCUMENTATION_OPTIONS = {
+ URL_ROOT: '../',
+ VERSION: '3.8',
+ COLLAPSE_INDEX: false,
+ FILE_SUFFIX: '.html',
+ HAS_SOURCE: true
+ };
+ </script>
+ <script type="text/javascript" src="../_static/jquery.js"></script>
+ <script type="text/javascript" src="../_static/underscore.js"></script>
+ <script type="text/javascript" src="../_static/doctools.js"></script>
+ <link rel="top" title="LLVM 3.8 documentation" href="../index.html" />
+ <link rel="up" title="LLVM Tutorial: Table of Contents" href="index.html" />
+ <link rel="next" title="8. Kaleidoscope: Adding Debug Information" href="LangImpl8.html" />
+ <link rel="prev" title="6. Kaleidoscope: Extending the Language: User-defined Operators" href="LangImpl6.html" />
+<style type="text/css">
+ table.right { float: right; margin-left: 20px; }
+ table.right td { border: 1px solid #ccc; }
+</style>
+
+ </head>
+ <body>
+<div class="logo">
+ <a href="../index.html">
+ <img src="../_static/logo.png"
+ alt="LLVM Logo" width="250" height="88"/></a>
+</div>
+
+ <div class="related">
+ <h3>Navigation</h3>
+ <ul>
+ <li class="right" style="margin-right: 10px">
+ <a href="../genindex.html" title="General Index"
+ accesskey="I">index</a></li>
+ <li class="right" >
+ <a href="LangImpl8.html" title="8. Kaleidoscope: Adding Debug Information"
+ accesskey="N">next</a> |</li>
+ <li class="right" >
+ <a href="LangImpl6.html" title="6. Kaleidoscope: Extending the Language: User-defined Operators"
+ accesskey="P">previous</a> |</li>
+ <li><a href="http://llvm.org/">LLVM Home</a> | </li>
+ <li><a href="../index.html">Documentation</a>»</li>
+
+ <li><a href="index.html" accesskey="U">LLVM Tutorial: Table of Contents</a> »</li>
+ </ul>
+ </div>
+
+
+ <div class="document">
+ <div class="documentwrapper">
+ <div class="body">
+
+ <div class="section" id="kaleidoscope-extending-the-language-mutable-variables">
+<h1>7. Kaleidoscope: Extending the Language: Mutable Variables<a class="headerlink" href="#kaleidoscope-extending-the-language-mutable-variables" title="Permalink to this headline">¶</a></h1>
+<div class="contents local topic" id="contents">
+<ul class="simple">
+<li><a class="reference internal" href="#chapter-7-introduction" id="id2">Chapter 7 Introduction</a></li>
+<li><a class="reference internal" href="#why-is-this-a-hard-problem" id="id3">Why is this a hard problem?</a></li>
+<li><a class="reference internal" href="#memory-in-llvm" id="id4">Memory in LLVM</a></li>
+<li><a class="reference internal" href="#mutable-variables-in-kaleidoscope" id="id5">Mutable Variables in Kaleidoscope</a></li>
+<li><a class="reference internal" href="#adjusting-existing-variables-for-mutation" id="id6">Adjusting Existing Variables for Mutation</a></li>
+<li><a class="reference internal" href="#new-assignment-operator" id="id7">New Assignment Operator</a></li>
+<li><a class="reference internal" href="#user-defined-local-variables" id="id8">User-defined Local Variables</a></li>
+<li><a class="reference internal" href="#id1" id="id9">Full Code Listing</a></li>
+</ul>
+</div>
+<div class="section" id="chapter-7-introduction">
+<h2><a class="toc-backref" href="#id2">7.1. Chapter 7 Introduction</a><a class="headerlink" href="#chapter-7-introduction" title="Permalink to this headline">¶</a></h2>
+<p>Welcome to Chapter 7 of the “<a class="reference external" href="index.html">Implementing a language with
+LLVM</a>” tutorial. In chapters 1 through 6, we’ve built a
+very respectable, albeit simple, <a class="reference external" href="http://en.wikipedia.org/wiki/Functional_programming">functional programming
+language</a>. In our
+journey, we learned some parsing techniques, how to build and represent
+an AST, how to build LLVM IR, and how to optimize the resultant code as
+well as JIT compile it.</p>
+<p>While Kaleidoscope is interesting as a functional language, the fact
+that it is functional makes it “too easy” to generate LLVM IR for it. In
+particular, a functional language makes it very easy to build LLVM IR
+directly in <a class="reference external" href="http://en.wikipedia.org/wiki/Static_single_assignment_form">SSA
+form</a>.
+Since LLVM requires that the input code be in SSA form, this is a very
+nice property and it is often unclear to newcomers how to generate code
+for an imperative language with mutable variables.</p>
+<p>The short (and happy) summary of this chapter is that there is no need
+for your front-end to build SSA form: LLVM provides highly tuned and
+well tested support for this, though the way it works is a bit
+unexpected for some.</p>
+</div>
+<div class="section" id="why-is-this-a-hard-problem">
+<h2><a class="toc-backref" href="#id3">7.2. Why is this a hard problem?</a><a class="headerlink" href="#why-is-this-a-hard-problem" title="Permalink to this headline">¶</a></h2>
+<p>To understand why mutable variables cause complexities in SSA
+construction, consider this extremely simple C example:</p>
+<div class="highlight-c"><div class="highlight"><pre><span class="kt">int</span> <span class="n">G</span><span class="p">,</span> <span class="n">H</span><span class="p">;</span>
+<span class="kt">int</span> <span class="nf">test</span><span class="p">(</span><span class="kt">_Bool</span> <span class="n">Condition</span><span class="p">)</span> <span class="p">{</span>
+ <span class="kt">int</span> <span class="n">X</span><span class="p">;</span>
+ <span class="k">if</span> <span class="p">(</span><span class="n">Condition</span><span class="p">)</span>
+ <span class="n">X</span> <span class="o">=</span> <span class="n">G</span><span class="p">;</span>
+ <span class="k">else</span>
+ <span class="n">X</span> <span class="o">=</span> <span class="n">H</span><span class="p">;</span>
+ <span class="k">return</span> <span class="n">X</span><span class="p">;</span>
+<span class="p">}</span>
+</pre></div>
+</div>
+<p>In this case, we have the variable “X”, whose value depends on the path
+executed in the program. Because there are two different possible values
+for X before the return instruction, a PHI node is inserted to merge the
+two values. The LLVM IR that we want for this example looks like this:</p>
+<div class="highlight-llvm"><div class="highlight"><pre><span class="vg">@G</span> <span class="p">=</span> <span class="k">weak</span> <span class="k">global</span> <span class="k">i32</span> <span class="m">0</span> <span class="c">; type of @G is i32*</span>
+<span class="vg">@H</span> <span class="p">=</span> <span class="k">weak</span> <span class="k">global</span> <span class="k">i32</span> <span class="m">0</span> <span class="c">; type of @H is i32*</span>
+
+<span class="k">define</span> <span class="k">i32</span> <span class="vg">@test</span><span class="p">(</span><span class="k">i1</span> <span class="nv">%Condition</span><span class="p">)</span> <span class="p">{</span>
+<span class="nl">entry:</span>
+ <span class="k">br</span> <span class="k">i1</span> <span class="nv">%Condition</span><span class="p">,</span> <span class="kt">label</span> <span class="nv">%cond_true</span><span class="p">,</span> <span class="kt">label</span> <span class="nv">%cond_false</span>
+
+<span class="nl">cond_true:</span>
+ <span class="nv">%X.0</span> <span class="p">=</span> <span class="k">load</span> <span class="k">i32</span><span class="p">*</span> <span class="vg">@G</span>
+ <span class="k">br</span> <span class="kt">label</span> <span class="nv">%cond_next</span>
+
+<span class="nl">cond_false:</span>
+ <span class="nv">%X.1</span> <span class="p">=</span> <span class="k">load</span> <span class="k">i32</span><span class="p">*</span> <span class="vg">@H</span>
+ <span class="k">br</span> <span class="kt">label</span> <span class="nv">%cond_next</span>
+
+<span class="nl">cond_next:</span>
+ <span class="nv">%X.2</span> <span class="p">=</span> <span class="k">phi</span> <span class="k">i32</span> <span class="p">[</span> <span class="nv">%X.1</span><span class="p">,</span> <span class="nv">%cond_false</span> <span class="p">],</span> <span class="p">[</span> <span class="nv">%X.0</span><span class="p">,</span> <span class="nv">%cond_true</span> <span class="p">]</span>
+ <span class="k">ret</span> <span class="k">i32</span> <span class="nv">%X.2</span>
+<span class="p">}</span>
+</pre></div>
+</div>
+<p>In this example, the loads from the G and H global variables are
+explicit in the LLVM IR, and they live in the then/else branches of the
+if statement (cond_true/cond_false). In order to merge the incoming
+values, the X.2 phi node in the cond_next block selects the right value
+to use based on where control flow is coming from: if control flow comes
+from the cond_false block, X.2 gets the value of X.1. Alternatively, if
+control flow comes from cond_true, it gets the value of X.0. The intent
+of this chapter is not to explain the details of SSA form. For more
+information, see one of the many <a class="reference external" href="http://en.wikipedia.org/wiki/Static_single_assignment_form">online
+references</a>.</p>
+<p>The question for this article is “who places the phi nodes when lowering
+assignments to mutable variables?”. The issue here is that LLVM
+<em>requires</em> that its IR be in SSA form: there is no “non-ssa” mode for
+it. However, SSA construction requires non-trivial algorithms and data
+structures, so it is inconvenient and wasteful for every front-end to
+have to reproduce this logic.</p>
+</div>
+<div class="section" id="memory-in-llvm">
+<h2><a class="toc-backref" href="#id4">7.3. Memory in LLVM</a><a class="headerlink" href="#memory-in-llvm" title="Permalink to this headline">¶</a></h2>
+<p>The ‘trick’ here is that while LLVM does require all register values to
+be in SSA form, it does not require (or permit) memory objects to be in
+SSA form. In the example above, note that the loads from G and H are
+direct accesses to G and H: they are not renamed or versioned. This
+differs from some other compiler systems, which do try to version memory
+objects. In LLVM, instead of encoding dataflow analysis of memory into
+the LLVM IR, it is handled with <a class="reference external" href="../WritingAnLLVMPass.html">Analysis
+Passes</a> which are computed on demand.</p>
+<p>With this in mind, the high-level idea is that we want to make a stack
+variable (which lives in memory, because it is on the stack) for each
+mutable object in a function. To take advantage of this trick, we need
+to talk about how LLVM represents stack variables.</p>
+<p>In LLVM, all memory accesses are explicit with load/store instructions,
+and it is carefully designed not to have (or need) an “address-of”
+operator. Notice how the type of the @G/@H global variables is actually
+“i32*” even though the variable is defined as “i32”. What this means is
+that @G defines <em>space</em> for an i32 in the global data area, but its
+<em>name</em> actually refers to the address for that space. Stack variables
+work the same way, except that instead of being declared with global
+variable definitions, they are declared with the <a class="reference external" href="../LangRef.html#alloca-instruction">LLVM alloca
+instruction</a>:</p>
+<div class="highlight-llvm"><div class="highlight"><pre><span class="k">define</span> <span class="k">i32</span> <span class="vg">@example</span><span class="p">()</span> <span class="p">{</span>
+<span class="nl">entry:</span>
+ <span class="nv">%X</span> <span class="p">=</span> <span class="k">alloca</span> <span class="k">i32</span> <span class="c">; type of %X is i32*.</span>
+ <span class="p">...</span>
+ <span class="nv">%tmp</span> <span class="p">=</span> <span class="k">load</span> <span class="k">i32</span><span class="p">*</span> <span class="nv">%X</span> <span class="c">; load the stack value %X from the stack.</span>
+ <span class="nv">%tmp2</span> <span class="p">=</span> <span class="k">add</span> <span class="k">i32</span> <span class="nv">%tmp</span><span class="p">,</span> <span class="m">1</span> <span class="c">; increment it</span>
+ <span class="k">store</span> <span class="k">i32</span> <span class="nv">%tmp2</span><span class="p">,</span> <span class="k">i32</span><span class="p">*</span> <span class="nv">%X</span> <span class="c">; store it back</span>
+ <span class="p">...</span>
+</pre></div>
+</div>
+<p>This code shows an example of how you can declare and manipulate a stack
+variable in the LLVM IR. Stack memory allocated with the alloca
+instruction is fully general: you can pass the address of the stack slot
+to functions, you can store it in other variables, etc. In our example
+above, we could rewrite the example to use the alloca technique to avoid
+using a PHI node:</p>
+<div class="highlight-llvm"><div class="highlight"><pre><span class="vg">@G</span> <span class="p">=</span> <span class="k">weak</span> <span class="k">global</span> <span class="k">i32</span> <span class="m">0</span> <span class="c">; type of @G is i32*</span>
+<span class="vg">@H</span> <span class="p">=</span> <span class="k">weak</span> <span class="k">global</span> <span class="k">i32</span> <span class="m">0</span> <span class="c">; type of @H is i32*</span>
+
+<span class="k">define</span> <span class="k">i32</span> <span class="vg">@test</span><span class="p">(</span><span class="k">i1</span> <span class="nv">%Condition</span><span class="p">)</span> <span class="p">{</span>
+<span class="nl">entry:</span>
+ <span class="nv">%X</span> <span class="p">=</span> <span class="k">alloca</span> <span class="k">i32</span> <span class="c">; type of %X is i32*.</span>
+ <span class="k">br</span> <span class="k">i1</span> <span class="nv">%Condition</span><span class="p">,</span> <span class="kt">label</span> <span class="nv">%cond_true</span><span class="p">,</span> <span class="kt">label</span> <span class="nv">%cond_false</span>
+
+<span class="nl">cond_true:</span>
+ <span class="nv">%X.0</span> <span class="p">=</span> <span class="k">load</span> <span class="k">i32</span><span class="p">*</span> <span class="vg">@G</span>
+ <span class="k">store</span> <span class="k">i32</span> <span class="nv">%X.0</span><span class="p">,</span> <span class="k">i32</span><span class="p">*</span> <span class="nv">%X</span> <span class="c">; Update X</span>
+ <span class="k">br</span> <span class="kt">label</span> <span class="nv">%cond_next</span>
+
+<span class="nl">cond_false:</span>
+ <span class="nv">%X.1</span> <span class="p">=</span> <span class="k">load</span> <span class="k">i32</span><span class="p">*</span> <span class="vg">@H</span>
+ <span class="k">store</span> <span class="k">i32</span> <span class="nv">%X.1</span><span class="p">,</span> <span class="k">i32</span><span class="p">*</span> <span class="nv">%X</span> <span class="c">; Update X</span>
+ <span class="k">br</span> <span class="kt">label</span> <span class="nv">%cond_next</span>
+
+<span class="nl">cond_next:</span>
+ <span class="nv">%X.2</span> <span class="p">=</span> <span class="k">load</span> <span class="k">i32</span><span class="p">*</span> <span class="nv">%X</span> <span class="c">; Read X</span>
+ <span class="k">ret</span> <span class="k">i32</span> <span class="nv">%X.2</span>
+<span class="p">}</span>
+</pre></div>
+</div>
+<p>With this, we have discovered a way to handle arbitrary mutable
+variables without the need to create Phi nodes at all:</p>
+<ol class="arabic simple">
+<li>Each mutable variable becomes a stack allocation.</li>
+<li>Each read of the variable becomes a load from the stack.</li>
+<li>Each update of the variable becomes a store to the stack.</li>
+<li>Taking the address of a variable just uses the stack address
+directly.</li>
+</ol>
+<p>While this solution has solved our immediate problem, it introduced
+another one: we have now apparently introduced a lot of stack traffic
+for very simple and common operations, a major performance problem.
+Fortunately for us, the LLVM optimizer has a highly-tuned optimization
+pass named “mem2reg” that handles this case, promoting allocas like this
+into SSA registers, inserting Phi nodes as appropriate. If you run this
+example through the pass, for example, you’ll get:</p>
+<div class="highlight-bash"><div class="highlight"><pre><span class="nv">$ </span>llvm-as < example.ll | opt -mem2reg | llvm-dis
+ at G <span class="o">=</span> weak global i32 0
+ at H <span class="o">=</span> weak global i32 0
+
+define i32 @test<span class="o">(</span>i1 %Condition<span class="o">)</span> <span class="o">{</span>
+entry:
+ br i1 %Condition, label %cond_true, label %cond_false
+
+cond_true:
+ %X.0 <span class="o">=</span> load i32* @G
+ br label %cond_next
+
+cond_false:
+ %X.1 <span class="o">=</span> load i32* @H
+ br label %cond_next
+
+cond_next:
+ %X.01 <span class="o">=</span> phi i32 <span class="o">[</span> %X.1, %cond_false <span class="o">]</span>, <span class="o">[</span> %X.0, %cond_true <span class="o">]</span>
+ ret i32 %X.01
+<span class="o">}</span>
+</pre></div>
+</div>
+<p>The mem2reg pass implements the standard “iterated dominance frontier”
+algorithm for constructing SSA form and has a number of optimizations
+that speed up (very common) degenerate cases. The mem2reg optimization
+pass is the answer to dealing with mutable variables, and we highly
+recommend that you depend on it. Note that mem2reg only works on
+variables in certain circumstances:</p>
+<ol class="arabic simple">
+<li>mem2reg is alloca-driven: it looks for allocas and if it can handle
+them, it promotes them. It does not apply to global variables or heap
+allocations.</li>
+<li>mem2reg only looks for alloca instructions in the entry block of the
+function. Being in the entry block guarantees that the alloca is only
+executed once, which makes analysis simpler.</li>
+<li>mem2reg only promotes allocas whose uses are direct loads and stores.
+If the address of the stack object is passed to a function, or if any
+funny pointer arithmetic is involved, the alloca will not be
+promoted.</li>
+<li>mem2reg only works on allocas of <a class="reference external" href="../LangRef.html#first-class-types">first
+class</a> values (such as pointers,
+scalars and vectors), and only if the array size of the allocation is
+1 (or missing in the .ll file). mem2reg is not capable of promoting
+structs or arrays to registers. Note that the “scalarrepl” pass is
+more powerful and can promote structs, “unions”, and arrays in many
+cases.</li>
+</ol>
+<p>All of these properties are easy to satisfy for most imperative
+languages, and we’ll illustrate it below with Kaleidoscope. The final
+question you may be asking is: should I bother with this nonsense for my
+front-end? Wouldn’t it be better if I just did SSA construction
+directly, avoiding use of the mem2reg optimization pass? In short, we
+strongly recommend that you use this technique for building SSA form,
+unless there is an extremely good reason not to. Using this technique
+is:</p>
+<ul class="simple">
+<li>Proven and well tested: clang uses this technique
+for local mutable variables. As such, the most common clients of LLVM
+are using this to handle a bulk of their variables. You can be sure
+that bugs are found fast and fixed early.</li>
+<li>Extremely Fast: mem2reg has a number of special cases that make it
+fast in common cases as well as fully general. For example, it has
+fast-paths for variables that are only used in a single block,
+variables that only have one assignment point, good heuristics to
+avoid insertion of unneeded phi nodes, etc.</li>
+<li>Needed for debug info generation: <a class="reference external" href="../SourceLevelDebugging.html">Debug information in
+LLVM</a> relies on having the address of
+the variable exposed so that debug info can be attached to it. This
+technique dovetails very naturally with this style of debug info.</li>
+</ul>
+<p>If nothing else, this makes it much easier to get your front-end up and
+running, and is very simple to implement. Lets extend Kaleidoscope with
+mutable variables now!</p>
+</div>
+<div class="section" id="mutable-variables-in-kaleidoscope">
+<h2><a class="toc-backref" href="#id5">7.4. Mutable Variables in Kaleidoscope</a><a class="headerlink" href="#mutable-variables-in-kaleidoscope" title="Permalink to this headline">¶</a></h2>
+<p>Now that we know the sort of problem we want to tackle, lets see what
+this looks like in the context of our little Kaleidoscope language.
+We’re going to add two features:</p>
+<ol class="arabic simple">
+<li>The ability to mutate variables with the ‘=’ operator.</li>
+<li>The ability to define new variables.</li>
+</ol>
+<p>While the first item is really what this is about, we only have
+variables for incoming arguments as well as for induction variables, and
+redefining those only goes so far :). Also, the ability to define new
+variables is a useful thing regardless of whether you will be mutating
+them. Here’s a motivating example that shows how we could use these:</p>
+<div class="highlight-python"><div class="highlight"><pre># Define ':' for sequencing: as a low-precedence operator that ignores operands
+# and just returns the RHS.
+def binary : 1 (x y) y;
+
+# Recursive fib, we could do this before.
+def fib(x)
+ if (x < 3) then
+ 1
+ else
+ fib(x-1)+fib(x-2);
+
+# Iterative fib.
+def fibi(x)
+ var a = 1, b = 1, c in
+ (for i = 3, i < x in
+ c = a + b :
+ a = b :
+ b = c) :
+ b;
+
+# Call it.
+fibi(10);
+</pre></div>
+</div>
+<p>In order to mutate variables, we have to change our existing variables
+to use the “alloca trick”. Once we have that, we’ll add our new
+operator, then extend Kaleidoscope to support new variable definitions.</p>
+</div>
+<div class="section" id="adjusting-existing-variables-for-mutation">
+<h2><a class="toc-backref" href="#id6">7.5. Adjusting Existing Variables for Mutation</a><a class="headerlink" href="#adjusting-existing-variables-for-mutation" title="Permalink to this headline">¶</a></h2>
+<p>The symbol table in Kaleidoscope is managed at code generation time by
+the ‘<tt class="docutils literal"><span class="pre">NamedValues</span></tt>‘ map. This map currently keeps track of the LLVM
+“Value*” that holds the double value for the named variable. In order
+to support mutation, we need to change this slightly, so that it
+<tt class="docutils literal"><span class="pre">NamedValues</span></tt> holds the <em>memory location</em> of the variable in question.
+Note that this change is a refactoring: it changes the structure of the
+code, but does not (by itself) change the behavior of the compiler. All
+of these changes are isolated in the Kaleidoscope code generator.</p>
+<p>At this point in Kaleidoscope’s development, it only supports variables
+for two things: incoming arguments to functions and the induction
+variable of ‘for’ loops. For consistency, we’ll allow mutation of these
+variables in addition to other user-defined variables. This means that
+these will both need memory locations.</p>
+<p>To start our transformation of Kaleidoscope, we’ll change the
+NamedValues map so that it maps to AllocaInst* instead of Value*. Once
+we do this, the C++ compiler will tell us what parts of the code we need
+to update:</p>
+<div class="highlight-c++"><div class="highlight"><pre><span class="k">static</span> <span class="n">std</span><span class="o">::</span><span class="n">map</span><span class="o"><</span><span class="n">std</span><span class="o">::</span><span class="n">string</span><span class="p">,</span> <span class="n">AllocaInst</span><span class="o">*></span> <span class="n">NamedValues</span><span class="p">;</span>
+</pre></div>
+</div>
+<p>Also, since we will need to create these alloca’s, we’ll use a helper
+function that ensures that the allocas are created in the entry block of
+the function:</p>
+<div class="highlight-c++"><div class="highlight"><pre><span class="c1">/// CreateEntryBlockAlloca - Create an alloca instruction in the entry block of</span>
+<span class="c1">/// the function. This is used for mutable variables etc.</span>
+<span class="k">static</span> <span class="n">AllocaInst</span> <span class="o">*</span><span class="nf">CreateEntryBlockAlloca</span><span class="p">(</span><span class="n">Function</span> <span class="o">*</span><span class="n">TheFunction</span><span class="p">,</span>
+ <span class="k">const</span> <span class="n">std</span><span class="o">::</span><span class="n">string</span> <span class="o">&</span><span class="n">VarName</span><span class="p">)</span> <span class="p">{</span>
+ <span class="n">IRBuilder</span><span class="o"><></span> <span class="n">TmpB</span><span class="p">(</span><span class="o">&</span><span class="n">TheFunction</span><span class="o">-></span><span class="n">getEntryBlock</span><span class="p">(),</span>
+ <span class="n">TheFunction</span><span class="o">-></span><span class="n">getEntryBlock</span><span class="p">().</span><span class="n">begin</span><span class="p">());</span>
+ <span class="k">return</span> <span class="n">TmpB</span><span class="p">.</span><span class="n">CreateAlloca</span><span class="p">(</span><span class="n">Type</span><span class="o">::</span><span class="n">getDoubleTy</span><span class="p">(</span><span class="n">getGlobalContext</span><span class="p">()),</span> <span class="mi">0</span><span class="p">,</span>
+ <span class="n">VarName</span><span class="p">.</span><span class="n">c_str</span><span class="p">());</span>
+<span class="p">}</span>
+</pre></div>
+</div>
+<p>This funny looking code creates an IRBuilder object that is pointing at
+the first instruction (.begin()) of the entry block. It then creates an
+alloca with the expected name and returns it. Because all values in
+Kaleidoscope are doubles, there is no need to pass in a type to use.</p>
+<p>With this in place, the first functionality change we want to make is to
+variable references. In our new scheme, variables live on the stack, so
+code generating a reference to them actually needs to produce a load
+from the stack slot:</p>
+<div class="highlight-c++"><div class="highlight"><pre><span class="n">Value</span> <span class="o">*</span><span class="n">VariableExprAST</span><span class="o">::</span><span class="n">codegen</span><span class="p">()</span> <span class="p">{</span>
+ <span class="c1">// Look this variable up in the function.</span>
+ <span class="n">Value</span> <span class="o">*</span><span class="n">V</span> <span class="o">=</span> <span class="n">NamedValues</span><span class="p">[</span><span class="n">Name</span><span class="p">];</span>
+ <span class="k">if</span> <span class="p">(</span><span class="o">!</span><span class="n">V</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">ErrorV</span><span class="p">(</span><span class="s">"Unknown variable name"</span><span class="p">);</span>
+
+ <span class="c1">// Load the value.</span>
+ <span class="k">return</span> <span class="n">Builder</span><span class="p">.</span><span class="n">CreateLoad</span><span class="p">(</span><span class="n">V</span><span class="p">,</span> <span class="n">Name</span><span class="p">.</span><span class="n">c_str</span><span class="p">());</span>
+<span class="p">}</span>
+</pre></div>
+</div>
+<p>As you can see, this is pretty straightforward. Now we need to update
+the things that define the variables to set up the alloca. We’ll start
+with <tt class="docutils literal"><span class="pre">ForExprAST::codegen()</span></tt> (see the <a class="reference external" href="#id1">full code listing</a> for
+the unabridged code):</p>
+<div class="highlight-c++"><div class="highlight"><pre><span class="n">Function</span> <span class="o">*</span><span class="n">TheFunction</span> <span class="o">=</span> <span class="n">Builder</span><span class="p">.</span><span class="n">GetInsertBlock</span><span class="p">()</span><span class="o">-></span><span class="n">getParent</span><span class="p">();</span>
+
+<span class="c1">// Create an alloca for the variable in the entry block.</span>
+<span class="n">AllocaInst</span> <span class="o">*</span><span class="n">Alloca</span> <span class="o">=</span> <span class="n">CreateEntryBlockAlloca</span><span class="p">(</span><span class="n">TheFunction</span><span class="p">,</span> <span class="n">VarName</span><span class="p">);</span>
+
+ <span class="c1">// Emit the start code first, without 'variable' in scope.</span>
+<span class="n">Value</span> <span class="o">*</span><span class="n">StartVal</span> <span class="o">=</span> <span class="n">Start</span><span class="o">-></span><span class="n">codegen</span><span class="p">();</span>
+<span class="k">if</span> <span class="p">(</span><span class="o">!</span><span class="n">StartVal</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">nullptr</span><span class="p">;</span>
+
+<span class="c1">// Store the value into the alloca.</span>
+<span class="n">Builder</span><span class="p">.</span><span class="n">CreateStore</span><span class="p">(</span><span class="n">StartVal</span><span class="p">,</span> <span class="n">Alloca</span><span class="p">);</span>
+<span class="p">...</span>
+
+<span class="c1">// Compute the end condition.</span>
+<span class="n">Value</span> <span class="o">*</span><span class="n">EndCond</span> <span class="o">=</span> <span class="n">End</span><span class="o">-></span><span class="n">codegen</span><span class="p">();</span>
+<span class="k">if</span> <span class="p">(</span><span class="o">!</span><span class="n">EndCond</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">nullptr</span><span class="p">;</span>
+
+<span class="c1">// Reload, increment, and restore the alloca. This handles the case where</span>
+<span class="c1">// the body of the loop mutates the variable.</span>
+<span class="n">Value</span> <span class="o">*</span><span class="n">CurVar</span> <span class="o">=</span> <span class="n">Builder</span><span class="p">.</span><span class="n">CreateLoad</span><span class="p">(</span><span class="n">Alloca</span><span class="p">);</span>
+<span class="n">Value</span> <span class="o">*</span><span class="n">NextVar</span> <span class="o">=</span> <span class="n">Builder</span><span class="p">.</span><span class="n">CreateFAdd</span><span class="p">(</span><span class="n">CurVar</span><span class="p">,</span> <span class="n">StepVal</span><span class="p">,</span> <span class="s">"nextvar"</span><span class="p">);</span>
+<span class="n">Builder</span><span class="p">.</span><span class="n">CreateStore</span><span class="p">(</span><span class="n">NextVar</span><span class="p">,</span> <span class="n">Alloca</span><span class="p">);</span>
+<span class="p">...</span>
+</pre></div>
+</div>
+<p>This code is virtually identical to the code <a class="reference external" href="LangImpl5.html#code-generation-for-the-for-loop">before we allowed mutable
+variables</a>. The big difference is that we
+no longer have to construct a PHI node, and we use load/store to access
+the variable as needed.</p>
+<p>To support mutable argument variables, we need to also make allocas for
+them. The code for this is also pretty simple:</p>
+<div class="highlight-c++"><div class="highlight"><pre><span class="c1">/// CreateArgumentAllocas - Create an alloca for each argument and register the</span>
+<span class="c1">/// argument in the symbol table so that references to it will succeed.</span>
+<span class="kt">void</span> <span class="n">PrototypeAST</span><span class="o">::</span><span class="n">CreateArgumentAllocas</span><span class="p">(</span><span class="n">Function</span> <span class="o">*</span><span class="n">F</span><span class="p">)</span> <span class="p">{</span>
+ <span class="n">Function</span><span class="o">::</span><span class="n">arg_iterator</span> <span class="n">AI</span> <span class="o">=</span> <span class="n">F</span><span class="o">-></span><span class="n">arg_begin</span><span class="p">();</span>
+ <span class="k">for</span> <span class="p">(</span><span class="kt">unsigned</span> <span class="n">Idx</span> <span class="o">=</span> <span class="mi">0</span><span class="p">,</span> <span class="n">e</span> <span class="o">=</span> <span class="n">Args</span><span class="p">.</span><span class="n">size</span><span class="p">();</span> <span class="n">Idx</span> <span class="o">!=</span> <span class="n">e</span><span class="p">;</span> <span class="o">++</span><span class="n">Idx</span><span class="p">,</span> <span class="o">++</span><span class="n">AI</span><span class="p">)</span> <span class="p">{</span>
+ <span class="c1">// Create an alloca for this variable.</span>
+ <span class="n">AllocaInst</span> <span class="o">*</span><span class="n">Alloca</span> <span class="o">=</span> <span class="n">CreateEntryBlockAlloca</span><span class="p">(</span><span class="n">F</span><span class="p">,</span> <span class="n">Args</span><span class="p">[</span><span class="n">Idx</span><span class="p">]);</span>
+
+ <span class="c1">// Store the initial value into the alloca.</span>
+ <span class="n">Builder</span><span class="p">.</span><span class="n">CreateStore</span><span class="p">(</span><span class="n">AI</span><span class="p">,</span> <span class="n">Alloca</span><span class="p">);</span>
+
+ <span class="c1">// Add arguments to variable symbol table.</span>
+ <span class="n">NamedValues</span><span class="p">[</span><span class="n">Args</span><span class="p">[</span><span class="n">Idx</span><span class="p">]]</span> <span class="o">=</span> <span class="n">Alloca</span><span class="p">;</span>
+ <span class="p">}</span>
+<span class="p">}</span>
+</pre></div>
+</div>
+<p>For each argument, we make an alloca, store the input value to the
+function into the alloca, and register the alloca as the memory location
+for the argument. This method gets invoked by <tt class="docutils literal"><span class="pre">FunctionAST::codegen()</span></tt>
+right after it sets up the entry block for the function.</p>
+<p>The final missing piece is adding the mem2reg pass, which allows us to
+get good codegen once again:</p>
+<div class="highlight-c++"><div class="highlight"><pre><span class="c1">// Set up the optimizer pipeline. Start with registering info about how the</span>
+<span class="c1">// target lays out data structures.</span>
+<span class="n">OurFPM</span><span class="p">.</span><span class="n">add</span><span class="p">(</span><span class="k">new</span> <span class="n">DataLayout</span><span class="p">(</span><span class="o">*</span><span class="n">TheExecutionEngine</span><span class="o">-></span><span class="n">getDataLayout</span><span class="p">()));</span>
+<span class="c1">// Promote allocas to registers.</span>
+<span class="n">OurFPM</span><span class="p">.</span><span class="n">add</span><span class="p">(</span><span class="n">createPromoteMemoryToRegisterPass</span><span class="p">());</span>
+<span class="c1">// Do simple "peephole" optimizations and bit-twiddling optzns.</span>
+<span class="n">OurFPM</span><span class="p">.</span><span class="n">add</span><span class="p">(</span><span class="n">createInstructionCombiningPass</span><span class="p">());</span>
+<span class="c1">// Reassociate expressions.</span>
+<span class="n">OurFPM</span><span class="p">.</span><span class="n">add</span><span class="p">(</span><span class="n">createReassociatePass</span><span class="p">());</span>
+</pre></div>
+</div>
+<p>It is interesting to see what the code looks like before and after the
+mem2reg optimization runs. For example, this is the before/after code
+for our recursive fib function. Before the optimization:</p>
+<div class="highlight-llvm"><div class="highlight"><pre><span class="k">define</span> <span class="kt">double</span> <span class="vg">@fib</span><span class="p">(</span><span class="kt">double</span> <span class="nv">%x</span><span class="p">)</span> <span class="p">{</span>
+<span class="nl">entry:</span>
+ <span class="nv">%x1</span> <span class="p">=</span> <span class="k">alloca</span> <span class="kt">double</span>
+ <span class="k">store</span> <span class="kt">double</span> <span class="nv">%x</span><span class="p">,</span> <span class="kt">double</span><span class="p">*</span> <span class="nv">%x1</span>
+ <span class="nv">%x2</span> <span class="p">=</span> <span class="k">load</span> <span class="kt">double</span><span class="p">*</span> <span class="nv">%x1</span>
+ <span class="nv">%cmptmp</span> <span class="p">=</span> <span class="k">fcmp</span> <span class="k">ult</span> <span class="kt">double</span> <span class="nv">%x2</span><span class="p">,</span> <span class="m">3.000000e+00</span>
+ <span class="nv">%booltmp</span> <span class="p">=</span> <span class="k">uitofp</span> <span class="k">i1</span> <span class="nv">%cmptmp</span> <span class="k">to</span> <span class="kt">double</span>
+ <span class="nv">%ifcond</span> <span class="p">=</span> <span class="k">fcmp</span> <span class="k">one</span> <span class="kt">double</span> <span class="nv">%booltmp</span><span class="p">,</span> <span class="m">0.000000e+00</span>
+ <span class="k">br</span> <span class="k">i1</span> <span class="nv">%ifcond</span><span class="p">,</span> <span class="kt">label</span> <span class="nv">%then</span><span class="p">,</span> <span class="kt">label</span> <span class="nv">%else</span>
+
+<span class="nl">then:</span> <span class="c">; preds = %entry</span>
+ <span class="k">br</span> <span class="kt">label</span> <span class="nv">%ifcont</span>
+
+<span class="nl">else:</span> <span class="c">; preds = %entry</span>
+ <span class="nv">%x3</span> <span class="p">=</span> <span class="k">load</span> <span class="kt">double</span><span class="p">*</span> <span class="nv">%x1</span>
+ <span class="nv">%subtmp</span> <span class="p">=</span> <span class="k">fsub</span> <span class="kt">double</span> <span class="nv">%x3</span><span class="p">,</span> <span class="m">1.000000e+00</span>
+ <span class="nv">%calltmp</span> <span class="p">=</span> <span class="k">call</span> <span class="kt">double</span> <span class="vg">@fib</span><span class="p">(</span><span class="kt">double</span> <span class="nv">%subtmp</span><span class="p">)</span>
+ <span class="nv">%x4</span> <span class="p">=</span> <span class="k">load</span> <span class="kt">double</span><span class="p">*</span> <span class="nv">%x1</span>
+ <span class="nv">%subtmp5</span> <span class="p">=</span> <span class="k">fsub</span> <span class="kt">double</span> <span class="nv">%x4</span><span class="p">,</span> <span class="m">2.000000e+00</span>
+ <span class="nv">%calltmp6</span> <span class="p">=</span> <span class="k">call</span> <span class="kt">double</span> <span class="vg">@fib</span><span class="p">(</span><span class="kt">double</span> <span class="nv">%subtmp5</span><span class="p">)</span>
+ <span class="nv">%addtmp</span> <span class="p">=</span> <span class="k">fadd</span> <span class="kt">double</span> <span class="nv">%calltmp</span><span class="p">,</span> <span class="nv">%calltmp6</span>
+ <span class="k">br</span> <span class="kt">label</span> <span class="nv">%ifcont</span>
+
+<span class="nl">ifcont:</span> <span class="c">; preds = %else, %then</span>
+ <span class="nv">%iftmp</span> <span class="p">=</span> <span class="k">phi</span> <span class="kt">double</span> <span class="p">[</span> <span class="m">1.000000e+00</span><span class="p">,</span> <span class="nv">%then</span> <span class="p">],</span> <span class="p">[</span> <span class="nv">%addtmp</span><span class="p">,</span> <span class="nv">%else</span> <span class="p">]</span>
+ <span class="k">ret</span> <span class="kt">double</span> <span class="nv">%iftmp</span>
+<span class="p">}</span>
+</pre></div>
+</div>
+<p>Here there is only one variable (x, the input argument) but you can
+still see the extremely simple-minded code generation strategy we are
+using. In the entry block, an alloca is created, and the initial input
+value is stored into it. Each reference to the variable does a reload
+from the stack. Also, note that we didn’t modify the if/then/else
+expression, so it still inserts a PHI node. While we could make an
+alloca for it, it is actually easier to create a PHI node for it, so we
+still just make the PHI.</p>
+<p>Here is the code after the mem2reg pass runs:</p>
+<div class="highlight-llvm"><div class="highlight"><pre><span class="k">define</span> <span class="kt">double</span> <span class="vg">@fib</span><span class="p">(</span><span class="kt">double</span> <span class="nv">%x</span><span class="p">)</span> <span class="p">{</span>
+<span class="nl">entry:</span>
+ <span class="nv">%cmptmp</span> <span class="p">=</span> <span class="k">fcmp</span> <span class="k">ult</span> <span class="kt">double</span> <span class="nv">%x</span><span class="p">,</span> <span class="m">3.000000e+00</span>
+ <span class="nv">%booltmp</span> <span class="p">=</span> <span class="k">uitofp</span> <span class="k">i1</span> <span class="nv">%cmptmp</span> <span class="k">to</span> <span class="kt">double</span>
+ <span class="nv">%ifcond</span> <span class="p">=</span> <span class="k">fcmp</span> <span class="k">one</span> <span class="kt">double</span> <span class="nv">%booltmp</span><span class="p">,</span> <span class="m">0.000000e+00</span>
+ <span class="k">br</span> <span class="k">i1</span> <span class="nv">%ifcond</span><span class="p">,</span> <span class="kt">label</span> <span class="nv">%then</span><span class="p">,</span> <span class="kt">label</span> <span class="nv">%else</span>
+
+<span class="nl">then:</span>
+ <span class="k">br</span> <span class="kt">label</span> <span class="nv">%ifcont</span>
+
+<span class="nl">else:</span>
+ <span class="nv">%subtmp</span> <span class="p">=</span> <span class="k">fsub</span> <span class="kt">double</span> <span class="nv">%x</span><span class="p">,</span> <span class="m">1.000000e+00</span>
+ <span class="nv">%calltmp</span> <span class="p">=</span> <span class="k">call</span> <span class="kt">double</span> <span class="vg">@fib</span><span class="p">(</span><span class="kt">double</span> <span class="nv">%subtmp</span><span class="p">)</span>
+ <span class="nv">%subtmp5</span> <span class="p">=</span> <span class="k">fsub</span> <span class="kt">double</span> <span class="nv">%x</span><span class="p">,</span> <span class="m">2.000000e+00</span>
+ <span class="nv">%calltmp6</span> <span class="p">=</span> <span class="k">call</span> <span class="kt">double</span> <span class="vg">@fib</span><span class="p">(</span><span class="kt">double</span> <span class="nv">%subtmp5</span><span class="p">)</span>
+ <span class="nv">%addtmp</span> <span class="p">=</span> <span class="k">fadd</span> <span class="kt">double</span> <span class="nv">%calltmp</span><span class="p">,</span> <span class="nv">%calltmp6</span>
+ <span class="k">br</span> <span class="kt">label</span> <span class="nv">%ifcont</span>
+
+<span class="nl">ifcont:</span> <span class="c">; preds = %else, %then</span>
+ <span class="nv">%iftmp</span> <span class="p">=</span> <span class="k">phi</span> <span class="kt">double</span> <span class="p">[</span> <span class="m">1.000000e+00</span><span class="p">,</span> <span class="nv">%then</span> <span class="p">],</span> <span class="p">[</span> <span class="nv">%addtmp</span><span class="p">,</span> <span class="nv">%else</span> <span class="p">]</span>
+ <span class="k">ret</span> <span class="kt">double</span> <span class="nv">%iftmp</span>
+<span class="p">}</span>
+</pre></div>
+</div>
+<p>This is a trivial case for mem2reg, since there are no redefinitions of
+the variable. The point of showing this is to calm your tension about
+inserting such blatent inefficiencies :).</p>
+<p>After the rest of the optimizers run, we get:</p>
+<div class="highlight-llvm"><div class="highlight"><pre><span class="k">define</span> <span class="kt">double</span> <span class="vg">@fib</span><span class="p">(</span><span class="kt">double</span> <span class="nv">%x</span><span class="p">)</span> <span class="p">{</span>
+<span class="nl">entry:</span>
+ <span class="nv">%cmptmp</span> <span class="p">=</span> <span class="k">fcmp</span> <span class="k">ult</span> <span class="kt">double</span> <span class="nv">%x</span><span class="p">,</span> <span class="m">3.000000e+00</span>
+ <span class="nv">%booltmp</span> <span class="p">=</span> <span class="k">uitofp</span> <span class="k">i1</span> <span class="nv">%cmptmp</span> <span class="k">to</span> <span class="kt">double</span>
+ <span class="nv">%ifcond</span> <span class="p">=</span> <span class="k">fcmp</span> <span class="k">ueq</span> <span class="kt">double</span> <span class="nv">%booltmp</span><span class="p">,</span> <span class="m">0.000000e+00</span>
+ <span class="k">br</span> <span class="k">i1</span> <span class="nv">%ifcond</span><span class="p">,</span> <span class="kt">label</span> <span class="nv">%else</span><span class="p">,</span> <span class="kt">label</span> <span class="nv">%ifcont</span>
+
+<span class="nl">else:</span>
+ <span class="nv">%subtmp</span> <span class="p">=</span> <span class="k">fsub</span> <span class="kt">double</span> <span class="nv">%x</span><span class="p">,</span> <span class="m">1.000000e+00</span>
+ <span class="nv">%calltmp</span> <span class="p">=</span> <span class="k">call</span> <span class="kt">double</span> <span class="vg">@fib</span><span class="p">(</span><span class="kt">double</span> <span class="nv">%subtmp</span><span class="p">)</span>
+ <span class="nv">%subtmp5</span> <span class="p">=</span> <span class="k">fsub</span> <span class="kt">double</span> <span class="nv">%x</span><span class="p">,</span> <span class="m">2.000000e+00</span>
+ <span class="nv">%calltmp6</span> <span class="p">=</span> <span class="k">call</span> <span class="kt">double</span> <span class="vg">@fib</span><span class="p">(</span><span class="kt">double</span> <span class="nv">%subtmp5</span><span class="p">)</span>
+ <span class="nv">%addtmp</span> <span class="p">=</span> <span class="k">fadd</span> <span class="kt">double</span> <span class="nv">%calltmp</span><span class="p">,</span> <span class="nv">%calltmp6</span>
+ <span class="k">ret</span> <span class="kt">double</span> <span class="nv">%addtmp</span>
+
+<span class="nl">ifcont:</span>
+ <span class="k">ret</span> <span class="kt">double</span> <span class="m">1.000000e+00</span>
+<span class="p">}</span>
+</pre></div>
+</div>
+<p>Here we see that the simplifycfg pass decided to clone the return
+instruction into the end of the ‘else’ block. This allowed it to
+eliminate some branches and the PHI node.</p>
+<p>Now that all symbol table references are updated to use stack variables,
+we’ll add the assignment operator.</p>
+</div>
+<div class="section" id="new-assignment-operator">
+<h2><a class="toc-backref" href="#id7">7.6. New Assignment Operator</a><a class="headerlink" href="#new-assignment-operator" title="Permalink to this headline">¶</a></h2>
+<p>With our current framework, adding a new assignment operator is really
+simple. We will parse it just like any other binary operator, but handle
+it internally (instead of allowing the user to define it). The first
+step is to set a precedence:</p>
+<div class="highlight-c++"><div class="highlight"><pre><span class="kt">int</span> <span class="nf">main</span><span class="p">()</span> <span class="p">{</span>
+ <span class="c1">// Install standard binary operators.</span>
+ <span class="c1">// 1 is lowest precedence.</span>
+ <span class="n">BinopPrecedence</span><span class="p">[</span><span class="sc">'='</span><span class="p">]</span> <span class="o">=</span> <span class="mi">2</span><span class="p">;</span>
+ <span class="n">BinopPrecedence</span><span class="p">[</span><span class="sc">'<'</span><span class="p">]</span> <span class="o">=</span> <span class="mi">10</span><span class="p">;</span>
+ <span class="n">BinopPrecedence</span><span class="p">[</span><span class="sc">'+'</span><span class="p">]</span> <span class="o">=</span> <span class="mi">20</span><span class="p">;</span>
+ <span class="n">BinopPrecedence</span><span class="p">[</span><span class="sc">'-'</span><span class="p">]</span> <span class="o">=</span> <span class="mi">20</span><span class="p">;</span>
+</pre></div>
+</div>
+<p>Now that the parser knows the precedence of the binary operator, it
+takes care of all the parsing and AST generation. We just need to
+implement codegen for the assignment operator. This looks like:</p>
+<div class="highlight-c++"><div class="highlight"><pre><span class="n">Value</span> <span class="o">*</span><span class="n">BinaryExprAST</span><span class="o">::</span><span class="n">codegen</span><span class="p">()</span> <span class="p">{</span>
+ <span class="c1">// Special case '=' because we don't want to emit the LHS as an expression.</span>
+ <span class="k">if</span> <span class="p">(</span><span class="n">Op</span> <span class="o">==</span> <span class="sc">'='</span><span class="p">)</span> <span class="p">{</span>
+ <span class="c1">// Assignment requires the LHS to be an identifier.</span>
+ <span class="n">VariableExprAST</span> <span class="o">*</span><span class="n">LHSE</span> <span class="o">=</span> <span class="k">dynamic_cast</span><span class="o"><</span><span class="n">VariableExprAST</span><span class="o">*></span><span class="p">(</span><span class="n">LHS</span><span class="p">.</span><span class="n">get</span><span class="p">());</span>
+ <span class="k">if</span> <span class="p">(</span><span class="o">!</span><span class="n">LHSE</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">ErrorV</span><span class="p">(</span><span class="s">"destination of '=' must be a variable"</span><span class="p">);</span>
+</pre></div>
+</div>
+<p>Unlike the rest of the binary operators, our assignment operator doesn’t
+follow the “emit LHS, emit RHS, do computation” model. As such, it is
+handled as a special case before the other binary operators are handled.
+The other strange thing is that it requires the LHS to be a variable. It
+is invalid to have “(x+1) = expr” - only things like “x = expr” are
+allowed.</p>
+<div class="highlight-c++"><div class="highlight"><pre> <span class="c1">// Codegen the RHS.</span>
+ <span class="n">Value</span> <span class="o">*</span><span class="n">Val</span> <span class="o">=</span> <span class="n">RHS</span><span class="o">-></span><span class="n">codegen</span><span class="p">();</span>
+ <span class="k">if</span> <span class="p">(</span><span class="o">!</span><span class="n">Val</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">nullptr</span><span class="p">;</span>
+
+ <span class="c1">// Look up the name.</span>
+ <span class="n">Value</span> <span class="o">*</span><span class="n">Variable</span> <span class="o">=</span> <span class="n">NamedValues</span><span class="p">[</span><span class="n">LHSE</span><span class="o">-></span><span class="n">getName</span><span class="p">()];</span>
+ <span class="k">if</span> <span class="p">(</span><span class="o">!</span><span class="n">Variable</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">ErrorV</span><span class="p">(</span><span class="s">"Unknown variable name"</span><span class="p">);</span>
+
+ <span class="n">Builder</span><span class="p">.</span><span class="n">CreateStore</span><span class="p">(</span><span class="n">Val</span><span class="p">,</span> <span class="n">Variable</span><span class="p">);</span>
+ <span class="k">return</span> <span class="n">Val</span><span class="p">;</span>
+<span class="p">}</span>
+<span class="p">...</span>
+</pre></div>
+</div>
+<p>Once we have the variable, codegen’ing the assignment is
+straightforward: we emit the RHS of the assignment, create a store, and
+return the computed value. Returning a value allows for chained
+assignments like “X = (Y = Z)”.</p>
+<p>Now that we have an assignment operator, we can mutate loop variables
+and arguments. For example, we can now run code like this:</p>
+<div class="highlight-python"><div class="highlight"><pre># Function to print a double.
+extern printd(x);
+
+# Define ':' for sequencing: as a low-precedence operator that ignores operands
+# and just returns the RHS.
+def binary : 1 (x y) y;
+
+def test(x)
+ printd(x) :
+ x = 4 :
+ printd(x);
+
+test(123);
+</pre></div>
+</div>
+<p>When run, this example prints “123” and then “4”, showing that we did
+actually mutate the value! Okay, we have now officially implemented our
+goal: getting this to work requires SSA construction in the general
+case. However, to be really useful, we want the ability to define our
+own local variables, lets add this next!</p>
+</div>
+<div class="section" id="user-defined-local-variables">
+<h2><a class="toc-backref" href="#id8">7.7. User-defined Local Variables</a><a class="headerlink" href="#user-defined-local-variables" title="Permalink to this headline">¶</a></h2>
+<p>Adding var/in is just like any other extension we made to
+Kaleidoscope: we extend the lexer, the parser, the AST and the code
+generator. The first step for adding our new ‘var/in’ construct is to
+extend the lexer. As before, this is pretty trivial, the code looks like
+this:</p>
+<div class="highlight-c++"><div class="highlight"><pre><span class="k">enum</span> <span class="n">Token</span> <span class="p">{</span>
+ <span class="p">...</span>
+ <span class="c1">// var definition</span>
+ <span class="n">tok_var</span> <span class="o">=</span> <span class="o">-</span><span class="mi">13</span>
+<span class="p">...</span>
+<span class="p">}</span>
+<span class="p">...</span>
+<span class="k">static</span> <span class="kt">int</span> <span class="n">gettok</span><span class="p">()</span> <span class="p">{</span>
+<span class="p">...</span>
+ <span class="k">if</span> <span class="p">(</span><span class="n">IdentifierStr</span> <span class="o">==</span> <span class="s">"in"</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">tok_in</span><span class="p">;</span>
+ <span class="k">if</span> <span class="p">(</span><span class="n">IdentifierStr</span> <span class="o">==</span> <span class="s">"binary"</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">tok_binary</span><span class="p">;</span>
+ <span class="k">if</span> <span class="p">(</span><span class="n">IdentifierStr</span> <span class="o">==</span> <span class="s">"unary"</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">tok_unary</span><span class="p">;</span>
+ <span class="k">if</span> <span class="p">(</span><span class="n">IdentifierStr</span> <span class="o">==</span> <span class="s">"var"</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">tok_var</span><span class="p">;</span>
+ <span class="k">return</span> <span class="n">tok_identifier</span><span class="p">;</span>
+<span class="p">...</span>
+</pre></div>
+</div>
+<p>The next step is to define the AST node that we will construct. For
+var/in, it looks like this:</p>
+<div class="highlight-c++"><div class="highlight"><pre><span class="c1">/// VarExprAST - Expression class for var/in</span>
+<span class="k">class</span> <span class="nc">VarExprAST</span> <span class="o">:</span> <span class="k">public</span> <span class="n">ExprAST</span> <span class="p">{</span>
+ <span class="n">std</span><span class="o">::</span><span class="n">vector</span><span class="o"><</span><span class="n">std</span><span class="o">::</span><span class="n">pair</span><span class="o"><</span><span class="n">std</span><span class="o">::</span><span class="n">string</span><span class="p">,</span> <span class="n">std</span><span class="o">::</span><span class="n">unique_ptr</span><span class="o"><</span><span class="n">ExprAST</span><span class="o">>>></span> <span class="n">VarNames</span><span class="p">;</span>
+ <span class="n">std</span><span class="o">::</span><span class="n">unique_ptr</span><span class="o"><</span><span class="n">ExprAST</span><span class="o">></span> <span class="n">Body</span><span class="p">;</span>
+
+<span class="nl">public:</span>
+ <span class="n">VarExprAST</span><span class="p">(</span><span class="n">std</span><span class="o">::</span><span class="n">vector</span><span class="o"><</span><span class="n">std</span><span class="o">::</span><span class="n">pair</span><span class="o"><</span><span class="n">std</span><span class="o">::</span><span class="n">string</span><span class="p">,</span> <span class="n">std</span><span class="o">::</span><span class="n">unique_ptr</span><span class="o"><</span><span class="n">ExprAST</span><span class="o">>>></span> <span class="n">VarNames</span><span class="p">,</span>
+ <span class="n">std</span><span class="o">::</span><span class="n">unique_ptr</span><span class="o"><</span><span class="n">ExprAST</span><span class="o">></span> <span class="n">body</span><span class="p">)</span>
+ <span class="o">:</span> <span class="n">VarNames</span><span class="p">(</span><span class="n">std</span><span class="o">::</span><span class="n">move</span><span class="p">(</span><span class="n">VarNames</span><span class="p">)),</span> <span class="n">Body</span><span class="p">(</span><span class="n">std</span><span class="o">::</span><span class="n">move</span><span class="p">(</span><span class="n">Body</span><span class="p">))</span> <span class="p">{}</span>
+
+ <span class="k">virtual</span> <span class="n">Value</span> <span class="o">*</span><span class="n">codegen</span><span class="p">();</span>
+<span class="p">};</span>
+</pre></div>
+</div>
+<p>var/in allows a list of names to be defined all at once, and each name
+can optionally have an initializer value. As such, we capture this
+information in the VarNames vector. Also, var/in has a body, this body
+is allowed to access the variables defined by the var/in.</p>
+<p>With this in place, we can define the parser pieces. The first thing we
+do is add it as a primary expression:</p>
+<div class="highlight-c++"><div class="highlight"><pre><span class="c1">/// primary</span>
+<span class="c1">/// ::= identifierexpr</span>
+<span class="c1">/// ::= numberexpr</span>
+<span class="c1">/// ::= parenexpr</span>
+<span class="c1">/// ::= ifexpr</span>
+<span class="c1">/// ::= forexpr</span>
+<span class="c1">/// ::= varexpr</span>
+<span class="k">static</span> <span class="n">std</span><span class="o">::</span><span class="n">unique_ptr</span><span class="o"><</span><span class="n">ExprAST</span><span class="o">></span> <span class="n">ParsePrimary</span><span class="p">()</span> <span class="p">{</span>
+ <span class="k">switch</span> <span class="p">(</span><span class="n">CurTok</span><span class="p">)</span> <span class="p">{</span>
+ <span class="nl">default:</span>
+ <span class="k">return</span> <span class="n">Error</span><span class="p">(</span><span class="s">"unknown token when expecting an expression"</span><span class="p">);</span>
+ <span class="k">case</span> <span class="n">tok_identifier</span>:
+ <span class="k">return</span> <span class="n">ParseIdentifierExpr</span><span class="p">();</span>
+ <span class="k">case</span> <span class="n">tok_number</span>:
+ <span class="k">return</span> <span class="n">ParseNumberExpr</span><span class="p">();</span>
+ <span class="k">case</span> <span class="sc">'('</span>:
+ <span class="k">return</span> <span class="n">ParseParenExpr</span><span class="p">();</span>
+ <span class="k">case</span> <span class="n">tok_if</span>:
+ <span class="k">return</span> <span class="n">ParseIfExpr</span><span class="p">();</span>
+ <span class="k">case</span> <span class="n">tok_for</span>:
+ <span class="k">return</span> <span class="n">ParseForExpr</span><span class="p">();</span>
+ <span class="k">case</span> <span class="n">tok_var</span>:
+ <span class="k">return</span> <span class="n">ParseVarExpr</span><span class="p">();</span>
+ <span class="p">}</span>
+<span class="p">}</span>
+</pre></div>
+</div>
+<p>Next we define ParseVarExpr:</p>
+<div class="highlight-c++"><div class="highlight"><pre><span class="c1">/// varexpr ::= 'var' identifier ('=' expression)?</span>
+<span class="c1">// (',' identifier ('=' expression)?)* 'in' expression</span>
+<span class="k">static</span> <span class="n">std</span><span class="o">::</span><span class="n">unique_ptr</span><span class="o"><</span><span class="n">ExprAST</span><span class="o">></span> <span class="n">ParseVarExpr</span><span class="p">()</span> <span class="p">{</span>
+ <span class="n">getNextToken</span><span class="p">();</span> <span class="c1">// eat the var.</span>
+
+ <span class="n">std</span><span class="o">::</span><span class="n">vector</span><span class="o"><</span><span class="n">std</span><span class="o">::</span><span class="n">pair</span><span class="o"><</span><span class="n">std</span><span class="o">::</span><span class="n">string</span><span class="p">,</span> <span class="n">std</span><span class="o">::</span><span class="n">unique_ptr</span><span class="o"><</span><span class="n">ExprAST</span><span class="o">>>></span> <span class="n">VarNames</span><span class="p">;</span>
+
+ <span class="c1">// At least one variable name is required.</span>
+ <span class="k">if</span> <span class="p">(</span><span class="n">CurTok</span> <span class="o">!=</span> <span class="n">tok_identifier</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">Error</span><span class="p">(</span><span class="s">"expected identifier after var"</span><span class="p">);</span>
+</pre></div>
+</div>
+<p>The first part of this code parses the list of identifier/expr pairs
+into the local <tt class="docutils literal"><span class="pre">VarNames</span></tt> vector.</p>
+<div class="highlight-c++"><div class="highlight"><pre><span class="k">while</span> <span class="p">(</span><span class="mi">1</span><span class="p">)</span> <span class="p">{</span>
+ <span class="n">std</span><span class="o">::</span><span class="n">string</span> <span class="n">Name</span> <span class="o">=</span> <span class="n">IdentifierStr</span><span class="p">;</span>
+ <span class="n">getNextToken</span><span class="p">();</span> <span class="c1">// eat identifier.</span>
+
+ <span class="c1">// Read the optional initializer.</span>
+ <span class="n">std</span><span class="o">::</span><span class="n">unique_ptr</span><span class="o"><</span><span class="n">ExprAST</span><span class="o">></span> <span class="n">Init</span><span class="p">;</span>
+ <span class="k">if</span> <span class="p">(</span><span class="n">CurTok</span> <span class="o">==</span> <span class="sc">'='</span><span class="p">)</span> <span class="p">{</span>
+ <span class="n">getNextToken</span><span class="p">();</span> <span class="c1">// eat the '='.</span>
+
+ <span class="n">Init</span> <span class="o">=</span> <span class="n">ParseExpression</span><span class="p">();</span>
+ <span class="k">if</span> <span class="p">(</span><span class="o">!</span><span class="n">Init</span><span class="p">)</span> <span class="k">return</span> <span class="n">nullptr</span><span class="p">;</span>
+ <span class="p">}</span>
+
+ <span class="n">VarNames</span><span class="p">.</span><span class="n">push_back</span><span class="p">(</span><span class="n">std</span><span class="o">::</span><span class="n">make_pair</span><span class="p">(</span><span class="n">Name</span><span class="p">,</span> <span class="n">std</span><span class="o">::</span><span class="n">move</span><span class="p">(</span><span class="n">Init</span><span class="p">)));</span>
+
+ <span class="c1">// End of var list, exit loop.</span>
+ <span class="k">if</span> <span class="p">(</span><span class="n">CurTok</span> <span class="o">!=</span> <span class="sc">','</span><span class="p">)</span> <span class="k">break</span><span class="p">;</span>
+ <span class="n">getNextToken</span><span class="p">();</span> <span class="c1">// eat the ','.</span>
+
+ <span class="k">if</span> <span class="p">(</span><span class="n">CurTok</span> <span class="o">!=</span> <span class="n">tok_identifier</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">Error</span><span class="p">(</span><span class="s">"expected identifier list after var"</span><span class="p">);</span>
+<span class="p">}</span>
+</pre></div>
+</div>
+<p>Once all the variables are parsed, we then parse the body and create the
+AST node:</p>
+<div class="highlight-c++"><div class="highlight"><pre> <span class="c1">// At this point, we have to have 'in'.</span>
+ <span class="k">if</span> <span class="p">(</span><span class="n">CurTok</span> <span class="o">!=</span> <span class="n">tok_in</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">Error</span><span class="p">(</span><span class="s">"expected 'in' keyword after 'var'"</span><span class="p">);</span>
+ <span class="n">getNextToken</span><span class="p">();</span> <span class="c1">// eat 'in'.</span>
+
+ <span class="k">auto</span> <span class="n">Body</span> <span class="o">=</span> <span class="n">ParseExpression</span><span class="p">();</span>
+ <span class="k">if</span> <span class="p">(</span><span class="o">!</span><span class="n">Body</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">nullptr</span><span class="p">;</span>
+
+ <span class="k">return</span> <span class="n">llvm</span><span class="o">::</span><span class="n">make_unique</span><span class="o"><</span><span class="n">VarExprAST</span><span class="o">></span><span class="p">(</span><span class="n">std</span><span class="o">::</span><span class="n">move</span><span class="p">(</span><span class="n">VarNames</span><span class="p">),</span>
+ <span class="n">std</span><span class="o">::</span><span class="n">move</span><span class="p">(</span><span class="n">Body</span><span class="p">));</span>
+<span class="p">}</span>
+</pre></div>
+</div>
+<p>Now that we can parse and represent the code, we need to support
+emission of LLVM IR for it. This code starts out with:</p>
+<div class="highlight-c++"><div class="highlight"><pre><span class="n">Value</span> <span class="o">*</span><span class="n">VarExprAST</span><span class="o">::</span><span class="n">codegen</span><span class="p">()</span> <span class="p">{</span>
+ <span class="n">std</span><span class="o">::</span><span class="n">vector</span><span class="o"><</span><span class="n">AllocaInst</span> <span class="o">*></span> <span class="n">OldBindings</span><span class="p">;</span>
+
+ <span class="n">Function</span> <span class="o">*</span><span class="n">TheFunction</span> <span class="o">=</span> <span class="n">Builder</span><span class="p">.</span><span class="n">GetInsertBlock</span><span class="p">()</span><span class="o">-></span><span class="n">getParent</span><span class="p">();</span>
+
+ <span class="c1">// Register all variables and emit their initializer.</span>
+ <span class="k">for</span> <span class="p">(</span><span class="kt">unsigned</span> <span class="n">i</span> <span class="o">=</span> <span class="mi">0</span><span class="p">,</span> <span class="n">e</span> <span class="o">=</span> <span class="n">VarNames</span><span class="p">.</span><span class="n">size</span><span class="p">();</span> <span class="n">i</span> <span class="o">!=</span> <span class="n">e</span><span class="p">;</span> <span class="o">++</span><span class="n">i</span><span class="p">)</span> <span class="p">{</span>
+ <span class="k">const</span> <span class="n">std</span><span class="o">::</span><span class="n">string</span> <span class="o">&</span><span class="n">VarName</span> <span class="o">=</span> <span class="n">VarNames</span><span class="p">[</span><span class="n">i</span><span class="p">].</span><span class="n">first</span><span class="p">;</span>
+ <span class="n">ExprAST</span> <span class="o">*</span><span class="n">Init</span> <span class="o">=</span> <span class="n">VarNames</span><span class="p">[</span><span class="n">i</span><span class="p">].</span><span class="n">second</span><span class="p">.</span><span class="n">get</span><span class="p">();</span>
+</pre></div>
+</div>
+<p>Basically it loops over all the variables, installing them one at a
+time. For each variable we put into the symbol table, we remember the
+previous value that we replace in OldBindings.</p>
+<div class="highlight-c++"><div class="highlight"><pre> <span class="c1">// Emit the initializer before adding the variable to scope, this prevents</span>
+ <span class="c1">// the initializer from referencing the variable itself, and permits stuff</span>
+ <span class="c1">// like this:</span>
+ <span class="c1">// var a = 1 in</span>
+ <span class="c1">// var a = a in ... # refers to outer 'a'.</span>
+ <span class="n">Value</span> <span class="o">*</span><span class="n">InitVal</span><span class="p">;</span>
+ <span class="k">if</span> <span class="p">(</span><span class="n">Init</span><span class="p">)</span> <span class="p">{</span>
+ <span class="n">InitVal</span> <span class="o">=</span> <span class="n">Init</span><span class="o">-></span><span class="n">codegen</span><span class="p">();</span>
+ <span class="k">if</span> <span class="p">(</span><span class="o">!</span><span class="n">InitVal</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">nullptr</span><span class="p">;</span>
+ <span class="p">}</span> <span class="k">else</span> <span class="p">{</span> <span class="c1">// If not specified, use 0.0.</span>
+ <span class="n">InitVal</span> <span class="o">=</span> <span class="n">ConstantFP</span><span class="o">::</span><span class="n">get</span><span class="p">(</span><span class="n">getGlobalContext</span><span class="p">(),</span> <span class="n">APFloat</span><span class="p">(</span><span class="mf">0.0</span><span class="p">));</span>
+ <span class="p">}</span>
+
+ <span class="n">AllocaInst</span> <span class="o">*</span><span class="n">Alloca</span> <span class="o">=</span> <span class="n">CreateEntryBlockAlloca</span><span class="p">(</span><span class="n">TheFunction</span><span class="p">,</span> <span class="n">VarName</span><span class="p">);</span>
+ <span class="n">Builder</span><span class="p">.</span><span class="n">CreateStore</span><span class="p">(</span><span class="n">InitVal</span><span class="p">,</span> <span class="n">Alloca</span><span class="p">);</span>
+
+ <span class="c1">// Remember the old variable binding so that we can restore the binding when</span>
+ <span class="c1">// we unrecurse.</span>
+ <span class="n">OldBindings</span><span class="p">.</span><span class="n">push_back</span><span class="p">(</span><span class="n">NamedValues</span><span class="p">[</span><span class="n">VarName</span><span class="p">]);</span>
+
+ <span class="c1">// Remember this binding.</span>
+ <span class="n">NamedValues</span><span class="p">[</span><span class="n">VarName</span><span class="p">]</span> <span class="o">=</span> <span class="n">Alloca</span><span class="p">;</span>
+<span class="p">}</span>
+</pre></div>
+</div>
+<p>There are more comments here than code. The basic idea is that we emit
+the initializer, create the alloca, then update the symbol table to
+point to it. Once all the variables are installed in the symbol table,
+we evaluate the body of the var/in expression:</p>
+<div class="highlight-c++"><div class="highlight"><pre><span class="c1">// Codegen the body, now that all vars are in scope.</span>
+<span class="n">Value</span> <span class="o">*</span><span class="n">BodyVal</span> <span class="o">=</span> <span class="n">Body</span><span class="o">-></span><span class="n">codegen</span><span class="p">();</span>
+<span class="k">if</span> <span class="p">(</span><span class="o">!</span><span class="n">BodyVal</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">nullptr</span><span class="p">;</span>
+</pre></div>
+</div>
+<p>Finally, before returning, we restore the previous variable bindings:</p>
+<div class="highlight-c++"><div class="highlight"><pre> <span class="c1">// Pop all our variables from scope.</span>
+ <span class="k">for</span> <span class="p">(</span><span class="kt">unsigned</span> <span class="n">i</span> <span class="o">=</span> <span class="mi">0</span><span class="p">,</span> <span class="n">e</span> <span class="o">=</span> <span class="n">VarNames</span><span class="p">.</span><span class="n">size</span><span class="p">();</span> <span class="n">i</span> <span class="o">!=</span> <span class="n">e</span><span class="p">;</span> <span class="o">++</span><span class="n">i</span><span class="p">)</span>
+ <span class="n">NamedValues</span><span class="p">[</span><span class="n">VarNames</span><span class="p">[</span><span class="n">i</span><span class="p">].</span><span class="n">first</span><span class="p">]</span> <span class="o">=</span> <span class="n">OldBindings</span><span class="p">[</span><span class="n">i</span><span class="p">];</span>
+
+ <span class="c1">// Return the body computation.</span>
+ <span class="k">return</span> <span class="n">BodyVal</span><span class="p">;</span>
+<span class="p">}</span>
+</pre></div>
+</div>
+<p>The end result of all of this is that we get properly scoped variable
+definitions, and we even (trivially) allow mutation of them :).</p>
+<p>With this, we completed what we set out to do. Our nice iterative fib
+example from the intro compiles and runs just fine. The mem2reg pass
+optimizes all of our stack variables into SSA registers, inserting PHI
+nodes where needed, and our front-end remains simple: no “iterated
+dominance frontier” computation anywhere in sight.</p>
+</div>
+<div class="section" id="id1">
+<h2><a class="toc-backref" href="#id9">7.8. Full Code Listing</a><a class="headerlink" href="#id1" title="Permalink to this headline">¶</a></h2>
+<p>Here is the complete code listing for our running example, enhanced with
+mutable variables and var/in support. To build this example, use:</p>
+<div class="highlight-bash"><div class="highlight"><pre><span class="c"># Compile</span>
+clang++ -g toy.cpp <span class="sb">`</span>llvm-config --cxxflags --ldflags --system-libs --libs core mcjit native<span class="sb">`</span> -O3 -o toy
+<span class="c"># Run</span>
+./toy
+</pre></div>
+</div>
+<p>Here is the code:</p>
+<div class="highlight-c++"><div class="highlight"><pre><span class="cp">#include "llvm/ADT/STLExtras.h"</span>
+<span class="cp">#include "llvm/Analysis/Passes.h"</span>
+<span class="cp">#include "llvm/IR/IRBuilder.h"</span>
+<span class="cp">#include "llvm/IR/LLVMContext.h"</span>
+<span class="cp">#include "llvm/IR/LegacyPassManager.h"</span>
+<span class="cp">#include "llvm/IR/Module.h"</span>
+<span class="cp">#include "llvm/IR/Verifier.h"</span>
+<span class="cp">#include "llvm/Support/TargetSelect.h"</span>
+<span class="cp">#include "llvm/Transforms/Scalar.h"</span>
+<span class="cp">#include <cctype></span>
+<span class="cp">#include <cstdio></span>
+<span class="cp">#include <map></span>
+<span class="cp">#include <string></span>
+<span class="cp">#include <vector></span>
+<span class="cp">#include "../include/KaleidoscopeJIT.h"</span>
+
+<span class="k">using</span> <span class="k">namespace</span> <span class="n">llvm</span><span class="p">;</span>
+<span class="k">using</span> <span class="k">namespace</span> <span class="n">llvm</span><span class="o">::</span><span class="n">orc</span><span class="p">;</span>
+
+<span class="c1">//===----------------------------------------------------------------------===//</span>
+<span class="c1">// Lexer</span>
+<span class="c1">//===----------------------------------------------------------------------===//</span>
+
+<span class="c1">// The lexer returns tokens [0-255] if it is an unknown character, otherwise one</span>
+<span class="c1">// of these for known things.</span>
+<span class="k">enum</span> <span class="n">Token</span> <span class="p">{</span>
+ <span class="n">tok_eof</span> <span class="o">=</span> <span class="o">-</span><span class="mi">1</span><span class="p">,</span>
+
+ <span class="c1">// commands</span>
+ <span class="n">tok_def</span> <span class="o">=</span> <span class="o">-</span><span class="mi">2</span><span class="p">,</span>
+ <span class="n">tok_extern</span> <span class="o">=</span> <span class="o">-</span><span class="mi">3</span><span class="p">,</span>
+
+ <span class="c1">// primary</span>
+ <span class="n">tok_identifier</span> <span class="o">=</span> <span class="o">-</span><span class="mi">4</span><span class="p">,</span>
+ <span class="n">tok_number</span> <span class="o">=</span> <span class="o">-</span><span class="mi">5</span><span class="p">,</span>
+
+ <span class="c1">// control</span>
+ <span class="n">tok_if</span> <span class="o">=</span> <span class="o">-</span><span class="mi">6</span><span class="p">,</span>
+ <span class="n">tok_then</span> <span class="o">=</span> <span class="o">-</span><span class="mi">7</span><span class="p">,</span>
+ <span class="n">tok_else</span> <span class="o">=</span> <span class="o">-</span><span class="mi">8</span><span class="p">,</span>
+ <span class="n">tok_for</span> <span class="o">=</span> <span class="o">-</span><span class="mi">9</span><span class="p">,</span>
+ <span class="n">tok_in</span> <span class="o">=</span> <span class="o">-</span><span class="mi">10</span><span class="p">,</span>
+
+ <span class="c1">// operators</span>
+ <span class="n">tok_binary</span> <span class="o">=</span> <span class="o">-</span><span class="mi">11</span><span class="p">,</span>
+ <span class="n">tok_unary</span> <span class="o">=</span> <span class="o">-</span><span class="mi">12</span><span class="p">,</span>
+
+ <span class="c1">// var definition</span>
+ <span class="n">tok_var</span> <span class="o">=</span> <span class="o">-</span><span class="mi">13</span>
+<span class="p">};</span>
+
+<span class="k">static</span> <span class="n">std</span><span class="o">::</span><span class="n">string</span> <span class="n">IdentifierStr</span><span class="p">;</span> <span class="c1">// Filled in if tok_identifier</span>
+<span class="k">static</span> <span class="kt">double</span> <span class="n">NumVal</span><span class="p">;</span> <span class="c1">// Filled in if tok_number</span>
+
+<span class="c1">/// gettok - Return the next token from standard input.</span>
+<span class="k">static</span> <span class="kt">int</span> <span class="nf">gettok</span><span class="p">()</span> <span class="p">{</span>
+ <span class="k">static</span> <span class="kt">int</span> <span class="n">LastChar</span> <span class="o">=</span> <span class="sc">' '</span><span class="p">;</span>
+
+ <span class="c1">// Skip any whitespace.</span>
+ <span class="k">while</span> <span class="p">(</span><span class="n">isspace</span><span class="p">(</span><span class="n">LastChar</span><span class="p">))</span>
+ <span class="n">LastChar</span> <span class="o">=</span> <span class="n">getchar</span><span class="p">();</span>
+
+ <span class="k">if</span> <span class="p">(</span><span class="n">isalpha</span><span class="p">(</span><span class="n">LastChar</span><span class="p">))</span> <span class="p">{</span> <span class="c1">// identifier: [a-zA-Z][a-zA-Z0-9]*</span>
+ <span class="n">IdentifierStr</span> <span class="o">=</span> <span class="n">LastChar</span><span class="p">;</span>
+ <span class="k">while</span> <span class="p">(</span><span class="n">isalnum</span><span class="p">((</span><span class="n">LastChar</span> <span class="o">=</span> <span class="n">getchar</span><span class="p">())))</span>
+ <span class="n">IdentifierStr</span> <span class="o">+=</span> <span class="n">LastChar</span><span class="p">;</span>
+
+ <span class="k">if</span> <span class="p">(</span><span class="n">IdentifierStr</span> <span class="o">==</span> <span class="s">"def"</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">tok_def</span><span class="p">;</span>
+ <span class="k">if</span> <span class="p">(</span><span class="n">IdentifierStr</span> <span class="o">==</span> <span class="s">"extern"</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">tok_extern</span><span class="p">;</span>
+ <span class="k">if</span> <span class="p">(</span><span class="n">IdentifierStr</span> <span class="o">==</span> <span class="s">"if"</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">tok_if</span><span class="p">;</span>
+ <span class="k">if</span> <span class="p">(</span><span class="n">IdentifierStr</span> <span class="o">==</span> <span class="s">"then"</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">tok_then</span><span class="p">;</span>
+ <span class="k">if</span> <span class="p">(</span><span class="n">IdentifierStr</span> <span class="o">==</span> <span class="s">"else"</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">tok_else</span><span class="p">;</span>
+ <span class="k">if</span> <span class="p">(</span><span class="n">IdentifierStr</span> <span class="o">==</span> <span class="s">"for"</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">tok_for</span><span class="p">;</span>
+ <span class="k">if</span> <span class="p">(</span><span class="n">IdentifierStr</span> <span class="o">==</span> <span class="s">"in"</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">tok_in</span><span class="p">;</span>
+ <span class="k">if</span> <span class="p">(</span><span class="n">IdentifierStr</span> <span class="o">==</span> <span class="s">"binary"</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">tok_binary</span><span class="p">;</span>
+ <span class="k">if</span> <span class="p">(</span><span class="n">IdentifierStr</span> <span class="o">==</span> <span class="s">"unary"</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">tok_unary</span><span class="p">;</span>
+ <span class="k">if</span> <span class="p">(</span><span class="n">IdentifierStr</span> <span class="o">==</span> <span class="s">"var"</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">tok_var</span><span class="p">;</span>
+ <span class="k">return</span> <span class="n">tok_identifier</span><span class="p">;</span>
+ <span class="p">}</span>
+
+ <span class="k">if</span> <span class="p">(</span><span class="n">isdigit</span><span class="p">(</span><span class="n">LastChar</span><span class="p">)</span> <span class="o">||</span> <span class="n">LastChar</span> <span class="o">==</span> <span class="sc">'.'</span><span class="p">)</span> <span class="p">{</span> <span class="c1">// Number: [0-9.]+</span>
+ <span class="n">std</span><span class="o">::</span><span class="n">string</span> <span class="n">NumStr</span><span class="p">;</span>
+ <span class="k">do</span> <span class="p">{</span>
+ <span class="n">NumStr</span> <span class="o">+=</span> <span class="n">LastChar</span><span class="p">;</span>
+ <span class="n">LastChar</span> <span class="o">=</span> <span class="n">getchar</span><span class="p">();</span>
+ <span class="p">}</span> <span class="k">while</span> <span class="p">(</span><span class="n">isdigit</span><span class="p">(</span><span class="n">LastChar</span><span class="p">)</span> <span class="o">||</span> <span class="n">LastChar</span> <span class="o">==</span> <span class="sc">'.'</span><span class="p">);</span>
+
+ <span class="n">NumVal</span> <span class="o">=</span> <span class="n">strtod</span><span class="p">(</span><span class="n">NumStr</span><span class="p">.</span><span class="n">c_str</span><span class="p">(),</span> <span class="n">nullptr</span><span class="p">);</span>
+ <span class="k">return</span> <span class="n">tok_number</span><span class="p">;</span>
+ <span class="p">}</span>
+
+ <span class="k">if</span> <span class="p">(</span><span class="n">LastChar</span> <span class="o">==</span> <span class="sc">'#'</span><span class="p">)</span> <span class="p">{</span>
+ <span class="c1">// Comment until end of line.</span>
+ <span class="k">do</span>
+ <span class="n">LastChar</span> <span class="o">=</span> <span class="n">getchar</span><span class="p">();</span>
+ <span class="k">while</span> <span class="p">(</span><span class="n">LastChar</span> <span class="o">!=</span> <span class="n">EOF</span> <span class="o">&&</span> <span class="n">LastChar</span> <span class="o">!=</span> <span class="sc">'\n'</span> <span class="o">&&</span> <span class="n">LastChar</span> <span class="o">!=</span> <span class="sc">'\r'</span><span class="p">);</span>
+
+ <span class="k">if</span> <span class="p">(</span><span class="n">LastChar</span> <span class="o">!=</span> <span class="n">EOF</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">gettok</span><span class="p">();</span>
+ <span class="p">}</span>
+
+ <span class="c1">// Check for end of file. Don't eat the EOF.</span>
+ <span class="k">if</span> <span class="p">(</span><span class="n">LastChar</span> <span class="o">==</span> <span class="n">EOF</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">tok_eof</span><span class="p">;</span>
+
+ <span class="c1">// Otherwise, just return the character as its ascii value.</span>
+ <span class="kt">int</span> <span class="n">ThisChar</span> <span class="o">=</span> <span class="n">LastChar</span><span class="p">;</span>
+ <span class="n">LastChar</span> <span class="o">=</span> <span class="n">getchar</span><span class="p">();</span>
+ <span class="k">return</span> <span class="n">ThisChar</span><span class="p">;</span>
+<span class="p">}</span>
+
+<span class="c1">//===----------------------------------------------------------------------===//</span>
+<span class="c1">// Abstract Syntax Tree (aka Parse Tree)</span>
+<span class="c1">//===----------------------------------------------------------------------===//</span>
+<span class="k">namespace</span> <span class="p">{</span>
+<span class="c1">/// ExprAST - Base class for all expression nodes.</span>
+<span class="k">class</span> <span class="nc">ExprAST</span> <span class="p">{</span>
+<span class="nl">public:</span>
+ <span class="k">virtual</span> <span class="o">~</span><span class="n">ExprAST</span><span class="p">()</span> <span class="p">{}</span>
+ <span class="k">virtual</span> <span class="n">Value</span> <span class="o">*</span><span class="n">codegen</span><span class="p">()</span> <span class="o">=</span> <span class="mi">0</span><span class="p">;</span>
+<span class="p">};</span>
+
+<span class="c1">/// NumberExprAST - Expression class for numeric literals like "1.0".</span>
+<span class="k">class</span> <span class="nc">NumberExprAST</span> <span class="o">:</span> <span class="k">public</span> <span class="n">ExprAST</span> <span class="p">{</span>
+ <span class="kt">double</span> <span class="n">Val</span><span class="p">;</span>
+
+<span class="nl">public:</span>
+ <span class="n">NumberExprAST</span><span class="p">(</span><span class="kt">double</span> <span class="n">Val</span><span class="p">)</span> <span class="o">:</span> <span class="n">Val</span><span class="p">(</span><span class="n">Val</span><span class="p">)</span> <span class="p">{}</span>
+ <span class="n">Value</span> <span class="o">*</span><span class="n">codegen</span><span class="p">()</span> <span class="n">override</span><span class="p">;</span>
+<span class="p">};</span>
+
+<span class="c1">/// VariableExprAST - Expression class for referencing a variable, like "a".</span>
+<span class="k">class</span> <span class="nc">VariableExprAST</span> <span class="o">:</span> <span class="k">public</span> <span class="n">ExprAST</span> <span class="p">{</span>
+ <span class="n">std</span><span class="o">::</span><span class="n">string</span> <span class="n">Name</span><span class="p">;</span>
+
+<span class="nl">public:</span>
+ <span class="n">VariableExprAST</span><span class="p">(</span><span class="k">const</span> <span class="n">std</span><span class="o">::</span><span class="n">string</span> <span class="o">&</span><span class="n">Name</span><span class="p">)</span> <span class="o">:</span> <span class="n">Name</span><span class="p">(</span><span class="n">Name</span><span class="p">)</span> <span class="p">{}</span>
+ <span class="k">const</span> <span class="n">std</span><span class="o">::</span><span class="n">string</span> <span class="o">&</span><span class="n">getName</span><span class="p">()</span> <span class="k">const</span> <span class="p">{</span> <span class="k">return</span> <span class="n">Name</span><span class="p">;</span> <span class="p">}</span>
+ <span class="n">Value</span> <span class="o">*</span><span class="n">codegen</span><span class="p">()</span> <span class="n">override</span><span class="p">;</span>
+<span class="p">};</span>
+
+<span class="c1">/// UnaryExprAST - Expression class for a unary operator.</span>
+<span class="k">class</span> <span class="nc">UnaryExprAST</span> <span class="o">:</span> <span class="k">public</span> <span class="n">ExprAST</span> <span class="p">{</span>
+ <span class="kt">char</span> <span class="n">Opcode</span><span class="p">;</span>
+ <span class="n">std</span><span class="o">::</span><span class="n">unique_ptr</span><span class="o"><</span><span class="n">ExprAST</span><span class="o">></span> <span class="n">Operand</span><span class="p">;</span>
+
+<span class="nl">public:</span>
+ <span class="n">UnaryExprAST</span><span class="p">(</span><span class="kt">char</span> <span class="n">Opcode</span><span class="p">,</span> <span class="n">std</span><span class="o">::</span><span class="n">unique_ptr</span><span class="o"><</span><span class="n">ExprAST</span><span class="o">></span> <span class="n">Operand</span><span class="p">)</span>
+ <span class="o">:</span> <span class="n">Opcode</span><span class="p">(</span><span class="n">Opcode</span><span class="p">),</span> <span class="n">Operand</span><span class="p">(</span><span class="n">std</span><span class="o">::</span><span class="n">move</span><span class="p">(</span><span class="n">Operand</span><span class="p">))</span> <span class="p">{}</span>
+ <span class="n">Value</span> <span class="o">*</span><span class="n">codegen</span><span class="p">()</span> <span class="n">override</span><span class="p">;</span>
+<span class="p">};</span>
+
+<span class="c1">/// BinaryExprAST - Expression class for a binary operator.</span>
+<span class="k">class</span> <span class="nc">BinaryExprAST</span> <span class="o">:</span> <span class="k">public</span> <span class="n">ExprAST</span> <span class="p">{</span>
+ <span class="kt">char</span> <span class="n">Op</span><span class="p">;</span>
+ <span class="n">std</span><span class="o">::</span><span class="n">unique_ptr</span><span class="o"><</span><span class="n">ExprAST</span><span class="o">></span> <span class="n">LHS</span><span class="p">,</span> <span class="n">RHS</span><span class="p">;</span>
+
+<span class="nl">public:</span>
+ <span class="n">BinaryExprAST</span><span class="p">(</span><span class="kt">char</span> <span class="n">Op</span><span class="p">,</span> <span class="n">std</span><span class="o">::</span><span class="n">unique_ptr</span><span class="o"><</span><span class="n">ExprAST</span><span class="o">></span> <span class="n">LHS</span><span class="p">,</span>
+ <span class="n">std</span><span class="o">::</span><span class="n">unique_ptr</span><span class="o"><</span><span class="n">ExprAST</span><span class="o">></span> <span class="n">RHS</span><span class="p">)</span>
+ <span class="o">:</span> <span class="n">Op</span><span class="p">(</span><span class="n">Op</span><span class="p">),</span> <span class="n">LHS</span><span class="p">(</span><span class="n">std</span><span class="o">::</span><span class="n">move</span><span class="p">(</span><span class="n">LHS</span><span class="p">)),</span> <span class="n">RHS</span><span class="p">(</span><span class="n">std</span><span class="o">::</span><span class="n">move</span><span class="p">(</span><span class="n">RHS</span><span class="p">))</span> <span class="p">{}</span>
+ <span class="n">Value</span> <span class="o">*</span><span class="n">codegen</span><span class="p">()</span> <span class="n">override</span><span class="p">;</span>
+<span class="p">};</span>
+
+<span class="c1">/// CallExprAST - Expression class for function calls.</span>
+<span class="k">class</span> <span class="nc">CallExprAST</span> <span class="o">:</span> <span class="k">public</span> <span class="n">ExprAST</span> <span class="p">{</span>
+ <span class="n">std</span><span class="o">::</span><span class="n">string</span> <span class="n">Callee</span><span class="p">;</span>
+ <span class="n">std</span><span class="o">::</span><span class="n">vector</span><span class="o"><</span><span class="n">std</span><span class="o">::</span><span class="n">unique_ptr</span><span class="o"><</span><span class="n">ExprAST</span><span class="o">>></span> <span class="n">Args</span><span class="p">;</span>
+
+<span class="nl">public:</span>
+ <span class="n">CallExprAST</span><span class="p">(</span><span class="k">const</span> <span class="n">std</span><span class="o">::</span><span class="n">string</span> <span class="o">&</span><span class="n">Callee</span><span class="p">,</span>
+ <span class="n">std</span><span class="o">::</span><span class="n">vector</span><span class="o"><</span><span class="n">std</span><span class="o">::</span><span class="n">unique_ptr</span><span class="o"><</span><span class="n">ExprAST</span><span class="o">>></span> <span class="n">Args</span><span class="p">)</span>
+ <span class="o">:</span> <span class="n">Callee</span><span class="p">(</span><span class="n">Callee</span><span class="p">),</span> <span class="n">Args</span><span class="p">(</span><span class="n">std</span><span class="o">::</span><span class="n">move</span><span class="p">(</span><span class="n">Args</span><span class="p">))</span> <span class="p">{}</span>
+ <span class="n">Value</span> <span class="o">*</span><span class="n">codegen</span><span class="p">()</span> <span class="n">override</span><span class="p">;</span>
+<span class="p">};</span>
+
+<span class="c1">/// IfExprAST - Expression class for if/then/else.</span>
+<span class="k">class</span> <span class="nc">IfExprAST</span> <span class="o">:</span> <span class="k">public</span> <span class="n">ExprAST</span> <span class="p">{</span>
+ <span class="n">std</span><span class="o">::</span><span class="n">unique_ptr</span><span class="o"><</span><span class="n">ExprAST</span><span class="o">></span> <span class="n">Cond</span><span class="p">,</span> <span class="n">Then</span><span class="p">,</span> <span class="n">Else</span><span class="p">;</span>
+
+<span class="nl">public:</span>
+ <span class="n">IfExprAST</span><span class="p">(</span><span class="n">std</span><span class="o">::</span><span class="n">unique_ptr</span><span class="o"><</span><span class="n">ExprAST</span><span class="o">></span> <span class="n">Cond</span><span class="p">,</span> <span class="n">std</span><span class="o">::</span><span class="n">unique_ptr</span><span class="o"><</span><span class="n">ExprAST</span><span class="o">></span> <span class="n">Then</span><span class="p">,</span>
+ <span class="n">std</span><span class="o">::</span><span class="n">unique_ptr</span><span class="o"><</span><span class="n">ExprAST</span><span class="o">></span> <span class="n">Else</span><span class="p">)</span>
+ <span class="o">:</span> <span class="n">Cond</span><span class="p">(</span><span class="n">std</span><span class="o">::</span><span class="n">move</span><span class="p">(</span><span class="n">Cond</span><span class="p">)),</span> <span class="n">Then</span><span class="p">(</span><span class="n">std</span><span class="o">::</span><span class="n">move</span><span class="p">(</span><span class="n">Then</span><span class="p">)),</span> <span class="n">Else</span><span class="p">(</span><span class="n">std</span><span class="o">::</span><span class="n">move</span><span class="p">(</span><span class="n">Else</span><span class="p">))</span> <span class="p">{}</span>
+ <span class="n">Value</span> <span class="o">*</span><span class="n">codegen</span><span class="p">()</span> <span class="n">override</span><span class="p">;</span>
+<span class="p">};</span>
+
+<span class="c1">/// ForExprAST - Expression class for for/in.</span>
+<span class="k">class</span> <span class="nc">ForExprAST</span> <span class="o">:</span> <span class="k">public</span> <span class="n">ExprAST</span> <span class="p">{</span>
+ <span class="n">std</span><span class="o">::</span><span class="n">string</span> <span class="n">VarName</span><span class="p">;</span>
+ <span class="n">std</span><span class="o">::</span><span class="n">unique_ptr</span><span class="o"><</span><span class="n">ExprAST</span><span class="o">></span> <span class="n">Start</span><span class="p">,</span> <span class="n">End</span><span class="p">,</span> <span class="n">Step</span><span class="p">,</span> <span class="n">Body</span><span class="p">;</span>
+
+<span class="nl">public:</span>
+ <span class="n">ForExprAST</span><span class="p">(</span><span class="k">const</span> <span class="n">std</span><span class="o">::</span><span class="n">string</span> <span class="o">&</span><span class="n">VarName</span><span class="p">,</span> <span class="n">std</span><span class="o">::</span><span class="n">unique_ptr</span><span class="o"><</span><span class="n">ExprAST</span><span class="o">></span> <span class="n">Start</span><span class="p">,</span>
+ <span class="n">std</span><span class="o">::</span><span class="n">unique_ptr</span><span class="o"><</span><span class="n">ExprAST</span><span class="o">></span> <span class="n">End</span><span class="p">,</span> <span class="n">std</span><span class="o">::</span><span class="n">unique_ptr</span><span class="o"><</span><span class="n">ExprAST</span><span class="o">></span> <span class="n">Step</span><span class="p">,</span>
+ <span class="n">std</span><span class="o">::</span><span class="n">unique_ptr</span><span class="o"><</span><span class="n">ExprAST</span><span class="o">></span> <span class="n">Body</span><span class="p">)</span>
+ <span class="o">:</span> <span class="n">VarName</span><span class="p">(</span><span class="n">VarName</span><span class="p">),</span> <span class="n">Start</span><span class="p">(</span><span class="n">std</span><span class="o">::</span><span class="n">move</span><span class="p">(</span><span class="n">Start</span><span class="p">)),</span> <span class="n">End</span><span class="p">(</span><span class="n">std</span><span class="o">::</span><span class="n">move</span><span class="p">(</span><span class="n">End</span><span class="p">)),</span>
+ <span class="n">Step</span><span class="p">(</span><span class="n">std</span><span class="o">::</span><span class="n">move</span><span class="p">(</span><span class="n">Step</span><span class="p">)),</span> <span class="n">Body</span><span class="p">(</span><span class="n">std</span><span class="o">::</span><span class="n">move</span><span class="p">(</span><span class="n">Body</span><span class="p">))</span> <span class="p">{}</span>
+ <span class="n">Value</span> <span class="o">*</span><span class="n">codegen</span><span class="p">()</span> <span class="n">override</span><span class="p">;</span>
+<span class="p">};</span>
+
+<span class="c1">/// VarExprAST - Expression class for var/in</span>
+<span class="k">class</span> <span class="nc">VarExprAST</span> <span class="o">:</span> <span class="k">public</span> <span class="n">ExprAST</span> <span class="p">{</span>
+ <span class="n">std</span><span class="o">::</span><span class="n">vector</span><span class="o"><</span><span class="n">std</span><span class="o">::</span><span class="n">pair</span><span class="o"><</span><span class="n">std</span><span class="o">::</span><span class="n">string</span><span class="p">,</span> <span class="n">std</span><span class="o">::</span><span class="n">unique_ptr</span><span class="o"><</span><span class="n">ExprAST</span><span class="o">>>></span> <span class="n">VarNames</span><span class="p">;</span>
+ <span class="n">std</span><span class="o">::</span><span class="n">unique_ptr</span><span class="o"><</span><span class="n">ExprAST</span><span class="o">></span> <span class="n">Body</span><span class="p">;</span>
+
+<span class="nl">public:</span>
+ <span class="n">VarExprAST</span><span class="p">(</span>
+ <span class="n">std</span><span class="o">::</span><span class="n">vector</span><span class="o"><</span><span class="n">std</span><span class="o">::</span><span class="n">pair</span><span class="o"><</span><span class="n">std</span><span class="o">::</span><span class="n">string</span><span class="p">,</span> <span class="n">std</span><span class="o">::</span><span class="n">unique_ptr</span><span class="o"><</span><span class="n">ExprAST</span><span class="o">>>></span> <span class="n">VarNames</span><span class="p">,</span>
+ <span class="n">std</span><span class="o">::</span><span class="n">unique_ptr</span><span class="o"><</span><span class="n">ExprAST</span><span class="o">></span> <span class="n">Body</span><span class="p">)</span>
+ <span class="o">:</span> <span class="n">VarNames</span><span class="p">(</span><span class="n">std</span><span class="o">::</span><span class="n">move</span><span class="p">(</span><span class="n">VarNames</span><span class="p">)),</span> <span class="n">Body</span><span class="p">(</span><span class="n">std</span><span class="o">::</span><span class="n">move</span><span class="p">(</span><span class="n">Body</span><span class="p">))</span> <span class="p">{}</span>
+ <span class="n">Value</span> <span class="o">*</span><span class="n">codegen</span><span class="p">()</span> <span class="n">override</span><span class="p">;</span>
+<span class="p">};</span>
+
+<span class="c1">/// PrototypeAST - This class represents the "prototype" for a function,</span>
+<span class="c1">/// which captures its name, and its argument names (thus implicitly the number</span>
+<span class="c1">/// of arguments the function takes), as well as if it is an operator.</span>
+<span class="k">class</span> <span class="nc">PrototypeAST</span> <span class="p">{</span>
+ <span class="n">std</span><span class="o">::</span><span class="n">string</span> <span class="n">Name</span><span class="p">;</span>
+ <span class="n">std</span><span class="o">::</span><span class="n">vector</span><span class="o"><</span><span class="n">std</span><span class="o">::</span><span class="n">string</span><span class="o">></span> <span class="n">Args</span><span class="p">;</span>
+ <span class="kt">bool</span> <span class="n">IsOperator</span><span class="p">;</span>
+ <span class="kt">unsigned</span> <span class="n">Precedence</span><span class="p">;</span> <span class="c1">// Precedence if a binary op.</span>
+
+<span class="nl">public:</span>
+ <span class="n">PrototypeAST</span><span class="p">(</span><span class="k">const</span> <span class="n">std</span><span class="o">::</span><span class="n">string</span> <span class="o">&</span><span class="n">Name</span><span class="p">,</span> <span class="n">std</span><span class="o">::</span><span class="n">vector</span><span class="o"><</span><span class="n">std</span><span class="o">::</span><span class="n">string</span><span class="o">></span> <span class="n">Args</span><span class="p">,</span>
+ <span class="kt">bool</span> <span class="n">IsOperator</span> <span class="o">=</span> <span class="nb">false</span><span class="p">,</span> <span class="kt">unsigned</span> <span class="n">Prec</span> <span class="o">=</span> <span class="mi">0</span><span class="p">)</span>
+ <span class="o">:</span> <span class="n">Name</span><span class="p">(</span><span class="n">Name</span><span class="p">),</span> <span class="n">Args</span><span class="p">(</span><span class="n">std</span><span class="o">::</span><span class="n">move</span><span class="p">(</span><span class="n">Args</span><span class="p">)),</span> <span class="n">IsOperator</span><span class="p">(</span><span class="n">IsOperator</span><span class="p">),</span>
+ <span class="n">Precedence</span><span class="p">(</span><span class="n">Prec</span><span class="p">)</span> <span class="p">{}</span>
+ <span class="n">Function</span> <span class="o">*</span><span class="n">codegen</span><span class="p">();</span>
+ <span class="k">const</span> <span class="n">std</span><span class="o">::</span><span class="n">string</span> <span class="o">&</span><span class="n">getName</span><span class="p">()</span> <span class="k">const</span> <span class="p">{</span> <span class="k">return</span> <span class="n">Name</span><span class="p">;</span> <span class="p">}</span>
+
+ <span class="kt">bool</span> <span class="n">isUnaryOp</span><span class="p">()</span> <span class="k">const</span> <span class="p">{</span> <span class="k">return</span> <span class="n">IsOperator</span> <span class="o">&&</span> <span class="n">Args</span><span class="p">.</span><span class="n">size</span><span class="p">()</span> <span class="o">==</span> <span class="mi">1</span><span class="p">;</span> <span class="p">}</span>
+ <span class="kt">bool</span> <span class="n">isBinaryOp</span><span class="p">()</span> <span class="k">const</span> <span class="p">{</span> <span class="k">return</span> <span class="n">IsOperator</span> <span class="o">&&</span> <span class="n">Args</span><span class="p">.</span><span class="n">size</span><span class="p">()</span> <span class="o">==</span> <span class="mi">2</span><span class="p">;</span> <span class="p">}</span>
+
+ <span class="kt">char</span> <span class="n">getOperatorName</span><span class="p">()</span> <span class="k">const</span> <span class="p">{</span>
+ <span class="n">assert</span><span class="p">(</span><span class="n">isUnaryOp</span><span class="p">()</span> <span class="o">||</span> <span class="n">isBinaryOp</span><span class="p">());</span>
+ <span class="k">return</span> <span class="n">Name</span><span class="p">[</span><span class="n">Name</span><span class="p">.</span><span class="n">size</span><span class="p">()</span> <span class="o">-</span> <span class="mi">1</span><span class="p">];</span>
+ <span class="p">}</span>
+
+ <span class="kt">unsigned</span> <span class="n">getBinaryPrecedence</span><span class="p">()</span> <span class="k">const</span> <span class="p">{</span> <span class="k">return</span> <span class="n">Precedence</span><span class="p">;</span> <span class="p">}</span>
+<span class="p">};</span>
+
+<span class="c1">/// FunctionAST - This class represents a function definition itself.</span>
+<span class="k">class</span> <span class="nc">FunctionAST</span> <span class="p">{</span>
+ <span class="n">std</span><span class="o">::</span><span class="n">unique_ptr</span><span class="o"><</span><span class="n">PrototypeAST</span><span class="o">></span> <span class="n">Proto</span><span class="p">;</span>
+ <span class="n">std</span><span class="o">::</span><span class="n">unique_ptr</span><span class="o"><</span><span class="n">ExprAST</span><span class="o">></span> <span class="n">Body</span><span class="p">;</span>
+
+<span class="nl">public:</span>
+ <span class="n">FunctionAST</span><span class="p">(</span><span class="n">std</span><span class="o">::</span><span class="n">unique_ptr</span><span class="o"><</span><span class="n">PrototypeAST</span><span class="o">></span> <span class="n">Proto</span><span class="p">,</span>
+ <span class="n">std</span><span class="o">::</span><span class="n">unique_ptr</span><span class="o"><</span><span class="n">ExprAST</span><span class="o">></span> <span class="n">Body</span><span class="p">)</span>
+ <span class="o">:</span> <span class="n">Proto</span><span class="p">(</span><span class="n">std</span><span class="o">::</span><span class="n">move</span><span class="p">(</span><span class="n">Proto</span><span class="p">)),</span> <span class="n">Body</span><span class="p">(</span><span class="n">std</span><span class="o">::</span><span class="n">move</span><span class="p">(</span><span class="n">Body</span><span class="p">))</span> <span class="p">{}</span>
+ <span class="n">Function</span> <span class="o">*</span><span class="n">codegen</span><span class="p">();</span>
+<span class="p">};</span>
+<span class="p">}</span> <span class="c1">// end anonymous namespace</span>
+
+<span class="c1">//===----------------------------------------------------------------------===//</span>
+<span class="c1">// Parser</span>
+<span class="c1">//===----------------------------------------------------------------------===//</span>
+
+<span class="c1">/// CurTok/getNextToken - Provide a simple token buffer. CurTok is the current</span>
+<span class="c1">/// token the parser is looking at. getNextToken reads another token from the</span>
+<span class="c1">/// lexer and updates CurTok with its results.</span>
+<span class="k">static</span> <span class="kt">int</span> <span class="n">CurTok</span><span class="p">;</span>
+<span class="k">static</span> <span class="kt">int</span> <span class="nf">getNextToken</span><span class="p">()</span> <span class="p">{</span> <span class="k">return</span> <span class="n">CurTok</span> <span class="o">=</span> <span class="n">gettok</span><span class="p">();</span> <span class="p">}</span>
+
+<span class="c1">/// BinopPrecedence - This holds the precedence for each binary operator that is</span>
+<span class="c1">/// defined.</span>
+<span class="k">static</span> <span class="n">std</span><span class="o">::</span><span class="n">map</span><span class="o"><</span><span class="kt">char</span><span class="p">,</span> <span class="kt">int</span><span class="o">></span> <span class="n">BinopPrecedence</span><span class="p">;</span>
+
+<span class="c1">/// GetTokPrecedence - Get the precedence of the pending binary operator token.</span>
+<span class="k">static</span> <span class="kt">int</span> <span class="nf">GetTokPrecedence</span><span class="p">()</span> <span class="p">{</span>
+ <span class="k">if</span> <span class="p">(</span><span class="o">!</span><span class="n">isascii</span><span class="p">(</span><span class="n">CurTok</span><span class="p">))</span>
+ <span class="k">return</span> <span class="o">-</span><span class="mi">1</span><span class="p">;</span>
+
+ <span class="c1">// Make sure it's a declared binop.</span>
+ <span class="kt">int</span> <span class="n">TokPrec</span> <span class="o">=</span> <span class="n">BinopPrecedence</span><span class="p">[</span><span class="n">CurTok</span><span class="p">];</span>
+ <span class="k">if</span> <span class="p">(</span><span class="n">TokPrec</span> <span class="o"><=</span> <span class="mi">0</span><span class="p">)</span>
+ <span class="k">return</span> <span class="o">-</span><span class="mi">1</span><span class="p">;</span>
+ <span class="k">return</span> <span class="n">TokPrec</span><span class="p">;</span>
+<span class="p">}</span>
+
+<span class="c1">/// Error* - These are little helper functions for error handling.</span>
+<span class="n">std</span><span class="o">::</span><span class="n">unique_ptr</span><span class="o"><</span><span class="n">ExprAST</span><span class="o">></span> <span class="n">Error</span><span class="p">(</span><span class="k">const</span> <span class="kt">char</span> <span class="o">*</span><span class="n">Str</span><span class="p">)</span> <span class="p">{</span>
+ <span class="n">fprintf</span><span class="p">(</span><span class="n">stderr</span><span class="p">,</span> <span class="s">"Error: %s</span><span class="se">\n</span><span class="s">"</span><span class="p">,</span> <span class="n">Str</span><span class="p">);</span>
+ <span class="k">return</span> <span class="n">nullptr</span><span class="p">;</span>
+<span class="p">}</span>
+
+<span class="n">std</span><span class="o">::</span><span class="n">unique_ptr</span><span class="o"><</span><span class="n">PrototypeAST</span><span class="o">></span> <span class="n">ErrorP</span><span class="p">(</span><span class="k">const</span> <span class="kt">char</span> <span class="o">*</span><span class="n">Str</span><span class="p">)</span> <span class="p">{</span>
+ <span class="n">Error</span><span class="p">(</span><span class="n">Str</span><span class="p">);</span>
+ <span class="k">return</span> <span class="n">nullptr</span><span class="p">;</span>
+<span class="p">}</span>
+
+<span class="k">static</span> <span class="n">std</span><span class="o">::</span><span class="n">unique_ptr</span><span class="o"><</span><span class="n">ExprAST</span><span class="o">></span> <span class="n">ParseExpression</span><span class="p">();</span>
+
+<span class="c1">/// numberexpr ::= number</span>
+<span class="k">static</span> <span class="n">std</span><span class="o">::</span><span class="n">unique_ptr</span><span class="o"><</span><span class="n">ExprAST</span><span class="o">></span> <span class="n">ParseNumberExpr</span><span class="p">()</span> <span class="p">{</span>
+ <span class="k">auto</span> <span class="n">Result</span> <span class="o">=</span> <span class="n">llvm</span><span class="o">::</span><span class="n">make_unique</span><span class="o"><</span><span class="n">NumberExprAST</span><span class="o">></span><span class="p">(</span><span class="n">NumVal</span><span class="p">);</span>
+ <span class="n">getNextToken</span><span class="p">();</span> <span class="c1">// consume the number</span>
+ <span class="k">return</span> <span class="n">std</span><span class="o">::</span><span class="n">move</span><span class="p">(</span><span class="n">Result</span><span class="p">);</span>
+<span class="p">}</span>
+
+<span class="c1">/// parenexpr ::= '(' expression ')'</span>
+<span class="k">static</span> <span class="n">std</span><span class="o">::</span><span class="n">unique_ptr</span><span class="o"><</span><span class="n">ExprAST</span><span class="o">></span> <span class="n">ParseParenExpr</span><span class="p">()</span> <span class="p">{</span>
+ <span class="n">getNextToken</span><span class="p">();</span> <span class="c1">// eat (.</span>
+ <span class="k">auto</span> <span class="n">V</span> <span class="o">=</span> <span class="n">ParseExpression</span><span class="p">();</span>
+ <span class="k">if</span> <span class="p">(</span><span class="o">!</span><span class="n">V</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">nullptr</span><span class="p">;</span>
+
+ <span class="k">if</span> <span class="p">(</span><span class="n">CurTok</span> <span class="o">!=</span> <span class="sc">')'</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">Error</span><span class="p">(</span><span class="s">"expected ')'"</span><span class="p">);</span>
+ <span class="n">getNextToken</span><span class="p">();</span> <span class="c1">// eat ).</span>
+ <span class="k">return</span> <span class="n">V</span><span class="p">;</span>
+<span class="p">}</span>
+
+<span class="c1">/// identifierexpr</span>
+<span class="c1">/// ::= identifier</span>
+<span class="c1">/// ::= identifier '(' expression* ')'</span>
+<span class="k">static</span> <span class="n">std</span><span class="o">::</span><span class="n">unique_ptr</span><span class="o"><</span><span class="n">ExprAST</span><span class="o">></span> <span class="n">ParseIdentifierExpr</span><span class="p">()</span> <span class="p">{</span>
+ <span class="n">std</span><span class="o">::</span><span class="n">string</span> <span class="n">IdName</span> <span class="o">=</span> <span class="n">IdentifierStr</span><span class="p">;</span>
+
+ <span class="n">getNextToken</span><span class="p">();</span> <span class="c1">// eat identifier.</span>
+
+ <span class="k">if</span> <span class="p">(</span><span class="n">CurTok</span> <span class="o">!=</span> <span class="sc">'('</span><span class="p">)</span> <span class="c1">// Simple variable ref.</span>
+ <span class="k">return</span> <span class="n">llvm</span><span class="o">::</span><span class="n">make_unique</span><span class="o"><</span><span class="n">VariableExprAST</span><span class="o">></span><span class="p">(</span><span class="n">IdName</span><span class="p">);</span>
+
+ <span class="c1">// Call.</span>
+ <span class="n">getNextToken</span><span class="p">();</span> <span class="c1">// eat (</span>
+ <span class="n">std</span><span class="o">::</span><span class="n">vector</span><span class="o"><</span><span class="n">std</span><span class="o">::</span><span class="n">unique_ptr</span><span class="o"><</span><span class="n">ExprAST</span><span class="o">>></span> <span class="n">Args</span><span class="p">;</span>
+ <span class="k">if</span> <span class="p">(</span><span class="n">CurTok</span> <span class="o">!=</span> <span class="sc">')'</span><span class="p">)</span> <span class="p">{</span>
+ <span class="k">while</span> <span class="p">(</span><span class="mi">1</span><span class="p">)</span> <span class="p">{</span>
+ <span class="k">if</span> <span class="p">(</span><span class="k">auto</span> <span class="n">Arg</span> <span class="o">=</span> <span class="n">ParseExpression</span><span class="p">())</span>
+ <span class="n">Args</span><span class="p">.</span><span class="n">push_back</span><span class="p">(</span><span class="n">std</span><span class="o">::</span><span class="n">move</span><span class="p">(</span><span class="n">Arg</span><span class="p">));</span>
+ <span class="k">else</span>
+ <span class="k">return</span> <span class="n">nullptr</span><span class="p">;</span>
+
+ <span class="k">if</span> <span class="p">(</span><span class="n">CurTok</span> <span class="o">==</span> <span class="sc">')'</span><span class="p">)</span>
+ <span class="k">break</span><span class="p">;</span>
+
+ <span class="k">if</span> <span class="p">(</span><span class="n">CurTok</span> <span class="o">!=</span> <span class="sc">','</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">Error</span><span class="p">(</span><span class="s">"Expected ')' or ',' in argument list"</span><span class="p">);</span>
+ <span class="n">getNextToken</span><span class="p">();</span>
+ <span class="p">}</span>
+ <span class="p">}</span>
+
+ <span class="c1">// Eat the ')'.</span>
+ <span class="n">getNextToken</span><span class="p">();</span>
+
+ <span class="k">return</span> <span class="n">llvm</span><span class="o">::</span><span class="n">make_unique</span><span class="o"><</span><span class="n">CallExprAST</span><span class="o">></span><span class="p">(</span><span class="n">IdName</span><span class="p">,</span> <span class="n">std</span><span class="o">::</span><span class="n">move</span><span class="p">(</span><span class="n">Args</span><span class="p">));</span>
+<span class="p">}</span>
+
+<span class="c1">/// ifexpr ::= 'if' expression 'then' expression 'else' expression</span>
+<span class="k">static</span> <span class="n">std</span><span class="o">::</span><span class="n">unique_ptr</span><span class="o"><</span><span class="n">ExprAST</span><span class="o">></span> <span class="n">ParseIfExpr</span><span class="p">()</span> <span class="p">{</span>
+ <span class="n">getNextToken</span><span class="p">();</span> <span class="c1">// eat the if.</span>
+
+ <span class="c1">// condition.</span>
+ <span class="k">auto</span> <span class="n">Cond</span> <span class="o">=</span> <span class="n">ParseExpression</span><span class="p">();</span>
+ <span class="k">if</span> <span class="p">(</span><span class="o">!</span><span class="n">Cond</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">nullptr</span><span class="p">;</span>
+
+ <span class="k">if</span> <span class="p">(</span><span class="n">CurTok</span> <span class="o">!=</span> <span class="n">tok_then</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">Error</span><span class="p">(</span><span class="s">"expected then"</span><span class="p">);</span>
+ <span class="n">getNextToken</span><span class="p">();</span> <span class="c1">// eat the then</span>
+
+ <span class="k">auto</span> <span class="n">Then</span> <span class="o">=</span> <span class="n">ParseExpression</span><span class="p">();</span>
+ <span class="k">if</span> <span class="p">(</span><span class="o">!</span><span class="n">Then</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">nullptr</span><span class="p">;</span>
+
+ <span class="k">if</span> <span class="p">(</span><span class="n">CurTok</span> <span class="o">!=</span> <span class="n">tok_else</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">Error</span><span class="p">(</span><span class="s">"expected else"</span><span class="p">);</span>
+
+ <span class="n">getNextToken</span><span class="p">();</span>
+
+ <span class="k">auto</span> <span class="n">Else</span> <span class="o">=</span> <span class="n">ParseExpression</span><span class="p">();</span>
+ <span class="k">if</span> <span class="p">(</span><span class="o">!</span><span class="n">Else</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">nullptr</span><span class="p">;</span>
+
+ <span class="k">return</span> <span class="n">llvm</span><span class="o">::</span><span class="n">make_unique</span><span class="o"><</span><span class="n">IfExprAST</span><span class="o">></span><span class="p">(</span><span class="n">std</span><span class="o">::</span><span class="n">move</span><span class="p">(</span><span class="n">Cond</span><span class="p">),</span> <span class="n">std</span><span class="o">::</span><span class="n">move</span><span class="p">(</span><span class="n">Then</span><span class="p">),</span>
+ <span class="n">std</span><span class="o">::</span><span class="n">move</span><span class="p">(</span><span class="n">Else</span><span class="p">));</span>
+<span class="p">}</span>
+
+<span class="c1">/// forexpr ::= 'for' identifier '=' expr ',' expr (',' expr)? 'in' expression</span>
+<span class="k">static</span> <span class="n">std</span><span class="o">::</span><span class="n">unique_ptr</span><span class="o"><</span><span class="n">ExprAST</span><span class="o">></span> <span class="n">ParseForExpr</span><span class="p">()</span> <span class="p">{</span>
+ <span class="n">getNextToken</span><span class="p">();</span> <span class="c1">// eat the for.</span>
+
+ <span class="k">if</span> <span class="p">(</span><span class="n">CurTok</span> <span class="o">!=</span> <span class="n">tok_identifier</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">Error</span><span class="p">(</span><span class="s">"expected identifier after for"</span><span class="p">);</span>
+
+ <span class="n">std</span><span class="o">::</span><span class="n">string</span> <span class="n">IdName</span> <span class="o">=</span> <span class="n">IdentifierStr</span><span class="p">;</span>
+ <span class="n">getNextToken</span><span class="p">();</span> <span class="c1">// eat identifier.</span>
+
+ <span class="k">if</span> <span class="p">(</span><span class="n">CurTok</span> <span class="o">!=</span> <span class="sc">'='</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">Error</span><span class="p">(</span><span class="s">"expected '=' after for"</span><span class="p">);</span>
+ <span class="n">getNextToken</span><span class="p">();</span> <span class="c1">// eat '='.</span>
+
+ <span class="k">auto</span> <span class="n">Start</span> <span class="o">=</span> <span class="n">ParseExpression</span><span class="p">();</span>
+ <span class="k">if</span> <span class="p">(</span><span class="o">!</span><span class="n">Start</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">nullptr</span><span class="p">;</span>
+ <span class="k">if</span> <span class="p">(</span><span class="n">CurTok</span> <span class="o">!=</span> <span class="sc">','</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">Error</span><span class="p">(</span><span class="s">"expected ',' after for start value"</span><span class="p">);</span>
+ <span class="n">getNextToken</span><span class="p">();</span>
+
+ <span class="k">auto</span> <span class="n">End</span> <span class="o">=</span> <span class="n">ParseExpression</span><span class="p">();</span>
+ <span class="k">if</span> <span class="p">(</span><span class="o">!</span><span class="n">End</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">nullptr</span><span class="p">;</span>
+
+ <span class="c1">// The step value is optional.</span>
+ <span class="n">std</span><span class="o">::</span><span class="n">unique_ptr</span><span class="o"><</span><span class="n">ExprAST</span><span class="o">></span> <span class="n">Step</span><span class="p">;</span>
+ <span class="k">if</span> <span class="p">(</span><span class="n">CurTok</span> <span class="o">==</span> <span class="sc">','</span><span class="p">)</span> <span class="p">{</span>
+ <span class="n">getNextToken</span><span class="p">();</span>
+ <span class="n">Step</span> <span class="o">=</span> <span class="n">ParseExpression</span><span class="p">();</span>
+ <span class="k">if</span> <span class="p">(</span><span class="o">!</span><span class="n">Step</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">nullptr</span><span class="p">;</span>
+ <span class="p">}</span>
+
+ <span class="k">if</span> <span class="p">(</span><span class="n">CurTok</span> <span class="o">!=</span> <span class="n">tok_in</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">Error</span><span class="p">(</span><span class="s">"expected 'in' after for"</span><span class="p">);</span>
+ <span class="n">getNextToken</span><span class="p">();</span> <span class="c1">// eat 'in'.</span>
+
+ <span class="k">auto</span> <span class="n">Body</span> <span class="o">=</span> <span class="n">ParseExpression</span><span class="p">();</span>
+ <span class="k">if</span> <span class="p">(</span><span class="o">!</span><span class="n">Body</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">nullptr</span><span class="p">;</span>
+
+ <span class="k">return</span> <span class="n">llvm</span><span class="o">::</span><span class="n">make_unique</span><span class="o"><</span><span class="n">ForExprAST</span><span class="o">></span><span class="p">(</span><span class="n">IdName</span><span class="p">,</span> <span class="n">std</span><span class="o">::</span><span class="n">move</span><span class="p">(</span><span class="n">Start</span><span class="p">),</span> <span class="n">std</span><span class="o">::</span><span class="n">move</span><span class="p">(</span><span class="n">End</span><span class="p">),</span>
+ <span class="n">std</span><span class="o">::</span><span class="n">move</span><span class="p">(</span><span class="n">Step</span><span class="p">),</span> <span class="n">std</span><span class="o">::</span><span class="n">move</span><span class="p">(</span><span class="n">Body</span><span class="p">));</span>
+<span class="p">}</span>
+
+<span class="c1">/// varexpr ::= 'var' identifier ('=' expression)?</span>
+<span class="c1">// (',' identifier ('=' expression)?)* 'in' expression</span>
+<span class="k">static</span> <span class="n">std</span><span class="o">::</span><span class="n">unique_ptr</span><span class="o"><</span><span class="n">ExprAST</span><span class="o">></span> <span class="n">ParseVarExpr</span><span class="p">()</span> <span class="p">{</span>
+ <span class="n">getNextToken</span><span class="p">();</span> <span class="c1">// eat the var.</span>
+
+ <span class="n">std</span><span class="o">::</span><span class="n">vector</span><span class="o"><</span><span class="n">std</span><span class="o">::</span><span class="n">pair</span><span class="o"><</span><span class="n">std</span><span class="o">::</span><span class="n">string</span><span class="p">,</span> <span class="n">std</span><span class="o">::</span><span class="n">unique_ptr</span><span class="o"><</span><span class="n">ExprAST</span><span class="o">>>></span> <span class="n">VarNames</span><span class="p">;</span>
+
+ <span class="c1">// At least one variable name is required.</span>
+ <span class="k">if</span> <span class="p">(</span><span class="n">CurTok</span> <span class="o">!=</span> <span class="n">tok_identifier</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">Error</span><span class="p">(</span><span class="s">"expected identifier after var"</span><span class="p">);</span>
+
+ <span class="k">while</span> <span class="p">(</span><span class="mi">1</span><span class="p">)</span> <span class="p">{</span>
+ <span class="n">std</span><span class="o">::</span><span class="n">string</span> <span class="n">Name</span> <span class="o">=</span> <span class="n">IdentifierStr</span><span class="p">;</span>
+ <span class="n">getNextToken</span><span class="p">();</span> <span class="c1">// eat identifier.</span>
+
+ <span class="c1">// Read the optional initializer.</span>
+ <span class="n">std</span><span class="o">::</span><span class="n">unique_ptr</span><span class="o"><</span><span class="n">ExprAST</span><span class="o">></span> <span class="n">Init</span> <span class="o">=</span> <span class="n">nullptr</span><span class="p">;</span>
+ <span class="k">if</span> <span class="p">(</span><span class="n">CurTok</span> <span class="o">==</span> <span class="sc">'='</span><span class="p">)</span> <span class="p">{</span>
+ <span class="n">getNextToken</span><span class="p">();</span> <span class="c1">// eat the '='.</span>
+
+ <span class="n">Init</span> <span class="o">=</span> <span class="n">ParseExpression</span><span class="p">();</span>
+ <span class="k">if</span> <span class="p">(</span><span class="o">!</span><span class="n">Init</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">nullptr</span><span class="p">;</span>
+ <span class="p">}</span>
+
+ <span class="n">VarNames</span><span class="p">.</span><span class="n">push_back</span><span class="p">(</span><span class="n">std</span><span class="o">::</span><span class="n">make_pair</span><span class="p">(</span><span class="n">Name</span><span class="p">,</span> <span class="n">std</span><span class="o">::</span><span class="n">move</span><span class="p">(</span><span class="n">Init</span><span class="p">)));</span>
+
+ <span class="c1">// End of var list, exit loop.</span>
+ <span class="k">if</span> <span class="p">(</span><span class="n">CurTok</span> <span class="o">!=</span> <span class="sc">','</span><span class="p">)</span>
+ <span class="k">break</span><span class="p">;</span>
+ <span class="n">getNextToken</span><span class="p">();</span> <span class="c1">// eat the ','.</span>
+
+ <span class="k">if</span> <span class="p">(</span><span class="n">CurTok</span> <span class="o">!=</span> <span class="n">tok_identifier</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">Error</span><span class="p">(</span><span class="s">"expected identifier list after var"</span><span class="p">);</span>
+ <span class="p">}</span>
+
+ <span class="c1">// At this point, we have to have 'in'.</span>
+ <span class="k">if</span> <span class="p">(</span><span class="n">CurTok</span> <span class="o">!=</span> <span class="n">tok_in</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">Error</span><span class="p">(</span><span class="s">"expected 'in' keyword after 'var'"</span><span class="p">);</span>
+ <span class="n">getNextToken</span><span class="p">();</span> <span class="c1">// eat 'in'.</span>
+
+ <span class="k">auto</span> <span class="n">Body</span> <span class="o">=</span> <span class="n">ParseExpression</span><span class="p">();</span>
+ <span class="k">if</span> <span class="p">(</span><span class="o">!</span><span class="n">Body</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">nullptr</span><span class="p">;</span>
+
+ <span class="k">return</span> <span class="n">llvm</span><span class="o">::</span><span class="n">make_unique</span><span class="o"><</span><span class="n">VarExprAST</span><span class="o">></span><span class="p">(</span><span class="n">std</span><span class="o">::</span><span class="n">move</span><span class="p">(</span><span class="n">VarNames</span><span class="p">),</span> <span class="n">std</span><span class="o">::</span><span class="n">move</span><span class="p">(</span><span class="n">Body</span><span class="p">));</span>
+<span class="p">}</span>
+
+<span class="c1">/// primary</span>
+<span class="c1">/// ::= identifierexpr</span>
+<span class="c1">/// ::= numberexpr</span>
+<span class="c1">/// ::= parenexpr</span>
+<span class="c1">/// ::= ifexpr</span>
+<span class="c1">/// ::= forexpr</span>
+<span class="c1">/// ::= varexpr</span>
+<span class="k">static</span> <span class="n">std</span><span class="o">::</span><span class="n">unique_ptr</span><span class="o"><</span><span class="n">ExprAST</span><span class="o">></span> <span class="n">ParsePrimary</span><span class="p">()</span> <span class="p">{</span>
+ <span class="k">switch</span> <span class="p">(</span><span class="n">CurTok</span><span class="p">)</span> <span class="p">{</span>
+ <span class="nl">default:</span>
+ <span class="k">return</span> <span class="n">Error</span><span class="p">(</span><span class="s">"unknown token when expecting an expression"</span><span class="p">);</span>
+ <span class="k">case</span> <span class="n">tok_identifier</span>:
+ <span class="k">return</span> <span class="n">ParseIdentifierExpr</span><span class="p">();</span>
+ <span class="k">case</span> <span class="n">tok_number</span>:
+ <span class="k">return</span> <span class="n">ParseNumberExpr</span><span class="p">();</span>
+ <span class="k">case</span> <span class="sc">'('</span>:
+ <span class="k">return</span> <span class="n">ParseParenExpr</span><span class="p">();</span>
+ <span class="k">case</span> <span class="n">tok_if</span>:
+ <span class="k">return</span> <span class="n">ParseIfExpr</span><span class="p">();</span>
+ <span class="k">case</span> <span class="n">tok_for</span>:
+ <span class="k">return</span> <span class="n">ParseForExpr</span><span class="p">();</span>
+ <span class="k">case</span> <span class="n">tok_var</span>:
+ <span class="k">return</span> <span class="n">ParseVarExpr</span><span class="p">();</span>
+ <span class="p">}</span>
+<span class="p">}</span>
+
+<span class="c1">/// unary</span>
+<span class="c1">/// ::= primary</span>
+<span class="c1">/// ::= '!' unary</span>
+<span class="k">static</span> <span class="n">std</span><span class="o">::</span><span class="n">unique_ptr</span><span class="o"><</span><span class="n">ExprAST</span><span class="o">></span> <span class="n">ParseUnary</span><span class="p">()</span> <span class="p">{</span>
+ <span class="c1">// If the current token is not an operator, it must be a primary expr.</span>
+ <span class="k">if</span> <span class="p">(</span><span class="o">!</span><span class="n">isascii</span><span class="p">(</span><span class="n">CurTok</span><span class="p">)</span> <span class="o">||</span> <span class="n">CurTok</span> <span class="o">==</span> <span class="sc">'('</span> <span class="o">||</span> <span class="n">CurTok</span> <span class="o">==</span> <span class="sc">','</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">ParsePrimary</span><span class="p">();</span>
+
+ <span class="c1">// If this is a unary operator, read it.</span>
+ <span class="kt">int</span> <span class="n">Opc</span> <span class="o">=</span> <span class="n">CurTok</span><span class="p">;</span>
+ <span class="n">getNextToken</span><span class="p">();</span>
+ <span class="k">if</span> <span class="p">(</span><span class="k">auto</span> <span class="n">Operand</span> <span class="o">=</span> <span class="n">ParseUnary</span><span class="p">())</span>
+ <span class="k">return</span> <span class="n">llvm</span><span class="o">::</span><span class="n">make_unique</span><span class="o"><</span><span class="n">UnaryExprAST</span><span class="o">></span><span class="p">(</span><span class="n">Opc</span><span class="p">,</span> <span class="n">std</span><span class="o">::</span><span class="n">move</span><span class="p">(</span><span class="n">Operand</span><span class="p">));</span>
+ <span class="k">return</span> <span class="n">nullptr</span><span class="p">;</span>
+<span class="p">}</span>
+
+<span class="c1">/// binoprhs</span>
+<span class="c1">/// ::= ('+' unary)*</span>
+<span class="k">static</span> <span class="n">std</span><span class="o">::</span><span class="n">unique_ptr</span><span class="o"><</span><span class="n">ExprAST</span><span class="o">></span> <span class="n">ParseBinOpRHS</span><span class="p">(</span><span class="kt">int</span> <span class="n">ExprPrec</span><span class="p">,</span>
+ <span class="n">std</span><span class="o">::</span><span class="n">unique_ptr</span><span class="o"><</span><span class="n">ExprAST</span><span class="o">></span> <span class="n">LHS</span><span class="p">)</span> <span class="p">{</span>
+ <span class="c1">// If this is a binop, find its precedence.</span>
+ <span class="k">while</span> <span class="p">(</span><span class="mi">1</span><span class="p">)</span> <span class="p">{</span>
+ <span class="kt">int</span> <span class="n">TokPrec</span> <span class="o">=</span> <span class="n">GetTokPrecedence</span><span class="p">();</span>
+
+ <span class="c1">// If this is a binop that binds at least as tightly as the current binop,</span>
+ <span class="c1">// consume it, otherwise we are done.</span>
+ <span class="k">if</span> <span class="p">(</span><span class="n">TokPrec</span> <span class="o"><</span> <span class="n">ExprPrec</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">LHS</span><span class="p">;</span>
+
+ <span class="c1">// Okay, we know this is a binop.</span>
+ <span class="kt">int</span> <span class="n">BinOp</span> <span class="o">=</span> <span class="n">CurTok</span><span class="p">;</span>
+ <span class="n">getNextToken</span><span class="p">();</span> <span class="c1">// eat binop</span>
+
+ <span class="c1">// Parse the unary expression after the binary operator.</span>
+ <span class="k">auto</span> <span class="n">RHS</span> <span class="o">=</span> <span class="n">ParseUnary</span><span class="p">();</span>
+ <span class="k">if</span> <span class="p">(</span><span class="o">!</span><span class="n">RHS</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">nullptr</span><span class="p">;</span>
+
+ <span class="c1">// If BinOp binds less tightly with RHS than the operator after RHS, let</span>
+ <span class="c1">// the pending operator take RHS as its LHS.</span>
+ <span class="kt">int</span> <span class="n">NextPrec</span> <span class="o">=</span> <span class="n">GetTokPrecedence</span><span class="p">();</span>
+ <span class="k">if</span> <span class="p">(</span><span class="n">TokPrec</span> <span class="o"><</span> <span class="n">NextPrec</span><span class="p">)</span> <span class="p">{</span>
+ <span class="n">RHS</span> <span class="o">=</span> <span class="n">ParseBinOpRHS</span><span class="p">(</span><span class="n">TokPrec</span> <span class="o">+</span> <span class="mi">1</span><span class="p">,</span> <span class="n">std</span><span class="o">::</span><span class="n">move</span><span class="p">(</span><span class="n">RHS</span><span class="p">));</span>
+ <span class="k">if</span> <span class="p">(</span><span class="o">!</span><span class="n">RHS</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">nullptr</span><span class="p">;</span>
+ <span class="p">}</span>
+
+ <span class="c1">// Merge LHS/RHS.</span>
+ <span class="n">LHS</span> <span class="o">=</span>
+ <span class="n">llvm</span><span class="o">::</span><span class="n">make_unique</span><span class="o"><</span><span class="n">BinaryExprAST</span><span class="o">></span><span class="p">(</span><span class="n">BinOp</span><span class="p">,</span> <span class="n">std</span><span class="o">::</span><span class="n">move</span><span class="p">(</span><span class="n">LHS</span><span class="p">),</span> <span class="n">std</span><span class="o">::</span><span class="n">move</span><span class="p">(</span><span class="n">RHS</span><span class="p">));</span>
+ <span class="p">}</span>
+<span class="p">}</span>
+
+<span class="c1">/// expression</span>
+<span class="c1">/// ::= unary binoprhs</span>
+<span class="c1">///</span>
+<span class="k">static</span> <span class="n">std</span><span class="o">::</span><span class="n">unique_ptr</span><span class="o"><</span><span class="n">ExprAST</span><span class="o">></span> <span class="n">ParseExpression</span><span class="p">()</span> <span class="p">{</span>
+ <span class="k">auto</span> <span class="n">LHS</span> <span class="o">=</span> <span class="n">ParseUnary</span><span class="p">();</span>
+ <span class="k">if</span> <span class="p">(</span><span class="o">!</span><span class="n">LHS</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">nullptr</span><span class="p">;</span>
+
+ <span class="k">return</span> <span class="nf">ParseBinOpRHS</span><span class="p">(</span><span class="mi">0</span><span class="p">,</span> <span class="n">std</span><span class="o">::</span><span class="n">move</span><span class="p">(</span><span class="n">LHS</span><span class="p">));</span>
+<span class="p">}</span>
+
+<span class="c1">/// prototype</span>
+<span class="c1">/// ::= id '(' id* ')'</span>
+<span class="c1">/// ::= binary LETTER number? (id, id)</span>
+<span class="c1">/// ::= unary LETTER (id)</span>
+<span class="k">static</span> <span class="n">std</span><span class="o">::</span><span class="n">unique_ptr</span><span class="o"><</span><span class="n">PrototypeAST</span><span class="o">></span> <span class="n">ParsePrototype</span><span class="p">()</span> <span class="p">{</span>
+ <span class="n">std</span><span class="o">::</span><span class="n">string</span> <span class="n">FnName</span><span class="p">;</span>
+
+ <span class="kt">unsigned</span> <span class="n">Kind</span> <span class="o">=</span> <span class="mi">0</span><span class="p">;</span> <span class="c1">// 0 = identifier, 1 = unary, 2 = binary.</span>
+ <span class="kt">unsigned</span> <span class="n">BinaryPrecedence</span> <span class="o">=</span> <span class="mi">30</span><span class="p">;</span>
+
+ <span class="k">switch</span> <span class="p">(</span><span class="n">CurTok</span><span class="p">)</span> <span class="p">{</span>
+ <span class="nl">default:</span>
+ <span class="k">return</span> <span class="n">ErrorP</span><span class="p">(</span><span class="s">"Expected function name in prototype"</span><span class="p">);</span>
+ <span class="k">case</span> <span class="n">tok_identifier</span>:
+ <span class="n">FnName</span> <span class="o">=</span> <span class="n">IdentifierStr</span><span class="p">;</span>
+ <span class="n">Kind</span> <span class="o">=</span> <span class="mi">0</span><span class="p">;</span>
+ <span class="n">getNextToken</span><span class="p">();</span>
+ <span class="k">break</span><span class="p">;</span>
+ <span class="k">case</span> <span class="n">tok_unary</span>:
+ <span class="n">getNextToken</span><span class="p">();</span>
+ <span class="k">if</span> <span class="p">(</span><span class="o">!</span><span class="n">isascii</span><span class="p">(</span><span class="n">CurTok</span><span class="p">))</span>
+ <span class="k">return</span> <span class="n">ErrorP</span><span class="p">(</span><span class="s">"Expected unary operator"</span><span class="p">);</span>
+ <span class="n">FnName</span> <span class="o">=</span> <span class="s">"unary"</span><span class="p">;</span>
+ <span class="n">FnName</span> <span class="o">+=</span> <span class="p">(</span><span class="kt">char</span><span class="p">)</span><span class="n">CurTok</span><span class="p">;</span>
+ <span class="n">Kind</span> <span class="o">=</span> <span class="mi">1</span><span class="p">;</span>
+ <span class="n">getNextToken</span><span class="p">();</span>
+ <span class="k">break</span><span class="p">;</span>
+ <span class="k">case</span> <span class="n">tok_binary</span>:
+ <span class="n">getNextToken</span><span class="p">();</span>
+ <span class="k">if</span> <span class="p">(</span><span class="o">!</span><span class="n">isascii</span><span class="p">(</span><span class="n">CurTok</span><span class="p">))</span>
+ <span class="k">return</span> <span class="n">ErrorP</span><span class="p">(</span><span class="s">"Expected binary operator"</span><span class="p">);</span>
+ <span class="n">FnName</span> <span class="o">=</span> <span class="s">"binary"</span><span class="p">;</span>
+ <span class="n">FnName</span> <span class="o">+=</span> <span class="p">(</span><span class="kt">char</span><span class="p">)</span><span class="n">CurTok</span><span class="p">;</span>
+ <span class="n">Kind</span> <span class="o">=</span> <span class="mi">2</span><span class="p">;</span>
+ <span class="n">getNextToken</span><span class="p">();</span>
+
+ <span class="c1">// Read the precedence if present.</span>
+ <span class="k">if</span> <span class="p">(</span><span class="n">CurTok</span> <span class="o">==</span> <span class="n">tok_number</span><span class="p">)</span> <span class="p">{</span>
+ <span class="k">if</span> <span class="p">(</span><span class="n">NumVal</span> <span class="o"><</span> <span class="mi">1</span> <span class="o">||</span> <span class="n">NumVal</span> <span class="o">></span> <span class="mi">100</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">ErrorP</span><span class="p">(</span><span class="s">"Invalid precedecnce: must be 1..100"</span><span class="p">);</span>
+ <span class="n">BinaryPrecedence</span> <span class="o">=</span> <span class="p">(</span><span class="kt">unsigned</span><span class="p">)</span><span class="n">NumVal</span><span class="p">;</span>
+ <span class="n">getNextToken</span><span class="p">();</span>
+ <span class="p">}</span>
+ <span class="k">break</span><span class="p">;</span>
+ <span class="p">}</span>
+
+ <span class="k">if</span> <span class="p">(</span><span class="n">CurTok</span> <span class="o">!=</span> <span class="sc">'('</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">ErrorP</span><span class="p">(</span><span class="s">"Expected '(' in prototype"</span><span class="p">);</span>
+
+ <span class="n">std</span><span class="o">::</span><span class="n">vector</span><span class="o"><</span><span class="n">std</span><span class="o">::</span><span class="n">string</span><span class="o">></span> <span class="n">ArgNames</span><span class="p">;</span>
+ <span class="k">while</span> <span class="p">(</span><span class="n">getNextToken</span><span class="p">()</span> <span class="o">==</span> <span class="n">tok_identifier</span><span class="p">)</span>
+ <span class="n">ArgNames</span><span class="p">.</span><span class="n">push_back</span><span class="p">(</span><span class="n">IdentifierStr</span><span class="p">);</span>
+ <span class="k">if</span> <span class="p">(</span><span class="n">CurTok</span> <span class="o">!=</span> <span class="sc">')'</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">ErrorP</span><span class="p">(</span><span class="s">"Expected ')' in prototype"</span><span class="p">);</span>
+
+ <span class="c1">// success.</span>
+ <span class="n">getNextToken</span><span class="p">();</span> <span class="c1">// eat ')'.</span>
+
+ <span class="c1">// Verify right number of names for operator.</span>
+ <span class="k">if</span> <span class="p">(</span><span class="n">Kind</span> <span class="o">&&</span> <span class="n">ArgNames</span><span class="p">.</span><span class="n">size</span><span class="p">()</span> <span class="o">!=</span> <span class="n">Kind</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">ErrorP</span><span class="p">(</span><span class="s">"Invalid number of operands for operator"</span><span class="p">);</span>
+
+ <span class="k">return</span> <span class="n">llvm</span><span class="o">::</span><span class="n">make_unique</span><span class="o"><</span><span class="n">PrototypeAST</span><span class="o">></span><span class="p">(</span><span class="n">FnName</span><span class="p">,</span> <span class="n">ArgNames</span><span class="p">,</span> <span class="n">Kind</span> <span class="o">!=</span> <span class="mi">0</span><span class="p">,</span>
+ <span class="n">BinaryPrecedence</span><span class="p">);</span>
+<span class="p">}</span>
+
+<span class="c1">/// definition ::= 'def' prototype expression</span>
+<span class="k">static</span> <span class="n">std</span><span class="o">::</span><span class="n">unique_ptr</span><span class="o"><</span><span class="n">FunctionAST</span><span class="o">></span> <span class="n">ParseDefinition</span><span class="p">()</span> <span class="p">{</span>
+ <span class="n">getNextToken</span><span class="p">();</span> <span class="c1">// eat def.</span>
+ <span class="k">auto</span> <span class="n">Proto</span> <span class="o">=</span> <span class="n">ParsePrototype</span><span class="p">();</span>
+ <span class="k">if</span> <span class="p">(</span><span class="o">!</span><span class="n">Proto</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">nullptr</span><span class="p">;</span>
+
+ <span class="k">if</span> <span class="p">(</span><span class="k">auto</span> <span class="n">E</span> <span class="o">=</span> <span class="n">ParseExpression</span><span class="p">())</span>
+ <span class="k">return</span> <span class="n">llvm</span><span class="o">::</span><span class="n">make_unique</span><span class="o"><</span><span class="n">FunctionAST</span><span class="o">></span><span class="p">(</span><span class="n">std</span><span class="o">::</span><span class="n">move</span><span class="p">(</span><span class="n">Proto</span><span class="p">),</span> <span class="n">std</span><span class="o">::</span><span class="n">move</span><span class="p">(</span><span class="n">E</span><span class="p">));</span>
+ <span class="k">return</span> <span class="n">nullptr</span><span class="p">;</span>
+<span class="p">}</span>
+
+<span class="c1">/// toplevelexpr ::= expression</span>
+<span class="k">static</span> <span class="n">std</span><span class="o">::</span><span class="n">unique_ptr</span><span class="o"><</span><span class="n">FunctionAST</span><span class="o">></span> <span class="n">ParseTopLevelExpr</span><span class="p">()</span> <span class="p">{</span>
+ <span class="k">if</span> <span class="p">(</span><span class="k">auto</span> <span class="n">E</span> <span class="o">=</span> <span class="n">ParseExpression</span><span class="p">())</span> <span class="p">{</span>
+ <span class="c1">// Make an anonymous proto.</span>
+ <span class="k">auto</span> <span class="n">Proto</span> <span class="o">=</span> <span class="n">llvm</span><span class="o">::</span><span class="n">make_unique</span><span class="o"><</span><span class="n">PrototypeAST</span><span class="o">></span><span class="p">(</span><span class="s">"__anon_expr"</span><span class="p">,</span>
+ <span class="n">std</span><span class="o">::</span><span class="n">vector</span><span class="o"><</span><span class="n">std</span><span class="o">::</span><span class="n">string</span><span class="o">></span><span class="p">());</span>
+ <span class="k">return</span> <span class="n">llvm</span><span class="o">::</span><span class="n">make_unique</span><span class="o"><</span><span class="n">FunctionAST</span><span class="o">></span><span class="p">(</span><span class="n">std</span><span class="o">::</span><span class="n">move</span><span class="p">(</span><span class="n">Proto</span><span class="p">),</span> <span class="n">std</span><span class="o">::</span><span class="n">move</span><span class="p">(</span><span class="n">E</span><span class="p">));</span>
+ <span class="p">}</span>
+ <span class="k">return</span> <span class="n">nullptr</span><span class="p">;</span>
+<span class="p">}</span>
+
+<span class="c1">/// external ::= 'extern' prototype</span>
+<span class="k">static</span> <span class="n">std</span><span class="o">::</span><span class="n">unique_ptr</span><span class="o"><</span><span class="n">PrototypeAST</span><span class="o">></span> <span class="n">ParseExtern</span><span class="p">()</span> <span class="p">{</span>
+ <span class="n">getNextToken</span><span class="p">();</span> <span class="c1">// eat extern.</span>
+ <span class="k">return</span> <span class="nf">ParsePrototype</span><span class="p">();</span>
+<span class="p">}</span>
+
+<span class="c1">//===----------------------------------------------------------------------===//</span>
+<span class="c1">// Code Generation</span>
+<span class="c1">//===----------------------------------------------------------------------===//</span>
+
+<span class="k">static</span> <span class="n">std</span><span class="o">::</span><span class="n">unique_ptr</span><span class="o"><</span><span class="n">Module</span><span class="o">></span> <span class="n">TheModule</span><span class="p">;</span>
+<span class="k">static</span> <span class="n">IRBuilder</span><span class="o"><></span> <span class="n">Builder</span><span class="p">(</span><span class="n">getGlobalContext</span><span class="p">());</span>
+<span class="k">static</span> <span class="n">std</span><span class="o">::</span><span class="n">map</span><span class="o"><</span><span class="n">std</span><span class="o">::</span><span class="n">string</span><span class="p">,</span> <span class="n">AllocaInst</span> <span class="o">*></span> <span class="n">NamedValues</span><span class="p">;</span>
+<span class="k">static</span> <span class="n">std</span><span class="o">::</span><span class="n">unique_ptr</span><span class="o"><</span><span class="n">legacy</span><span class="o">::</span><span class="n">FunctionPassManager</span><span class="o">></span> <span class="n">TheFPM</span><span class="p">;</span>
+<span class="k">static</span> <span class="n">std</span><span class="o">::</span><span class="n">unique_ptr</span><span class="o"><</span><span class="n">KaleidoscopeJIT</span><span class="o">></span> <span class="n">TheJIT</span><span class="p">;</span>
+<span class="k">static</span> <span class="n">std</span><span class="o">::</span><span class="n">map</span><span class="o"><</span><span class="n">std</span><span class="o">::</span><span class="n">string</span><span class="p">,</span> <span class="n">std</span><span class="o">::</span><span class="n">unique_ptr</span><span class="o"><</span><span class="n">PrototypeAST</span><span class="o">>></span> <span class="n">FunctionProtos</span><span class="p">;</span>
+
+<span class="n">Value</span> <span class="o">*</span><span class="nf">ErrorV</span><span class="p">(</span><span class="k">const</span> <span class="kt">char</span> <span class="o">*</span><span class="n">Str</span><span class="p">)</span> <span class="p">{</span>
+ <span class="n">Error</span><span class="p">(</span><span class="n">Str</span><span class="p">);</span>
+ <span class="k">return</span> <span class="n">nullptr</span><span class="p">;</span>
+<span class="p">}</span>
+
+<span class="n">Function</span> <span class="o">*</span><span class="nf">getFunction</span><span class="p">(</span><span class="n">std</span><span class="o">::</span><span class="n">string</span> <span class="n">Name</span><span class="p">)</span> <span class="p">{</span>
+ <span class="c1">// First, see if the function has already been added to the current module.</span>
+ <span class="k">if</span> <span class="p">(</span><span class="k">auto</span> <span class="o">*</span><span class="n">F</span> <span class="o">=</span> <span class="n">TheModule</span><span class="o">-></span><span class="n">getFunction</span><span class="p">(</span><span class="n">Name</span><span class="p">))</span>
+ <span class="k">return</span> <span class="n">F</span><span class="p">;</span>
+
+ <span class="c1">// If not, check whether we can codegen the declaration from some existing</span>
+ <span class="c1">// prototype.</span>
+ <span class="k">auto</span> <span class="n">FI</span> <span class="o">=</span> <span class="n">FunctionProtos</span><span class="p">.</span><span class="n">find</span><span class="p">(</span><span class="n">Name</span><span class="p">);</span>
+ <span class="k">if</span> <span class="p">(</span><span class="n">FI</span> <span class="o">!=</span> <span class="n">FunctionProtos</span><span class="p">.</span><span class="n">end</span><span class="p">())</span>
+ <span class="k">return</span> <span class="n">FI</span><span class="o">-></span><span class="n">second</span><span class="o">-></span><span class="n">codegen</span><span class="p">();</span>
+
+ <span class="c1">// If no existing prototype exists, return null.</span>
+ <span class="k">return</span> <span class="n">nullptr</span><span class="p">;</span>
+<span class="p">}</span>
+
+<span class="c1">/// CreateEntryBlockAlloca - Create an alloca instruction in the entry block of</span>
+<span class="c1">/// the function. This is used for mutable variables etc.</span>
+<span class="k">static</span> <span class="n">AllocaInst</span> <span class="o">*</span><span class="nf">CreateEntryBlockAlloca</span><span class="p">(</span><span class="n">Function</span> <span class="o">*</span><span class="n">TheFunction</span><span class="p">,</span>
+ <span class="k">const</span> <span class="n">std</span><span class="o">::</span><span class="n">string</span> <span class="o">&</span><span class="n">VarName</span><span class="p">)</span> <span class="p">{</span>
+ <span class="n">IRBuilder</span><span class="o"><></span> <span class="n">TmpB</span><span class="p">(</span><span class="o">&</span><span class="n">TheFunction</span><span class="o">-></span><span class="n">getEntryBlock</span><span class="p">(),</span>
+ <span class="n">TheFunction</span><span class="o">-></span><span class="n">getEntryBlock</span><span class="p">().</span><span class="n">begin</span><span class="p">());</span>
+ <span class="k">return</span> <span class="n">TmpB</span><span class="p">.</span><span class="n">CreateAlloca</span><span class="p">(</span><span class="n">Type</span><span class="o">::</span><span class="n">getDoubleTy</span><span class="p">(</span><span class="n">getGlobalContext</span><span class="p">()),</span> <span class="n">nullptr</span><span class="p">,</span>
+ <span class="n">VarName</span><span class="p">.</span><span class="n">c_str</span><span class="p">());</span>
+<span class="p">}</span>
+
+<span class="n">Value</span> <span class="o">*</span><span class="n">NumberExprAST</span><span class="o">::</span><span class="n">codegen</span><span class="p">()</span> <span class="p">{</span>
+ <span class="k">return</span> <span class="n">ConstantFP</span><span class="o">::</span><span class="n">get</span><span class="p">(</span><span class="n">getGlobalContext</span><span class="p">(),</span> <span class="n">APFloat</span><span class="p">(</span><span class="n">Val</span><span class="p">));</span>
+<span class="p">}</span>
+
+<span class="n">Value</span> <span class="o">*</span><span class="n">VariableExprAST</span><span class="o">::</span><span class="n">codegen</span><span class="p">()</span> <span class="p">{</span>
+ <span class="c1">// Look this variable up in the function.</span>
+ <span class="n">Value</span> <span class="o">*</span><span class="n">V</span> <span class="o">=</span> <span class="n">NamedValues</span><span class="p">[</span><span class="n">Name</span><span class="p">];</span>
+ <span class="k">if</span> <span class="p">(</span><span class="o">!</span><span class="n">V</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">ErrorV</span><span class="p">(</span><span class="s">"Unknown variable name"</span><span class="p">);</span>
+
+ <span class="c1">// Load the value.</span>
+ <span class="k">return</span> <span class="n">Builder</span><span class="p">.</span><span class="n">CreateLoad</span><span class="p">(</span><span class="n">V</span><span class="p">,</span> <span class="n">Name</span><span class="p">.</span><span class="n">c_str</span><span class="p">());</span>
+<span class="p">}</span>
+
+<span class="n">Value</span> <span class="o">*</span><span class="n">UnaryExprAST</span><span class="o">::</span><span class="n">codegen</span><span class="p">()</span> <span class="p">{</span>
+ <span class="n">Value</span> <span class="o">*</span><span class="n">OperandV</span> <span class="o">=</span> <span class="n">Operand</span><span class="o">-></span><span class="n">codegen</span><span class="p">();</span>
+ <span class="k">if</span> <span class="p">(</span><span class="o">!</span><span class="n">OperandV</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">nullptr</span><span class="p">;</span>
+
+ <span class="n">Function</span> <span class="o">*</span><span class="n">F</span> <span class="o">=</span> <span class="n">getFunction</span><span class="p">(</span><span class="n">std</span><span class="o">::</span><span class="n">string</span><span class="p">(</span><span class="s">"unary"</span><span class="p">)</span> <span class="o">+</span> <span class="n">Opcode</span><span class="p">);</span>
+ <span class="k">if</span> <span class="p">(</span><span class="o">!</span><span class="n">F</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">ErrorV</span><span class="p">(</span><span class="s">"Unknown unary operator"</span><span class="p">);</span>
+
+ <span class="k">return</span> <span class="n">Builder</span><span class="p">.</span><span class="n">CreateCall</span><span class="p">(</span><span class="n">F</span><span class="p">,</span> <span class="n">OperandV</span><span class="p">,</span> <span class="s">"unop"</span><span class="p">);</span>
+<span class="p">}</span>
+
+<span class="n">Value</span> <span class="o">*</span><span class="n">BinaryExprAST</span><span class="o">::</span><span class="n">codegen</span><span class="p">()</span> <span class="p">{</span>
+ <span class="c1">// Special case '=' because we don't want to emit the LHS as an expression.</span>
+ <span class="k">if</span> <span class="p">(</span><span class="n">Op</span> <span class="o">==</span> <span class="sc">'='</span><span class="p">)</span> <span class="p">{</span>
+ <span class="c1">// Assignment requires the LHS to be an identifier.</span>
+ <span class="c1">// This assume we're building without RTTI because LLVM builds that way by</span>
+ <span class="c1">// default. If you build LLVM with RTTI this can be changed to a</span>
+ <span class="c1">// dynamic_cast for automatic error checking.</span>
+ <span class="n">VariableExprAST</span> <span class="o">*</span><span class="n">LHSE</span> <span class="o">=</span> <span class="k">static_cast</span><span class="o"><</span><span class="n">VariableExprAST</span> <span class="o">*></span><span class="p">(</span><span class="n">LHS</span><span class="p">.</span><span class="n">get</span><span class="p">());</span>
+ <span class="k">if</span> <span class="p">(</span><span class="o">!</span><span class="n">LHSE</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">ErrorV</span><span class="p">(</span><span class="s">"destination of '=' must be a variable"</span><span class="p">);</span>
+ <span class="c1">// Codegen the RHS.</span>
+ <span class="n">Value</span> <span class="o">*</span><span class="n">Val</span> <span class="o">=</span> <span class="n">RHS</span><span class="o">-></span><span class="n">codegen</span><span class="p">();</span>
+ <span class="k">if</span> <span class="p">(</span><span class="o">!</span><span class="n">Val</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">nullptr</span><span class="p">;</span>
+
+ <span class="c1">// Look up the name.</span>
+ <span class="n">Value</span> <span class="o">*</span><span class="n">Variable</span> <span class="o">=</span> <span class="n">NamedValues</span><span class="p">[</span><span class="n">LHSE</span><span class="o">-></span><span class="n">getName</span><span class="p">()];</span>
+ <span class="k">if</span> <span class="p">(</span><span class="o">!</span><span class="n">Variable</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">ErrorV</span><span class="p">(</span><span class="s">"Unknown variable name"</span><span class="p">);</span>
+
+ <span class="n">Builder</span><span class="p">.</span><span class="n">CreateStore</span><span class="p">(</span><span class="n">Val</span><span class="p">,</span> <span class="n">Variable</span><span class="p">);</span>
+ <span class="k">return</span> <span class="n">Val</span><span class="p">;</span>
+ <span class="p">}</span>
+
+ <span class="n">Value</span> <span class="o">*</span><span class="n">L</span> <span class="o">=</span> <span class="n">LHS</span><span class="o">-></span><span class="n">codegen</span><span class="p">();</span>
+ <span class="n">Value</span> <span class="o">*</span><span class="n">R</span> <span class="o">=</span> <span class="n">RHS</span><span class="o">-></span><span class="n">codegen</span><span class="p">();</span>
+ <span class="k">if</span> <span class="p">(</span><span class="o">!</span><span class="n">L</span> <span class="o">||</span> <span class="o">!</span><span class="n">R</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">nullptr</span><span class="p">;</span>
+
+ <span class="k">switch</span> <span class="p">(</span><span class="n">Op</span><span class="p">)</span> <span class="p">{</span>
+ <span class="k">case</span> <span class="sc">'+'</span>:
+ <span class="k">return</span> <span class="n">Builder</span><span class="p">.</span><span class="n">CreateFAdd</span><span class="p">(</span><span class="n">L</span><span class="p">,</span> <span class="n">R</span><span class="p">,</span> <span class="s">"addtmp"</span><span class="p">);</span>
+ <span class="k">case</span> <span class="sc">'-'</span>:
+ <span class="k">return</span> <span class="n">Builder</span><span class="p">.</span><span class="n">CreateFSub</span><span class="p">(</span><span class="n">L</span><span class="p">,</span> <span class="n">R</span><span class="p">,</span> <span class="s">"subtmp"</span><span class="p">);</span>
+ <span class="k">case</span> <span class="sc">'*'</span>:
+ <span class="k">return</span> <span class="n">Builder</span><span class="p">.</span><span class="n">CreateFMul</span><span class="p">(</span><span class="n">L</span><span class="p">,</span> <span class="n">R</span><span class="p">,</span> <span class="s">"multmp"</span><span class="p">);</span>
+ <span class="k">case</span> <span class="sc">'<'</span>:
+ <span class="n">L</span> <span class="o">=</span> <span class="n">Builder</span><span class="p">.</span><span class="n">CreateFCmpULT</span><span class="p">(</span><span class="n">L</span><span class="p">,</span> <span class="n">R</span><span class="p">,</span> <span class="s">"cmptmp"</span><span class="p">);</span>
+ <span class="c1">// Convert bool 0/1 to double 0.0 or 1.0</span>
+ <span class="k">return</span> <span class="n">Builder</span><span class="p">.</span><span class="n">CreateUIToFP</span><span class="p">(</span><span class="n">L</span><span class="p">,</span> <span class="n">Type</span><span class="o">::</span><span class="n">getDoubleTy</span><span class="p">(</span><span class="n">getGlobalContext</span><span class="p">()),</span>
+ <span class="s">"booltmp"</span><span class="p">);</span>
+ <span class="nl">default:</span>
+ <span class="k">break</span><span class="p">;</span>
+ <span class="p">}</span>
+
+ <span class="c1">// If it wasn't a builtin binary operator, it must be a user defined one. Emit</span>
+ <span class="c1">// a call to it.</span>
+ <span class="n">Function</span> <span class="o">*</span><span class="n">F</span> <span class="o">=</span> <span class="n">getFunction</span><span class="p">(</span><span class="n">std</span><span class="o">::</span><span class="n">string</span><span class="p">(</span><span class="s">"binary"</span><span class="p">)</span> <span class="o">+</span> <span class="n">Op</span><span class="p">);</span>
+ <span class="n">assert</span><span class="p">(</span><span class="n">F</span> <span class="o">&&</span> <span class="s">"binary operator not found!"</span><span class="p">);</span>
+
+ <span class="n">Value</span> <span class="o">*</span><span class="n">Ops</span><span class="p">[]</span> <span class="o">=</span> <span class="p">{</span><span class="n">L</span><span class="p">,</span> <span class="n">R</span><span class="p">};</span>
+ <span class="k">return</span> <span class="n">Builder</span><span class="p">.</span><span class="n">CreateCall</span><span class="p">(</span><span class="n">F</span><span class="p">,</span> <span class="n">Ops</span><span class="p">,</span> <span class="s">"binop"</span><span class="p">);</span>
+<span class="p">}</span>
+
+<span class="n">Value</span> <span class="o">*</span><span class="n">CallExprAST</span><span class="o">::</span><span class="n">codegen</span><span class="p">()</span> <span class="p">{</span>
+ <span class="c1">// Look up the name in the global module table.</span>
+ <span class="n">Function</span> <span class="o">*</span><span class="n">CalleeF</span> <span class="o">=</span> <span class="n">getFunction</span><span class="p">(</span><span class="n">Callee</span><span class="p">);</span>
+ <span class="k">if</span> <span class="p">(</span><span class="o">!</span><span class="n">CalleeF</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">ErrorV</span><span class="p">(</span><span class="s">"Unknown function referenced"</span><span class="p">);</span>
+
+ <span class="c1">// If argument mismatch error.</span>
+ <span class="k">if</span> <span class="p">(</span><span class="n">CalleeF</span><span class="o">-></span><span class="n">arg_size</span><span class="p">()</span> <span class="o">!=</span> <span class="n">Args</span><span class="p">.</span><span class="n">size</span><span class="p">())</span>
+ <span class="k">return</span> <span class="n">ErrorV</span><span class="p">(</span><span class="s">"Incorrect # arguments passed"</span><span class="p">);</span>
+
+ <span class="n">std</span><span class="o">::</span><span class="n">vector</span><span class="o"><</span><span class="n">Value</span> <span class="o">*></span> <span class="n">ArgsV</span><span class="p">;</span>
+ <span class="k">for</span> <span class="p">(</span><span class="kt">unsigned</span> <span class="n">i</span> <span class="o">=</span> <span class="mi">0</span><span class="p">,</span> <span class="n">e</span> <span class="o">=</span> <span class="n">Args</span><span class="p">.</span><span class="n">size</span><span class="p">();</span> <span class="n">i</span> <span class="o">!=</span> <span class="n">e</span><span class="p">;</span> <span class="o">++</span><span class="n">i</span><span class="p">)</span> <span class="p">{</span>
+ <span class="n">ArgsV</span><span class="p">.</span><span class="n">push_back</span><span class="p">(</span><span class="n">Args</span><span class="p">[</span><span class="n">i</span><span class="p">]</span><span class="o">-></span><span class="n">codegen</span><span class="p">());</span>
+ <span class="k">if</span> <span class="p">(</span><span class="o">!</span><span class="n">ArgsV</span><span class="p">.</span><span class="n">back</span><span class="p">())</span>
+ <span class="k">return</span> <span class="n">nullptr</span><span class="p">;</span>
+ <span class="p">}</span>
+
+ <span class="k">return</span> <span class="n">Builder</span><span class="p">.</span><span class="n">CreateCall</span><span class="p">(</span><span class="n">CalleeF</span><span class="p">,</span> <span class="n">ArgsV</span><span class="p">,</span> <span class="s">"calltmp"</span><span class="p">);</span>
+<span class="p">}</span>
+
+<span class="n">Value</span> <span class="o">*</span><span class="n">IfExprAST</span><span class="o">::</span><span class="n">codegen</span><span class="p">()</span> <span class="p">{</span>
+ <span class="n">Value</span> <span class="o">*</span><span class="n">CondV</span> <span class="o">=</span> <span class="n">Cond</span><span class="o">-></span><span class="n">codegen</span><span class="p">();</span>
+ <span class="k">if</span> <span class="p">(</span><span class="o">!</span><span class="n">CondV</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">nullptr</span><span class="p">;</span>
+
+ <span class="c1">// Convert condition to a bool by comparing equal to 0.0.</span>
+ <span class="n">CondV</span> <span class="o">=</span> <span class="n">Builder</span><span class="p">.</span><span class="n">CreateFCmpONE</span><span class="p">(</span>
+ <span class="n">CondV</span><span class="p">,</span> <span class="n">ConstantFP</span><span class="o">::</span><span class="n">get</span><span class="p">(</span><span class="n">getGlobalContext</span><span class="p">(),</span> <span class="n">APFloat</span><span class="p">(</span><span class="mf">0.0</span><span class="p">)),</span> <span class="s">"ifcond"</span><span class="p">);</span>
+
+ <span class="n">Function</span> <span class="o">*</span><span class="n">TheFunction</span> <span class="o">=</span> <span class="n">Builder</span><span class="p">.</span><span class="n">GetInsertBlock</span><span class="p">()</span><span class="o">-></span><span class="n">getParent</span><span class="p">();</span>
+
+ <span class="c1">// Create blocks for the then and else cases. Insert the 'then' block at the</span>
+ <span class="c1">// end of the function.</span>
+ <span class="n">BasicBlock</span> <span class="o">*</span><span class="n">ThenBB</span> <span class="o">=</span>
+ <span class="n">BasicBlock</span><span class="o">::</span><span class="n">Create</span><span class="p">(</span><span class="n">getGlobalContext</span><span class="p">(),</span> <span class="s">"then"</span><span class="p">,</span> <span class="n">TheFunction</span><span class="p">);</span>
+ <span class="n">BasicBlock</span> <span class="o">*</span><span class="n">ElseBB</span> <span class="o">=</span> <span class="n">BasicBlock</span><span class="o">::</span><span class="n">Create</span><span class="p">(</span><span class="n">getGlobalContext</span><span class="p">(),</span> <span class="s">"else"</span><span class="p">);</span>
+ <span class="n">BasicBlock</span> <span class="o">*</span><span class="n">MergeBB</span> <span class="o">=</span> <span class="n">BasicBlock</span><span class="o">::</span><span class="n">Create</span><span class="p">(</span><span class="n">getGlobalContext</span><span class="p">(),</span> <span class="s">"ifcont"</span><span class="p">);</span>
+
+ <span class="n">Builder</span><span class="p">.</span><span class="n">CreateCondBr</span><span class="p">(</span><span class="n">CondV</span><span class="p">,</span> <span class="n">ThenBB</span><span class="p">,</span> <span class="n">ElseBB</span><span class="p">);</span>
+
+ <span class="c1">// Emit then value.</span>
+ <span class="n">Builder</span><span class="p">.</span><span class="n">SetInsertPoint</span><span class="p">(</span><span class="n">ThenBB</span><span class="p">);</span>
+
+ <span class="n">Value</span> <span class="o">*</span><span class="n">ThenV</span> <span class="o">=</span> <span class="n">Then</span><span class="o">-></span><span class="n">codegen</span><span class="p">();</span>
+ <span class="k">if</span> <span class="p">(</span><span class="o">!</span><span class="n">ThenV</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">nullptr</span><span class="p">;</span>
+
+ <span class="n">Builder</span><span class="p">.</span><span class="n">CreateBr</span><span class="p">(</span><span class="n">MergeBB</span><span class="p">);</span>
+ <span class="c1">// Codegen of 'Then' can change the current block, update ThenBB for the PHI.</span>
+ <span class="n">ThenBB</span> <span class="o">=</span> <span class="n">Builder</span><span class="p">.</span><span class="n">GetInsertBlock</span><span class="p">();</span>
+
+ <span class="c1">// Emit else block.</span>
+ <span class="n">TheFunction</span><span class="o">-></span><span class="n">getBasicBlockList</span><span class="p">().</span><span class="n">push_back</span><span class="p">(</span><span class="n">ElseBB</span><span class="p">);</span>
+ <span class="n">Builder</span><span class="p">.</span><span class="n">SetInsertPoint</span><span class="p">(</span><span class="n">ElseBB</span><span class="p">);</span>
+
+ <span class="n">Value</span> <span class="o">*</span><span class="n">ElseV</span> <span class="o">=</span> <span class="n">Else</span><span class="o">-></span><span class="n">codegen</span><span class="p">();</span>
+ <span class="k">if</span> <span class="p">(</span><span class="o">!</span><span class="n">ElseV</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">nullptr</span><span class="p">;</span>
+
+ <span class="n">Builder</span><span class="p">.</span><span class="n">CreateBr</span><span class="p">(</span><span class="n">MergeBB</span><span class="p">);</span>
+ <span class="c1">// Codegen of 'Else' can change the current block, update ElseBB for the PHI.</span>
+ <span class="n">ElseBB</span> <span class="o">=</span> <span class="n">Builder</span><span class="p">.</span><span class="n">GetInsertBlock</span><span class="p">();</span>
+
+ <span class="c1">// Emit merge block.</span>
+ <span class="n">TheFunction</span><span class="o">-></span><span class="n">getBasicBlockList</span><span class="p">().</span><span class="n">push_back</span><span class="p">(</span><span class="n">MergeBB</span><span class="p">);</span>
+ <span class="n">Builder</span><span class="p">.</span><span class="n">SetInsertPoint</span><span class="p">(</span><span class="n">MergeBB</span><span class="p">);</span>
+ <span class="n">PHINode</span> <span class="o">*</span><span class="n">PN</span> <span class="o">=</span>
+ <span class="n">Builder</span><span class="p">.</span><span class="n">CreatePHI</span><span class="p">(</span><span class="n">Type</span><span class="o">::</span><span class="n">getDoubleTy</span><span class="p">(</span><span class="n">getGlobalContext</span><span class="p">()),</span> <span class="mi">2</span><span class="p">,</span> <span class="s">"iftmp"</span><span class="p">);</span>
+
+ <span class="n">PN</span><span class="o">-></span><span class="n">addIncoming</span><span class="p">(</span><span class="n">ThenV</span><span class="p">,</span> <span class="n">ThenBB</span><span class="p">);</span>
+ <span class="n">PN</span><span class="o">-></span><span class="n">addIncoming</span><span class="p">(</span><span class="n">ElseV</span><span class="p">,</span> <span class="n">ElseBB</span><span class="p">);</span>
+ <span class="k">return</span> <span class="n">PN</span><span class="p">;</span>
+<span class="p">}</span>
+
+<span class="c1">// Output for-loop as:</span>
+<span class="c1">// var = alloca double</span>
+<span class="c1">// ...</span>
+<span class="c1">// start = startexpr</span>
+<span class="c1">// store start -> var</span>
+<span class="c1">// goto loop</span>
+<span class="c1">// loop:</span>
+<span class="c1">// ...</span>
+<span class="c1">// bodyexpr</span>
+<span class="c1">// ...</span>
+<span class="c1">// loopend:</span>
+<span class="c1">// step = stepexpr</span>
+<span class="c1">// endcond = endexpr</span>
+<span class="c1">//</span>
+<span class="c1">// curvar = load var</span>
+<span class="c1">// nextvar = curvar + step</span>
+<span class="c1">// store nextvar -> var</span>
+<span class="c1">// br endcond, loop, endloop</span>
+<span class="c1">// outloop:</span>
+<span class="n">Value</span> <span class="o">*</span><span class="n">ForExprAST</span><span class="o">::</span><span class="n">codegen</span><span class="p">()</span> <span class="p">{</span>
+ <span class="n">Function</span> <span class="o">*</span><span class="n">TheFunction</span> <span class="o">=</span> <span class="n">Builder</span><span class="p">.</span><span class="n">GetInsertBlock</span><span class="p">()</span><span class="o">-></span><span class="n">getParent</span><span class="p">();</span>
+
+ <span class="c1">// Create an alloca for the variable in the entry block.</span>
+ <span class="n">AllocaInst</span> <span class="o">*</span><span class="n">Alloca</span> <span class="o">=</span> <span class="n">CreateEntryBlockAlloca</span><span class="p">(</span><span class="n">TheFunction</span><span class="p">,</span> <span class="n">VarName</span><span class="p">);</span>
+
+ <span class="c1">// Emit the start code first, without 'variable' in scope.</span>
+ <span class="n">Value</span> <span class="o">*</span><span class="n">StartVal</span> <span class="o">=</span> <span class="n">Start</span><span class="o">-></span><span class="n">codegen</span><span class="p">();</span>
+ <span class="k">if</span> <span class="p">(</span><span class="o">!</span><span class="n">StartVal</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">nullptr</span><span class="p">;</span>
+
+ <span class="c1">// Store the value into the alloca.</span>
+ <span class="n">Builder</span><span class="p">.</span><span class="n">CreateStore</span><span class="p">(</span><span class="n">StartVal</span><span class="p">,</span> <span class="n">Alloca</span><span class="p">);</span>
+
+ <span class="c1">// Make the new basic block for the loop header, inserting after current</span>
+ <span class="c1">// block.</span>
+ <span class="n">BasicBlock</span> <span class="o">*</span><span class="n">LoopBB</span> <span class="o">=</span>
+ <span class="n">BasicBlock</span><span class="o">::</span><span class="n">Create</span><span class="p">(</span><span class="n">getGlobalContext</span><span class="p">(),</span> <span class="s">"loop"</span><span class="p">,</span> <span class="n">TheFunction</span><span class="p">);</span>
+
+ <span class="c1">// Insert an explicit fall through from the current block to the LoopBB.</span>
+ <span class="n">Builder</span><span class="p">.</span><span class="n">CreateBr</span><span class="p">(</span><span class="n">LoopBB</span><span class="p">);</span>
+
+ <span class="c1">// Start insertion in LoopBB.</span>
+ <span class="n">Builder</span><span class="p">.</span><span class="n">SetInsertPoint</span><span class="p">(</span><span class="n">LoopBB</span><span class="p">);</span>
+
+ <span class="c1">// Within the loop, the variable is defined equal to the PHI node. If it</span>
+ <span class="c1">// shadows an existing variable, we have to restore it, so save it now.</span>
+ <span class="n">AllocaInst</span> <span class="o">*</span><span class="n">OldVal</span> <span class="o">=</span> <span class="n">NamedValues</span><span class="p">[</span><span class="n">VarName</span><span class="p">];</span>
+ <span class="n">NamedValues</span><span class="p">[</span><span class="n">VarName</span><span class="p">]</span> <span class="o">=</span> <span class="n">Alloca</span><span class="p">;</span>
+
+ <span class="c1">// Emit the body of the loop. This, like any other expr, can change the</span>
+ <span class="c1">// current BB. Note that we ignore the value computed by the body, but don't</span>
+ <span class="c1">// allow an error.</span>
+ <span class="k">if</span> <span class="p">(</span><span class="o">!</span><span class="n">Body</span><span class="o">-></span><span class="n">codegen</span><span class="p">())</span>
+ <span class="k">return</span> <span class="n">nullptr</span><span class="p">;</span>
+
+ <span class="c1">// Emit the step value.</span>
+ <span class="n">Value</span> <span class="o">*</span><span class="n">StepVal</span> <span class="o">=</span> <span class="n">nullptr</span><span class="p">;</span>
+ <span class="k">if</span> <span class="p">(</span><span class="n">Step</span><span class="p">)</span> <span class="p">{</span>
+ <span class="n">StepVal</span> <span class="o">=</span> <span class="n">Step</span><span class="o">-></span><span class="n">codegen</span><span class="p">();</span>
+ <span class="k">if</span> <span class="p">(</span><span class="o">!</span><span class="n">StepVal</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">nullptr</span><span class="p">;</span>
+ <span class="p">}</span> <span class="k">else</span> <span class="p">{</span>
+ <span class="c1">// If not specified, use 1.0.</span>
+ <span class="n">StepVal</span> <span class="o">=</span> <span class="n">ConstantFP</span><span class="o">::</span><span class="n">get</span><span class="p">(</span><span class="n">getGlobalContext</span><span class="p">(),</span> <span class="n">APFloat</span><span class="p">(</span><span class="mf">1.0</span><span class="p">));</span>
+ <span class="p">}</span>
+
+ <span class="c1">// Compute the end condition.</span>
+ <span class="n">Value</span> <span class="o">*</span><span class="n">EndCond</span> <span class="o">=</span> <span class="n">End</span><span class="o">-></span><span class="n">codegen</span><span class="p">();</span>
+ <span class="k">if</span> <span class="p">(</span><span class="o">!</span><span class="n">EndCond</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">nullptr</span><span class="p">;</span>
+
+ <span class="c1">// Reload, increment, and restore the alloca. This handles the case where</span>
+ <span class="c1">// the body of the loop mutates the variable.</span>
+ <span class="n">Value</span> <span class="o">*</span><span class="n">CurVar</span> <span class="o">=</span> <span class="n">Builder</span><span class="p">.</span><span class="n">CreateLoad</span><span class="p">(</span><span class="n">Alloca</span><span class="p">,</span> <span class="n">VarName</span><span class="p">.</span><span class="n">c_str</span><span class="p">());</span>
+ <span class="n">Value</span> <span class="o">*</span><span class="n">NextVar</span> <span class="o">=</span> <span class="n">Builder</span><span class="p">.</span><span class="n">CreateFAdd</span><span class="p">(</span><span class="n">CurVar</span><span class="p">,</span> <span class="n">StepVal</span><span class="p">,</span> <span class="s">"nextvar"</span><span class="p">);</span>
+ <span class="n">Builder</span><span class="p">.</span><span class="n">CreateStore</span><span class="p">(</span><span class="n">NextVar</span><span class="p">,</span> <span class="n">Alloca</span><span class="p">);</span>
+
+ <span class="c1">// Convert condition to a bool by comparing equal to 0.0.</span>
+ <span class="n">EndCond</span> <span class="o">=</span> <span class="n">Builder</span><span class="p">.</span><span class="n">CreateFCmpONE</span><span class="p">(</span>
+ <span class="n">EndCond</span><span class="p">,</span> <span class="n">ConstantFP</span><span class="o">::</span><span class="n">get</span><span class="p">(</span><span class="n">getGlobalContext</span><span class="p">(),</span> <span class="n">APFloat</span><span class="p">(</span><span class="mf">0.0</span><span class="p">)),</span> <span class="s">"loopcond"</span><span class="p">);</span>
+
+ <span class="c1">// Create the "after loop" block and insert it.</span>
+ <span class="n">BasicBlock</span> <span class="o">*</span><span class="n">AfterBB</span> <span class="o">=</span>
+ <span class="n">BasicBlock</span><span class="o">::</span><span class="n">Create</span><span class="p">(</span><span class="n">getGlobalContext</span><span class="p">(),</span> <span class="s">"afterloop"</span><span class="p">,</span> <span class="n">TheFunction</span><span class="p">);</span>
+
+ <span class="c1">// Insert the conditional branch into the end of LoopEndBB.</span>
+ <span class="n">Builder</span><span class="p">.</span><span class="n">CreateCondBr</span><span class="p">(</span><span class="n">EndCond</span><span class="p">,</span> <span class="n">LoopBB</span><span class="p">,</span> <span class="n">AfterBB</span><span class="p">);</span>
+
+ <span class="c1">// Any new code will be inserted in AfterBB.</span>
+ <span class="n">Builder</span><span class="p">.</span><span class="n">SetInsertPoint</span><span class="p">(</span><span class="n">AfterBB</span><span class="p">);</span>
+
+ <span class="c1">// Restore the unshadowed variable.</span>
+ <span class="k">if</span> <span class="p">(</span><span class="n">OldVal</span><span class="p">)</span>
+ <span class="n">NamedValues</span><span class="p">[</span><span class="n">VarName</span><span class="p">]</span> <span class="o">=</span> <span class="n">OldVal</span><span class="p">;</span>
+ <span class="k">else</span>
+ <span class="n">NamedValues</span><span class="p">.</span><span class="n">erase</span><span class="p">(</span><span class="n">VarName</span><span class="p">);</span>
+
+ <span class="c1">// for expr always returns 0.0.</span>
+ <span class="k">return</span> <span class="n">Constant</span><span class="o">::</span><span class="n">getNullValue</span><span class="p">(</span><span class="n">Type</span><span class="o">::</span><span class="n">getDoubleTy</span><span class="p">(</span><span class="n">getGlobalContext</span><span class="p">()));</span>
+<span class="p">}</span>
+
+<span class="n">Value</span> <span class="o">*</span><span class="n">VarExprAST</span><span class="o">::</span><span class="n">codegen</span><span class="p">()</span> <span class="p">{</span>
+ <span class="n">std</span><span class="o">::</span><span class="n">vector</span><span class="o"><</span><span class="n">AllocaInst</span> <span class="o">*></span> <span class="n">OldBindings</span><span class="p">;</span>
+
+ <span class="n">Function</span> <span class="o">*</span><span class="n">TheFunction</span> <span class="o">=</span> <span class="n">Builder</span><span class="p">.</span><span class="n">GetInsertBlock</span><span class="p">()</span><span class="o">-></span><span class="n">getParent</span><span class="p">();</span>
+
+ <span class="c1">// Register all variables and emit their initializer.</span>
+ <span class="k">for</span> <span class="p">(</span><span class="kt">unsigned</span> <span class="n">i</span> <span class="o">=</span> <span class="mi">0</span><span class="p">,</span> <span class="n">e</span> <span class="o">=</span> <span class="n">VarNames</span><span class="p">.</span><span class="n">size</span><span class="p">();</span> <span class="n">i</span> <span class="o">!=</span> <span class="n">e</span><span class="p">;</span> <span class="o">++</span><span class="n">i</span><span class="p">)</span> <span class="p">{</span>
+ <span class="k">const</span> <span class="n">std</span><span class="o">::</span><span class="n">string</span> <span class="o">&</span><span class="n">VarName</span> <span class="o">=</span> <span class="n">VarNames</span><span class="p">[</span><span class="n">i</span><span class="p">].</span><span class="n">first</span><span class="p">;</span>
+ <span class="n">ExprAST</span> <span class="o">*</span><span class="n">Init</span> <span class="o">=</span> <span class="n">VarNames</span><span class="p">[</span><span class="n">i</span><span class="p">].</span><span class="n">second</span><span class="p">.</span><span class="n">get</span><span class="p">();</span>
+
+ <span class="c1">// Emit the initializer before adding the variable to scope, this prevents</span>
+ <span class="c1">// the initializer from referencing the variable itself, and permits stuff</span>
+ <span class="c1">// like this:</span>
+ <span class="c1">// var a = 1 in</span>
+ <span class="c1">// var a = a in ... # refers to outer 'a'.</span>
+ <span class="n">Value</span> <span class="o">*</span><span class="n">InitVal</span><span class="p">;</span>
+ <span class="k">if</span> <span class="p">(</span><span class="n">Init</span><span class="p">)</span> <span class="p">{</span>
+ <span class="n">InitVal</span> <span class="o">=</span> <span class="n">Init</span><span class="o">-></span><span class="n">codegen</span><span class="p">();</span>
+ <span class="k">if</span> <span class="p">(</span><span class="o">!</span><span class="n">InitVal</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">nullptr</span><span class="p">;</span>
+ <span class="p">}</span> <span class="k">else</span> <span class="p">{</span> <span class="c1">// If not specified, use 0.0.</span>
+ <span class="n">InitVal</span> <span class="o">=</span> <span class="n">ConstantFP</span><span class="o">::</span><span class="n">get</span><span class="p">(</span><span class="n">getGlobalContext</span><span class="p">(),</span> <span class="n">APFloat</span><span class="p">(</span><span class="mf">0.0</span><span class="p">));</span>
+ <span class="p">}</span>
+
+ <span class="n">AllocaInst</span> <span class="o">*</span><span class="n">Alloca</span> <span class="o">=</span> <span class="n">CreateEntryBlockAlloca</span><span class="p">(</span><span class="n">TheFunction</span><span class="p">,</span> <span class="n">VarName</span><span class="p">);</span>
+ <span class="n">Builder</span><span class="p">.</span><span class="n">CreateStore</span><span class="p">(</span><span class="n">InitVal</span><span class="p">,</span> <span class="n">Alloca</span><span class="p">);</span>
+
+ <span class="c1">// Remember the old variable binding so that we can restore the binding when</span>
+ <span class="c1">// we unrecurse.</span>
+ <span class="n">OldBindings</span><span class="p">.</span><span class="n">push_back</span><span class="p">(</span><span class="n">NamedValues</span><span class="p">[</span><span class="n">VarName</span><span class="p">]);</span>
+
+ <span class="c1">// Remember this binding.</span>
+ <span class="n">NamedValues</span><span class="p">[</span><span class="n">VarName</span><span class="p">]</span> <span class="o">=</span> <span class="n">Alloca</span><span class="p">;</span>
+ <span class="p">}</span>
+
+ <span class="c1">// Codegen the body, now that all vars are in scope.</span>
+ <span class="n">Value</span> <span class="o">*</span><span class="n">BodyVal</span> <span class="o">=</span> <span class="n">Body</span><span class="o">-></span><span class="n">codegen</span><span class="p">();</span>
+ <span class="k">if</span> <span class="p">(</span><span class="o">!</span><span class="n">BodyVal</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">nullptr</span><span class="p">;</span>
+
+ <span class="c1">// Pop all our variables from scope.</span>
+ <span class="k">for</span> <span class="p">(</span><span class="kt">unsigned</span> <span class="n">i</span> <span class="o">=</span> <span class="mi">0</span><span class="p">,</span> <span class="n">e</span> <span class="o">=</span> <span class="n">VarNames</span><span class="p">.</span><span class="n">size</span><span class="p">();</span> <span class="n">i</span> <span class="o">!=</span> <span class="n">e</span><span class="p">;</span> <span class="o">++</span><span class="n">i</span><span class="p">)</span>
+ <span class="n">NamedValues</span><span class="p">[</span><span class="n">VarNames</span><span class="p">[</span><span class="n">i</span><span class="p">].</span><span class="n">first</span><span class="p">]</span> <span class="o">=</span> <span class="n">OldBindings</span><span class="p">[</span><span class="n">i</span><span class="p">];</span>
+
+ <span class="c1">// Return the body computation.</span>
+ <span class="k">return</span> <span class="n">BodyVal</span><span class="p">;</span>
+<span class="p">}</span>
+
+<span class="n">Function</span> <span class="o">*</span><span class="n">PrototypeAST</span><span class="o">::</span><span class="n">codegen</span><span class="p">()</span> <span class="p">{</span>
+ <span class="c1">// Make the function type: double(double,double) etc.</span>
+ <span class="n">std</span><span class="o">::</span><span class="n">vector</span><span class="o"><</span><span class="n">Type</span> <span class="o">*></span> <span class="n">Doubles</span><span class="p">(</span><span class="n">Args</span><span class="p">.</span><span class="n">size</span><span class="p">(),</span>
+ <span class="n">Type</span><span class="o">::</span><span class="n">getDoubleTy</span><span class="p">(</span><span class="n">getGlobalContext</span><span class="p">()));</span>
+ <span class="n">FunctionType</span> <span class="o">*</span><span class="n">FT</span> <span class="o">=</span>
+ <span class="n">FunctionType</span><span class="o">::</span><span class="n">get</span><span class="p">(</span><span class="n">Type</span><span class="o">::</span><span class="n">getDoubleTy</span><span class="p">(</span><span class="n">getGlobalContext</span><span class="p">()),</span> <span class="n">Doubles</span><span class="p">,</span> <span class="nb">false</span><span class="p">);</span>
+
+ <span class="n">Function</span> <span class="o">*</span><span class="n">F</span> <span class="o">=</span>
+ <span class="n">Function</span><span class="o">::</span><span class="n">Create</span><span class="p">(</span><span class="n">FT</span><span class="p">,</span> <span class="n">Function</span><span class="o">::</span><span class="n">ExternalLinkage</span><span class="p">,</span> <span class="n">Name</span><span class="p">,</span> <span class="n">TheModule</span><span class="p">.</span><span class="n">get</span><span class="p">());</span>
+
+ <span class="c1">// Set names for all arguments.</span>
+ <span class="kt">unsigned</span> <span class="n">Idx</span> <span class="o">=</span> <span class="mi">0</span><span class="p">;</span>
+ <span class="k">for</span> <span class="p">(</span><span class="k">auto</span> <span class="o">&</span><span class="n">Arg</span> <span class="o">:</span> <span class="n">F</span><span class="o">-></span><span class="n">args</span><span class="p">())</span>
+ <span class="n">Arg</span><span class="p">.</span><span class="n">setName</span><span class="p">(</span><span class="n">Args</span><span class="p">[</span><span class="n">Idx</span><span class="o">++</span><span class="p">]);</span>
+
+ <span class="k">return</span> <span class="n">F</span><span class="p">;</span>
+<span class="p">}</span>
+
+<span class="n">Function</span> <span class="o">*</span><span class="n">FunctionAST</span><span class="o">::</span><span class="n">codegen</span><span class="p">()</span> <span class="p">{</span>
+ <span class="c1">// Transfer ownership of the prototype to the FunctionProtos map, but keep a</span>
+ <span class="c1">// reference to it for use below.</span>
+ <span class="k">auto</span> <span class="o">&</span><span class="n">P</span> <span class="o">=</span> <span class="o">*</span><span class="n">Proto</span><span class="p">;</span>
+ <span class="n">FunctionProtos</span><span class="p">[</span><span class="n">Proto</span><span class="o">-></span><span class="n">getName</span><span class="p">()]</span> <span class="o">=</span> <span class="n">std</span><span class="o">::</span><span class="n">move</span><span class="p">(</span><span class="n">Proto</span><span class="p">);</span>
+ <span class="n">Function</span> <span class="o">*</span><span class="n">TheFunction</span> <span class="o">=</span> <span class="n">getFunction</span><span class="p">(</span><span class="n">P</span><span class="p">.</span><span class="n">getName</span><span class="p">());</span>
+ <span class="k">if</span> <span class="p">(</span><span class="o">!</span><span class="n">TheFunction</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">nullptr</span><span class="p">;</span>
+
+ <span class="c1">// If this is an operator, install it.</span>
+ <span class="k">if</span> <span class="p">(</span><span class="n">P</span><span class="p">.</span><span class="n">isBinaryOp</span><span class="p">())</span>
+ <span class="n">BinopPrecedence</span><span class="p">[</span><span class="n">P</span><span class="p">.</span><span class="n">getOperatorName</span><span class="p">()]</span> <span class="o">=</span> <span class="n">P</span><span class="p">.</span><span class="n">getBinaryPrecedence</span><span class="p">();</span>
+
+ <span class="c1">// Create a new basic block to start insertion into.</span>
+ <span class="n">BasicBlock</span> <span class="o">*</span><span class="n">BB</span> <span class="o">=</span> <span class="n">BasicBlock</span><span class="o">::</span><span class="n">Create</span><span class="p">(</span><span class="n">getGlobalContext</span><span class="p">(),</span> <span class="s">"entry"</span><span class="p">,</span> <span class="n">TheFunction</span><span class="p">);</span>
+ <span class="n">Builder</span><span class="p">.</span><span class="n">SetInsertPoint</span><span class="p">(</span><span class="n">BB</span><span class="p">);</span>
+
+ <span class="c1">// Record the function arguments in the NamedValues map.</span>
+ <span class="n">NamedValues</span><span class="p">.</span><span class="n">clear</span><span class="p">();</span>
+ <span class="k">for</span> <span class="p">(</span><span class="k">auto</span> <span class="o">&</span><span class="n">Arg</span> <span class="o">:</span> <span class="n">TheFunction</span><span class="o">-></span><span class="n">args</span><span class="p">())</span> <span class="p">{</span>
+ <span class="c1">// Create an alloca for this variable.</span>
+ <span class="n">AllocaInst</span> <span class="o">*</span><span class="n">Alloca</span> <span class="o">=</span> <span class="n">CreateEntryBlockAlloca</span><span class="p">(</span><span class="n">TheFunction</span><span class="p">,</span> <span class="n">Arg</span><span class="p">.</span><span class="n">getName</span><span class="p">());</span>
+
+ <span class="c1">// Store the initial value into the alloca.</span>
+ <span class="n">Builder</span><span class="p">.</span><span class="n">CreateStore</span><span class="p">(</span><span class="o">&</span><span class="n">Arg</span><span class="p">,</span> <span class="n">Alloca</span><span class="p">);</span>
+
+ <span class="c1">// Add arguments to variable symbol table.</span>
+ <span class="n">NamedValues</span><span class="p">[</span><span class="n">Arg</span><span class="p">.</span><span class="n">getName</span><span class="p">()]</span> <span class="o">=</span> <span class="n">Alloca</span><span class="p">;</span>
+ <span class="p">}</span>
+
+ <span class="k">if</span> <span class="p">(</span><span class="n">Value</span> <span class="o">*</span><span class="n">RetVal</span> <span class="o">=</span> <span class="n">Body</span><span class="o">-></span><span class="n">codegen</span><span class="p">())</span> <span class="p">{</span>
+ <span class="c1">// Finish off the function.</span>
+ <span class="n">Builder</span><span class="p">.</span><span class="n">CreateRet</span><span class="p">(</span><span class="n">RetVal</span><span class="p">);</span>
+
+ <span class="c1">// Validate the generated code, checking for consistency.</span>
+ <span class="n">verifyFunction</span><span class="p">(</span><span class="o">*</span><span class="n">TheFunction</span><span class="p">);</span>
+
+ <span class="c1">// Run the optimizer on the function.</span>
+ <span class="n">TheFPM</span><span class="o">-></span><span class="n">run</span><span class="p">(</span><span class="o">*</span><span class="n">TheFunction</span><span class="p">);</span>
+
+ <span class="k">return</span> <span class="n">TheFunction</span><span class="p">;</span>
+ <span class="p">}</span>
+
+ <span class="c1">// Error reading body, remove function.</span>
+ <span class="n">TheFunction</span><span class="o">-></span><span class="n">eraseFromParent</span><span class="p">();</span>
+
+ <span class="k">if</span> <span class="p">(</span><span class="n">P</span><span class="p">.</span><span class="n">isBinaryOp</span><span class="p">())</span>
+ <span class="n">BinopPrecedence</span><span class="p">.</span><span class="n">erase</span><span class="p">(</span><span class="n">Proto</span><span class="o">-></span><span class="n">getOperatorName</span><span class="p">());</span>
+ <span class="k">return</span> <span class="n">nullptr</span><span class="p">;</span>
+<span class="p">}</span>
+
+<span class="c1">//===----------------------------------------------------------------------===//</span>
+<span class="c1">// Top-Level parsing and JIT Driver</span>
+<span class="c1">//===----------------------------------------------------------------------===//</span>
+
+<span class="k">static</span> <span class="kt">void</span> <span class="n">InitializeModuleAndPassManager</span><span class="p">()</span> <span class="p">{</span>
+ <span class="c1">// Open a new module.</span>
+ <span class="n">TheModule</span> <span class="o">=</span> <span class="n">llvm</span><span class="o">::</span><span class="n">make_unique</span><span class="o"><</span><span class="n">Module</span><span class="o">></span><span class="p">(</span><span class="s">"my cool jit"</span><span class="p">,</span> <span class="n">getGlobalContext</span><span class="p">());</span>
+ <span class="n">TheModule</span><span class="o">-></span><span class="n">setDataLayout</span><span class="p">(</span><span class="n">TheJIT</span><span class="o">-></span><span class="n">getTargetMachine</span><span class="p">().</span><span class="n">createDataLayout</span><span class="p">());</span>
+
+ <span class="c1">// Create a new pass manager attached to it.</span>
+ <span class="n">TheFPM</span> <span class="o">=</span> <span class="n">llvm</span><span class="o">::</span><span class="n">make_unique</span><span class="o"><</span><span class="n">legacy</span><span class="o">::</span><span class="n">FunctionPassManager</span><span class="o">></span><span class="p">(</span><span class="n">TheModule</span><span class="p">.</span><span class="n">get</span><span class="p">());</span>
+
+ <span class="c1">// Do simple "peephole" optimizations and bit-twiddling optzns.</span>
+ <span class="n">TheFPM</span><span class="o">-></span><span class="n">add</span><span class="p">(</span><span class="n">createInstructionCombiningPass</span><span class="p">());</span>
+ <span class="c1">// Reassociate expressions.</span>
+ <span class="n">TheFPM</span><span class="o">-></span><span class="n">add</span><span class="p">(</span><span class="n">createReassociatePass</span><span class="p">());</span>
+ <span class="c1">// Eliminate Common SubExpressions.</span>
+ <span class="n">TheFPM</span><span class="o">-></span><span class="n">add</span><span class="p">(</span><span class="n">createGVNPass</span><span class="p">());</span>
+ <span class="c1">// Simplify the control flow graph (deleting unreachable blocks, etc).</span>
+ <span class="n">TheFPM</span><span class="o">-></span><span class="n">add</span><span class="p">(</span><span class="n">createCFGSimplificationPass</span><span class="p">());</span>
+
+ <span class="n">TheFPM</span><span class="o">-></span><span class="n">doInitialization</span><span class="p">();</span>
+<span class="p">}</span>
+
+<span class="k">static</span> <span class="kt">void</span> <span class="n">HandleDefinition</span><span class="p">()</span> <span class="p">{</span>
+ <span class="k">if</span> <span class="p">(</span><span class="k">auto</span> <span class="n">FnAST</span> <span class="o">=</span> <span class="n">ParseDefinition</span><span class="p">())</span> <span class="p">{</span>
+ <span class="k">if</span> <span class="p">(</span><span class="k">auto</span> <span class="o">*</span><span class="n">FnIR</span> <span class="o">=</span> <span class="n">FnAST</span><span class="o">-></span><span class="n">codegen</span><span class="p">())</span> <span class="p">{</span>
+ <span class="n">fprintf</span><span class="p">(</span><span class="n">stderr</span><span class="p">,</span> <span class="s">"Read function definition:"</span><span class="p">);</span>
+ <span class="n">FnIR</span><span class="o">-></span><span class="n">dump</span><span class="p">();</span>
+ <span class="n">TheJIT</span><span class="o">-></span><span class="n">addModule</span><span class="p">(</span><span class="n">std</span><span class="o">::</span><span class="n">move</span><span class="p">(</span><span class="n">TheModule</span><span class="p">));</span>
+ <span class="n">InitializeModuleAndPassManager</span><span class="p">();</span>
+ <span class="p">}</span>
+ <span class="p">}</span> <span class="k">else</span> <span class="p">{</span>
+ <span class="c1">// Skip token for error recovery.</span>
+ <span class="n">getNextToken</span><span class="p">();</span>
+ <span class="p">}</span>
+<span class="p">}</span>
+
+<span class="k">static</span> <span class="kt">void</span> <span class="n">HandleExtern</span><span class="p">()</span> <span class="p">{</span>
+ <span class="k">if</span> <span class="p">(</span><span class="k">auto</span> <span class="n">ProtoAST</span> <span class="o">=</span> <span class="n">ParseExtern</span><span class="p">())</span> <span class="p">{</span>
+ <span class="k">if</span> <span class="p">(</span><span class="k">auto</span> <span class="o">*</span><span class="n">FnIR</span> <span class="o">=</span> <span class="n">ProtoAST</span><span class="o">-></span><span class="n">codegen</span><span class="p">())</span> <span class="p">{</span>
+ <span class="n">fprintf</span><span class="p">(</span><span class="n">stderr</span><span class="p">,</span> <span class="s">"Read extern: "</span><span class="p">);</span>
+ <span class="n">FnIR</span><span class="o">-></span><span class="n">dump</span><span class="p">();</span>
+ <span class="n">FunctionProtos</span><span class="p">[</span><span class="n">ProtoAST</span><span class="o">-></span><span class="n">getName</span><span class="p">()]</span> <span class="o">=</span> <span class="n">std</span><span class="o">::</span><span class="n">move</span><span class="p">(</span><span class="n">ProtoAST</span><span class="p">);</span>
+ <span class="p">}</span>
+ <span class="p">}</span> <span class="k">else</span> <span class="p">{</span>
+ <span class="c1">// Skip token for error recovery.</span>
+ <span class="n">getNextToken</span><span class="p">();</span>
+ <span class="p">}</span>
+<span class="p">}</span>
+
+<span class="k">static</span> <span class="kt">void</span> <span class="n">HandleTopLevelExpression</span><span class="p">()</span> <span class="p">{</span>
+ <span class="c1">// Evaluate a top-level expression into an anonymous function.</span>
+ <span class="k">if</span> <span class="p">(</span><span class="k">auto</span> <span class="n">FnAST</span> <span class="o">=</span> <span class="n">ParseTopLevelExpr</span><span class="p">())</span> <span class="p">{</span>
+ <span class="k">if</span> <span class="p">(</span><span class="n">FnAST</span><span class="o">-></span><span class="n">codegen</span><span class="p">())</span> <span class="p">{</span>
+
+ <span class="c1">// JIT the module containing the anonymous expression, keeping a handle so</span>
+ <span class="c1">// we can free it later.</span>
+ <span class="k">auto</span> <span class="n">H</span> <span class="o">=</span> <span class="n">TheJIT</span><span class="o">-></span><span class="n">addModule</span><span class="p">(</span><span class="n">std</span><span class="o">::</span><span class="n">move</span><span class="p">(</span><span class="n">TheModule</span><span class="p">));</span>
+ <span class="n">InitializeModuleAndPassManager</span><span class="p">();</span>
+
+ <span class="c1">// Search the JIT for the __anon_expr symbol.</span>
+ <span class="k">auto</span> <span class="n">ExprSymbol</span> <span class="o">=</span> <span class="n">TheJIT</span><span class="o">-></span><span class="n">findSymbol</span><span class="p">(</span><span class="s">"__anon_expr"</span><span class="p">);</span>
+ <span class="n">assert</span><span class="p">(</span><span class="n">ExprSymbol</span> <span class="o">&&</span> <span class="s">"Function not found"</span><span class="p">);</span>
+
+ <span class="c1">// Get the symbol's address and cast it to the right type (takes no</span>
+ <span class="c1">// arguments, returns a double) so we can call it as a native function.</span>
+ <span class="kt">double</span> <span class="p">(</span><span class="o">*</span><span class="n">FP</span><span class="p">)()</span> <span class="o">=</span> <span class="p">(</span><span class="kt">double</span> <span class="p">(</span><span class="o">*</span><span class="p">)())(</span><span class="kt">intptr_t</span><span class="p">)</span><span class="n">ExprSymbol</span><span class="p">.</span><span class="n">getAddress</span><span class="p">();</span>
+ <span class="n">fprintf</span><span class="p">(</span><span class="n">stderr</span><span class="p">,</span> <span class="s">"Evaluated to %f</span><span class="se">\n</span><span class="s">"</span><span class="p">,</span> <span class="n">FP</span><span class="p">());</span>
+
+ <span class="c1">// Delete the anonymous expression module from the JIT.</span>
+ <span class="n">TheJIT</span><span class="o">-></span><span class="n">removeModule</span><span class="p">(</span><span class="n">H</span><span class="p">);</span>
+ <span class="p">}</span>
+ <span class="p">}</span> <span class="k">else</span> <span class="p">{</span>
+ <span class="c1">// Skip token for error recovery.</span>
+ <span class="n">getNextToken</span><span class="p">();</span>
+ <span class="p">}</span>
+<span class="p">}</span>
+
+<span class="c1">/// top ::= definition | external | expression | ';'</span>
+<span class="k">static</span> <span class="kt">void</span> <span class="n">MainLoop</span><span class="p">()</span> <span class="p">{</span>
+ <span class="k">while</span> <span class="p">(</span><span class="mi">1</span><span class="p">)</span> <span class="p">{</span>
+ <span class="n">fprintf</span><span class="p">(</span><span class="n">stderr</span><span class="p">,</span> <span class="s">"ready> "</span><span class="p">);</span>
+ <span class="k">switch</span> <span class="p">(</span><span class="n">CurTok</span><span class="p">)</span> <span class="p">{</span>
+ <span class="k">case</span> <span class="n">tok_eof</span>:
+ <span class="k">return</span><span class="p">;</span>
+ <span class="k">case</span> <span class="sc">';'</span>: <span class="c1">// ignore top-level semicolons.</span>
+ <span class="n">getNextToken</span><span class="p">();</span>
+ <span class="k">break</span><span class="p">;</span>
+ <span class="k">case</span> <span class="n">tok_def</span>:
+ <span class="n">HandleDefinition</span><span class="p">();</span>
+ <span class="k">break</span><span class="p">;</span>
+ <span class="k">case</span> <span class="n">tok_extern</span>:
+ <span class="n">HandleExtern</span><span class="p">();</span>
+ <span class="k">break</span><span class="p">;</span>
+ <span class="nl">default:</span>
+ <span class="n">HandleTopLevelExpression</span><span class="p">();</span>
+ <span class="k">break</span><span class="p">;</span>
+ <span class="p">}</span>
+ <span class="p">}</span>
+<span class="p">}</span>
+
+<span class="c1">//===----------------------------------------------------------------------===//</span>
+<span class="c1">// "Library" functions that can be "extern'd" from user code.</span>
+<span class="c1">//===----------------------------------------------------------------------===//</span>
+
+<span class="c1">/// putchard - putchar that takes a double and returns 0.</span>
+<span class="k">extern</span> <span class="s">"C"</span> <span class="kt">double</span> <span class="n">putchard</span><span class="p">(</span><span class="kt">double</span> <span class="n">X</span><span class="p">)</span> <span class="p">{</span>
+ <span class="n">fputc</span><span class="p">((</span><span class="kt">char</span><span class="p">)</span><span class="n">X</span><span class="p">,</span> <span class="n">stderr</span><span class="p">);</span>
+ <span class="k">return</span> <span class="mi">0</span><span class="p">;</span>
+<span class="p">}</span>
+
+<span class="c1">/// printd - printf that takes a double prints it as "%f\n", returning 0.</span>
+<span class="k">extern</span> <span class="s">"C"</span> <span class="kt">double</span> <span class="n">printd</span><span class="p">(</span><span class="kt">double</span> <span class="n">X</span><span class="p">)</span> <span class="p">{</span>
+ <span class="n">fprintf</span><span class="p">(</span><span class="n">stderr</span><span class="p">,</span> <span class="s">"%f</span><span class="se">\n</span><span class="s">"</span><span class="p">,</span> <span class="n">X</span><span class="p">);</span>
+ <span class="k">return</span> <span class="mi">0</span><span class="p">;</span>
+<span class="p">}</span>
+
+<span class="c1">//===----------------------------------------------------------------------===//</span>
+<span class="c1">// Main driver code.</span>
+<span class="c1">//===----------------------------------------------------------------------===//</span>
+
+<span class="kt">int</span> <span class="n">main</span><span class="p">()</span> <span class="p">{</span>
+ <span class="n">InitializeNativeTarget</span><span class="p">();</span>
+ <span class="n">InitializeNativeTargetAsmPrinter</span><span class="p">();</span>
+ <span class="n">InitializeNativeTargetAsmParser</span><span class="p">();</span>
+
+ <span class="c1">// Install standard binary operators.</span>
+ <span class="c1">// 1 is lowest precedence.</span>
+ <span class="n">BinopPrecedence</span><span class="p">[</span><span class="sc">'='</span><span class="p">]</span> <span class="o">=</span> <span class="mi">2</span><span class="p">;</span>
+ <span class="n">BinopPrecedence</span><span class="p">[</span><span class="sc">'<'</span><span class="p">]</span> <span class="o">=</span> <span class="mi">10</span><span class="p">;</span>
+ <span class="n">BinopPrecedence</span><span class="p">[</span><span class="sc">'+'</span><span class="p">]</span> <span class="o">=</span> <span class="mi">20</span><span class="p">;</span>
+ <span class="n">BinopPrecedence</span><span class="p">[</span><span class="sc">'-'</span><span class="p">]</span> <span class="o">=</span> <span class="mi">20</span><span class="p">;</span>
+ <span class="n">BinopPrecedence</span><span class="p">[</span><span class="sc">'*'</span><span class="p">]</span> <span class="o">=</span> <span class="mi">40</span><span class="p">;</span> <span class="c1">// highest.</span>
+
+ <span class="c1">// Prime the first token.</span>
+ <span class="n">fprintf</span><span class="p">(</span><span class="n">stderr</span><span class="p">,</span> <span class="s">"ready> "</span><span class="p">);</span>
+ <span class="n">getNextToken</span><span class="p">();</span>
+
+ <span class="n">TheJIT</span> <span class="o">=</span> <span class="n">llvm</span><span class="o">::</span><span class="n">make_unique</span><span class="o"><</span><span class="n">KaleidoscopeJIT</span><span class="o">></span><span class="p">();</span>
+
+ <span class="n">InitializeModuleAndPassManager</span><span class="p">();</span>
+
+ <span class="c1">// Run the main "interpreter loop" now.</span>
+ <span class="n">MainLoop</span><span class="p">();</span>
+
+ <span class="k">return</span> <span class="mi">0</span><span class="p">;</span>
+<span class="p">}</span>
+</pre></div>
+</div>
+<p><a class="reference external" href="LangImpl8.html">Next: Adding Debug Information</a></p>
+</div>
+</div>
+
+
+ </div>
+ </div>
+ <div class="clearer"></div>
+ </div>
+ <div class="related">
+ <h3>Navigation</h3>
+ <ul>
+ <li class="right" style="margin-right: 10px">
+ <a href="../genindex.html" title="General Index"
+ >index</a></li>
+ <li class="right" >
+ <a href="LangImpl8.html" title="8. Kaleidoscope: Adding Debug Information"
+ >next</a> |</li>
+ <li class="right" >
+ <a href="LangImpl6.html" title="6. Kaleidoscope: Extending the Language: User-defined Operators"
+ >previous</a> |</li>
+ <li><a href="http://llvm.org/">LLVM Home</a> | </li>
+ <li><a href="../index.html">Documentation</a>»</li>
+
+ <li><a href="index.html" >LLVM Tutorial: Table of Contents</a> »</li>
+ </ul>
+ </div>
+ <div class="footer">
+ © Copyright 2003-2016, LLVM Project.
+ Last updated on 2016-07-11.
+ Created using <a href="http://sphinx-doc.org/">Sphinx</a> 1.2.2.
+ </div>
+ </body>
+</html>
\ No newline at end of file
Added: www-releases/trunk/3.8.1/docs/tutorial/LangImpl8.html
URL: http://llvm.org/viewvc/llvm-project/www-releases/trunk/3.8.1/docs/tutorial/LangImpl8.html?rev=275092&view=auto
==============================================================================
--- www-releases/trunk/3.8.1/docs/tutorial/LangImpl8.html (added)
+++ www-releases/trunk/3.8.1/docs/tutorial/LangImpl8.html Mon Jul 11 14:36:11 2016
@@ -0,0 +1,1950 @@
+
+<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN"
+ "http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd">
+
+
+<html xmlns="http://www.w3.org/1999/xhtml">
+ <head>
+ <meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
+
+ <title>8. Kaleidoscope: Adding Debug Information — LLVM 3.8 documentation</title>
+
+ <link rel="stylesheet" href="../_static/llvm-theme.css" type="text/css" />
+ <link rel="stylesheet" href="../_static/pygments.css" type="text/css" />
+
+ <script type="text/javascript">
+ var DOCUMENTATION_OPTIONS = {
+ URL_ROOT: '../',
+ VERSION: '3.8',
+ COLLAPSE_INDEX: false,
+ FILE_SUFFIX: '.html',
+ HAS_SOURCE: true
+ };
+ </script>
+ <script type="text/javascript" src="../_static/jquery.js"></script>
+ <script type="text/javascript" src="../_static/underscore.js"></script>
+ <script type="text/javascript" src="../_static/doctools.js"></script>
+ <link rel="top" title="LLVM 3.8 documentation" href="../index.html" />
+ <link rel="up" title="LLVM Tutorial: Table of Contents" href="index.html" />
+ <link rel="next" title="9. Kaleidoscope: Conclusion and other useful LLVM tidbits" href="LangImpl9.html" />
+ <link rel="prev" title="7. Kaleidoscope: Extending the Language: Mutable Variables" href="LangImpl7.html" />
+<style type="text/css">
+ table.right { float: right; margin-left: 20px; }
+ table.right td { border: 1px solid #ccc; }
+</style>
+
+ </head>
+ <body>
+<div class="logo">
+ <a href="../index.html">
+ <img src="../_static/logo.png"
+ alt="LLVM Logo" width="250" height="88"/></a>
+</div>
+
+ <div class="related">
+ <h3>Navigation</h3>
+ <ul>
+ <li class="right" style="margin-right: 10px">
+ <a href="../genindex.html" title="General Index"
+ accesskey="I">index</a></li>
+ <li class="right" >
+ <a href="LangImpl9.html" title="9. Kaleidoscope: Conclusion and other useful LLVM tidbits"
+ accesskey="N">next</a> |</li>
+ <li class="right" >
+ <a href="LangImpl7.html" title="7. Kaleidoscope: Extending the Language: Mutable Variables"
+ accesskey="P">previous</a> |</li>
+ <li><a href="http://llvm.org/">LLVM Home</a> | </li>
+ <li><a href="../index.html">Documentation</a>»</li>
+
+ <li><a href="index.html" accesskey="U">LLVM Tutorial: Table of Contents</a> »</li>
+ </ul>
+ </div>
+
+
+ <div class="document">
+ <div class="documentwrapper">
+ <div class="body">
+
+ <div class="section" id="kaleidoscope-adding-debug-information">
+<h1>8. Kaleidoscope: Adding Debug Information<a class="headerlink" href="#kaleidoscope-adding-debug-information" title="Permalink to this headline">¶</a></h1>
+<div class="contents local topic" id="contents">
+<ul class="simple">
+<li><a class="reference internal" href="#chapter-8-introduction" id="id1">Chapter 8 Introduction</a></li>
+<li><a class="reference internal" href="#why-is-this-a-hard-problem" id="id2">Why is this a hard problem?</a></li>
+<li><a class="reference internal" href="#ahead-of-time-compilation-mode" id="id3">Ahead-of-Time Compilation Mode</a></li>
+<li><a class="reference internal" href="#compile-unit" id="id4">Compile Unit</a></li>
+<li><a class="reference internal" href="#dwarf-emission-setup" id="id5">DWARF Emission Setup</a></li>
+<li><a class="reference internal" href="#functions" id="id6">Functions</a></li>
+<li><a class="reference internal" href="#source-locations" id="id7">Source Locations</a></li>
+<li><a class="reference internal" href="#variables" id="id8">Variables</a></li>
+<li><a class="reference internal" href="#full-code-listing" id="id9">Full Code Listing</a></li>
+</ul>
+</div>
+<div class="section" id="chapter-8-introduction">
+<h2><a class="toc-backref" href="#id1">8.1. Chapter 8 Introduction</a><a class="headerlink" href="#chapter-8-introduction" title="Permalink to this headline">¶</a></h2>
+<p>Welcome to Chapter 8 of the “<a class="reference external" href="index.html">Implementing a language with
+LLVM</a>” tutorial. In chapters 1 through 7, we’ve built a
+decent little programming language with functions and variables.
+What happens if something goes wrong though, how do you debug your
+program?</p>
+<p>Source level debugging uses formatted data that helps a debugger
+translate from binary and the state of the machine back to the
+source that the programmer wrote. In LLVM we generally use a format
+called <a class="reference external" href="http://dwarfstd.org">DWARF</a>. DWARF is a compact encoding
+that represents types, source locations, and variable locations.</p>
+<p>The short summary of this chapter is that we’ll go through the
+various things you have to add to a programming language to
+support debug info, and how you translate that into DWARF.</p>
+<p>Caveat: For now we can’t debug via the JIT, so we’ll need to compile
+our program down to something small and standalone. As part of this
+we’ll make a few modifications to the running of the language and
+how programs are compiled. This means that we’ll have a source file
+with a simple program written in Kaleidoscope rather than the
+interactive JIT. It does involve a limitation that we can only
+have one “top level” command at a time to reduce the number of
+changes necessary.</p>
+<p>Here’s the sample program we’ll be compiling:</p>
+<div class="highlight-python"><div class="highlight"><pre><span class="k">def</span> <span class="nf">fib</span><span class="p">(</span><span class="n">x</span><span class="p">)</span>
+ <span class="k">if</span> <span class="n">x</span> <span class="o"><</span> <span class="mi">3</span> <span class="n">then</span>
+ <span class="mi">1</span>
+ <span class="k">else</span>
+ <span class="n">fib</span><span class="p">(</span><span class="n">x</span><span class="o">-</span><span class="mi">1</span><span class="p">)</span><span class="o">+</span><span class="n">fib</span><span class="p">(</span><span class="n">x</span><span class="o">-</span><span class="mi">2</span><span class="p">);</span>
+
+<span class="n">fib</span><span class="p">(</span><span class="mi">10</span><span class="p">)</span>
+</pre></div>
+</div>
+</div>
+<div class="section" id="why-is-this-a-hard-problem">
+<h2><a class="toc-backref" href="#id2">8.2. Why is this a hard problem?</a><a class="headerlink" href="#why-is-this-a-hard-problem" title="Permalink to this headline">¶</a></h2>
+<p>Debug information is a hard problem for a few different reasons - mostly
+centered around optimized code. First, optimization makes keeping source
+locations more difficult. In LLVM IR we keep the original source location
+for each IR level instruction on the instruction. Optimization passes
+should keep the source locations for newly created instructions, but merged
+instructions only get to keep a single location - this can cause jumping
+around when stepping through optimized programs. Secondly, optimization
+can move variables in ways that are either optimized out, shared in memory
+with other variables, or difficult to track. For the purposes of this
+tutorial we’re going to avoid optimization (as you’ll see with one of the
+next sets of patches).</p>
+</div>
+<div class="section" id="ahead-of-time-compilation-mode">
+<h2><a class="toc-backref" href="#id3">8.3. Ahead-of-Time Compilation Mode</a><a class="headerlink" href="#ahead-of-time-compilation-mode" title="Permalink to this headline">¶</a></h2>
+<p>To highlight only the aspects of adding debug information to a source
+language without needing to worry about the complexities of JIT debugging
+we’re going to make a few changes to Kaleidoscope to support compiling
+the IR emitted by the front end into a simple standalone program that
+you can execute, debug, and see results.</p>
+<p>First we make our anonymous function that contains our top level
+statement be our “main”:</p>
+<div class="highlight-udiff"><div class="highlight"><pre><span class="gd">- auto Proto = llvm::make_unique<PrototypeAST>("", std::vector<std::string>());</span>
+<span class="gi">+ auto Proto = llvm::make_unique<PrototypeAST>("main", std::vector<std::string>());</span>
+</pre></div>
+</div>
+<p>just with the simple change of giving it a name.</p>
+<p>Then we’re going to remove the command line code wherever it exists:</p>
+<div class="highlight-udiff"><div class="highlight"><pre><span class="gu">@@ -1129,7 +1129,6 @@ static void HandleTopLevelExpression() {</span>
+ /// top ::= definition | external | expression | ';'
+ static void MainLoop() {
+ while (1) {
+<span class="gd">- fprintf(stderr, "ready> ");</span>
+ switch (CurTok) {
+ case tok_eof:
+ return;
+<span class="gu">@@ -1184,7 +1183,6 @@ int main() {</span>
+ BinopPrecedence['*'] = 40; // highest.
+
+ // Prime the first token.
+<span class="gd">- fprintf(stderr, "ready> ");</span>
+ getNextToken();
+</pre></div>
+</div>
+<p>Lastly we’re going to disable all of the optimization passes and the JIT so
+that the only thing that happens after we’re done parsing and generating
+code is that the llvm IR goes to standard error:</p>
+<div class="highlight-udiff"><div class="highlight"><pre><span class="gu">@@ -1108,17 +1108,8 @@ static void HandleExtern() {</span>
+ static void HandleTopLevelExpression() {
+ // Evaluate a top-level expression into an anonymous function.
+ if (auto FnAST = ParseTopLevelExpr()) {
+<span class="gd">- if (auto *FnIR = FnAST->codegen()) {</span>
+<span class="gd">- // We're just doing this to make sure it executes.</span>
+<span class="gd">- TheExecutionEngine->finalizeObject();</span>
+<span class="gd">- // JIT the function, returning a function pointer.</span>
+<span class="gd">- void *FPtr = TheExecutionEngine->getPointerToFunction(FnIR);</span>
+<span class="gd">-</span>
+<span class="gd">- // Cast it to the right type (takes no arguments, returns a double) so we</span>
+<span class="gd">- // can call it as a native function.</span>
+<span class="gd">- double (*FP)() = (double (*)())(intptr_t)FPtr;</span>
+<span class="gd">- // Ignore the return value for this.</span>
+<span class="gd">- (void)FP;</span>
+<span class="gi">+ if (!F->codegen()) {</span>
+<span class="gi">+ fprintf(stderr, "Error generating code for top level expr");</span>
+ }
+ } else {
+ // Skip token for error recovery.
+<span class="gu">@@ -1439,11 +1459,11 @@ int main() {</span>
+ // target lays out data structures.
+ TheModule->setDataLayout(TheExecutionEngine->getDataLayout());
+ OurFPM.add(new DataLayoutPass());
+<span class="gi">+#if 0</span>
+ OurFPM.add(createBasicAliasAnalysisPass());
+ // Promote allocas to registers.
+ OurFPM.add(createPromoteMemoryToRegisterPass());
+<span class="gu">@@ -1218,7 +1210,7 @@ int main() {</span>
+ OurFPM.add(createGVNPass());
+ // Simplify the control flow graph (deleting unreachable blocks, etc).
+ OurFPM.add(createCFGSimplificationPass());
+<span class="gd">-</span>
+<span class="gi">+ #endif</span>
+ OurFPM.doInitialization();
+
+ // Set the global so the code gen can use this.
+</pre></div>
+</div>
+<p>This relatively small set of changes get us to the point that we can compile
+our piece of Kaleidoscope language down to an executable program via this
+command line:</p>
+<div class="highlight-bash"><div class="highlight"><pre>Kaleidoscope-Ch8 < fib.ks | & clang -x ir -
+</pre></div>
+</div>
+<p>which gives an a.out/a.exe in the current working directory.</p>
+</div>
+<div class="section" id="compile-unit">
+<h2><a class="toc-backref" href="#id4">8.4. Compile Unit</a><a class="headerlink" href="#compile-unit" title="Permalink to this headline">¶</a></h2>
+<p>The top level container for a section of code in DWARF is a compile unit.
+This contains the type and function data for an individual translation unit
+(read: one file of source code). So the first thing we need to do is
+construct one for our fib.ks file.</p>
+</div>
+<div class="section" id="dwarf-emission-setup">
+<h2><a class="toc-backref" href="#id5">8.5. DWARF Emission Setup</a><a class="headerlink" href="#dwarf-emission-setup" title="Permalink to this headline">¶</a></h2>
+<p>Similar to the <tt class="docutils literal"><span class="pre">IRBuilder</span></tt> class we have a
+<a class="reference external" href="http://llvm.org/doxygen/classllvm_1_1DIBuilder.html">DIBuilder</a> class
+that helps in constructing debug metadata for an llvm IR file. It
+corresponds 1:1 similarly to <tt class="docutils literal"><span class="pre">IRBuilder</span></tt> and llvm IR, but with nicer names.
+Using it does require that you be more familiar with DWARF terminology than
+you needed to be with <tt class="docutils literal"><span class="pre">IRBuilder</span></tt> and <tt class="docutils literal"><span class="pre">Instruction</span></tt> names, but if you
+read through the general documentation on the
+<a class="reference external" href="http://llvm.org/docs/SourceLevelDebugging.html">Metadata Format</a> it
+should be a little more clear. We’ll be using this class to construct all
+of our IR level descriptions. Construction for it takes a module so we
+need to construct it shortly after we construct our module. We’ve left it
+as a global static variable to make it a bit easier to use.</p>
+<p>Next we’re going to create a small container to cache some of our frequent
+data. The first will be our compile unit, but we’ll also write a bit of
+code for our one type since we won’t have to worry about multiple typed
+expressions:</p>
+<div class="highlight-c++"><div class="highlight"><pre><span class="k">static</span> <span class="n">DIBuilder</span> <span class="o">*</span><span class="n">DBuilder</span><span class="p">;</span>
+
+<span class="k">struct</span> <span class="n">DebugInfo</span> <span class="p">{</span>
+ <span class="n">DICompileUnit</span> <span class="o">*</span><span class="n">TheCU</span><span class="p">;</span>
+ <span class="n">DIType</span> <span class="o">*</span><span class="n">DblTy</span><span class="p">;</span>
+
+ <span class="n">DIType</span> <span class="o">*</span><span class="nf">getDoubleTy</span><span class="p">();</span>
+<span class="p">}</span> <span class="n">KSDbgInfo</span><span class="p">;</span>
+
+<span class="n">DIType</span> <span class="o">*</span><span class="n">DebugInfo</span><span class="o">::</span><span class="n">getDoubleTy</span><span class="p">()</span> <span class="p">{</span>
+ <span class="k">if</span> <span class="p">(</span><span class="n">DblTy</span><span class="p">.</span><span class="n">isValid</span><span class="p">())</span>
+ <span class="k">return</span> <span class="n">DblTy</span><span class="p">;</span>
+
+ <span class="n">DblTy</span> <span class="o">=</span> <span class="n">DBuilder</span><span class="o">-></span><span class="n">createBasicType</span><span class="p">(</span><span class="s">"double"</span><span class="p">,</span> <span class="mi">64</span><span class="p">,</span> <span class="mi">64</span><span class="p">,</span> <span class="n">dwarf</span><span class="o">::</span><span class="n">DW_ATE_float</span><span class="p">);</span>
+ <span class="k">return</span> <span class="n">DblTy</span><span class="p">;</span>
+<span class="p">}</span>
+</pre></div>
+</div>
+<p>And then later on in <tt class="docutils literal"><span class="pre">main</span></tt> when we’re constructing our module:</p>
+<div class="highlight-c++"><div class="highlight"><pre><span class="n">DBuilder</span> <span class="o">=</span> <span class="k">new</span> <span class="n">DIBuilder</span><span class="p">(</span><span class="o">*</span><span class="n">TheModule</span><span class="p">);</span>
+
+<span class="n">KSDbgInfo</span><span class="p">.</span><span class="n">TheCU</span> <span class="o">=</span> <span class="n">DBuilder</span><span class="o">-></span><span class="n">createCompileUnit</span><span class="p">(</span>
+ <span class="n">dwarf</span><span class="o">::</span><span class="n">DW_LANG_C</span><span class="p">,</span> <span class="s">"fib.ks"</span><span class="p">,</span> <span class="s">"."</span><span class="p">,</span> <span class="s">"Kaleidoscope Compiler"</span><span class="p">,</span> <span class="mi">0</span><span class="p">,</span> <span class="s">""</span><span class="p">,</span> <span class="mi">0</span><span class="p">);</span>
+</pre></div>
+</div>
+<p>There are a couple of things to note here. First, while we’re producing a
+compile unit for a language called Kaleidoscope we used the language
+constant for C. This is because a debugger wouldn’t necessarily understand
+the calling conventions or default ABI for a language it doesn’t recognize
+and we follow the C ABI in our llvm code generation so it’s the closest
+thing to accurate. This ensures we can actually call functions from the
+debugger and have them execute. Secondly, you’ll see the “fib.ks” in the
+call to <tt class="docutils literal"><span class="pre">createCompileUnit</span></tt>. This is a default hard coded value since
+we’re using shell redirection to put our source into the Kaleidoscope
+compiler. In a usual front end you’d have an input file name and it would
+go there.</p>
+<p>One last thing as part of emitting debug information via DIBuilder is that
+we need to “finalize” the debug information. The reasons are part of the
+underlying API for DIBuilder, but make sure you do this near the end of
+main:</p>
+<div class="highlight-c++"><div class="highlight"><pre><span class="n">DBuilder</span><span class="o">-></span><span class="n">finalize</span><span class="p">();</span>
+</pre></div>
+</div>
+<p>before you dump out the module.</p>
+</div>
+<div class="section" id="functions">
+<h2><a class="toc-backref" href="#id6">8.6. Functions</a><a class="headerlink" href="#functions" title="Permalink to this headline">¶</a></h2>
+<p>Now that we have our <tt class="docutils literal"><span class="pre">Compile</span> <span class="pre">Unit</span></tt> and our source locations, we can add
+function definitions to the debug info. So in <tt class="docutils literal"><span class="pre">PrototypeAST::codegen()</span></tt> we
+add a few lines of code to describe a context for our subprogram, in this
+case the “File”, and the actual definition of the function itself.</p>
+<p>So the context:</p>
+<div class="highlight-c++"><div class="highlight"><pre><span class="n">DIFile</span> <span class="o">*</span><span class="n">Unit</span> <span class="o">=</span> <span class="n">DBuilder</span><span class="o">-></span><span class="n">createFile</span><span class="p">(</span><span class="n">KSDbgInfo</span><span class="p">.</span><span class="n">TheCU</span><span class="p">.</span><span class="n">getFilename</span><span class="p">(),</span>
+ <span class="n">KSDbgInfo</span><span class="p">.</span><span class="n">TheCU</span><span class="p">.</span><span class="n">getDirectory</span><span class="p">());</span>
+</pre></div>
+</div>
+<p>giving us an DIFile and asking the <tt class="docutils literal"><span class="pre">Compile</span> <span class="pre">Unit</span></tt> we created above for the
+directory and filename where we are currently. Then, for now, we use some
+source locations of 0 (since our AST doesn’t currently have source location
+information) and construct our function definition:</p>
+<div class="highlight-c++"><div class="highlight"><pre><span class="n">DIScope</span> <span class="o">*</span><span class="n">FContext</span> <span class="o">=</span> <span class="n">Unit</span><span class="p">;</span>
+<span class="kt">unsigned</span> <span class="n">LineNo</span> <span class="o">=</span> <span class="mi">0</span><span class="p">;</span>
+<span class="kt">unsigned</span> <span class="n">ScopeLine</span> <span class="o">=</span> <span class="mi">0</span><span class="p">;</span>
+<span class="n">DISubprogram</span> <span class="o">*</span><span class="n">SP</span> <span class="o">=</span> <span class="n">DBuilder</span><span class="o">-></span><span class="n">createFunction</span><span class="p">(</span>
+ <span class="n">FContext</span><span class="p">,</span> <span class="n">Name</span><span class="p">,</span> <span class="n">StringRef</span><span class="p">(),</span> <span class="n">Unit</span><span class="p">,</span> <span class="n">LineNo</span><span class="p">,</span>
+ <span class="n">CreateFunctionType</span><span class="p">(</span><span class="n">Args</span><span class="p">.</span><span class="n">size</span><span class="p">(),</span> <span class="n">Unit</span><span class="p">),</span> <span class="nb">false</span> <span class="cm">/* internal linkage */</span><span class="p">,</span>
+ <span class="nb">true</span> <span class="cm">/* definition */</span><span class="p">,</span> <span class="n">ScopeLine</span><span class="p">,</span> <span class="n">DINode</span><span class="o">::</span><span class="n">FlagPrototyped</span><span class="p">,</span> <span class="nb">false</span><span class="p">);</span>
+<span class="n">F</span><span class="o">-></span><span class="n">setSubprogram</span><span class="p">(</span><span class="n">SP</span><span class="p">);</span>
+</pre></div>
+</div>
+<p>and we now have an DISubprogram that contains a reference to all of our
+metadata for the function.</p>
+</div>
+<div class="section" id="source-locations">
+<h2><a class="toc-backref" href="#id7">8.7. Source Locations</a><a class="headerlink" href="#source-locations" title="Permalink to this headline">¶</a></h2>
+<p>The most important thing for debug information is accurate source location -
+this makes it possible to map your source code back. We have a problem though,
+Kaleidoscope really doesn’t have any source location information in the lexer
+or parser so we’ll need to add it.</p>
+<div class="highlight-c++"><div class="highlight"><pre><span class="k">struct</span> <span class="n">SourceLocation</span> <span class="p">{</span>
+ <span class="kt">int</span> <span class="n">Line</span><span class="p">;</span>
+ <span class="kt">int</span> <span class="n">Col</span><span class="p">;</span>
+<span class="p">};</span>
+<span class="k">static</span> <span class="n">SourceLocation</span> <span class="n">CurLoc</span><span class="p">;</span>
+<span class="k">static</span> <span class="n">SourceLocation</span> <span class="n">LexLoc</span> <span class="o">=</span> <span class="p">{</span><span class="mi">1</span><span class="p">,</span> <span class="mi">0</span><span class="p">};</span>
+
+<span class="k">static</span> <span class="kt">int</span> <span class="nf">advance</span><span class="p">()</span> <span class="p">{</span>
+ <span class="kt">int</span> <span class="n">LastChar</span> <span class="o">=</span> <span class="n">getchar</span><span class="p">();</span>
+
+ <span class="k">if</span> <span class="p">(</span><span class="n">LastChar</span> <span class="o">==</span> <span class="sc">'\n'</span> <span class="o">||</span> <span class="n">LastChar</span> <span class="o">==</span> <span class="sc">'\r'</span><span class="p">)</span> <span class="p">{</span>
+ <span class="n">LexLoc</span><span class="p">.</span><span class="n">Line</span><span class="o">++</span><span class="p">;</span>
+ <span class="n">LexLoc</span><span class="p">.</span><span class="n">Col</span> <span class="o">=</span> <span class="mi">0</span><span class="p">;</span>
+ <span class="p">}</span> <span class="k">else</span>
+ <span class="n">LexLoc</span><span class="p">.</span><span class="n">Col</span><span class="o">++</span><span class="p">;</span>
+ <span class="k">return</span> <span class="n">LastChar</span><span class="p">;</span>
+<span class="p">}</span>
+</pre></div>
+</div>
+<p>In this set of code we’ve added some functionality on how to keep track of the
+line and column of the “source file”. As we lex every token we set our current
+current “lexical location” to the assorted line and column for the beginning
+of the token. We do this by overriding all of the previous calls to
+<tt class="docutils literal"><span class="pre">getchar()</span></tt> with our new <tt class="docutils literal"><span class="pre">advance()</span></tt> that keeps track of the information
+and then we have added to all of our AST classes a source location:</p>
+<div class="highlight-c++"><div class="highlight"><pre><span class="k">class</span> <span class="nc">ExprAST</span> <span class="p">{</span>
+ <span class="n">SourceLocation</span> <span class="n">Loc</span><span class="p">;</span>
+
+ <span class="nl">public:</span>
+ <span class="n">ExprAST</span><span class="p">(</span><span class="n">SourceLocation</span> <span class="n">Loc</span> <span class="o">=</span> <span class="n">CurLoc</span><span class="p">)</span> <span class="o">:</span> <span class="n">Loc</span><span class="p">(</span><span class="n">Loc</span><span class="p">)</span> <span class="p">{}</span>
+ <span class="k">virtual</span> <span class="o">~</span><span class="n">ExprAST</span><span class="p">()</span> <span class="p">{}</span>
+ <span class="k">virtual</span> <span class="n">Value</span><span class="o">*</span> <span class="n">codegen</span><span class="p">()</span> <span class="o">=</span> <span class="mi">0</span><span class="p">;</span>
+ <span class="kt">int</span> <span class="n">getLine</span><span class="p">()</span> <span class="k">const</span> <span class="p">{</span> <span class="k">return</span> <span class="n">Loc</span><span class="p">.</span><span class="n">Line</span><span class="p">;</span> <span class="p">}</span>
+ <span class="kt">int</span> <span class="n">getCol</span><span class="p">()</span> <span class="k">const</span> <span class="p">{</span> <span class="k">return</span> <span class="n">Loc</span><span class="p">.</span><span class="n">Col</span><span class="p">;</span> <span class="p">}</span>
+ <span class="k">virtual</span> <span class="n">raw_ostream</span> <span class="o">&</span><span class="n">dump</span><span class="p">(</span><span class="n">raw_ostream</span> <span class="o">&</span><span class="n">out</span><span class="p">,</span> <span class="kt">int</span> <span class="n">ind</span><span class="p">)</span> <span class="p">{</span>
+ <span class="k">return</span> <span class="n">out</span> <span class="o"><<</span> <span class="sc">':'</span> <span class="o"><<</span> <span class="n">getLine</span><span class="p">()</span> <span class="o"><<</span> <span class="sc">':'</span> <span class="o"><<</span> <span class="n">getCol</span><span class="p">()</span> <span class="o"><<</span> <span class="sc">'\n'</span><span class="p">;</span>
+ <span class="p">}</span>
+</pre></div>
+</div>
+<p>that we pass down through when we create a new expression:</p>
+<div class="highlight-c++"><div class="highlight"><pre><span class="n">LHS</span> <span class="o">=</span> <span class="n">llvm</span><span class="o">::</span><span class="n">make_unique</span><span class="o"><</span><span class="n">BinaryExprAST</span><span class="o">></span><span class="p">(</span><span class="n">BinLoc</span><span class="p">,</span> <span class="n">BinOp</span><span class="p">,</span> <span class="n">std</span><span class="o">::</span><span class="n">move</span><span class="p">(</span><span class="n">LHS</span><span class="p">),</span>
+ <span class="n">std</span><span class="o">::</span><span class="n">move</span><span class="p">(</span><span class="n">RHS</span><span class="p">));</span>
+</pre></div>
+</div>
+<p>giving us locations for each of our expressions and variables.</p>
+<p>From this we can make sure to tell <tt class="docutils literal"><span class="pre">DIBuilder</span></tt> when we’re at a new source
+location so it can use that when we generate the rest of our code and make
+sure that each instruction has source location information. We do this
+by constructing another small function:</p>
+<div class="highlight-c++"><div class="highlight"><pre><span class="kt">void</span> <span class="n">DebugInfo</span><span class="o">::</span><span class="n">emitLocation</span><span class="p">(</span><span class="n">ExprAST</span> <span class="o">*</span><span class="n">AST</span><span class="p">)</span> <span class="p">{</span>
+ <span class="n">DIScope</span> <span class="o">*</span><span class="n">Scope</span><span class="p">;</span>
+ <span class="k">if</span> <span class="p">(</span><span class="n">LexicalBlocks</span><span class="p">.</span><span class="n">empty</span><span class="p">())</span>
+ <span class="n">Scope</span> <span class="o">=</span> <span class="n">TheCU</span><span class="p">;</span>
+ <span class="k">else</span>
+ <span class="n">Scope</span> <span class="o">=</span> <span class="n">LexicalBlocks</span><span class="p">.</span><span class="n">back</span><span class="p">();</span>
+ <span class="n">Builder</span><span class="p">.</span><span class="n">SetCurrentDebugLocation</span><span class="p">(</span>
+ <span class="n">DebugLoc</span><span class="o">::</span><span class="n">get</span><span class="p">(</span><span class="n">AST</span><span class="o">-></span><span class="n">getLine</span><span class="p">(),</span> <span class="n">AST</span><span class="o">-></span><span class="n">getCol</span><span class="p">(),</span> <span class="n">Scope</span><span class="p">));</span>
+<span class="p">}</span>
+</pre></div>
+</div>
+<p>that both tells the main <tt class="docutils literal"><span class="pre">IRBuilder</span></tt> where we are, but also what scope
+we’re in. Since we’ve just created a function above we can either be in
+the main file scope (like when we created our function), or now we can be
+in the function scope we just created. To represent this we create a stack
+of scopes:</p>
+<div class="highlight-c++"><div class="highlight"><pre><span class="n">std</span><span class="o">::</span><span class="n">vector</span><span class="o"><</span><span class="n">DIScope</span> <span class="o">*></span> <span class="n">LexicalBlocks</span><span class="p">;</span>
+<span class="n">std</span><span class="o">::</span><span class="n">map</span><span class="o"><</span><span class="k">const</span> <span class="n">PrototypeAST</span> <span class="o">*</span><span class="p">,</span> <span class="n">DIScope</span> <span class="o">*></span> <span class="n">FnScopeMap</span><span class="p">;</span>
+</pre></div>
+</div>
+<p>and keep a map of each function to the scope that it represents (an
+DISubprogram is also an DIScope).</p>
+<p>Then we make sure to:</p>
+<div class="highlight-c++"><div class="highlight"><pre><span class="n">KSDbgInfo</span><span class="p">.</span><span class="n">emitLocation</span><span class="p">(</span><span class="k">this</span><span class="p">);</span>
+</pre></div>
+</div>
+<p>emit the location every time we start to generate code for a new AST, and
+also:</p>
+<div class="highlight-c++"><div class="highlight"><pre><span class="n">KSDbgInfo</span><span class="p">.</span><span class="n">FnScopeMap</span><span class="p">[</span><span class="k">this</span><span class="p">]</span> <span class="o">=</span> <span class="n">SP</span><span class="p">;</span>
+</pre></div>
+</div>
+<p>store the scope (function) when we create it and use it:</p>
+<blockquote>
+<div>KSDbgInfo.LexicalBlocks.push_back(&KSDbgInfo.FnScopeMap[Proto]);</div></blockquote>
+<p>when we start generating the code for each function.</p>
+<p>also, don’t forget to pop the scope back off of your scope stack at the
+end of the code generation for the function:</p>
+<div class="highlight-c++"><div class="highlight"><pre><span class="c1">// Pop off the lexical block for the function since we added it</span>
+<span class="c1">// unconditionally.</span>
+<span class="n">KSDbgInfo</span><span class="p">.</span><span class="n">LexicalBlocks</span><span class="p">.</span><span class="n">pop_back</span><span class="p">();</span>
+</pre></div>
+</div>
+</div>
+<div class="section" id="variables">
+<h2><a class="toc-backref" href="#id8">8.8. Variables</a><a class="headerlink" href="#variables" title="Permalink to this headline">¶</a></h2>
+<p>Now that we have functions, we need to be able to print out the variables
+we have in scope. Let’s get our function arguments set up so we can get
+decent backtraces and see how our functions are being called. It isn’t
+a lot of code, and we generally handle it when we’re creating the
+argument allocas in <tt class="docutils literal"><span class="pre">PrototypeAST::CreateArgumentAllocas</span></tt>.</p>
+<div class="highlight-c++"><div class="highlight"><pre><span class="n">DIScope</span> <span class="o">*</span><span class="n">Scope</span> <span class="o">=</span> <span class="n">KSDbgInfo</span><span class="p">.</span><span class="n">LexicalBlocks</span><span class="p">.</span><span class="n">back</span><span class="p">();</span>
+<span class="n">DIFile</span> <span class="o">*</span><span class="n">Unit</span> <span class="o">=</span> <span class="n">DBuilder</span><span class="o">-></span><span class="n">createFile</span><span class="p">(</span><span class="n">KSDbgInfo</span><span class="p">.</span><span class="n">TheCU</span><span class="p">.</span><span class="n">getFilename</span><span class="p">(),</span>
+ <span class="n">KSDbgInfo</span><span class="p">.</span><span class="n">TheCU</span><span class="p">.</span><span class="n">getDirectory</span><span class="p">());</span>
+<span class="n">DILocalVariable</span> <span class="n">D</span> <span class="o">=</span> <span class="n">DBuilder</span><span class="o">-></span><span class="n">createParameterVariable</span><span class="p">(</span>
+ <span class="n">Scope</span><span class="p">,</span> <span class="n">Args</span><span class="p">[</span><span class="n">Idx</span><span class="p">],</span> <span class="n">Idx</span> <span class="o">+</span> <span class="mi">1</span><span class="p">,</span> <span class="n">Unit</span><span class="p">,</span> <span class="n">Line</span><span class="p">,</span> <span class="n">KSDbgInfo</span><span class="p">.</span><span class="n">getDoubleTy</span><span class="p">(),</span> <span class="nb">true</span><span class="p">);</span>
+
+<span class="n">DBuilder</span><span class="o">-></span><span class="n">insertDeclare</span><span class="p">(</span><span class="n">Alloca</span><span class="p">,</span> <span class="n">D</span><span class="p">,</span> <span class="n">DBuilder</span><span class="o">-></span><span class="n">createExpression</span><span class="p">(),</span>
+ <span class="n">DebugLoc</span><span class="o">::</span><span class="n">get</span><span class="p">(</span><span class="n">Line</span><span class="p">,</span> <span class="mi">0</span><span class="p">,</span> <span class="n">Scope</span><span class="p">),</span>
+ <span class="n">Builder</span><span class="p">.</span><span class="n">GetInsertBlock</span><span class="p">());</span>
+</pre></div>
+</div>
+<p>Here we’re doing a few things. First, we’re grabbing our current scope
+for the variable so we can say what range of code our variable is valid
+through. Second, we’re creating the variable, giving it the scope,
+the name, source location, type, and since it’s an argument, the argument
+index. Third, we create an <tt class="docutils literal"><span class="pre">lvm.dbg.declare</span></tt> call to indicate at the IR
+level that we’ve got a variable in an alloca (and it gives a starting
+location for the variable), and setting a source location for the
+beginning of the scope on the declare.</p>
+<p>One interesting thing to note at this point is that various debuggers have
+assumptions based on how code and debug information was generated for them
+in the past. In this case we need to do a little bit of a hack to avoid
+generating line information for the function prologue so that the debugger
+knows to skip over those instructions when setting a breakpoint. So in
+<tt class="docutils literal"><span class="pre">FunctionAST::CodeGen</span></tt> we add a couple of lines:</p>
+<div class="highlight-c++"><div class="highlight"><pre><span class="c1">// Unset the location for the prologue emission (leading instructions with no</span>
+<span class="c1">// location in a function are considered part of the prologue and the debugger</span>
+<span class="c1">// will run past them when breaking on a function)</span>
+<span class="n">KSDbgInfo</span><span class="p">.</span><span class="n">emitLocation</span><span class="p">(</span><span class="n">nullptr</span><span class="p">);</span>
+</pre></div>
+</div>
+<p>and then emit a new location when we actually start generating code for the
+body of the function:</p>
+<div class="highlight-c++"><div class="highlight"><pre><span class="n">KSDbgInfo</span><span class="p">.</span><span class="n">emitLocation</span><span class="p">(</span><span class="n">Body</span><span class="p">);</span>
+</pre></div>
+</div>
+<p>With this we have enough debug information to set breakpoints in functions,
+print out argument variables, and call functions. Not too bad for just a
+few simple lines of code!</p>
+</div>
+<div class="section" id="full-code-listing">
+<h2><a class="toc-backref" href="#id9">8.9. Full Code Listing</a><a class="headerlink" href="#full-code-listing" title="Permalink to this headline">¶</a></h2>
+<p>Here is the complete code listing for our running example, enhanced with
+debug information. To build this example, use:</p>
+<div class="highlight-bash"><div class="highlight"><pre><span class="c"># Compile</span>
+clang++ -g toy.cpp <span class="sb">`</span>llvm-config --cxxflags --ldflags --system-libs --libs core mcjit native<span class="sb">`</span> -O3 -o toy
+<span class="c"># Run</span>
+./toy
+</pre></div>
+</div>
+<p>Here is the code:</p>
+<div class="highlight-c++"><div class="highlight"><pre><span class="cp">#include "llvm/ADT/STLExtras.h"</span>
+<span class="cp">#include "llvm/Analysis/BasicAliasAnalysis.h"</span>
+<span class="cp">#include "llvm/Analysis/Passes.h"</span>
+<span class="cp">#include "llvm/IR/DIBuilder.h"</span>
+<span class="cp">#include "llvm/IR/IRBuilder.h"</span>
+<span class="cp">#include "llvm/IR/LLVMContext.h"</span>
+<span class="cp">#include "llvm/IR/LegacyPassManager.h"</span>
+<span class="cp">#include "llvm/IR/Module.h"</span>
+<span class="cp">#include "llvm/IR/Verifier.h"</span>
+<span class="cp">#include "llvm/Support/TargetSelect.h"</span>
+<span class="cp">#include "llvm/Transforms/Scalar.h"</span>
+<span class="cp">#include <cctype></span>
+<span class="cp">#include <cstdio></span>
+<span class="cp">#include <map></span>
+<span class="cp">#include <string></span>
+<span class="cp">#include <vector></span>
+<span class="cp">#include "../include/KaleidoscopeJIT.h"</span>
+
+<span class="k">using</span> <span class="k">namespace</span> <span class="n">llvm</span><span class="p">;</span>
+<span class="k">using</span> <span class="k">namespace</span> <span class="n">llvm</span><span class="o">::</span><span class="n">orc</span><span class="p">;</span>
+
+<span class="c1">//===----------------------------------------------------------------------===//</span>
+<span class="c1">// Lexer</span>
+<span class="c1">//===----------------------------------------------------------------------===//</span>
+
+<span class="c1">// The lexer returns tokens [0-255] if it is an unknown character, otherwise one</span>
+<span class="c1">// of these for known things.</span>
+<span class="k">enum</span> <span class="n">Token</span> <span class="p">{</span>
+ <span class="n">tok_eof</span> <span class="o">=</span> <span class="o">-</span><span class="mi">1</span><span class="p">,</span>
+
+ <span class="c1">// commands</span>
+ <span class="n">tok_def</span> <span class="o">=</span> <span class="o">-</span><span class="mi">2</span><span class="p">,</span>
+ <span class="n">tok_extern</span> <span class="o">=</span> <span class="o">-</span><span class="mi">3</span><span class="p">,</span>
+
+ <span class="c1">// primary</span>
+ <span class="n">tok_identifier</span> <span class="o">=</span> <span class="o">-</span><span class="mi">4</span><span class="p">,</span>
+ <span class="n">tok_number</span> <span class="o">=</span> <span class="o">-</span><span class="mi">5</span><span class="p">,</span>
+
+ <span class="c1">// control</span>
+ <span class="n">tok_if</span> <span class="o">=</span> <span class="o">-</span><span class="mi">6</span><span class="p">,</span>
+ <span class="n">tok_then</span> <span class="o">=</span> <span class="o">-</span><span class="mi">7</span><span class="p">,</span>
+ <span class="n">tok_else</span> <span class="o">=</span> <span class="o">-</span><span class="mi">8</span><span class="p">,</span>
+ <span class="n">tok_for</span> <span class="o">=</span> <span class="o">-</span><span class="mi">9</span><span class="p">,</span>
+ <span class="n">tok_in</span> <span class="o">=</span> <span class="o">-</span><span class="mi">10</span><span class="p">,</span>
+
+ <span class="c1">// operators</span>
+ <span class="n">tok_binary</span> <span class="o">=</span> <span class="o">-</span><span class="mi">11</span><span class="p">,</span>
+ <span class="n">tok_unary</span> <span class="o">=</span> <span class="o">-</span><span class="mi">12</span><span class="p">,</span>
+
+ <span class="c1">// var definition</span>
+ <span class="n">tok_var</span> <span class="o">=</span> <span class="o">-</span><span class="mi">13</span>
+<span class="p">};</span>
+
+<span class="n">std</span><span class="o">::</span><span class="n">string</span> <span class="n">getTokName</span><span class="p">(</span><span class="kt">int</span> <span class="n">Tok</span><span class="p">)</span> <span class="p">{</span>
+ <span class="k">switch</span> <span class="p">(</span><span class="n">Tok</span><span class="p">)</span> <span class="p">{</span>
+ <span class="k">case</span> <span class="n">tok_eof</span>:
+ <span class="k">return</span> <span class="s">"eof"</span><span class="p">;</span>
+ <span class="k">case</span> <span class="n">tok_def</span>:
+ <span class="k">return</span> <span class="s">"def"</span><span class="p">;</span>
+ <span class="k">case</span> <span class="n">tok_extern</span>:
+ <span class="k">return</span> <span class="s">"extern"</span><span class="p">;</span>
+ <span class="k">case</span> <span class="n">tok_identifier</span>:
+ <span class="k">return</span> <span class="s">"identifier"</span><span class="p">;</span>
+ <span class="k">case</span> <span class="n">tok_number</span>:
+ <span class="k">return</span> <span class="s">"number"</span><span class="p">;</span>
+ <span class="k">case</span> <span class="n">tok_if</span>:
+ <span class="k">return</span> <span class="s">"if"</span><span class="p">;</span>
+ <span class="k">case</span> <span class="n">tok_then</span>:
+ <span class="k">return</span> <span class="s">"then"</span><span class="p">;</span>
+ <span class="k">case</span> <span class="n">tok_else</span>:
+ <span class="k">return</span> <span class="s">"else"</span><span class="p">;</span>
+ <span class="k">case</span> <span class="n">tok_for</span>:
+ <span class="k">return</span> <span class="s">"for"</span><span class="p">;</span>
+ <span class="k">case</span> <span class="n">tok_in</span>:
+ <span class="k">return</span> <span class="s">"in"</span><span class="p">;</span>
+ <span class="k">case</span> <span class="n">tok_binary</span>:
+ <span class="k">return</span> <span class="s">"binary"</span><span class="p">;</span>
+ <span class="k">case</span> <span class="n">tok_unary</span>:
+ <span class="k">return</span> <span class="s">"unary"</span><span class="p">;</span>
+ <span class="k">case</span> <span class="n">tok_var</span>:
+ <span class="k">return</span> <span class="s">"var"</span><span class="p">;</span>
+ <span class="p">}</span>
+ <span class="k">return</span> <span class="n">std</span><span class="o">::</span><span class="n">string</span><span class="p">(</span><span class="mi">1</span><span class="p">,</span> <span class="p">(</span><span class="kt">char</span><span class="p">)</span><span class="n">Tok</span><span class="p">);</span>
+<span class="p">}</span>
+
+<span class="k">namespace</span> <span class="p">{</span>
+<span class="k">class</span> <span class="nc">PrototypeAST</span><span class="p">;</span>
+<span class="k">class</span> <span class="nc">ExprAST</span><span class="p">;</span>
+<span class="p">}</span>
+<span class="k">static</span> <span class="n">IRBuilder</span><span class="o"><></span> <span class="n">Builder</span><span class="p">(</span><span class="n">getGlobalContext</span><span class="p">());</span>
+<span class="k">struct</span> <span class="n">DebugInfo</span> <span class="p">{</span>
+ <span class="n">DICompileUnit</span> <span class="o">*</span><span class="n">TheCU</span><span class="p">;</span>
+ <span class="n">DIType</span> <span class="o">*</span><span class="n">DblTy</span><span class="p">;</span>
+ <span class="n">std</span><span class="o">::</span><span class="n">vector</span><span class="o"><</span><span class="n">DIScope</span> <span class="o">*></span> <span class="n">LexicalBlocks</span><span class="p">;</span>
+
+ <span class="kt">void</span> <span class="nf">emitLocation</span><span class="p">(</span><span class="n">ExprAST</span> <span class="o">*</span><span class="n">AST</span><span class="p">);</span>
+ <span class="n">DIType</span> <span class="o">*</span><span class="nf">getDoubleTy</span><span class="p">();</span>
+<span class="p">}</span> <span class="n">KSDbgInfo</span><span class="p">;</span>
+
+<span class="k">struct</span> <span class="n">SourceLocation</span> <span class="p">{</span>
+ <span class="kt">int</span> <span class="n">Line</span><span class="p">;</span>
+ <span class="kt">int</span> <span class="n">Col</span><span class="p">;</span>
+<span class="p">};</span>
+<span class="k">static</span> <span class="n">SourceLocation</span> <span class="n">CurLoc</span><span class="p">;</span>
+<span class="k">static</span> <span class="n">SourceLocation</span> <span class="n">LexLoc</span> <span class="o">=</span> <span class="p">{</span><span class="mi">1</span><span class="p">,</span> <span class="mi">0</span><span class="p">};</span>
+
+<span class="k">static</span> <span class="kt">int</span> <span class="nf">advance</span><span class="p">()</span> <span class="p">{</span>
+ <span class="kt">int</span> <span class="n">LastChar</span> <span class="o">=</span> <span class="n">getchar</span><span class="p">();</span>
+
+ <span class="k">if</span> <span class="p">(</span><span class="n">LastChar</span> <span class="o">==</span> <span class="sc">'\n'</span> <span class="o">||</span> <span class="n">LastChar</span> <span class="o">==</span> <span class="sc">'\r'</span><span class="p">)</span> <span class="p">{</span>
+ <span class="n">LexLoc</span><span class="p">.</span><span class="n">Line</span><span class="o">++</span><span class="p">;</span>
+ <span class="n">LexLoc</span><span class="p">.</span><span class="n">Col</span> <span class="o">=</span> <span class="mi">0</span><span class="p">;</span>
+ <span class="p">}</span> <span class="k">else</span>
+ <span class="n">LexLoc</span><span class="p">.</span><span class="n">Col</span><span class="o">++</span><span class="p">;</span>
+ <span class="k">return</span> <span class="n">LastChar</span><span class="p">;</span>
+<span class="p">}</span>
+
+<span class="k">static</span> <span class="n">std</span><span class="o">::</span><span class="n">string</span> <span class="n">IdentifierStr</span><span class="p">;</span> <span class="c1">// Filled in if tok_identifier</span>
+<span class="k">static</span> <span class="kt">double</span> <span class="n">NumVal</span><span class="p">;</span> <span class="c1">// Filled in if tok_number</span>
+
+<span class="c1">/// gettok - Return the next token from standard input.</span>
+<span class="k">static</span> <span class="kt">int</span> <span class="nf">gettok</span><span class="p">()</span> <span class="p">{</span>
+ <span class="k">static</span> <span class="kt">int</span> <span class="n">LastChar</span> <span class="o">=</span> <span class="sc">' '</span><span class="p">;</span>
+
+ <span class="c1">// Skip any whitespace.</span>
+ <span class="k">while</span> <span class="p">(</span><span class="n">isspace</span><span class="p">(</span><span class="n">LastChar</span><span class="p">))</span>
+ <span class="n">LastChar</span> <span class="o">=</span> <span class="n">advance</span><span class="p">();</span>
+
+ <span class="n">CurLoc</span> <span class="o">=</span> <span class="n">LexLoc</span><span class="p">;</span>
+
+ <span class="k">if</span> <span class="p">(</span><span class="n">isalpha</span><span class="p">(</span><span class="n">LastChar</span><span class="p">))</span> <span class="p">{</span> <span class="c1">// identifier: [a-zA-Z][a-zA-Z0-9]*</span>
+ <span class="n">IdentifierStr</span> <span class="o">=</span> <span class="n">LastChar</span><span class="p">;</span>
+ <span class="k">while</span> <span class="p">(</span><span class="n">isalnum</span><span class="p">((</span><span class="n">LastChar</span> <span class="o">=</span> <span class="n">advance</span><span class="p">())))</span>
+ <span class="n">IdentifierStr</span> <span class="o">+=</span> <span class="n">LastChar</span><span class="p">;</span>
+
+ <span class="k">if</span> <span class="p">(</span><span class="n">IdentifierStr</span> <span class="o">==</span> <span class="s">"def"</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">tok_def</span><span class="p">;</span>
+ <span class="k">if</span> <span class="p">(</span><span class="n">IdentifierStr</span> <span class="o">==</span> <span class="s">"extern"</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">tok_extern</span><span class="p">;</span>
+ <span class="k">if</span> <span class="p">(</span><span class="n">IdentifierStr</span> <span class="o">==</span> <span class="s">"if"</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">tok_if</span><span class="p">;</span>
+ <span class="k">if</span> <span class="p">(</span><span class="n">IdentifierStr</span> <span class="o">==</span> <span class="s">"then"</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">tok_then</span><span class="p">;</span>
+ <span class="k">if</span> <span class="p">(</span><span class="n">IdentifierStr</span> <span class="o">==</span> <span class="s">"else"</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">tok_else</span><span class="p">;</span>
+ <span class="k">if</span> <span class="p">(</span><span class="n">IdentifierStr</span> <span class="o">==</span> <span class="s">"for"</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">tok_for</span><span class="p">;</span>
+ <span class="k">if</span> <span class="p">(</span><span class="n">IdentifierStr</span> <span class="o">==</span> <span class="s">"in"</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">tok_in</span><span class="p">;</span>
+ <span class="k">if</span> <span class="p">(</span><span class="n">IdentifierStr</span> <span class="o">==</span> <span class="s">"binary"</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">tok_binary</span><span class="p">;</span>
+ <span class="k">if</span> <span class="p">(</span><span class="n">IdentifierStr</span> <span class="o">==</span> <span class="s">"unary"</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">tok_unary</span><span class="p">;</span>
+ <span class="k">if</span> <span class="p">(</span><span class="n">IdentifierStr</span> <span class="o">==</span> <span class="s">"var"</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">tok_var</span><span class="p">;</span>
+ <span class="k">return</span> <span class="n">tok_identifier</span><span class="p">;</span>
+ <span class="p">}</span>
+
+ <span class="k">if</span> <span class="p">(</span><span class="n">isdigit</span><span class="p">(</span><span class="n">LastChar</span><span class="p">)</span> <span class="o">||</span> <span class="n">LastChar</span> <span class="o">==</span> <span class="sc">'.'</span><span class="p">)</span> <span class="p">{</span> <span class="c1">// Number: [0-9.]+</span>
+ <span class="n">std</span><span class="o">::</span><span class="n">string</span> <span class="n">NumStr</span><span class="p">;</span>
+ <span class="k">do</span> <span class="p">{</span>
+ <span class="n">NumStr</span> <span class="o">+=</span> <span class="n">LastChar</span><span class="p">;</span>
+ <span class="n">LastChar</span> <span class="o">=</span> <span class="n">advance</span><span class="p">();</span>
+ <span class="p">}</span> <span class="k">while</span> <span class="p">(</span><span class="n">isdigit</span><span class="p">(</span><span class="n">LastChar</span><span class="p">)</span> <span class="o">||</span> <span class="n">LastChar</span> <span class="o">==</span> <span class="sc">'.'</span><span class="p">);</span>
+
+ <span class="n">NumVal</span> <span class="o">=</span> <span class="n">strtod</span><span class="p">(</span><span class="n">NumStr</span><span class="p">.</span><span class="n">c_str</span><span class="p">(),</span> <span class="n">nullptr</span><span class="p">);</span>
+ <span class="k">return</span> <span class="n">tok_number</span><span class="p">;</span>
+ <span class="p">}</span>
+
+ <span class="k">if</span> <span class="p">(</span><span class="n">LastChar</span> <span class="o">==</span> <span class="sc">'#'</span><span class="p">)</span> <span class="p">{</span>
+ <span class="c1">// Comment until end of line.</span>
+ <span class="k">do</span>
+ <span class="n">LastChar</span> <span class="o">=</span> <span class="n">advance</span><span class="p">();</span>
+ <span class="k">while</span> <span class="p">(</span><span class="n">LastChar</span> <span class="o">!=</span> <span class="n">EOF</span> <span class="o">&&</span> <span class="n">LastChar</span> <span class="o">!=</span> <span class="sc">'\n'</span> <span class="o">&&</span> <span class="n">LastChar</span> <span class="o">!=</span> <span class="sc">'\r'</span><span class="p">);</span>
+
+ <span class="k">if</span> <span class="p">(</span><span class="n">LastChar</span> <span class="o">!=</span> <span class="n">EOF</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">gettok</span><span class="p">();</span>
+ <span class="p">}</span>
+
+ <span class="c1">// Check for end of file. Don't eat the EOF.</span>
+ <span class="k">if</span> <span class="p">(</span><span class="n">LastChar</span> <span class="o">==</span> <span class="n">EOF</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">tok_eof</span><span class="p">;</span>
+
+ <span class="c1">// Otherwise, just return the character as its ascii value.</span>
+ <span class="kt">int</span> <span class="n">ThisChar</span> <span class="o">=</span> <span class="n">LastChar</span><span class="p">;</span>
+ <span class="n">LastChar</span> <span class="o">=</span> <span class="n">advance</span><span class="p">();</span>
+ <span class="k">return</span> <span class="n">ThisChar</span><span class="p">;</span>
+<span class="p">}</span>
+
+<span class="c1">//===----------------------------------------------------------------------===//</span>
+<span class="c1">// Abstract Syntax Tree (aka Parse Tree)</span>
+<span class="c1">//===----------------------------------------------------------------------===//</span>
+<span class="k">namespace</span> <span class="p">{</span>
+
+<span class="n">raw_ostream</span> <span class="o">&</span><span class="n">indent</span><span class="p">(</span><span class="n">raw_ostream</span> <span class="o">&</span><span class="n">O</span><span class="p">,</span> <span class="kt">int</span> <span class="n">size</span><span class="p">)</span> <span class="p">{</span>
+ <span class="k">return</span> <span class="n">O</span> <span class="o"><<</span> <span class="n">std</span><span class="o">::</span><span class="n">string</span><span class="p">(</span><span class="n">size</span><span class="p">,</span> <span class="sc">' '</span><span class="p">);</span>
+<span class="p">}</span>
+
+<span class="c1">/// ExprAST - Base class for all expression nodes.</span>
+<span class="k">class</span> <span class="nc">ExprAST</span> <span class="p">{</span>
+ <span class="n">SourceLocation</span> <span class="n">Loc</span><span class="p">;</span>
+
+<span class="nl">public:</span>
+ <span class="n">ExprAST</span><span class="p">(</span><span class="n">SourceLocation</span> <span class="n">Loc</span> <span class="o">=</span> <span class="n">CurLoc</span><span class="p">)</span> <span class="o">:</span> <span class="n">Loc</span><span class="p">(</span><span class="n">Loc</span><span class="p">)</span> <span class="p">{}</span>
+ <span class="k">virtual</span> <span class="o">~</span><span class="n">ExprAST</span><span class="p">()</span> <span class="p">{}</span>
+ <span class="k">virtual</span> <span class="n">Value</span> <span class="o">*</span><span class="n">codegen</span><span class="p">()</span> <span class="o">=</span> <span class="mi">0</span><span class="p">;</span>
+ <span class="kt">int</span> <span class="n">getLine</span><span class="p">()</span> <span class="k">const</span> <span class="p">{</span> <span class="k">return</span> <span class="n">Loc</span><span class="p">.</span><span class="n">Line</span><span class="p">;</span> <span class="p">}</span>
+ <span class="kt">int</span> <span class="n">getCol</span><span class="p">()</span> <span class="k">const</span> <span class="p">{</span> <span class="k">return</span> <span class="n">Loc</span><span class="p">.</span><span class="n">Col</span><span class="p">;</span> <span class="p">}</span>
+ <span class="k">virtual</span> <span class="n">raw_ostream</span> <span class="o">&</span><span class="n">dump</span><span class="p">(</span><span class="n">raw_ostream</span> <span class="o">&</span><span class="n">out</span><span class="p">,</span> <span class="kt">int</span> <span class="n">ind</span><span class="p">)</span> <span class="p">{</span>
+ <span class="k">return</span> <span class="n">out</span> <span class="o"><<</span> <span class="sc">':'</span> <span class="o"><<</span> <span class="n">getLine</span><span class="p">()</span> <span class="o"><<</span> <span class="sc">':'</span> <span class="o"><<</span> <span class="n">getCol</span><span class="p">()</span> <span class="o"><<</span> <span class="sc">'\n'</span><span class="p">;</span>
+ <span class="p">}</span>
+<span class="p">};</span>
+
+<span class="c1">/// NumberExprAST - Expression class for numeric literals like "1.0".</span>
+<span class="k">class</span> <span class="nc">NumberExprAST</span> <span class="o">:</span> <span class="k">public</span> <span class="n">ExprAST</span> <span class="p">{</span>
+ <span class="kt">double</span> <span class="n">Val</span><span class="p">;</span>
+
+<span class="nl">public:</span>
+ <span class="n">NumberExprAST</span><span class="p">(</span><span class="kt">double</span> <span class="n">Val</span><span class="p">)</span> <span class="o">:</span> <span class="n">Val</span><span class="p">(</span><span class="n">Val</span><span class="p">)</span> <span class="p">{}</span>
+ <span class="n">raw_ostream</span> <span class="o">&</span><span class="n">dump</span><span class="p">(</span><span class="n">raw_ostream</span> <span class="o">&</span><span class="n">out</span><span class="p">,</span> <span class="kt">int</span> <span class="n">ind</span><span class="p">)</span> <span class="n">override</span> <span class="p">{</span>
+ <span class="k">return</span> <span class="n">ExprAST</span><span class="o">::</span><span class="n">dump</span><span class="p">(</span><span class="n">out</span> <span class="o"><<</span> <span class="n">Val</span><span class="p">,</span> <span class="n">ind</span><span class="p">);</span>
+ <span class="p">}</span>
+ <span class="n">Value</span> <span class="o">*</span><span class="n">codegen</span><span class="p">()</span> <span class="n">override</span><span class="p">;</span>
+<span class="p">};</span>
+
+<span class="c1">/// VariableExprAST - Expression class for referencing a variable, like "a".</span>
+<span class="k">class</span> <span class="nc">VariableExprAST</span> <span class="o">:</span> <span class="k">public</span> <span class="n">ExprAST</span> <span class="p">{</span>
+ <span class="n">std</span><span class="o">::</span><span class="n">string</span> <span class="n">Name</span><span class="p">;</span>
+
+<span class="nl">public:</span>
+ <span class="n">VariableExprAST</span><span class="p">(</span><span class="n">SourceLocation</span> <span class="n">Loc</span><span class="p">,</span> <span class="k">const</span> <span class="n">std</span><span class="o">::</span><span class="n">string</span> <span class="o">&</span><span class="n">Name</span><span class="p">)</span>
+ <span class="o">:</span> <span class="n">ExprAST</span><span class="p">(</span><span class="n">Loc</span><span class="p">),</span> <span class="n">Name</span><span class="p">(</span><span class="n">Name</span><span class="p">)</span> <span class="p">{}</span>
+ <span class="k">const</span> <span class="n">std</span><span class="o">::</span><span class="n">string</span> <span class="o">&</span><span class="n">getName</span><span class="p">()</span> <span class="k">const</span> <span class="p">{</span> <span class="k">return</span> <span class="n">Name</span><span class="p">;</span> <span class="p">}</span>
+ <span class="n">Value</span> <span class="o">*</span><span class="n">codegen</span><span class="p">()</span> <span class="n">override</span><span class="p">;</span>
+ <span class="n">raw_ostream</span> <span class="o">&</span><span class="n">dump</span><span class="p">(</span><span class="n">raw_ostream</span> <span class="o">&</span><span class="n">out</span><span class="p">,</span> <span class="kt">int</span> <span class="n">ind</span><span class="p">)</span> <span class="n">override</span> <span class="p">{</span>
+ <span class="k">return</span> <span class="n">ExprAST</span><span class="o">::</span><span class="n">dump</span><span class="p">(</span><span class="n">out</span> <span class="o"><<</span> <span class="n">Name</span><span class="p">,</span> <span class="n">ind</span><span class="p">);</span>
+ <span class="p">}</span>
+<span class="p">};</span>
+
+<span class="c1">/// UnaryExprAST - Expression class for a unary operator.</span>
+<span class="k">class</span> <span class="nc">UnaryExprAST</span> <span class="o">:</span> <span class="k">public</span> <span class="n">ExprAST</span> <span class="p">{</span>
+ <span class="kt">char</span> <span class="n">Opcode</span><span class="p">;</span>
+ <span class="n">std</span><span class="o">::</span><span class="n">unique_ptr</span><span class="o"><</span><span class="n">ExprAST</span><span class="o">></span> <span class="n">Operand</span><span class="p">;</span>
+
+<span class="nl">public:</span>
+ <span class="n">UnaryExprAST</span><span class="p">(</span><span class="kt">char</span> <span class="n">Opcode</span><span class="p">,</span> <span class="n">std</span><span class="o">::</span><span class="n">unique_ptr</span><span class="o"><</span><span class="n">ExprAST</span><span class="o">></span> <span class="n">Operand</span><span class="p">)</span>
+ <span class="o">:</span> <span class="n">Opcode</span><span class="p">(</span><span class="n">Opcode</span><span class="p">),</span> <span class="n">Operand</span><span class="p">(</span><span class="n">std</span><span class="o">::</span><span class="n">move</span><span class="p">(</span><span class="n">Operand</span><span class="p">))</span> <span class="p">{}</span>
+ <span class="n">Value</span> <span class="o">*</span><span class="n">codegen</span><span class="p">()</span> <span class="n">override</span><span class="p">;</span>
+ <span class="n">raw_ostream</span> <span class="o">&</span><span class="n">dump</span><span class="p">(</span><span class="n">raw_ostream</span> <span class="o">&</span><span class="n">out</span><span class="p">,</span> <span class="kt">int</span> <span class="n">ind</span><span class="p">)</span> <span class="n">override</span> <span class="p">{</span>
+ <span class="n">ExprAST</span><span class="o">::</span><span class="n">dump</span><span class="p">(</span><span class="n">out</span> <span class="o"><<</span> <span class="s">"unary"</span> <span class="o"><<</span> <span class="n">Opcode</span><span class="p">,</span> <span class="n">ind</span><span class="p">);</span>
+ <span class="n">Operand</span><span class="o">-></span><span class="n">dump</span><span class="p">(</span><span class="n">out</span><span class="p">,</span> <span class="n">ind</span> <span class="o">+</span> <span class="mi">1</span><span class="p">);</span>
+ <span class="k">return</span> <span class="n">out</span><span class="p">;</span>
+ <span class="p">}</span>
+<span class="p">};</span>
+
+<span class="c1">/// BinaryExprAST - Expression class for a binary operator.</span>
+<span class="k">class</span> <span class="nc">BinaryExprAST</span> <span class="o">:</span> <span class="k">public</span> <span class="n">ExprAST</span> <span class="p">{</span>
+ <span class="kt">char</span> <span class="n">Op</span><span class="p">;</span>
+ <span class="n">std</span><span class="o">::</span><span class="n">unique_ptr</span><span class="o"><</span><span class="n">ExprAST</span><span class="o">></span> <span class="n">LHS</span><span class="p">,</span> <span class="n">RHS</span><span class="p">;</span>
+
+<span class="nl">public:</span>
+ <span class="n">BinaryExprAST</span><span class="p">(</span><span class="n">SourceLocation</span> <span class="n">Loc</span><span class="p">,</span> <span class="kt">char</span> <span class="n">Op</span><span class="p">,</span> <span class="n">std</span><span class="o">::</span><span class="n">unique_ptr</span><span class="o"><</span><span class="n">ExprAST</span><span class="o">></span> <span class="n">LHS</span><span class="p">,</span>
+ <span class="n">std</span><span class="o">::</span><span class="n">unique_ptr</span><span class="o"><</span><span class="n">ExprAST</span><span class="o">></span> <span class="n">RHS</span><span class="p">)</span>
+ <span class="o">:</span> <span class="n">ExprAST</span><span class="p">(</span><span class="n">Loc</span><span class="p">),</span> <span class="n">Op</span><span class="p">(</span><span class="n">Op</span><span class="p">),</span> <span class="n">LHS</span><span class="p">(</span><span class="n">std</span><span class="o">::</span><span class="n">move</span><span class="p">(</span><span class="n">LHS</span><span class="p">)),</span> <span class="n">RHS</span><span class="p">(</span><span class="n">std</span><span class="o">::</span><span class="n">move</span><span class="p">(</span><span class="n">RHS</span><span class="p">))</span> <span class="p">{}</span>
+ <span class="n">Value</span> <span class="o">*</span><span class="n">codegen</span><span class="p">()</span> <span class="n">override</span><span class="p">;</span>
+ <span class="n">raw_ostream</span> <span class="o">&</span><span class="n">dump</span><span class="p">(</span><span class="n">raw_ostream</span> <span class="o">&</span><span class="n">out</span><span class="p">,</span> <span class="kt">int</span> <span class="n">ind</span><span class="p">)</span> <span class="n">override</span> <span class="p">{</span>
+ <span class="n">ExprAST</span><span class="o">::</span><span class="n">dump</span><span class="p">(</span><span class="n">out</span> <span class="o"><<</span> <span class="s">"binary"</span> <span class="o"><<</span> <span class="n">Op</span><span class="p">,</span> <span class="n">ind</span><span class="p">);</span>
+ <span class="n">LHS</span><span class="o">-></span><span class="n">dump</span><span class="p">(</span><span class="n">indent</span><span class="p">(</span><span class="n">out</span><span class="p">,</span> <span class="n">ind</span><span class="p">)</span> <span class="o"><<</span> <span class="s">"LHS:"</span><span class="p">,</span> <span class="n">ind</span> <span class="o">+</span> <span class="mi">1</span><span class="p">);</span>
+ <span class="n">RHS</span><span class="o">-></span><span class="n">dump</span><span class="p">(</span><span class="n">indent</span><span class="p">(</span><span class="n">out</span><span class="p">,</span> <span class="n">ind</span><span class="p">)</span> <span class="o"><<</span> <span class="s">"RHS:"</span><span class="p">,</span> <span class="n">ind</span> <span class="o">+</span> <span class="mi">1</span><span class="p">);</span>
+ <span class="k">return</span> <span class="n">out</span><span class="p">;</span>
+ <span class="p">}</span>
+<span class="p">};</span>
+
+<span class="c1">/// CallExprAST - Expression class for function calls.</span>
+<span class="k">class</span> <span class="nc">CallExprAST</span> <span class="o">:</span> <span class="k">public</span> <span class="n">ExprAST</span> <span class="p">{</span>
+ <span class="n">std</span><span class="o">::</span><span class="n">string</span> <span class="n">Callee</span><span class="p">;</span>
+ <span class="n">std</span><span class="o">::</span><span class="n">vector</span><span class="o"><</span><span class="n">std</span><span class="o">::</span><span class="n">unique_ptr</span><span class="o"><</span><span class="n">ExprAST</span><span class="o">>></span> <span class="n">Args</span><span class="p">;</span>
+
+<span class="nl">public:</span>
+ <span class="n">CallExprAST</span><span class="p">(</span><span class="n">SourceLocation</span> <span class="n">Loc</span><span class="p">,</span> <span class="k">const</span> <span class="n">std</span><span class="o">::</span><span class="n">string</span> <span class="o">&</span><span class="n">Callee</span><span class="p">,</span>
+ <span class="n">std</span><span class="o">::</span><span class="n">vector</span><span class="o"><</span><span class="n">std</span><span class="o">::</span><span class="n">unique_ptr</span><span class="o"><</span><span class="n">ExprAST</span><span class="o">>></span> <span class="n">Args</span><span class="p">)</span>
+ <span class="o">:</span> <span class="n">ExprAST</span><span class="p">(</span><span class="n">Loc</span><span class="p">),</span> <span class="n">Callee</span><span class="p">(</span><span class="n">Callee</span><span class="p">),</span> <span class="n">Args</span><span class="p">(</span><span class="n">std</span><span class="o">::</span><span class="n">move</span><span class="p">(</span><span class="n">Args</span><span class="p">))</span> <span class="p">{}</span>
+ <span class="n">Value</span> <span class="o">*</span><span class="n">codegen</span><span class="p">()</span> <span class="n">override</span><span class="p">;</span>
+ <span class="n">raw_ostream</span> <span class="o">&</span><span class="n">dump</span><span class="p">(</span><span class="n">raw_ostream</span> <span class="o">&</span><span class="n">out</span><span class="p">,</span> <span class="kt">int</span> <span class="n">ind</span><span class="p">)</span> <span class="n">override</span> <span class="p">{</span>
+ <span class="n">ExprAST</span><span class="o">::</span><span class="n">dump</span><span class="p">(</span><span class="n">out</span> <span class="o"><<</span> <span class="s">"call "</span> <span class="o"><<</span> <span class="n">Callee</span><span class="p">,</span> <span class="n">ind</span><span class="p">);</span>
+ <span class="k">for</span> <span class="p">(</span><span class="k">const</span> <span class="k">auto</span> <span class="o">&</span><span class="n">Arg</span> <span class="o">:</span> <span class="n">Args</span><span class="p">)</span>
+ <span class="n">Arg</span><span class="o">-></span><span class="n">dump</span><span class="p">(</span><span class="n">indent</span><span class="p">(</span><span class="n">out</span><span class="p">,</span> <span class="n">ind</span> <span class="o">+</span> <span class="mi">1</span><span class="p">),</span> <span class="n">ind</span> <span class="o">+</span> <span class="mi">1</span><span class="p">);</span>
+ <span class="k">return</span> <span class="n">out</span><span class="p">;</span>
+ <span class="p">}</span>
+<span class="p">};</span>
+
+<span class="c1">/// IfExprAST - Expression class for if/then/else.</span>
+<span class="k">class</span> <span class="nc">IfExprAST</span> <span class="o">:</span> <span class="k">public</span> <span class="n">ExprAST</span> <span class="p">{</span>
+ <span class="n">std</span><span class="o">::</span><span class="n">unique_ptr</span><span class="o"><</span><span class="n">ExprAST</span><span class="o">></span> <span class="n">Cond</span><span class="p">,</span> <span class="n">Then</span><span class="p">,</span> <span class="n">Else</span><span class="p">;</span>
+
+<span class="nl">public:</span>
+ <span class="n">IfExprAST</span><span class="p">(</span><span class="n">SourceLocation</span> <span class="n">Loc</span><span class="p">,</span> <span class="n">std</span><span class="o">::</span><span class="n">unique_ptr</span><span class="o"><</span><span class="n">ExprAST</span><span class="o">></span> <span class="n">Cond</span><span class="p">,</span>
+ <span class="n">std</span><span class="o">::</span><span class="n">unique_ptr</span><span class="o"><</span><span class="n">ExprAST</span><span class="o">></span> <span class="n">Then</span><span class="p">,</span> <span class="n">std</span><span class="o">::</span><span class="n">unique_ptr</span><span class="o"><</span><span class="n">ExprAST</span><span class="o">></span> <span class="n">Else</span><span class="p">)</span>
+ <span class="o">:</span> <span class="n">ExprAST</span><span class="p">(</span><span class="n">Loc</span><span class="p">),</span> <span class="n">Cond</span><span class="p">(</span><span class="n">std</span><span class="o">::</span><span class="n">move</span><span class="p">(</span><span class="n">Cond</span><span class="p">)),</span> <span class="n">Then</span><span class="p">(</span><span class="n">std</span><span class="o">::</span><span class="n">move</span><span class="p">(</span><span class="n">Then</span><span class="p">)),</span>
+ <span class="n">Else</span><span class="p">(</span><span class="n">std</span><span class="o">::</span><span class="n">move</span><span class="p">(</span><span class="n">Else</span><span class="p">))</span> <span class="p">{}</span>
+ <span class="n">Value</span> <span class="o">*</span><span class="n">codegen</span><span class="p">()</span> <span class="n">override</span><span class="p">;</span>
+ <span class="n">raw_ostream</span> <span class="o">&</span><span class="n">dump</span><span class="p">(</span><span class="n">raw_ostream</span> <span class="o">&</span><span class="n">out</span><span class="p">,</span> <span class="kt">int</span> <span class="n">ind</span><span class="p">)</span> <span class="n">override</span> <span class="p">{</span>
+ <span class="n">ExprAST</span><span class="o">::</span><span class="n">dump</span><span class="p">(</span><span class="n">out</span> <span class="o"><<</span> <span class="s">"if"</span><span class="p">,</span> <span class="n">ind</span><span class="p">);</span>
+ <span class="n">Cond</span><span class="o">-></span><span class="n">dump</span><span class="p">(</span><span class="n">indent</span><span class="p">(</span><span class="n">out</span><span class="p">,</span> <span class="n">ind</span><span class="p">)</span> <span class="o"><<</span> <span class="s">"Cond:"</span><span class="p">,</span> <span class="n">ind</span> <span class="o">+</span> <span class="mi">1</span><span class="p">);</span>
+ <span class="n">Then</span><span class="o">-></span><span class="n">dump</span><span class="p">(</span><span class="n">indent</span><span class="p">(</span><span class="n">out</span><span class="p">,</span> <span class="n">ind</span><span class="p">)</span> <span class="o"><<</span> <span class="s">"Then:"</span><span class="p">,</span> <span class="n">ind</span> <span class="o">+</span> <span class="mi">1</span><span class="p">);</span>
+ <span class="n">Else</span><span class="o">-></span><span class="n">dump</span><span class="p">(</span><span class="n">indent</span><span class="p">(</span><span class="n">out</span><span class="p">,</span> <span class="n">ind</span><span class="p">)</span> <span class="o"><<</span> <span class="s">"Else:"</span><span class="p">,</span> <span class="n">ind</span> <span class="o">+</span> <span class="mi">1</span><span class="p">);</span>
+ <span class="k">return</span> <span class="n">out</span><span class="p">;</span>
+ <span class="p">}</span>
+<span class="p">};</span>
+
+<span class="c1">/// ForExprAST - Expression class for for/in.</span>
+<span class="k">class</span> <span class="nc">ForExprAST</span> <span class="o">:</span> <span class="k">public</span> <span class="n">ExprAST</span> <span class="p">{</span>
+ <span class="n">std</span><span class="o">::</span><span class="n">string</span> <span class="n">VarName</span><span class="p">;</span>
+ <span class="n">std</span><span class="o">::</span><span class="n">unique_ptr</span><span class="o"><</span><span class="n">ExprAST</span><span class="o">></span> <span class="n">Start</span><span class="p">,</span> <span class="n">End</span><span class="p">,</span> <span class="n">Step</span><span class="p">,</span> <span class="n">Body</span><span class="p">;</span>
+
+<span class="nl">public:</span>
+ <span class="n">ForExprAST</span><span class="p">(</span><span class="k">const</span> <span class="n">std</span><span class="o">::</span><span class="n">string</span> <span class="o">&</span><span class="n">VarName</span><span class="p">,</span> <span class="n">std</span><span class="o">::</span><span class="n">unique_ptr</span><span class="o"><</span><span class="n">ExprAST</span><span class="o">></span> <span class="n">Start</span><span class="p">,</span>
+ <span class="n">std</span><span class="o">::</span><span class="n">unique_ptr</span><span class="o"><</span><span class="n">ExprAST</span><span class="o">></span> <span class="n">End</span><span class="p">,</span> <span class="n">std</span><span class="o">::</span><span class="n">unique_ptr</span><span class="o"><</span><span class="n">ExprAST</span><span class="o">></span> <span class="n">Step</span><span class="p">,</span>
+ <span class="n">std</span><span class="o">::</span><span class="n">unique_ptr</span><span class="o"><</span><span class="n">ExprAST</span><span class="o">></span> <span class="n">Body</span><span class="p">)</span>
+ <span class="o">:</span> <span class="n">VarName</span><span class="p">(</span><span class="n">VarName</span><span class="p">),</span> <span class="n">Start</span><span class="p">(</span><span class="n">std</span><span class="o">::</span><span class="n">move</span><span class="p">(</span><span class="n">Start</span><span class="p">)),</span> <span class="n">End</span><span class="p">(</span><span class="n">std</span><span class="o">::</span><span class="n">move</span><span class="p">(</span><span class="n">End</span><span class="p">)),</span>
+ <span class="n">Step</span><span class="p">(</span><span class="n">std</span><span class="o">::</span><span class="n">move</span><span class="p">(</span><span class="n">Step</span><span class="p">)),</span> <span class="n">Body</span><span class="p">(</span><span class="n">std</span><span class="o">::</span><span class="n">move</span><span class="p">(</span><span class="n">Body</span><span class="p">))</span> <span class="p">{}</span>
+ <span class="n">Value</span> <span class="o">*</span><span class="n">codegen</span><span class="p">()</span> <span class="n">override</span><span class="p">;</span>
+ <span class="n">raw_ostream</span> <span class="o">&</span><span class="n">dump</span><span class="p">(</span><span class="n">raw_ostream</span> <span class="o">&</span><span class="n">out</span><span class="p">,</span> <span class="kt">int</span> <span class="n">ind</span><span class="p">)</span> <span class="n">override</span> <span class="p">{</span>
+ <span class="n">ExprAST</span><span class="o">::</span><span class="n">dump</span><span class="p">(</span><span class="n">out</span> <span class="o"><<</span> <span class="s">"for"</span><span class="p">,</span> <span class="n">ind</span><span class="p">);</span>
+ <span class="n">Start</span><span class="o">-></span><span class="n">dump</span><span class="p">(</span><span class="n">indent</span><span class="p">(</span><span class="n">out</span><span class="p">,</span> <span class="n">ind</span><span class="p">)</span> <span class="o"><<</span> <span class="s">"Cond:"</span><span class="p">,</span> <span class="n">ind</span> <span class="o">+</span> <span class="mi">1</span><span class="p">);</span>
+ <span class="n">End</span><span class="o">-></span><span class="n">dump</span><span class="p">(</span><span class="n">indent</span><span class="p">(</span><span class="n">out</span><span class="p">,</span> <span class="n">ind</span><span class="p">)</span> <span class="o"><<</span> <span class="s">"End:"</span><span class="p">,</span> <span class="n">ind</span> <span class="o">+</span> <span class="mi">1</span><span class="p">);</span>
+ <span class="n">Step</span><span class="o">-></span><span class="n">dump</span><span class="p">(</span><span class="n">indent</span><span class="p">(</span><span class="n">out</span><span class="p">,</span> <span class="n">ind</span><span class="p">)</span> <span class="o"><<</span> <span class="s">"Step:"</span><span class="p">,</span> <span class="n">ind</span> <span class="o">+</span> <span class="mi">1</span><span class="p">);</span>
+ <span class="n">Body</span><span class="o">-></span><span class="n">dump</span><span class="p">(</span><span class="n">indent</span><span class="p">(</span><span class="n">out</span><span class="p">,</span> <span class="n">ind</span><span class="p">)</span> <span class="o"><<</span> <span class="s">"Body:"</span><span class="p">,</span> <span class="n">ind</span> <span class="o">+</span> <span class="mi">1</span><span class="p">);</span>
+ <span class="k">return</span> <span class="n">out</span><span class="p">;</span>
+ <span class="p">}</span>
+<span class="p">};</span>
+
+<span class="c1">/// VarExprAST - Expression class for var/in</span>
+<span class="k">class</span> <span class="nc">VarExprAST</span> <span class="o">:</span> <span class="k">public</span> <span class="n">ExprAST</span> <span class="p">{</span>
+ <span class="n">std</span><span class="o">::</span><span class="n">vector</span><span class="o"><</span><span class="n">std</span><span class="o">::</span><span class="n">pair</span><span class="o"><</span><span class="n">std</span><span class="o">::</span><span class="n">string</span><span class="p">,</span> <span class="n">std</span><span class="o">::</span><span class="n">unique_ptr</span><span class="o"><</span><span class="n">ExprAST</span><span class="o">>>></span> <span class="n">VarNames</span><span class="p">;</span>
+ <span class="n">std</span><span class="o">::</span><span class="n">unique_ptr</span><span class="o"><</span><span class="n">ExprAST</span><span class="o">></span> <span class="n">Body</span><span class="p">;</span>
+
+<span class="nl">public:</span>
+ <span class="n">VarExprAST</span><span class="p">(</span>
+ <span class="n">std</span><span class="o">::</span><span class="n">vector</span><span class="o"><</span><span class="n">std</span><span class="o">::</span><span class="n">pair</span><span class="o"><</span><span class="n">std</span><span class="o">::</span><span class="n">string</span><span class="p">,</span> <span class="n">std</span><span class="o">::</span><span class="n">unique_ptr</span><span class="o"><</span><span class="n">ExprAST</span><span class="o">>>></span> <span class="n">VarNames</span><span class="p">,</span>
+ <span class="n">std</span><span class="o">::</span><span class="n">unique_ptr</span><span class="o"><</span><span class="n">ExprAST</span><span class="o">></span> <span class="n">Body</span><span class="p">)</span>
+ <span class="o">:</span> <span class="n">VarNames</span><span class="p">(</span><span class="n">std</span><span class="o">::</span><span class="n">move</span><span class="p">(</span><span class="n">VarNames</span><span class="p">)),</span> <span class="n">Body</span><span class="p">(</span><span class="n">std</span><span class="o">::</span><span class="n">move</span><span class="p">(</span><span class="n">Body</span><span class="p">))</span> <span class="p">{}</span>
+ <span class="n">Value</span> <span class="o">*</span><span class="n">codegen</span><span class="p">()</span> <span class="n">override</span><span class="p">;</span>
+ <span class="n">raw_ostream</span> <span class="o">&</span><span class="n">dump</span><span class="p">(</span><span class="n">raw_ostream</span> <span class="o">&</span><span class="n">out</span><span class="p">,</span> <span class="kt">int</span> <span class="n">ind</span><span class="p">)</span> <span class="n">override</span> <span class="p">{</span>
+ <span class="n">ExprAST</span><span class="o">::</span><span class="n">dump</span><span class="p">(</span><span class="n">out</span> <span class="o"><<</span> <span class="s">"var"</span><span class="p">,</span> <span class="n">ind</span><span class="p">);</span>
+ <span class="k">for</span> <span class="p">(</span><span class="k">const</span> <span class="k">auto</span> <span class="o">&</span><span class="n">NamedVar</span> <span class="o">:</span> <span class="n">VarNames</span><span class="p">)</span>
+ <span class="n">NamedVar</span><span class="p">.</span><span class="n">second</span><span class="o">-></span><span class="n">dump</span><span class="p">(</span><span class="n">indent</span><span class="p">(</span><span class="n">out</span><span class="p">,</span> <span class="n">ind</span><span class="p">)</span> <span class="o"><<</span> <span class="n">NamedVar</span><span class="p">.</span><span class="n">first</span> <span class="o"><<</span> <span class="sc">':'</span><span class="p">,</span> <span class="n">ind</span> <span class="o">+</span> <span class="mi">1</span><span class="p">);</span>
+ <span class="n">Body</span><span class="o">-></span><span class="n">dump</span><span class="p">(</span><span class="n">indent</span><span class="p">(</span><span class="n">out</span><span class="p">,</span> <span class="n">ind</span><span class="p">)</span> <span class="o"><<</span> <span class="s">"Body:"</span><span class="p">,</span> <span class="n">ind</span> <span class="o">+</span> <span class="mi">1</span><span class="p">);</span>
+ <span class="k">return</span> <span class="n">out</span><span class="p">;</span>
+ <span class="p">}</span>
+<span class="p">};</span>
+
+<span class="c1">/// PrototypeAST - This class represents the "prototype" for a function,</span>
+<span class="c1">/// which captures its name, and its argument names (thus implicitly the number</span>
+<span class="c1">/// of arguments the function takes), as well as if it is an operator.</span>
+<span class="k">class</span> <span class="nc">PrototypeAST</span> <span class="p">{</span>
+ <span class="n">std</span><span class="o">::</span><span class="n">string</span> <span class="n">Name</span><span class="p">;</span>
+ <span class="n">std</span><span class="o">::</span><span class="n">vector</span><span class="o"><</span><span class="n">std</span><span class="o">::</span><span class="n">string</span><span class="o">></span> <span class="n">Args</span><span class="p">;</span>
+ <span class="kt">bool</span> <span class="n">IsOperator</span><span class="p">;</span>
+ <span class="kt">unsigned</span> <span class="n">Precedence</span><span class="p">;</span> <span class="c1">// Precedence if a binary op.</span>
+ <span class="kt">int</span> <span class="n">Line</span><span class="p">;</span>
+
+<span class="nl">public:</span>
+ <span class="n">PrototypeAST</span><span class="p">(</span><span class="n">SourceLocation</span> <span class="n">Loc</span><span class="p">,</span> <span class="k">const</span> <span class="n">std</span><span class="o">::</span><span class="n">string</span> <span class="o">&</span><span class="n">Name</span><span class="p">,</span>
+ <span class="n">std</span><span class="o">::</span><span class="n">vector</span><span class="o"><</span><span class="n">std</span><span class="o">::</span><span class="n">string</span><span class="o">></span> <span class="n">Args</span><span class="p">,</span> <span class="kt">bool</span> <span class="n">IsOperator</span> <span class="o">=</span> <span class="nb">false</span><span class="p">,</span>
+ <span class="kt">unsigned</span> <span class="n">Prec</span> <span class="o">=</span> <span class="mi">0</span><span class="p">)</span>
+ <span class="o">:</span> <span class="n">Name</span><span class="p">(</span><span class="n">Name</span><span class="p">),</span> <span class="n">Args</span><span class="p">(</span><span class="n">std</span><span class="o">::</span><span class="n">move</span><span class="p">(</span><span class="n">Args</span><span class="p">)),</span> <span class="n">IsOperator</span><span class="p">(</span><span class="n">IsOperator</span><span class="p">),</span>
+ <span class="n">Precedence</span><span class="p">(</span><span class="n">Prec</span><span class="p">),</span> <span class="n">Line</span><span class="p">(</span><span class="n">Loc</span><span class="p">.</span><span class="n">Line</span><span class="p">)</span> <span class="p">{}</span>
+ <span class="n">Function</span> <span class="o">*</span><span class="n">codegen</span><span class="p">();</span>
+ <span class="k">const</span> <span class="n">std</span><span class="o">::</span><span class="n">string</span> <span class="o">&</span><span class="n">getName</span><span class="p">()</span> <span class="k">const</span> <span class="p">{</span> <span class="k">return</span> <span class="n">Name</span><span class="p">;</span> <span class="p">}</span>
+
+ <span class="kt">bool</span> <span class="n">isUnaryOp</span><span class="p">()</span> <span class="k">const</span> <span class="p">{</span> <span class="k">return</span> <span class="n">IsOperator</span> <span class="o">&&</span> <span class="n">Args</span><span class="p">.</span><span class="n">size</span><span class="p">()</span> <span class="o">==</span> <span class="mi">1</span><span class="p">;</span> <span class="p">}</span>
+ <span class="kt">bool</span> <span class="n">isBinaryOp</span><span class="p">()</span> <span class="k">const</span> <span class="p">{</span> <span class="k">return</span> <span class="n">IsOperator</span> <span class="o">&&</span> <span class="n">Args</span><span class="p">.</span><span class="n">size</span><span class="p">()</span> <span class="o">==</span> <span class="mi">2</span><span class="p">;</span> <span class="p">}</span>
+
+ <span class="kt">char</span> <span class="n">getOperatorName</span><span class="p">()</span> <span class="k">const</span> <span class="p">{</span>
+ <span class="n">assert</span><span class="p">(</span><span class="n">isUnaryOp</span><span class="p">()</span> <span class="o">||</span> <span class="n">isBinaryOp</span><span class="p">());</span>
+ <span class="k">return</span> <span class="n">Name</span><span class="p">[</span><span class="n">Name</span><span class="p">.</span><span class="n">size</span><span class="p">()</span> <span class="o">-</span> <span class="mi">1</span><span class="p">];</span>
+ <span class="p">}</span>
+
+ <span class="kt">unsigned</span> <span class="n">getBinaryPrecedence</span><span class="p">()</span> <span class="k">const</span> <span class="p">{</span> <span class="k">return</span> <span class="n">Precedence</span><span class="p">;</span> <span class="p">}</span>
+ <span class="kt">int</span> <span class="n">getLine</span><span class="p">()</span> <span class="k">const</span> <span class="p">{</span> <span class="k">return</span> <span class="n">Line</span><span class="p">;</span> <span class="p">}</span>
+<span class="p">};</span>
+
+<span class="c1">/// FunctionAST - This class represents a function definition itself.</span>
+<span class="k">class</span> <span class="nc">FunctionAST</span> <span class="p">{</span>
+ <span class="n">std</span><span class="o">::</span><span class="n">unique_ptr</span><span class="o"><</span><span class="n">PrototypeAST</span><span class="o">></span> <span class="n">Proto</span><span class="p">;</span>
+ <span class="n">std</span><span class="o">::</span><span class="n">unique_ptr</span><span class="o"><</span><span class="n">ExprAST</span><span class="o">></span> <span class="n">Body</span><span class="p">;</span>
+
+<span class="nl">public:</span>
+ <span class="n">FunctionAST</span><span class="p">(</span><span class="n">std</span><span class="o">::</span><span class="n">unique_ptr</span><span class="o"><</span><span class="n">PrototypeAST</span><span class="o">></span> <span class="n">Proto</span><span class="p">,</span>
+ <span class="n">std</span><span class="o">::</span><span class="n">unique_ptr</span><span class="o"><</span><span class="n">ExprAST</span><span class="o">></span> <span class="n">Body</span><span class="p">)</span>
+ <span class="o">:</span> <span class="n">Proto</span><span class="p">(</span><span class="n">std</span><span class="o">::</span><span class="n">move</span><span class="p">(</span><span class="n">Proto</span><span class="p">)),</span> <span class="n">Body</span><span class="p">(</span><span class="n">std</span><span class="o">::</span><span class="n">move</span><span class="p">(</span><span class="n">Body</span><span class="p">))</span> <span class="p">{}</span>
+ <span class="n">Function</span> <span class="o">*</span><span class="n">codegen</span><span class="p">();</span>
+ <span class="n">raw_ostream</span> <span class="o">&</span><span class="n">dump</span><span class="p">(</span><span class="n">raw_ostream</span> <span class="o">&</span><span class="n">out</span><span class="p">,</span> <span class="kt">int</span> <span class="n">ind</span><span class="p">)</span> <span class="p">{</span>
+ <span class="n">indent</span><span class="p">(</span><span class="n">out</span><span class="p">,</span> <span class="n">ind</span><span class="p">)</span> <span class="o"><<</span> <span class="s">"FunctionAST</span><span class="se">\n</span><span class="s">"</span><span class="p">;</span>
+ <span class="o">++</span><span class="n">ind</span><span class="p">;</span>
+ <span class="n">indent</span><span class="p">(</span><span class="n">out</span><span class="p">,</span> <span class="n">ind</span><span class="p">)</span> <span class="o"><<</span> <span class="s">"Body:"</span><span class="p">;</span>
+ <span class="k">return</span> <span class="n">Body</span> <span class="o">?</span> <span class="n">Body</span><span class="o">-></span><span class="n">dump</span><span class="p">(</span><span class="n">out</span><span class="p">,</span> <span class="n">ind</span><span class="p">)</span> <span class="o">:</span> <span class="n">out</span> <span class="o"><<</span> <span class="s">"null</span><span class="se">\n</span><span class="s">"</span><span class="p">;</span>
+ <span class="p">}</span>
+<span class="p">};</span>
+<span class="p">}</span> <span class="c1">// end anonymous namespace</span>
+
+<span class="c1">//===----------------------------------------------------------------------===//</span>
+<span class="c1">// Parser</span>
+<span class="c1">//===----------------------------------------------------------------------===//</span>
+
+<span class="c1">/// CurTok/getNextToken - Provide a simple token buffer. CurTok is the current</span>
+<span class="c1">/// token the parser is looking at. getNextToken reads another token from the</span>
+<span class="c1">/// lexer and updates CurTok with its results.</span>
+<span class="k">static</span> <span class="kt">int</span> <span class="n">CurTok</span><span class="p">;</span>
+<span class="k">static</span> <span class="kt">int</span> <span class="nf">getNextToken</span><span class="p">()</span> <span class="p">{</span> <span class="k">return</span> <span class="n">CurTok</span> <span class="o">=</span> <span class="n">gettok</span><span class="p">();</span> <span class="p">}</span>
+
+<span class="c1">/// BinopPrecedence - This holds the precedence for each binary operator that is</span>
+<span class="c1">/// defined.</span>
+<span class="k">static</span> <span class="n">std</span><span class="o">::</span><span class="n">map</span><span class="o"><</span><span class="kt">char</span><span class="p">,</span> <span class="kt">int</span><span class="o">></span> <span class="n">BinopPrecedence</span><span class="p">;</span>
+
+<span class="c1">/// GetTokPrecedence - Get the precedence of the pending binary operator token.</span>
+<span class="k">static</span> <span class="kt">int</span> <span class="nf">GetTokPrecedence</span><span class="p">()</span> <span class="p">{</span>
+ <span class="k">if</span> <span class="p">(</span><span class="o">!</span><span class="n">isascii</span><span class="p">(</span><span class="n">CurTok</span><span class="p">))</span>
+ <span class="k">return</span> <span class="o">-</span><span class="mi">1</span><span class="p">;</span>
+
+ <span class="c1">// Make sure it's a declared binop.</span>
+ <span class="kt">int</span> <span class="n">TokPrec</span> <span class="o">=</span> <span class="n">BinopPrecedence</span><span class="p">[</span><span class="n">CurTok</span><span class="p">];</span>
+ <span class="k">if</span> <span class="p">(</span><span class="n">TokPrec</span> <span class="o"><=</span> <span class="mi">0</span><span class="p">)</span>
+ <span class="k">return</span> <span class="o">-</span><span class="mi">1</span><span class="p">;</span>
+ <span class="k">return</span> <span class="n">TokPrec</span><span class="p">;</span>
+<span class="p">}</span>
+
+<span class="c1">/// Error* - These are little helper functions for error handling.</span>
+<span class="n">std</span><span class="o">::</span><span class="n">unique_ptr</span><span class="o"><</span><span class="n">ExprAST</span><span class="o">></span> <span class="n">Error</span><span class="p">(</span><span class="k">const</span> <span class="kt">char</span> <span class="o">*</span><span class="n">Str</span><span class="p">)</span> <span class="p">{</span>
+ <span class="n">fprintf</span><span class="p">(</span><span class="n">stderr</span><span class="p">,</span> <span class="s">"Error: %s</span><span class="se">\n</span><span class="s">"</span><span class="p">,</span> <span class="n">Str</span><span class="p">);</span>
+ <span class="k">return</span> <span class="n">nullptr</span><span class="p">;</span>
+<span class="p">}</span>
+
+<span class="n">std</span><span class="o">::</span><span class="n">unique_ptr</span><span class="o"><</span><span class="n">PrototypeAST</span><span class="o">></span> <span class="n">ErrorP</span><span class="p">(</span><span class="k">const</span> <span class="kt">char</span> <span class="o">*</span><span class="n">Str</span><span class="p">)</span> <span class="p">{</span>
+ <span class="n">Error</span><span class="p">(</span><span class="n">Str</span><span class="p">);</span>
+ <span class="k">return</span> <span class="n">nullptr</span><span class="p">;</span>
+<span class="p">}</span>
+
+<span class="k">static</span> <span class="n">std</span><span class="o">::</span><span class="n">unique_ptr</span><span class="o"><</span><span class="n">ExprAST</span><span class="o">></span> <span class="n">ParseExpression</span><span class="p">();</span>
+
+<span class="c1">/// numberexpr ::= number</span>
+<span class="k">static</span> <span class="n">std</span><span class="o">::</span><span class="n">unique_ptr</span><span class="o"><</span><span class="n">ExprAST</span><span class="o">></span> <span class="n">ParseNumberExpr</span><span class="p">()</span> <span class="p">{</span>
+ <span class="k">auto</span> <span class="n">Result</span> <span class="o">=</span> <span class="n">llvm</span><span class="o">::</span><span class="n">make_unique</span><span class="o"><</span><span class="n">NumberExprAST</span><span class="o">></span><span class="p">(</span><span class="n">NumVal</span><span class="p">);</span>
+ <span class="n">getNextToken</span><span class="p">();</span> <span class="c1">// consume the number</span>
+ <span class="k">return</span> <span class="n">std</span><span class="o">::</span><span class="n">move</span><span class="p">(</span><span class="n">Result</span><span class="p">);</span>
+<span class="p">}</span>
+
+<span class="c1">/// parenexpr ::= '(' expression ')'</span>
+<span class="k">static</span> <span class="n">std</span><span class="o">::</span><span class="n">unique_ptr</span><span class="o"><</span><span class="n">ExprAST</span><span class="o">></span> <span class="n">ParseParenExpr</span><span class="p">()</span> <span class="p">{</span>
+ <span class="n">getNextToken</span><span class="p">();</span> <span class="c1">// eat (.</span>
+ <span class="k">auto</span> <span class="n">V</span> <span class="o">=</span> <span class="n">ParseExpression</span><span class="p">();</span>
+ <span class="k">if</span> <span class="p">(</span><span class="o">!</span><span class="n">V</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">nullptr</span><span class="p">;</span>
+
+ <span class="k">if</span> <span class="p">(</span><span class="n">CurTok</span> <span class="o">!=</span> <span class="sc">')'</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">Error</span><span class="p">(</span><span class="s">"expected ')'"</span><span class="p">);</span>
+ <span class="n">getNextToken</span><span class="p">();</span> <span class="c1">// eat ).</span>
+ <span class="k">return</span> <span class="n">V</span><span class="p">;</span>
+<span class="p">}</span>
+
+<span class="c1">/// identifierexpr</span>
+<span class="c1">/// ::= identifier</span>
+<span class="c1">/// ::= identifier '(' expression* ')'</span>
+<span class="k">static</span> <span class="n">std</span><span class="o">::</span><span class="n">unique_ptr</span><span class="o"><</span><span class="n">ExprAST</span><span class="o">></span> <span class="n">ParseIdentifierExpr</span><span class="p">()</span> <span class="p">{</span>
+ <span class="n">std</span><span class="o">::</span><span class="n">string</span> <span class="n">IdName</span> <span class="o">=</span> <span class="n">IdentifierStr</span><span class="p">;</span>
+
+ <span class="n">SourceLocation</span> <span class="n">LitLoc</span> <span class="o">=</span> <span class="n">CurLoc</span><span class="p">;</span>
+
+ <span class="n">getNextToken</span><span class="p">();</span> <span class="c1">// eat identifier.</span>
+
+ <span class="k">if</span> <span class="p">(</span><span class="n">CurTok</span> <span class="o">!=</span> <span class="sc">'('</span><span class="p">)</span> <span class="c1">// Simple variable ref.</span>
+ <span class="k">return</span> <span class="n">llvm</span><span class="o">::</span><span class="n">make_unique</span><span class="o"><</span><span class="n">VariableExprAST</span><span class="o">></span><span class="p">(</span><span class="n">LitLoc</span><span class="p">,</span> <span class="n">IdName</span><span class="p">);</span>
+
+ <span class="c1">// Call.</span>
+ <span class="n">getNextToken</span><span class="p">();</span> <span class="c1">// eat (</span>
+ <span class="n">std</span><span class="o">::</span><span class="n">vector</span><span class="o"><</span><span class="n">std</span><span class="o">::</span><span class="n">unique_ptr</span><span class="o"><</span><span class="n">ExprAST</span><span class="o">>></span> <span class="n">Args</span><span class="p">;</span>
+ <span class="k">if</span> <span class="p">(</span><span class="n">CurTok</span> <span class="o">!=</span> <span class="sc">')'</span><span class="p">)</span> <span class="p">{</span>
+ <span class="k">while</span> <span class="p">(</span><span class="mi">1</span><span class="p">)</span> <span class="p">{</span>
+ <span class="k">if</span> <span class="p">(</span><span class="k">auto</span> <span class="n">Arg</span> <span class="o">=</span> <span class="n">ParseExpression</span><span class="p">())</span>
+ <span class="n">Args</span><span class="p">.</span><span class="n">push_back</span><span class="p">(</span><span class="n">std</span><span class="o">::</span><span class="n">move</span><span class="p">(</span><span class="n">Arg</span><span class="p">));</span>
+ <span class="k">else</span>
+ <span class="k">return</span> <span class="n">nullptr</span><span class="p">;</span>
+
+ <span class="k">if</span> <span class="p">(</span><span class="n">CurTok</span> <span class="o">==</span> <span class="sc">')'</span><span class="p">)</span>
+ <span class="k">break</span><span class="p">;</span>
+
+ <span class="k">if</span> <span class="p">(</span><span class="n">CurTok</span> <span class="o">!=</span> <span class="sc">','</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">Error</span><span class="p">(</span><span class="s">"Expected ')' or ',' in argument list"</span><span class="p">);</span>
+ <span class="n">getNextToken</span><span class="p">();</span>
+ <span class="p">}</span>
+ <span class="p">}</span>
+
+ <span class="c1">// Eat the ')'.</span>
+ <span class="n">getNextToken</span><span class="p">();</span>
+
+ <span class="k">return</span> <span class="n">llvm</span><span class="o">::</span><span class="n">make_unique</span><span class="o"><</span><span class="n">CallExprAST</span><span class="o">></span><span class="p">(</span><span class="n">LitLoc</span><span class="p">,</span> <span class="n">IdName</span><span class="p">,</span> <span class="n">std</span><span class="o">::</span><span class="n">move</span><span class="p">(</span><span class="n">Args</span><span class="p">));</span>
+<span class="p">}</span>
+
+<span class="c1">/// ifexpr ::= 'if' expression 'then' expression 'else' expression</span>
+<span class="k">static</span> <span class="n">std</span><span class="o">::</span><span class="n">unique_ptr</span><span class="o"><</span><span class="n">ExprAST</span><span class="o">></span> <span class="n">ParseIfExpr</span><span class="p">()</span> <span class="p">{</span>
+ <span class="n">SourceLocation</span> <span class="n">IfLoc</span> <span class="o">=</span> <span class="n">CurLoc</span><span class="p">;</span>
+
+ <span class="n">getNextToken</span><span class="p">();</span> <span class="c1">// eat the if.</span>
+
+ <span class="c1">// condition.</span>
+ <span class="k">auto</span> <span class="n">Cond</span> <span class="o">=</span> <span class="n">ParseExpression</span><span class="p">();</span>
+ <span class="k">if</span> <span class="p">(</span><span class="o">!</span><span class="n">Cond</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">nullptr</span><span class="p">;</span>
+
+ <span class="k">if</span> <span class="p">(</span><span class="n">CurTok</span> <span class="o">!=</span> <span class="n">tok_then</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">Error</span><span class="p">(</span><span class="s">"expected then"</span><span class="p">);</span>
+ <span class="n">getNextToken</span><span class="p">();</span> <span class="c1">// eat the then</span>
+
+ <span class="k">auto</span> <span class="n">Then</span> <span class="o">=</span> <span class="n">ParseExpression</span><span class="p">();</span>
+ <span class="k">if</span> <span class="p">(</span><span class="o">!</span><span class="n">Then</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">nullptr</span><span class="p">;</span>
+
+ <span class="k">if</span> <span class="p">(</span><span class="n">CurTok</span> <span class="o">!=</span> <span class="n">tok_else</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">Error</span><span class="p">(</span><span class="s">"expected else"</span><span class="p">);</span>
+
+ <span class="n">getNextToken</span><span class="p">();</span>
+
+ <span class="k">auto</span> <span class="n">Else</span> <span class="o">=</span> <span class="n">ParseExpression</span><span class="p">();</span>
+ <span class="k">if</span> <span class="p">(</span><span class="o">!</span><span class="n">Else</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">nullptr</span><span class="p">;</span>
+
+ <span class="k">return</span> <span class="n">llvm</span><span class="o">::</span><span class="n">make_unique</span><span class="o"><</span><span class="n">IfExprAST</span><span class="o">></span><span class="p">(</span><span class="n">IfLoc</span><span class="p">,</span> <span class="n">std</span><span class="o">::</span><span class="n">move</span><span class="p">(</span><span class="n">Cond</span><span class="p">),</span> <span class="n">std</span><span class="o">::</span><span class="n">move</span><span class="p">(</span><span class="n">Then</span><span class="p">),</span>
+ <span class="n">std</span><span class="o">::</span><span class="n">move</span><span class="p">(</span><span class="n">Else</span><span class="p">));</span>
+<span class="p">}</span>
+
+<span class="c1">/// forexpr ::= 'for' identifier '=' expr ',' expr (',' expr)? 'in' expression</span>
+<span class="k">static</span> <span class="n">std</span><span class="o">::</span><span class="n">unique_ptr</span><span class="o"><</span><span class="n">ExprAST</span><span class="o">></span> <span class="n">ParseForExpr</span><span class="p">()</span> <span class="p">{</span>
+ <span class="n">getNextToken</span><span class="p">();</span> <span class="c1">// eat the for.</span>
+
+ <span class="k">if</span> <span class="p">(</span><span class="n">CurTok</span> <span class="o">!=</span> <span class="n">tok_identifier</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">Error</span><span class="p">(</span><span class="s">"expected identifier after for"</span><span class="p">);</span>
+
+ <span class="n">std</span><span class="o">::</span><span class="n">string</span> <span class="n">IdName</span> <span class="o">=</span> <span class="n">IdentifierStr</span><span class="p">;</span>
+ <span class="n">getNextToken</span><span class="p">();</span> <span class="c1">// eat identifier.</span>
+
+ <span class="k">if</span> <span class="p">(</span><span class="n">CurTok</span> <span class="o">!=</span> <span class="sc">'='</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">Error</span><span class="p">(</span><span class="s">"expected '=' after for"</span><span class="p">);</span>
+ <span class="n">getNextToken</span><span class="p">();</span> <span class="c1">// eat '='.</span>
+
+ <span class="k">auto</span> <span class="n">Start</span> <span class="o">=</span> <span class="n">ParseExpression</span><span class="p">();</span>
+ <span class="k">if</span> <span class="p">(</span><span class="o">!</span><span class="n">Start</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">nullptr</span><span class="p">;</span>
+ <span class="k">if</span> <span class="p">(</span><span class="n">CurTok</span> <span class="o">!=</span> <span class="sc">','</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">Error</span><span class="p">(</span><span class="s">"expected ',' after for start value"</span><span class="p">);</span>
+ <span class="n">getNextToken</span><span class="p">();</span>
+
+ <span class="k">auto</span> <span class="n">End</span> <span class="o">=</span> <span class="n">ParseExpression</span><span class="p">();</span>
+ <span class="k">if</span> <span class="p">(</span><span class="o">!</span><span class="n">End</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">nullptr</span><span class="p">;</span>
+
+ <span class="c1">// The step value is optional.</span>
+ <span class="n">std</span><span class="o">::</span><span class="n">unique_ptr</span><span class="o"><</span><span class="n">ExprAST</span><span class="o">></span> <span class="n">Step</span><span class="p">;</span>
+ <span class="k">if</span> <span class="p">(</span><span class="n">CurTok</span> <span class="o">==</span> <span class="sc">','</span><span class="p">)</span> <span class="p">{</span>
+ <span class="n">getNextToken</span><span class="p">();</span>
+ <span class="n">Step</span> <span class="o">=</span> <span class="n">ParseExpression</span><span class="p">();</span>
+ <span class="k">if</span> <span class="p">(</span><span class="o">!</span><span class="n">Step</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">nullptr</span><span class="p">;</span>
+ <span class="p">}</span>
+
+ <span class="k">if</span> <span class="p">(</span><span class="n">CurTok</span> <span class="o">!=</span> <span class="n">tok_in</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">Error</span><span class="p">(</span><span class="s">"expected 'in' after for"</span><span class="p">);</span>
+ <span class="n">getNextToken</span><span class="p">();</span> <span class="c1">// eat 'in'.</span>
+
+ <span class="k">auto</span> <span class="n">Body</span> <span class="o">=</span> <span class="n">ParseExpression</span><span class="p">();</span>
+ <span class="k">if</span> <span class="p">(</span><span class="o">!</span><span class="n">Body</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">nullptr</span><span class="p">;</span>
+
+ <span class="k">return</span> <span class="n">llvm</span><span class="o">::</span><span class="n">make_unique</span><span class="o"><</span><span class="n">ForExprAST</span><span class="o">></span><span class="p">(</span><span class="n">IdName</span><span class="p">,</span> <span class="n">std</span><span class="o">::</span><span class="n">move</span><span class="p">(</span><span class="n">Start</span><span class="p">),</span> <span class="n">std</span><span class="o">::</span><span class="n">move</span><span class="p">(</span><span class="n">End</span><span class="p">),</span>
+ <span class="n">std</span><span class="o">::</span><span class="n">move</span><span class="p">(</span><span class="n">Step</span><span class="p">),</span> <span class="n">std</span><span class="o">::</span><span class="n">move</span><span class="p">(</span><span class="n">Body</span><span class="p">));</span>
+<span class="p">}</span>
+
+<span class="c1">/// varexpr ::= 'var' identifier ('=' expression)?</span>
+<span class="c1">// (',' identifier ('=' expression)?)* 'in' expression</span>
+<span class="k">static</span> <span class="n">std</span><span class="o">::</span><span class="n">unique_ptr</span><span class="o"><</span><span class="n">ExprAST</span><span class="o">></span> <span class="n">ParseVarExpr</span><span class="p">()</span> <span class="p">{</span>
+ <span class="n">getNextToken</span><span class="p">();</span> <span class="c1">// eat the var.</span>
+
+ <span class="n">std</span><span class="o">::</span><span class="n">vector</span><span class="o"><</span><span class="n">std</span><span class="o">::</span><span class="n">pair</span><span class="o"><</span><span class="n">std</span><span class="o">::</span><span class="n">string</span><span class="p">,</span> <span class="n">std</span><span class="o">::</span><span class="n">unique_ptr</span><span class="o"><</span><span class="n">ExprAST</span><span class="o">>>></span> <span class="n">VarNames</span><span class="p">;</span>
+
+ <span class="c1">// At least one variable name is required.</span>
+ <span class="k">if</span> <span class="p">(</span><span class="n">CurTok</span> <span class="o">!=</span> <span class="n">tok_identifier</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">Error</span><span class="p">(</span><span class="s">"expected identifier after var"</span><span class="p">);</span>
+
+ <span class="k">while</span> <span class="p">(</span><span class="mi">1</span><span class="p">)</span> <span class="p">{</span>
+ <span class="n">std</span><span class="o">::</span><span class="n">string</span> <span class="n">Name</span> <span class="o">=</span> <span class="n">IdentifierStr</span><span class="p">;</span>
+ <span class="n">getNextToken</span><span class="p">();</span> <span class="c1">// eat identifier.</span>
+
+ <span class="c1">// Read the optional initializer.</span>
+ <span class="n">std</span><span class="o">::</span><span class="n">unique_ptr</span><span class="o"><</span><span class="n">ExprAST</span><span class="o">></span> <span class="n">Init</span> <span class="o">=</span> <span class="n">nullptr</span><span class="p">;</span>
+ <span class="k">if</span> <span class="p">(</span><span class="n">CurTok</span> <span class="o">==</span> <span class="sc">'='</span><span class="p">)</span> <span class="p">{</span>
+ <span class="n">getNextToken</span><span class="p">();</span> <span class="c1">// eat the '='.</span>
+
+ <span class="n">Init</span> <span class="o">=</span> <span class="n">ParseExpression</span><span class="p">();</span>
+ <span class="k">if</span> <span class="p">(</span><span class="o">!</span><span class="n">Init</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">nullptr</span><span class="p">;</span>
+ <span class="p">}</span>
+
+ <span class="n">VarNames</span><span class="p">.</span><span class="n">push_back</span><span class="p">(</span><span class="n">std</span><span class="o">::</span><span class="n">make_pair</span><span class="p">(</span><span class="n">Name</span><span class="p">,</span> <span class="n">std</span><span class="o">::</span><span class="n">move</span><span class="p">(</span><span class="n">Init</span><span class="p">)));</span>
+
+ <span class="c1">// End of var list, exit loop.</span>
+ <span class="k">if</span> <span class="p">(</span><span class="n">CurTok</span> <span class="o">!=</span> <span class="sc">','</span><span class="p">)</span>
+ <span class="k">break</span><span class="p">;</span>
+ <span class="n">getNextToken</span><span class="p">();</span> <span class="c1">// eat the ','.</span>
+
+ <span class="k">if</span> <span class="p">(</span><span class="n">CurTok</span> <span class="o">!=</span> <span class="n">tok_identifier</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">Error</span><span class="p">(</span><span class="s">"expected identifier list after var"</span><span class="p">);</span>
+ <span class="p">}</span>
+
+ <span class="c1">// At this point, we have to have 'in'.</span>
+ <span class="k">if</span> <span class="p">(</span><span class="n">CurTok</span> <span class="o">!=</span> <span class="n">tok_in</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">Error</span><span class="p">(</span><span class="s">"expected 'in' keyword after 'var'"</span><span class="p">);</span>
+ <span class="n">getNextToken</span><span class="p">();</span> <span class="c1">// eat 'in'.</span>
+
+ <span class="k">auto</span> <span class="n">Body</span> <span class="o">=</span> <span class="n">ParseExpression</span><span class="p">();</span>
+ <span class="k">if</span> <span class="p">(</span><span class="o">!</span><span class="n">Body</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">nullptr</span><span class="p">;</span>
+
+ <span class="k">return</span> <span class="n">llvm</span><span class="o">::</span><span class="n">make_unique</span><span class="o"><</span><span class="n">VarExprAST</span><span class="o">></span><span class="p">(</span><span class="n">std</span><span class="o">::</span><span class="n">move</span><span class="p">(</span><span class="n">VarNames</span><span class="p">),</span> <span class="n">std</span><span class="o">::</span><span class="n">move</span><span class="p">(</span><span class="n">Body</span><span class="p">));</span>
+<span class="p">}</span>
+
+<span class="c1">/// primary</span>
+<span class="c1">/// ::= identifierexpr</span>
+<span class="c1">/// ::= numberexpr</span>
+<span class="c1">/// ::= parenexpr</span>
+<span class="c1">/// ::= ifexpr</span>
+<span class="c1">/// ::= forexpr</span>
+<span class="c1">/// ::= varexpr</span>
+<span class="k">static</span> <span class="n">std</span><span class="o">::</span><span class="n">unique_ptr</span><span class="o"><</span><span class="n">ExprAST</span><span class="o">></span> <span class="n">ParsePrimary</span><span class="p">()</span> <span class="p">{</span>
+ <span class="k">switch</span> <span class="p">(</span><span class="n">CurTok</span><span class="p">)</span> <span class="p">{</span>
+ <span class="nl">default:</span>
+ <span class="k">return</span> <span class="n">Error</span><span class="p">(</span><span class="s">"unknown token when expecting an expression"</span><span class="p">);</span>
+ <span class="k">case</span> <span class="n">tok_identifier</span>:
+ <span class="k">return</span> <span class="n">ParseIdentifierExpr</span><span class="p">();</span>
+ <span class="k">case</span> <span class="n">tok_number</span>:
+ <span class="k">return</span> <span class="n">ParseNumberExpr</span><span class="p">();</span>
+ <span class="k">case</span> <span class="sc">'('</span>:
+ <span class="k">return</span> <span class="n">ParseParenExpr</span><span class="p">();</span>
+ <span class="k">case</span> <span class="n">tok_if</span>:
+ <span class="k">return</span> <span class="n">ParseIfExpr</span><span class="p">();</span>
+ <span class="k">case</span> <span class="n">tok_for</span>:
+ <span class="k">return</span> <span class="n">ParseForExpr</span><span class="p">();</span>
+ <span class="k">case</span> <span class="n">tok_var</span>:
+ <span class="k">return</span> <span class="n">ParseVarExpr</span><span class="p">();</span>
+ <span class="p">}</span>
+<span class="p">}</span>
+
+<span class="c1">/// unary</span>
+<span class="c1">/// ::= primary</span>
+<span class="c1">/// ::= '!' unary</span>
+<span class="k">static</span> <span class="n">std</span><span class="o">::</span><span class="n">unique_ptr</span><span class="o"><</span><span class="n">ExprAST</span><span class="o">></span> <span class="n">ParseUnary</span><span class="p">()</span> <span class="p">{</span>
+ <span class="c1">// If the current token is not an operator, it must be a primary expr.</span>
+ <span class="k">if</span> <span class="p">(</span><span class="o">!</span><span class="n">isascii</span><span class="p">(</span><span class="n">CurTok</span><span class="p">)</span> <span class="o">||</span> <span class="n">CurTok</span> <span class="o">==</span> <span class="sc">'('</span> <span class="o">||</span> <span class="n">CurTok</span> <span class="o">==</span> <span class="sc">','</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">ParsePrimary</span><span class="p">();</span>
+
+ <span class="c1">// If this is a unary operator, read it.</span>
+ <span class="kt">int</span> <span class="n">Opc</span> <span class="o">=</span> <span class="n">CurTok</span><span class="p">;</span>
+ <span class="n">getNextToken</span><span class="p">();</span>
+ <span class="k">if</span> <span class="p">(</span><span class="k">auto</span> <span class="n">Operand</span> <span class="o">=</span> <span class="n">ParseUnary</span><span class="p">())</span>
+ <span class="k">return</span> <span class="n">llvm</span><span class="o">::</span><span class="n">make_unique</span><span class="o"><</span><span class="n">UnaryExprAST</span><span class="o">></span><span class="p">(</span><span class="n">Opc</span><span class="p">,</span> <span class="n">std</span><span class="o">::</span><span class="n">move</span><span class="p">(</span><span class="n">Operand</span><span class="p">));</span>
+ <span class="k">return</span> <span class="n">nullptr</span><span class="p">;</span>
+<span class="p">}</span>
+
+<span class="c1">/// binoprhs</span>
+<span class="c1">/// ::= ('+' unary)*</span>
+<span class="k">static</span> <span class="n">std</span><span class="o">::</span><span class="n">unique_ptr</span><span class="o"><</span><span class="n">ExprAST</span><span class="o">></span> <span class="n">ParseBinOpRHS</span><span class="p">(</span><span class="kt">int</span> <span class="n">ExprPrec</span><span class="p">,</span>
+ <span class="n">std</span><span class="o">::</span><span class="n">unique_ptr</span><span class="o"><</span><span class="n">ExprAST</span><span class="o">></span> <span class="n">LHS</span><span class="p">)</span> <span class="p">{</span>
+ <span class="c1">// If this is a binop, find its precedence.</span>
+ <span class="k">while</span> <span class="p">(</span><span class="mi">1</span><span class="p">)</span> <span class="p">{</span>
+ <span class="kt">int</span> <span class="n">TokPrec</span> <span class="o">=</span> <span class="n">GetTokPrecedence</span><span class="p">();</span>
+
+ <span class="c1">// If this is a binop that binds at least as tightly as the current binop,</span>
+ <span class="c1">// consume it, otherwise we are done.</span>
+ <span class="k">if</span> <span class="p">(</span><span class="n">TokPrec</span> <span class="o"><</span> <span class="n">ExprPrec</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">LHS</span><span class="p">;</span>
+
+ <span class="c1">// Okay, we know this is a binop.</span>
+ <span class="kt">int</span> <span class="n">BinOp</span> <span class="o">=</span> <span class="n">CurTok</span><span class="p">;</span>
+ <span class="n">SourceLocation</span> <span class="n">BinLoc</span> <span class="o">=</span> <span class="n">CurLoc</span><span class="p">;</span>
+ <span class="n">getNextToken</span><span class="p">();</span> <span class="c1">// eat binop</span>
+
+ <span class="c1">// Parse the unary expression after the binary operator.</span>
+ <span class="k">auto</span> <span class="n">RHS</span> <span class="o">=</span> <span class="n">ParseUnary</span><span class="p">();</span>
+ <span class="k">if</span> <span class="p">(</span><span class="o">!</span><span class="n">RHS</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">nullptr</span><span class="p">;</span>
+
+ <span class="c1">// If BinOp binds less tightly with RHS than the operator after RHS, let</span>
+ <span class="c1">// the pending operator take RHS as its LHS.</span>
+ <span class="kt">int</span> <span class="n">NextPrec</span> <span class="o">=</span> <span class="n">GetTokPrecedence</span><span class="p">();</span>
+ <span class="k">if</span> <span class="p">(</span><span class="n">TokPrec</span> <span class="o"><</span> <span class="n">NextPrec</span><span class="p">)</span> <span class="p">{</span>
+ <span class="n">RHS</span> <span class="o">=</span> <span class="n">ParseBinOpRHS</span><span class="p">(</span><span class="n">TokPrec</span> <span class="o">+</span> <span class="mi">1</span><span class="p">,</span> <span class="n">std</span><span class="o">::</span><span class="n">move</span><span class="p">(</span><span class="n">RHS</span><span class="p">));</span>
+ <span class="k">if</span> <span class="p">(</span><span class="o">!</span><span class="n">RHS</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">nullptr</span><span class="p">;</span>
+ <span class="p">}</span>
+
+ <span class="c1">// Merge LHS/RHS.</span>
+ <span class="n">LHS</span> <span class="o">=</span> <span class="n">llvm</span><span class="o">::</span><span class="n">make_unique</span><span class="o"><</span><span class="n">BinaryExprAST</span><span class="o">></span><span class="p">(</span><span class="n">BinLoc</span><span class="p">,</span> <span class="n">BinOp</span><span class="p">,</span> <span class="n">std</span><span class="o">::</span><span class="n">move</span><span class="p">(</span><span class="n">LHS</span><span class="p">),</span>
+ <span class="n">std</span><span class="o">::</span><span class="n">move</span><span class="p">(</span><span class="n">RHS</span><span class="p">));</span>
+ <span class="p">}</span>
+<span class="p">}</span>
+
+<span class="c1">/// expression</span>
+<span class="c1">/// ::= unary binoprhs</span>
+<span class="c1">///</span>
+<span class="k">static</span> <span class="n">std</span><span class="o">::</span><span class="n">unique_ptr</span><span class="o"><</span><span class="n">ExprAST</span><span class="o">></span> <span class="n">ParseExpression</span><span class="p">()</span> <span class="p">{</span>
+ <span class="k">auto</span> <span class="n">LHS</span> <span class="o">=</span> <span class="n">ParseUnary</span><span class="p">();</span>
+ <span class="k">if</span> <span class="p">(</span><span class="o">!</span><span class="n">LHS</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">nullptr</span><span class="p">;</span>
+
+ <span class="k">return</span> <span class="nf">ParseBinOpRHS</span><span class="p">(</span><span class="mi">0</span><span class="p">,</span> <span class="n">std</span><span class="o">::</span><span class="n">move</span><span class="p">(</span><span class="n">LHS</span><span class="p">));</span>
+<span class="p">}</span>
+
+<span class="c1">/// prototype</span>
+<span class="c1">/// ::= id '(' id* ')'</span>
+<span class="c1">/// ::= binary LETTER number? (id, id)</span>
+<span class="c1">/// ::= unary LETTER (id)</span>
+<span class="k">static</span> <span class="n">std</span><span class="o">::</span><span class="n">unique_ptr</span><span class="o"><</span><span class="n">PrototypeAST</span><span class="o">></span> <span class="n">ParsePrototype</span><span class="p">()</span> <span class="p">{</span>
+ <span class="n">std</span><span class="o">::</span><span class="n">string</span> <span class="n">FnName</span><span class="p">;</span>
+
+ <span class="n">SourceLocation</span> <span class="n">FnLoc</span> <span class="o">=</span> <span class="n">CurLoc</span><span class="p">;</span>
+
+ <span class="kt">unsigned</span> <span class="n">Kind</span> <span class="o">=</span> <span class="mi">0</span><span class="p">;</span> <span class="c1">// 0 = identifier, 1 = unary, 2 = binary.</span>
+ <span class="kt">unsigned</span> <span class="n">BinaryPrecedence</span> <span class="o">=</span> <span class="mi">30</span><span class="p">;</span>
+
+ <span class="k">switch</span> <span class="p">(</span><span class="n">CurTok</span><span class="p">)</span> <span class="p">{</span>
+ <span class="nl">default:</span>
+ <span class="k">return</span> <span class="n">ErrorP</span><span class="p">(</span><span class="s">"Expected function name in prototype"</span><span class="p">);</span>
+ <span class="k">case</span> <span class="n">tok_identifier</span>:
+ <span class="n">FnName</span> <span class="o">=</span> <span class="n">IdentifierStr</span><span class="p">;</span>
+ <span class="n">Kind</span> <span class="o">=</span> <span class="mi">0</span><span class="p">;</span>
+ <span class="n">getNextToken</span><span class="p">();</span>
+ <span class="k">break</span><span class="p">;</span>
+ <span class="k">case</span> <span class="n">tok_unary</span>:
+ <span class="n">getNextToken</span><span class="p">();</span>
+ <span class="k">if</span> <span class="p">(</span><span class="o">!</span><span class="n">isascii</span><span class="p">(</span><span class="n">CurTok</span><span class="p">))</span>
+ <span class="k">return</span> <span class="n">ErrorP</span><span class="p">(</span><span class="s">"Expected unary operator"</span><span class="p">);</span>
+ <span class="n">FnName</span> <span class="o">=</span> <span class="s">"unary"</span><span class="p">;</span>
+ <span class="n">FnName</span> <span class="o">+=</span> <span class="p">(</span><span class="kt">char</span><span class="p">)</span><span class="n">CurTok</span><span class="p">;</span>
+ <span class="n">Kind</span> <span class="o">=</span> <span class="mi">1</span><span class="p">;</span>
+ <span class="n">getNextToken</span><span class="p">();</span>
+ <span class="k">break</span><span class="p">;</span>
+ <span class="k">case</span> <span class="n">tok_binary</span>:
+ <span class="n">getNextToken</span><span class="p">();</span>
+ <span class="k">if</span> <span class="p">(</span><span class="o">!</span><span class="n">isascii</span><span class="p">(</span><span class="n">CurTok</span><span class="p">))</span>
+ <span class="k">return</span> <span class="n">ErrorP</span><span class="p">(</span><span class="s">"Expected binary operator"</span><span class="p">);</span>
+ <span class="n">FnName</span> <span class="o">=</span> <span class="s">"binary"</span><span class="p">;</span>
+ <span class="n">FnName</span> <span class="o">+=</span> <span class="p">(</span><span class="kt">char</span><span class="p">)</span><span class="n">CurTok</span><span class="p">;</span>
+ <span class="n">Kind</span> <span class="o">=</span> <span class="mi">2</span><span class="p">;</span>
+ <span class="n">getNextToken</span><span class="p">();</span>
+
+ <span class="c1">// Read the precedence if present.</span>
+ <span class="k">if</span> <span class="p">(</span><span class="n">CurTok</span> <span class="o">==</span> <span class="n">tok_number</span><span class="p">)</span> <span class="p">{</span>
+ <span class="k">if</span> <span class="p">(</span><span class="n">NumVal</span> <span class="o"><</span> <span class="mi">1</span> <span class="o">||</span> <span class="n">NumVal</span> <span class="o">></span> <span class="mi">100</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">ErrorP</span><span class="p">(</span><span class="s">"Invalid precedecnce: must be 1..100"</span><span class="p">);</span>
+ <span class="n">BinaryPrecedence</span> <span class="o">=</span> <span class="p">(</span><span class="kt">unsigned</span><span class="p">)</span><span class="n">NumVal</span><span class="p">;</span>
+ <span class="n">getNextToken</span><span class="p">();</span>
+ <span class="p">}</span>
+ <span class="k">break</span><span class="p">;</span>
+ <span class="p">}</span>
+
+ <span class="k">if</span> <span class="p">(</span><span class="n">CurTok</span> <span class="o">!=</span> <span class="sc">'('</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">ErrorP</span><span class="p">(</span><span class="s">"Expected '(' in prototype"</span><span class="p">);</span>
+
+ <span class="n">std</span><span class="o">::</span><span class="n">vector</span><span class="o"><</span><span class="n">std</span><span class="o">::</span><span class="n">string</span><span class="o">></span> <span class="n">ArgNames</span><span class="p">;</span>
+ <span class="k">while</span> <span class="p">(</span><span class="n">getNextToken</span><span class="p">()</span> <span class="o">==</span> <span class="n">tok_identifier</span><span class="p">)</span>
+ <span class="n">ArgNames</span><span class="p">.</span><span class="n">push_back</span><span class="p">(</span><span class="n">IdentifierStr</span><span class="p">);</span>
+ <span class="k">if</span> <span class="p">(</span><span class="n">CurTok</span> <span class="o">!=</span> <span class="sc">')'</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">ErrorP</span><span class="p">(</span><span class="s">"Expected ')' in prototype"</span><span class="p">);</span>
+
+ <span class="c1">// success.</span>
+ <span class="n">getNextToken</span><span class="p">();</span> <span class="c1">// eat ')'.</span>
+
+ <span class="c1">// Verify right number of names for operator.</span>
+ <span class="k">if</span> <span class="p">(</span><span class="n">Kind</span> <span class="o">&&</span> <span class="n">ArgNames</span><span class="p">.</span><span class="n">size</span><span class="p">()</span> <span class="o">!=</span> <span class="n">Kind</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">ErrorP</span><span class="p">(</span><span class="s">"Invalid number of operands for operator"</span><span class="p">);</span>
+
+ <span class="k">return</span> <span class="n">llvm</span><span class="o">::</span><span class="n">make_unique</span><span class="o"><</span><span class="n">PrototypeAST</span><span class="o">></span><span class="p">(</span><span class="n">FnLoc</span><span class="p">,</span> <span class="n">FnName</span><span class="p">,</span> <span class="n">ArgNames</span><span class="p">,</span> <span class="n">Kind</span> <span class="o">!=</span> <span class="mi">0</span><span class="p">,</span>
+ <span class="n">BinaryPrecedence</span><span class="p">);</span>
+<span class="p">}</span>
+
+<span class="c1">/// definition ::= 'def' prototype expression</span>
+<span class="k">static</span> <span class="n">std</span><span class="o">::</span><span class="n">unique_ptr</span><span class="o"><</span><span class="n">FunctionAST</span><span class="o">></span> <span class="n">ParseDefinition</span><span class="p">()</span> <span class="p">{</span>
+ <span class="n">getNextToken</span><span class="p">();</span> <span class="c1">// eat def.</span>
+ <span class="k">auto</span> <span class="n">Proto</span> <span class="o">=</span> <span class="n">ParsePrototype</span><span class="p">();</span>
+ <span class="k">if</span> <span class="p">(</span><span class="o">!</span><span class="n">Proto</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">nullptr</span><span class="p">;</span>
+
+ <span class="k">if</span> <span class="p">(</span><span class="k">auto</span> <span class="n">E</span> <span class="o">=</span> <span class="n">ParseExpression</span><span class="p">())</span>
+ <span class="k">return</span> <span class="n">llvm</span><span class="o">::</span><span class="n">make_unique</span><span class="o"><</span><span class="n">FunctionAST</span><span class="o">></span><span class="p">(</span><span class="n">std</span><span class="o">::</span><span class="n">move</span><span class="p">(</span><span class="n">Proto</span><span class="p">),</span> <span class="n">std</span><span class="o">::</span><span class="n">move</span><span class="p">(</span><span class="n">E</span><span class="p">));</span>
+ <span class="k">return</span> <span class="n">nullptr</span><span class="p">;</span>
+<span class="p">}</span>
+
+<span class="c1">/// toplevelexpr ::= expression</span>
+<span class="k">static</span> <span class="n">std</span><span class="o">::</span><span class="n">unique_ptr</span><span class="o"><</span><span class="n">FunctionAST</span><span class="o">></span> <span class="n">ParseTopLevelExpr</span><span class="p">()</span> <span class="p">{</span>
+ <span class="n">SourceLocation</span> <span class="n">FnLoc</span> <span class="o">=</span> <span class="n">CurLoc</span><span class="p">;</span>
+ <span class="k">if</span> <span class="p">(</span><span class="k">auto</span> <span class="n">E</span> <span class="o">=</span> <span class="n">ParseExpression</span><span class="p">())</span> <span class="p">{</span>
+ <span class="c1">// Make an anonymous proto.</span>
+ <span class="k">auto</span> <span class="n">Proto</span> <span class="o">=</span> <span class="n">llvm</span><span class="o">::</span><span class="n">make_unique</span><span class="o"><</span><span class="n">PrototypeAST</span><span class="o">></span><span class="p">(</span><span class="n">FnLoc</span><span class="p">,</span> <span class="s">"__anon_expr"</span><span class="p">,</span>
+ <span class="n">std</span><span class="o">::</span><span class="n">vector</span><span class="o"><</span><span class="n">std</span><span class="o">::</span><span class="n">string</span><span class="o">></span><span class="p">());</span>
+ <span class="k">return</span> <span class="n">llvm</span><span class="o">::</span><span class="n">make_unique</span><span class="o"><</span><span class="n">FunctionAST</span><span class="o">></span><span class="p">(</span><span class="n">std</span><span class="o">::</span><span class="n">move</span><span class="p">(</span><span class="n">Proto</span><span class="p">),</span> <span class="n">std</span><span class="o">::</span><span class="n">move</span><span class="p">(</span><span class="n">E</span><span class="p">));</span>
+ <span class="p">}</span>
+ <span class="k">return</span> <span class="n">nullptr</span><span class="p">;</span>
+<span class="p">}</span>
+
+<span class="c1">/// external ::= 'extern' prototype</span>
+<span class="k">static</span> <span class="n">std</span><span class="o">::</span><span class="n">unique_ptr</span><span class="o"><</span><span class="n">PrototypeAST</span><span class="o">></span> <span class="n">ParseExtern</span><span class="p">()</span> <span class="p">{</span>
+ <span class="n">getNextToken</span><span class="p">();</span> <span class="c1">// eat extern.</span>
+ <span class="k">return</span> <span class="nf">ParsePrototype</span><span class="p">();</span>
+<span class="p">}</span>
+
+<span class="c1">//===----------------------------------------------------------------------===//</span>
+<span class="c1">// Debug Info Support</span>
+<span class="c1">//===----------------------------------------------------------------------===//</span>
+
+<span class="k">static</span> <span class="n">std</span><span class="o">::</span><span class="n">unique_ptr</span><span class="o"><</span><span class="n">DIBuilder</span><span class="o">></span> <span class="n">DBuilder</span><span class="p">;</span>
+
+<span class="n">DIType</span> <span class="o">*</span><span class="n">DebugInfo</span><span class="o">::</span><span class="n">getDoubleTy</span><span class="p">()</span> <span class="p">{</span>
+ <span class="k">if</span> <span class="p">(</span><span class="n">DblTy</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">DblTy</span><span class="p">;</span>
+
+ <span class="n">DblTy</span> <span class="o">=</span> <span class="n">DBuilder</span><span class="o">-></span><span class="n">createBasicType</span><span class="p">(</span><span class="s">"double"</span><span class="p">,</span> <span class="mi">64</span><span class="p">,</span> <span class="mi">64</span><span class="p">,</span> <span class="n">dwarf</span><span class="o">::</span><span class="n">DW_ATE_float</span><span class="p">);</span>
+ <span class="k">return</span> <span class="n">DblTy</span><span class="p">;</span>
+<span class="p">}</span>
+
+<span class="kt">void</span> <span class="n">DebugInfo</span><span class="o">::</span><span class="n">emitLocation</span><span class="p">(</span><span class="n">ExprAST</span> <span class="o">*</span><span class="n">AST</span><span class="p">)</span> <span class="p">{</span>
+ <span class="k">if</span> <span class="p">(</span><span class="o">!</span><span class="n">AST</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">Builder</span><span class="p">.</span><span class="n">SetCurrentDebugLocation</span><span class="p">(</span><span class="n">DebugLoc</span><span class="p">());</span>
+ <span class="n">DIScope</span> <span class="o">*</span><span class="n">Scope</span><span class="p">;</span>
+ <span class="k">if</span> <span class="p">(</span><span class="n">LexicalBlocks</span><span class="p">.</span><span class="n">empty</span><span class="p">())</span>
+ <span class="n">Scope</span> <span class="o">=</span> <span class="n">TheCU</span><span class="p">;</span>
+ <span class="k">else</span>
+ <span class="n">Scope</span> <span class="o">=</span> <span class="n">LexicalBlocks</span><span class="p">.</span><span class="n">back</span><span class="p">();</span>
+ <span class="n">Builder</span><span class="p">.</span><span class="n">SetCurrentDebugLocation</span><span class="p">(</span>
+ <span class="n">DebugLoc</span><span class="o">::</span><span class="n">get</span><span class="p">(</span><span class="n">AST</span><span class="o">-></span><span class="n">getLine</span><span class="p">(),</span> <span class="n">AST</span><span class="o">-></span><span class="n">getCol</span><span class="p">(),</span> <span class="n">Scope</span><span class="p">));</span>
+<span class="p">}</span>
+
+<span class="k">static</span> <span class="n">DISubroutineType</span> <span class="o">*</span><span class="n">CreateFunctionType</span><span class="p">(</span><span class="kt">unsigned</span> <span class="n">NumArgs</span><span class="p">,</span> <span class="n">DIFile</span> <span class="o">*</span><span class="n">Unit</span><span class="p">)</span> <span class="p">{</span>
+ <span class="n">SmallVector</span><span class="o"><</span><span class="n">Metadata</span> <span class="o">*</span><span class="p">,</span> <span class="mi">8</span><span class="o">></span> <span class="n">EltTys</span><span class="p">;</span>
+ <span class="n">DIType</span> <span class="o">*</span><span class="n">DblTy</span> <span class="o">=</span> <span class="n">KSDbgInfo</span><span class="p">.</span><span class="n">getDoubleTy</span><span class="p">();</span>
+
+ <span class="c1">// Add the result type.</span>
+ <span class="n">EltTys</span><span class="p">.</span><span class="n">push_back</span><span class="p">(</span><span class="n">DblTy</span><span class="p">);</span>
+
+ <span class="k">for</span> <span class="p">(</span><span class="kt">unsigned</span> <span class="n">i</span> <span class="o">=</span> <span class="mi">0</span><span class="p">,</span> <span class="n">e</span> <span class="o">=</span> <span class="n">NumArgs</span><span class="p">;</span> <span class="n">i</span> <span class="o">!=</span> <span class="n">e</span><span class="p">;</span> <span class="o">++</span><span class="n">i</span><span class="p">)</span>
+ <span class="n">EltTys</span><span class="p">.</span><span class="n">push_back</span><span class="p">(</span><span class="n">DblTy</span><span class="p">);</span>
+
+ <span class="k">return</span> <span class="n">DBuilder</span><span class="o">-></span><span class="n">createSubroutineType</span><span class="p">(</span><span class="n">DBuilder</span><span class="o">-></span><span class="n">getOrCreateTypeArray</span><span class="p">(</span><span class="n">EltTys</span><span class="p">));</span>
+<span class="p">}</span>
+
+<span class="c1">//===----------------------------------------------------------------------===//</span>
+<span class="c1">// Code Generation</span>
+<span class="c1">//===----------------------------------------------------------------------===//</span>
+
+<span class="k">static</span> <span class="n">std</span><span class="o">::</span><span class="n">unique_ptr</span><span class="o"><</span><span class="n">Module</span><span class="o">></span> <span class="n">TheModule</span><span class="p">;</span>
+<span class="k">static</span> <span class="n">std</span><span class="o">::</span><span class="n">map</span><span class="o"><</span><span class="n">std</span><span class="o">::</span><span class="n">string</span><span class="p">,</span> <span class="n">AllocaInst</span> <span class="o">*></span> <span class="n">NamedValues</span><span class="p">;</span>
+<span class="k">static</span> <span class="n">std</span><span class="o">::</span><span class="n">unique_ptr</span><span class="o"><</span><span class="n">KaleidoscopeJIT</span><span class="o">></span> <span class="n">TheJIT</span><span class="p">;</span>
+<span class="k">static</span> <span class="n">std</span><span class="o">::</span><span class="n">map</span><span class="o"><</span><span class="n">std</span><span class="o">::</span><span class="n">string</span><span class="p">,</span> <span class="n">std</span><span class="o">::</span><span class="n">unique_ptr</span><span class="o"><</span><span class="n">PrototypeAST</span><span class="o">>></span> <span class="n">FunctionProtos</span><span class="p">;</span>
+
+<span class="n">Value</span> <span class="o">*</span><span class="nf">ErrorV</span><span class="p">(</span><span class="k">const</span> <span class="kt">char</span> <span class="o">*</span><span class="n">Str</span><span class="p">)</span> <span class="p">{</span>
+ <span class="n">Error</span><span class="p">(</span><span class="n">Str</span><span class="p">);</span>
+ <span class="k">return</span> <span class="n">nullptr</span><span class="p">;</span>
+<span class="p">}</span>
+
+<span class="n">Function</span> <span class="o">*</span><span class="nf">getFunction</span><span class="p">(</span><span class="n">std</span><span class="o">::</span><span class="n">string</span> <span class="n">Name</span><span class="p">)</span> <span class="p">{</span>
+ <span class="c1">// First, see if the function has already been added to the current module.</span>
+ <span class="k">if</span> <span class="p">(</span><span class="k">auto</span> <span class="o">*</span><span class="n">F</span> <span class="o">=</span> <span class="n">TheModule</span><span class="o">-></span><span class="n">getFunction</span><span class="p">(</span><span class="n">Name</span><span class="p">))</span>
+ <span class="k">return</span> <span class="n">F</span><span class="p">;</span>
+
+ <span class="c1">// If not, check whether we can codegen the declaration from some existing</span>
+ <span class="c1">// prototype.</span>
+ <span class="k">auto</span> <span class="n">FI</span> <span class="o">=</span> <span class="n">FunctionProtos</span><span class="p">.</span><span class="n">find</span><span class="p">(</span><span class="n">Name</span><span class="p">);</span>
+ <span class="k">if</span> <span class="p">(</span><span class="n">FI</span> <span class="o">!=</span> <span class="n">FunctionProtos</span><span class="p">.</span><span class="n">end</span><span class="p">())</span>
+ <span class="k">return</span> <span class="n">FI</span><span class="o">-></span><span class="n">second</span><span class="o">-></span><span class="n">codegen</span><span class="p">();</span>
+
+ <span class="c1">// If no existing prototype exists, return null.</span>
+ <span class="k">return</span> <span class="n">nullptr</span><span class="p">;</span>
+<span class="p">}</span>
+
+<span class="c1">/// CreateEntryBlockAlloca - Create an alloca instruction in the entry block of</span>
+<span class="c1">/// the function. This is used for mutable variables etc.</span>
+<span class="k">static</span> <span class="n">AllocaInst</span> <span class="o">*</span><span class="nf">CreateEntryBlockAlloca</span><span class="p">(</span><span class="n">Function</span> <span class="o">*</span><span class="n">TheFunction</span><span class="p">,</span>
+ <span class="k">const</span> <span class="n">std</span><span class="o">::</span><span class="n">string</span> <span class="o">&</span><span class="n">VarName</span><span class="p">)</span> <span class="p">{</span>
+ <span class="n">IRBuilder</span><span class="o"><></span> <span class="n">TmpB</span><span class="p">(</span><span class="o">&</span><span class="n">TheFunction</span><span class="o">-></span><span class="n">getEntryBlock</span><span class="p">(),</span>
+ <span class="n">TheFunction</span><span class="o">-></span><span class="n">getEntryBlock</span><span class="p">().</span><span class="n">begin</span><span class="p">());</span>
+ <span class="k">return</span> <span class="n">TmpB</span><span class="p">.</span><span class="n">CreateAlloca</span><span class="p">(</span><span class="n">Type</span><span class="o">::</span><span class="n">getDoubleTy</span><span class="p">(</span><span class="n">getGlobalContext</span><span class="p">()),</span> <span class="n">nullptr</span><span class="p">,</span>
+ <span class="n">VarName</span><span class="p">.</span><span class="n">c_str</span><span class="p">());</span>
+<span class="p">}</span>
+
+<span class="n">Value</span> <span class="o">*</span><span class="n">NumberExprAST</span><span class="o">::</span><span class="n">codegen</span><span class="p">()</span> <span class="p">{</span>
+ <span class="n">KSDbgInfo</span><span class="p">.</span><span class="n">emitLocation</span><span class="p">(</span><span class="k">this</span><span class="p">);</span>
+ <span class="k">return</span> <span class="n">ConstantFP</span><span class="o">::</span><span class="n">get</span><span class="p">(</span><span class="n">getGlobalContext</span><span class="p">(),</span> <span class="n">APFloat</span><span class="p">(</span><span class="n">Val</span><span class="p">));</span>
+<span class="p">}</span>
+
+<span class="n">Value</span> <span class="o">*</span><span class="n">VariableExprAST</span><span class="o">::</span><span class="n">codegen</span><span class="p">()</span> <span class="p">{</span>
+ <span class="c1">// Look this variable up in the function.</span>
+ <span class="n">Value</span> <span class="o">*</span><span class="n">V</span> <span class="o">=</span> <span class="n">NamedValues</span><span class="p">[</span><span class="n">Name</span><span class="p">];</span>
+ <span class="k">if</span> <span class="p">(</span><span class="o">!</span><span class="n">V</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">ErrorV</span><span class="p">(</span><span class="s">"Unknown variable name"</span><span class="p">);</span>
+
+ <span class="n">KSDbgInfo</span><span class="p">.</span><span class="n">emitLocation</span><span class="p">(</span><span class="k">this</span><span class="p">);</span>
+ <span class="c1">// Load the value.</span>
+ <span class="k">return</span> <span class="n">Builder</span><span class="p">.</span><span class="n">CreateLoad</span><span class="p">(</span><span class="n">V</span><span class="p">,</span> <span class="n">Name</span><span class="p">.</span><span class="n">c_str</span><span class="p">());</span>
+<span class="p">}</span>
+
+<span class="n">Value</span> <span class="o">*</span><span class="n">UnaryExprAST</span><span class="o">::</span><span class="n">codegen</span><span class="p">()</span> <span class="p">{</span>
+ <span class="n">Value</span> <span class="o">*</span><span class="n">OperandV</span> <span class="o">=</span> <span class="n">Operand</span><span class="o">-></span><span class="n">codegen</span><span class="p">();</span>
+ <span class="k">if</span> <span class="p">(</span><span class="o">!</span><span class="n">OperandV</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">nullptr</span><span class="p">;</span>
+
+ <span class="n">Function</span> <span class="o">*</span><span class="n">F</span> <span class="o">=</span> <span class="n">getFunction</span><span class="p">(</span><span class="n">std</span><span class="o">::</span><span class="n">string</span><span class="p">(</span><span class="s">"unary"</span><span class="p">)</span> <span class="o">+</span> <span class="n">Opcode</span><span class="p">);</span>
+ <span class="k">if</span> <span class="p">(</span><span class="o">!</span><span class="n">F</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">ErrorV</span><span class="p">(</span><span class="s">"Unknown unary operator"</span><span class="p">);</span>
+
+ <span class="n">KSDbgInfo</span><span class="p">.</span><span class="n">emitLocation</span><span class="p">(</span><span class="k">this</span><span class="p">);</span>
+ <span class="k">return</span> <span class="n">Builder</span><span class="p">.</span><span class="n">CreateCall</span><span class="p">(</span><span class="n">F</span><span class="p">,</span> <span class="n">OperandV</span><span class="p">,</span> <span class="s">"unop"</span><span class="p">);</span>
+<span class="p">}</span>
+
+<span class="n">Value</span> <span class="o">*</span><span class="n">BinaryExprAST</span><span class="o">::</span><span class="n">codegen</span><span class="p">()</span> <span class="p">{</span>
+ <span class="n">KSDbgInfo</span><span class="p">.</span><span class="n">emitLocation</span><span class="p">(</span><span class="k">this</span><span class="p">);</span>
+
+ <span class="c1">// Special case '=' because we don't want to emit the LHS as an expression.</span>
+ <span class="k">if</span> <span class="p">(</span><span class="n">Op</span> <span class="o">==</span> <span class="sc">'='</span><span class="p">)</span> <span class="p">{</span>
+ <span class="c1">// Assignment requires the LHS to be an identifier.</span>
+ <span class="c1">// This assume we're building without RTTI because LLVM builds that way by</span>
+ <span class="c1">// default. If you build LLVM with RTTI this can be changed to a</span>
+ <span class="c1">// dynamic_cast for automatic error checking.</span>
+ <span class="n">VariableExprAST</span> <span class="o">*</span><span class="n">LHSE</span> <span class="o">=</span> <span class="k">static_cast</span><span class="o"><</span><span class="n">VariableExprAST</span> <span class="o">*></span><span class="p">(</span><span class="n">LHS</span><span class="p">.</span><span class="n">get</span><span class="p">());</span>
+ <span class="k">if</span> <span class="p">(</span><span class="o">!</span><span class="n">LHSE</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">ErrorV</span><span class="p">(</span><span class="s">"destination of '=' must be a variable"</span><span class="p">);</span>
+ <span class="c1">// Codegen the RHS.</span>
+ <span class="n">Value</span> <span class="o">*</span><span class="n">Val</span> <span class="o">=</span> <span class="n">RHS</span><span class="o">-></span><span class="n">codegen</span><span class="p">();</span>
+ <span class="k">if</span> <span class="p">(</span><span class="o">!</span><span class="n">Val</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">nullptr</span><span class="p">;</span>
+
+ <span class="c1">// Look up the name.</span>
+ <span class="n">Value</span> <span class="o">*</span><span class="n">Variable</span> <span class="o">=</span> <span class="n">NamedValues</span><span class="p">[</span><span class="n">LHSE</span><span class="o">-></span><span class="n">getName</span><span class="p">()];</span>
+ <span class="k">if</span> <span class="p">(</span><span class="o">!</span><span class="n">Variable</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">ErrorV</span><span class="p">(</span><span class="s">"Unknown variable name"</span><span class="p">);</span>
+
+ <span class="n">Builder</span><span class="p">.</span><span class="n">CreateStore</span><span class="p">(</span><span class="n">Val</span><span class="p">,</span> <span class="n">Variable</span><span class="p">);</span>
+ <span class="k">return</span> <span class="n">Val</span><span class="p">;</span>
+ <span class="p">}</span>
+
+ <span class="n">Value</span> <span class="o">*</span><span class="n">L</span> <span class="o">=</span> <span class="n">LHS</span><span class="o">-></span><span class="n">codegen</span><span class="p">();</span>
+ <span class="n">Value</span> <span class="o">*</span><span class="n">R</span> <span class="o">=</span> <span class="n">RHS</span><span class="o">-></span><span class="n">codegen</span><span class="p">();</span>
+ <span class="k">if</span> <span class="p">(</span><span class="o">!</span><span class="n">L</span> <span class="o">||</span> <span class="o">!</span><span class="n">R</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">nullptr</span><span class="p">;</span>
+
+ <span class="k">switch</span> <span class="p">(</span><span class="n">Op</span><span class="p">)</span> <span class="p">{</span>
+ <span class="k">case</span> <span class="sc">'+'</span>:
+ <span class="k">return</span> <span class="n">Builder</span><span class="p">.</span><span class="n">CreateFAdd</span><span class="p">(</span><span class="n">L</span><span class="p">,</span> <span class="n">R</span><span class="p">,</span> <span class="s">"addtmp"</span><span class="p">);</span>
+ <span class="k">case</span> <span class="sc">'-'</span>:
+ <span class="k">return</span> <span class="n">Builder</span><span class="p">.</span><span class="n">CreateFSub</span><span class="p">(</span><span class="n">L</span><span class="p">,</span> <span class="n">R</span><span class="p">,</span> <span class="s">"subtmp"</span><span class="p">);</span>
+ <span class="k">case</span> <span class="sc">'*'</span>:
+ <span class="k">return</span> <span class="n">Builder</span><span class="p">.</span><span class="n">CreateFMul</span><span class="p">(</span><span class="n">L</span><span class="p">,</span> <span class="n">R</span><span class="p">,</span> <span class="s">"multmp"</span><span class="p">);</span>
+ <span class="k">case</span> <span class="sc">'<'</span>:
+ <span class="n">L</span> <span class="o">=</span> <span class="n">Builder</span><span class="p">.</span><span class="n">CreateFCmpULT</span><span class="p">(</span><span class="n">L</span><span class="p">,</span> <span class="n">R</span><span class="p">,</span> <span class="s">"cmptmp"</span><span class="p">);</span>
+ <span class="c1">// Convert bool 0/1 to double 0.0 or 1.0</span>
+ <span class="k">return</span> <span class="n">Builder</span><span class="p">.</span><span class="n">CreateUIToFP</span><span class="p">(</span><span class="n">L</span><span class="p">,</span> <span class="n">Type</span><span class="o">::</span><span class="n">getDoubleTy</span><span class="p">(</span><span class="n">getGlobalContext</span><span class="p">()),</span>
+ <span class="s">"booltmp"</span><span class="p">);</span>
+ <span class="nl">default:</span>
+ <span class="k">break</span><span class="p">;</span>
+ <span class="p">}</span>
+
+ <span class="c1">// If it wasn't a builtin binary operator, it must be a user defined one. Emit</span>
+ <span class="c1">// a call to it.</span>
+ <span class="n">Function</span> <span class="o">*</span><span class="n">F</span> <span class="o">=</span> <span class="n">getFunction</span><span class="p">(</span><span class="n">std</span><span class="o">::</span><span class="n">string</span><span class="p">(</span><span class="s">"binary"</span><span class="p">)</span> <span class="o">+</span> <span class="n">Op</span><span class="p">);</span>
+ <span class="n">assert</span><span class="p">(</span><span class="n">F</span> <span class="o">&&</span> <span class="s">"binary operator not found!"</span><span class="p">);</span>
+
+ <span class="n">Value</span> <span class="o">*</span><span class="n">Ops</span><span class="p">[]</span> <span class="o">=</span> <span class="p">{</span><span class="n">L</span><span class="p">,</span> <span class="n">R</span><span class="p">};</span>
+ <span class="k">return</span> <span class="n">Builder</span><span class="p">.</span><span class="n">CreateCall</span><span class="p">(</span><span class="n">F</span><span class="p">,</span> <span class="n">Ops</span><span class="p">,</span> <span class="s">"binop"</span><span class="p">);</span>
+<span class="p">}</span>
+
+<span class="n">Value</span> <span class="o">*</span><span class="n">CallExprAST</span><span class="o">::</span><span class="n">codegen</span><span class="p">()</span> <span class="p">{</span>
+ <span class="n">KSDbgInfo</span><span class="p">.</span><span class="n">emitLocation</span><span class="p">(</span><span class="k">this</span><span class="p">);</span>
+
+ <span class="c1">// Look up the name in the global module table.</span>
+ <span class="n">Function</span> <span class="o">*</span><span class="n">CalleeF</span> <span class="o">=</span> <span class="n">getFunction</span><span class="p">(</span><span class="n">Callee</span><span class="p">);</span>
+ <span class="k">if</span> <span class="p">(</span><span class="o">!</span><span class="n">CalleeF</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">ErrorV</span><span class="p">(</span><span class="s">"Unknown function referenced"</span><span class="p">);</span>
+
+ <span class="c1">// If argument mismatch error.</span>
+ <span class="k">if</span> <span class="p">(</span><span class="n">CalleeF</span><span class="o">-></span><span class="n">arg_size</span><span class="p">()</span> <span class="o">!=</span> <span class="n">Args</span><span class="p">.</span><span class="n">size</span><span class="p">())</span>
+ <span class="k">return</span> <span class="n">ErrorV</span><span class="p">(</span><span class="s">"Incorrect # arguments passed"</span><span class="p">);</span>
+
+ <span class="n">std</span><span class="o">::</span><span class="n">vector</span><span class="o"><</span><span class="n">Value</span> <span class="o">*></span> <span class="n">ArgsV</span><span class="p">;</span>
+ <span class="k">for</span> <span class="p">(</span><span class="kt">unsigned</span> <span class="n">i</span> <span class="o">=</span> <span class="mi">0</span><span class="p">,</span> <span class="n">e</span> <span class="o">=</span> <span class="n">Args</span><span class="p">.</span><span class="n">size</span><span class="p">();</span> <span class="n">i</span> <span class="o">!=</span> <span class="n">e</span><span class="p">;</span> <span class="o">++</span><span class="n">i</span><span class="p">)</span> <span class="p">{</span>
+ <span class="n">ArgsV</span><span class="p">.</span><span class="n">push_back</span><span class="p">(</span><span class="n">Args</span><span class="p">[</span><span class="n">i</span><span class="p">]</span><span class="o">-></span><span class="n">codegen</span><span class="p">());</span>
+ <span class="k">if</span> <span class="p">(</span><span class="o">!</span><span class="n">ArgsV</span><span class="p">.</span><span class="n">back</span><span class="p">())</span>
+ <span class="k">return</span> <span class="n">nullptr</span><span class="p">;</span>
+ <span class="p">}</span>
+
+ <span class="k">return</span> <span class="n">Builder</span><span class="p">.</span><span class="n">CreateCall</span><span class="p">(</span><span class="n">CalleeF</span><span class="p">,</span> <span class="n">ArgsV</span><span class="p">,</span> <span class="s">"calltmp"</span><span class="p">);</span>
+<span class="p">}</span>
+
+<span class="n">Value</span> <span class="o">*</span><span class="n">IfExprAST</span><span class="o">::</span><span class="n">codegen</span><span class="p">()</span> <span class="p">{</span>
+ <span class="n">KSDbgInfo</span><span class="p">.</span><span class="n">emitLocation</span><span class="p">(</span><span class="k">this</span><span class="p">);</span>
+
+ <span class="n">Value</span> <span class="o">*</span><span class="n">CondV</span> <span class="o">=</span> <span class="n">Cond</span><span class="o">-></span><span class="n">codegen</span><span class="p">();</span>
+ <span class="k">if</span> <span class="p">(</span><span class="o">!</span><span class="n">CondV</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">nullptr</span><span class="p">;</span>
+
+ <span class="c1">// Convert condition to a bool by comparing equal to 0.0.</span>
+ <span class="n">CondV</span> <span class="o">=</span> <span class="n">Builder</span><span class="p">.</span><span class="n">CreateFCmpONE</span><span class="p">(</span>
+ <span class="n">CondV</span><span class="p">,</span> <span class="n">ConstantFP</span><span class="o">::</span><span class="n">get</span><span class="p">(</span><span class="n">getGlobalContext</span><span class="p">(),</span> <span class="n">APFloat</span><span class="p">(</span><span class="mf">0.0</span><span class="p">)),</span> <span class="s">"ifcond"</span><span class="p">);</span>
+
+ <span class="n">Function</span> <span class="o">*</span><span class="n">TheFunction</span> <span class="o">=</span> <span class="n">Builder</span><span class="p">.</span><span class="n">GetInsertBlock</span><span class="p">()</span><span class="o">-></span><span class="n">getParent</span><span class="p">();</span>
+
+ <span class="c1">// Create blocks for the then and else cases. Insert the 'then' block at the</span>
+ <span class="c1">// end of the function.</span>
+ <span class="n">BasicBlock</span> <span class="o">*</span><span class="n">ThenBB</span> <span class="o">=</span>
+ <span class="n">BasicBlock</span><span class="o">::</span><span class="n">Create</span><span class="p">(</span><span class="n">getGlobalContext</span><span class="p">(),</span> <span class="s">"then"</span><span class="p">,</span> <span class="n">TheFunction</span><span class="p">);</span>
+ <span class="n">BasicBlock</span> <span class="o">*</span><span class="n">ElseBB</span> <span class="o">=</span> <span class="n">BasicBlock</span><span class="o">::</span><span class="n">Create</span><span class="p">(</span><span class="n">getGlobalContext</span><span class="p">(),</span> <span class="s">"else"</span><span class="p">);</span>
+ <span class="n">BasicBlock</span> <span class="o">*</span><span class="n">MergeBB</span> <span class="o">=</span> <span class="n">BasicBlock</span><span class="o">::</span><span class="n">Create</span><span class="p">(</span><span class="n">getGlobalContext</span><span class="p">(),</span> <span class="s">"ifcont"</span><span class="p">);</span>
+
+ <span class="n">Builder</span><span class="p">.</span><span class="n">CreateCondBr</span><span class="p">(</span><span class="n">CondV</span><span class="p">,</span> <span class="n">ThenBB</span><span class="p">,</span> <span class="n">ElseBB</span><span class="p">);</span>
+
+ <span class="c1">// Emit then value.</span>
+ <span class="n">Builder</span><span class="p">.</span><span class="n">SetInsertPoint</span><span class="p">(</span><span class="n">ThenBB</span><span class="p">);</span>
+
+ <span class="n">Value</span> <span class="o">*</span><span class="n">ThenV</span> <span class="o">=</span> <span class="n">Then</span><span class="o">-></span><span class="n">codegen</span><span class="p">();</span>
+ <span class="k">if</span> <span class="p">(</span><span class="o">!</span><span class="n">ThenV</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">nullptr</span><span class="p">;</span>
+
+ <span class="n">Builder</span><span class="p">.</span><span class="n">CreateBr</span><span class="p">(</span><span class="n">MergeBB</span><span class="p">);</span>
+ <span class="c1">// Codegen of 'Then' can change the current block, update ThenBB for the PHI.</span>
+ <span class="n">ThenBB</span> <span class="o">=</span> <span class="n">Builder</span><span class="p">.</span><span class="n">GetInsertBlock</span><span class="p">();</span>
+
+ <span class="c1">// Emit else block.</span>
+ <span class="n">TheFunction</span><span class="o">-></span><span class="n">getBasicBlockList</span><span class="p">().</span><span class="n">push_back</span><span class="p">(</span><span class="n">ElseBB</span><span class="p">);</span>
+ <span class="n">Builder</span><span class="p">.</span><span class="n">SetInsertPoint</span><span class="p">(</span><span class="n">ElseBB</span><span class="p">);</span>
+
+ <span class="n">Value</span> <span class="o">*</span><span class="n">ElseV</span> <span class="o">=</span> <span class="n">Else</span><span class="o">-></span><span class="n">codegen</span><span class="p">();</span>
+ <span class="k">if</span> <span class="p">(</span><span class="o">!</span><span class="n">ElseV</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">nullptr</span><span class="p">;</span>
+
+ <span class="n">Builder</span><span class="p">.</span><span class="n">CreateBr</span><span class="p">(</span><span class="n">MergeBB</span><span class="p">);</span>
+ <span class="c1">// Codegen of 'Else' can change the current block, update ElseBB for the PHI.</span>
+ <span class="n">ElseBB</span> <span class="o">=</span> <span class="n">Builder</span><span class="p">.</span><span class="n">GetInsertBlock</span><span class="p">();</span>
+
+ <span class="c1">// Emit merge block.</span>
+ <span class="n">TheFunction</span><span class="o">-></span><span class="n">getBasicBlockList</span><span class="p">().</span><span class="n">push_back</span><span class="p">(</span><span class="n">MergeBB</span><span class="p">);</span>
+ <span class="n">Builder</span><span class="p">.</span><span class="n">SetInsertPoint</span><span class="p">(</span><span class="n">MergeBB</span><span class="p">);</span>
+ <span class="n">PHINode</span> <span class="o">*</span><span class="n">PN</span> <span class="o">=</span>
+ <span class="n">Builder</span><span class="p">.</span><span class="n">CreatePHI</span><span class="p">(</span><span class="n">Type</span><span class="o">::</span><span class="n">getDoubleTy</span><span class="p">(</span><span class="n">getGlobalContext</span><span class="p">()),</span> <span class="mi">2</span><span class="p">,</span> <span class="s">"iftmp"</span><span class="p">);</span>
+
+ <span class="n">PN</span><span class="o">-></span><span class="n">addIncoming</span><span class="p">(</span><span class="n">ThenV</span><span class="p">,</span> <span class="n">ThenBB</span><span class="p">);</span>
+ <span class="n">PN</span><span class="o">-></span><span class="n">addIncoming</span><span class="p">(</span><span class="n">ElseV</span><span class="p">,</span> <span class="n">ElseBB</span><span class="p">);</span>
+ <span class="k">return</span> <span class="n">PN</span><span class="p">;</span>
+<span class="p">}</span>
+
+<span class="c1">// Output for-loop as:</span>
+<span class="c1">// var = alloca double</span>
+<span class="c1">// ...</span>
+<span class="c1">// start = startexpr</span>
+<span class="c1">// store start -> var</span>
+<span class="c1">// goto loop</span>
+<span class="c1">// loop:</span>
+<span class="c1">// ...</span>
+<span class="c1">// bodyexpr</span>
+<span class="c1">// ...</span>
+<span class="c1">// loopend:</span>
+<span class="c1">// step = stepexpr</span>
+<span class="c1">// endcond = endexpr</span>
+<span class="c1">//</span>
+<span class="c1">// curvar = load var</span>
+<span class="c1">// nextvar = curvar + step</span>
+<span class="c1">// store nextvar -> var</span>
+<span class="c1">// br endcond, loop, endloop</span>
+<span class="c1">// outloop:</span>
+<span class="n">Value</span> <span class="o">*</span><span class="n">ForExprAST</span><span class="o">::</span><span class="n">codegen</span><span class="p">()</span> <span class="p">{</span>
+ <span class="n">Function</span> <span class="o">*</span><span class="n">TheFunction</span> <span class="o">=</span> <span class="n">Builder</span><span class="p">.</span><span class="n">GetInsertBlock</span><span class="p">()</span><span class="o">-></span><span class="n">getParent</span><span class="p">();</span>
+
+ <span class="c1">// Create an alloca for the variable in the entry block.</span>
+ <span class="n">AllocaInst</span> <span class="o">*</span><span class="n">Alloca</span> <span class="o">=</span> <span class="n">CreateEntryBlockAlloca</span><span class="p">(</span><span class="n">TheFunction</span><span class="p">,</span> <span class="n">VarName</span><span class="p">);</span>
+
+ <span class="n">KSDbgInfo</span><span class="p">.</span><span class="n">emitLocation</span><span class="p">(</span><span class="k">this</span><span class="p">);</span>
+
+ <span class="c1">// Emit the start code first, without 'variable' in scope.</span>
+ <span class="n">Value</span> <span class="o">*</span><span class="n">StartVal</span> <span class="o">=</span> <span class="n">Start</span><span class="o">-></span><span class="n">codegen</span><span class="p">();</span>
+ <span class="k">if</span> <span class="p">(</span><span class="o">!</span><span class="n">StartVal</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">nullptr</span><span class="p">;</span>
+
+ <span class="c1">// Store the value into the alloca.</span>
+ <span class="n">Builder</span><span class="p">.</span><span class="n">CreateStore</span><span class="p">(</span><span class="n">StartVal</span><span class="p">,</span> <span class="n">Alloca</span><span class="p">);</span>
+
+ <span class="c1">// Make the new basic block for the loop header, inserting after current</span>
+ <span class="c1">// block.</span>
+ <span class="n">BasicBlock</span> <span class="o">*</span><span class="n">LoopBB</span> <span class="o">=</span>
+ <span class="n">BasicBlock</span><span class="o">::</span><span class="n">Create</span><span class="p">(</span><span class="n">getGlobalContext</span><span class="p">(),</span> <span class="s">"loop"</span><span class="p">,</span> <span class="n">TheFunction</span><span class="p">);</span>
+
+ <span class="c1">// Insert an explicit fall through from the current block to the LoopBB.</span>
+ <span class="n">Builder</span><span class="p">.</span><span class="n">CreateBr</span><span class="p">(</span><span class="n">LoopBB</span><span class="p">);</span>
+
+ <span class="c1">// Start insertion in LoopBB.</span>
+ <span class="n">Builder</span><span class="p">.</span><span class="n">SetInsertPoint</span><span class="p">(</span><span class="n">LoopBB</span><span class="p">);</span>
+
+ <span class="c1">// Within the loop, the variable is defined equal to the PHI node. If it</span>
+ <span class="c1">// shadows an existing variable, we have to restore it, so save it now.</span>
+ <span class="n">AllocaInst</span> <span class="o">*</span><span class="n">OldVal</span> <span class="o">=</span> <span class="n">NamedValues</span><span class="p">[</span><span class="n">VarName</span><span class="p">];</span>
+ <span class="n">NamedValues</span><span class="p">[</span><span class="n">VarName</span><span class="p">]</span> <span class="o">=</span> <span class="n">Alloca</span><span class="p">;</span>
+
+ <span class="c1">// Emit the body of the loop. This, like any other expr, can change the</span>
+ <span class="c1">// current BB. Note that we ignore the value computed by the body, but don't</span>
+ <span class="c1">// allow an error.</span>
+ <span class="k">if</span> <span class="p">(</span><span class="o">!</span><span class="n">Body</span><span class="o">-></span><span class="n">codegen</span><span class="p">())</span>
+ <span class="k">return</span> <span class="n">nullptr</span><span class="p">;</span>
+
+ <span class="c1">// Emit the step value.</span>
+ <span class="n">Value</span> <span class="o">*</span><span class="n">StepVal</span> <span class="o">=</span> <span class="n">nullptr</span><span class="p">;</span>
+ <span class="k">if</span> <span class="p">(</span><span class="n">Step</span><span class="p">)</span> <span class="p">{</span>
+ <span class="n">StepVal</span> <span class="o">=</span> <span class="n">Step</span><span class="o">-></span><span class="n">codegen</span><span class="p">();</span>
+ <span class="k">if</span> <span class="p">(</span><span class="o">!</span><span class="n">StepVal</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">nullptr</span><span class="p">;</span>
+ <span class="p">}</span> <span class="k">else</span> <span class="p">{</span>
+ <span class="c1">// If not specified, use 1.0.</span>
+ <span class="n">StepVal</span> <span class="o">=</span> <span class="n">ConstantFP</span><span class="o">::</span><span class="n">get</span><span class="p">(</span><span class="n">getGlobalContext</span><span class="p">(),</span> <span class="n">APFloat</span><span class="p">(</span><span class="mf">1.0</span><span class="p">));</span>
+ <span class="p">}</span>
+
+ <span class="c1">// Compute the end condition.</span>
+ <span class="n">Value</span> <span class="o">*</span><span class="n">EndCond</span> <span class="o">=</span> <span class="n">End</span><span class="o">-></span><span class="n">codegen</span><span class="p">();</span>
+ <span class="k">if</span> <span class="p">(</span><span class="o">!</span><span class="n">EndCond</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">nullptr</span><span class="p">;</span>
+
+ <span class="c1">// Reload, increment, and restore the alloca. This handles the case where</span>
+ <span class="c1">// the body of the loop mutates the variable.</span>
+ <span class="n">Value</span> <span class="o">*</span><span class="n">CurVar</span> <span class="o">=</span> <span class="n">Builder</span><span class="p">.</span><span class="n">CreateLoad</span><span class="p">(</span><span class="n">Alloca</span><span class="p">,</span> <span class="n">VarName</span><span class="p">.</span><span class="n">c_str</span><span class="p">());</span>
+ <span class="n">Value</span> <span class="o">*</span><span class="n">NextVar</span> <span class="o">=</span> <span class="n">Builder</span><span class="p">.</span><span class="n">CreateFAdd</span><span class="p">(</span><span class="n">CurVar</span><span class="p">,</span> <span class="n">StepVal</span><span class="p">,</span> <span class="s">"nextvar"</span><span class="p">);</span>
+ <span class="n">Builder</span><span class="p">.</span><span class="n">CreateStore</span><span class="p">(</span><span class="n">NextVar</span><span class="p">,</span> <span class="n">Alloca</span><span class="p">);</span>
+
+ <span class="c1">// Convert condition to a bool by comparing equal to 0.0.</span>
+ <span class="n">EndCond</span> <span class="o">=</span> <span class="n">Builder</span><span class="p">.</span><span class="n">CreateFCmpONE</span><span class="p">(</span>
+ <span class="n">EndCond</span><span class="p">,</span> <span class="n">ConstantFP</span><span class="o">::</span><span class="n">get</span><span class="p">(</span><span class="n">getGlobalContext</span><span class="p">(),</span> <span class="n">APFloat</span><span class="p">(</span><span class="mf">0.0</span><span class="p">)),</span> <span class="s">"loopcond"</span><span class="p">);</span>
+
+ <span class="c1">// Create the "after loop" block and insert it.</span>
+ <span class="n">BasicBlock</span> <span class="o">*</span><span class="n">AfterBB</span> <span class="o">=</span>
+ <span class="n">BasicBlock</span><span class="o">::</span><span class="n">Create</span><span class="p">(</span><span class="n">getGlobalContext</span><span class="p">(),</span> <span class="s">"afterloop"</span><span class="p">,</span> <span class="n">TheFunction</span><span class="p">);</span>
+
+ <span class="c1">// Insert the conditional branch into the end of LoopEndBB.</span>
+ <span class="n">Builder</span><span class="p">.</span><span class="n">CreateCondBr</span><span class="p">(</span><span class="n">EndCond</span><span class="p">,</span> <span class="n">LoopBB</span><span class="p">,</span> <span class="n">AfterBB</span><span class="p">);</span>
+
+ <span class="c1">// Any new code will be inserted in AfterBB.</span>
+ <span class="n">Builder</span><span class="p">.</span><span class="n">SetInsertPoint</span><span class="p">(</span><span class="n">AfterBB</span><span class="p">);</span>
+
+ <span class="c1">// Restore the unshadowed variable.</span>
+ <span class="k">if</span> <span class="p">(</span><span class="n">OldVal</span><span class="p">)</span>
+ <span class="n">NamedValues</span><span class="p">[</span><span class="n">VarName</span><span class="p">]</span> <span class="o">=</span> <span class="n">OldVal</span><span class="p">;</span>
+ <span class="k">else</span>
+ <span class="n">NamedValues</span><span class="p">.</span><span class="n">erase</span><span class="p">(</span><span class="n">VarName</span><span class="p">);</span>
+
+ <span class="c1">// for expr always returns 0.0.</span>
+ <span class="k">return</span> <span class="n">Constant</span><span class="o">::</span><span class="n">getNullValue</span><span class="p">(</span><span class="n">Type</span><span class="o">::</span><span class="n">getDoubleTy</span><span class="p">(</span><span class="n">getGlobalContext</span><span class="p">()));</span>
+<span class="p">}</span>
+
+<span class="n">Value</span> <span class="o">*</span><span class="n">VarExprAST</span><span class="o">::</span><span class="n">codegen</span><span class="p">()</span> <span class="p">{</span>
+ <span class="n">std</span><span class="o">::</span><span class="n">vector</span><span class="o"><</span><span class="n">AllocaInst</span> <span class="o">*></span> <span class="n">OldBindings</span><span class="p">;</span>
+
+ <span class="n">Function</span> <span class="o">*</span><span class="n">TheFunction</span> <span class="o">=</span> <span class="n">Builder</span><span class="p">.</span><span class="n">GetInsertBlock</span><span class="p">()</span><span class="o">-></span><span class="n">getParent</span><span class="p">();</span>
+
+ <span class="c1">// Register all variables and emit their initializer.</span>
+ <span class="k">for</span> <span class="p">(</span><span class="kt">unsigned</span> <span class="n">i</span> <span class="o">=</span> <span class="mi">0</span><span class="p">,</span> <span class="n">e</span> <span class="o">=</span> <span class="n">VarNames</span><span class="p">.</span><span class="n">size</span><span class="p">();</span> <span class="n">i</span> <span class="o">!=</span> <span class="n">e</span><span class="p">;</span> <span class="o">++</span><span class="n">i</span><span class="p">)</span> <span class="p">{</span>
+ <span class="k">const</span> <span class="n">std</span><span class="o">::</span><span class="n">string</span> <span class="o">&</span><span class="n">VarName</span> <span class="o">=</span> <span class="n">VarNames</span><span class="p">[</span><span class="n">i</span><span class="p">].</span><span class="n">first</span><span class="p">;</span>
+ <span class="n">ExprAST</span> <span class="o">*</span><span class="n">Init</span> <span class="o">=</span> <span class="n">VarNames</span><span class="p">[</span><span class="n">i</span><span class="p">].</span><span class="n">second</span><span class="p">.</span><span class="n">get</span><span class="p">();</span>
+
+ <span class="c1">// Emit the initializer before adding the variable to scope, this prevents</span>
+ <span class="c1">// the initializer from referencing the variable itself, and permits stuff</span>
+ <span class="c1">// like this:</span>
+ <span class="c1">// var a = 1 in</span>
+ <span class="c1">// var a = a in ... # refers to outer 'a'.</span>
+ <span class="n">Value</span> <span class="o">*</span><span class="n">InitVal</span><span class="p">;</span>
+ <span class="k">if</span> <span class="p">(</span><span class="n">Init</span><span class="p">)</span> <span class="p">{</span>
+ <span class="n">InitVal</span> <span class="o">=</span> <span class="n">Init</span><span class="o">-></span><span class="n">codegen</span><span class="p">();</span>
+ <span class="k">if</span> <span class="p">(</span><span class="o">!</span><span class="n">InitVal</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">nullptr</span><span class="p">;</span>
+ <span class="p">}</span> <span class="k">else</span> <span class="p">{</span> <span class="c1">// If not specified, use 0.0.</span>
+ <span class="n">InitVal</span> <span class="o">=</span> <span class="n">ConstantFP</span><span class="o">::</span><span class="n">get</span><span class="p">(</span><span class="n">getGlobalContext</span><span class="p">(),</span> <span class="n">APFloat</span><span class="p">(</span><span class="mf">0.0</span><span class="p">));</span>
+ <span class="p">}</span>
+
+ <span class="n">AllocaInst</span> <span class="o">*</span><span class="n">Alloca</span> <span class="o">=</span> <span class="n">CreateEntryBlockAlloca</span><span class="p">(</span><span class="n">TheFunction</span><span class="p">,</span> <span class="n">VarName</span><span class="p">);</span>
+ <span class="n">Builder</span><span class="p">.</span><span class="n">CreateStore</span><span class="p">(</span><span class="n">InitVal</span><span class="p">,</span> <span class="n">Alloca</span><span class="p">);</span>
+
+ <span class="c1">// Remember the old variable binding so that we can restore the binding when</span>
+ <span class="c1">// we unrecurse.</span>
+ <span class="n">OldBindings</span><span class="p">.</span><span class="n">push_back</span><span class="p">(</span><span class="n">NamedValues</span><span class="p">[</span><span class="n">VarName</span><span class="p">]);</span>
+
+ <span class="c1">// Remember this binding.</span>
+ <span class="n">NamedValues</span><span class="p">[</span><span class="n">VarName</span><span class="p">]</span> <span class="o">=</span> <span class="n">Alloca</span><span class="p">;</span>
+ <span class="p">}</span>
+
+ <span class="n">KSDbgInfo</span><span class="p">.</span><span class="n">emitLocation</span><span class="p">(</span><span class="k">this</span><span class="p">);</span>
+
+ <span class="c1">// Codegen the body, now that all vars are in scope.</span>
+ <span class="n">Value</span> <span class="o">*</span><span class="n">BodyVal</span> <span class="o">=</span> <span class="n">Body</span><span class="o">-></span><span class="n">codegen</span><span class="p">();</span>
+ <span class="k">if</span> <span class="p">(</span><span class="o">!</span><span class="n">BodyVal</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">nullptr</span><span class="p">;</span>
+
+ <span class="c1">// Pop all our variables from scope.</span>
+ <span class="k">for</span> <span class="p">(</span><span class="kt">unsigned</span> <span class="n">i</span> <span class="o">=</span> <span class="mi">0</span><span class="p">,</span> <span class="n">e</span> <span class="o">=</span> <span class="n">VarNames</span><span class="p">.</span><span class="n">size</span><span class="p">();</span> <span class="n">i</span> <span class="o">!=</span> <span class="n">e</span><span class="p">;</span> <span class="o">++</span><span class="n">i</span><span class="p">)</span>
+ <span class="n">NamedValues</span><span class="p">[</span><span class="n">VarNames</span><span class="p">[</span><span class="n">i</span><span class="p">].</span><span class="n">first</span><span class="p">]</span> <span class="o">=</span> <span class="n">OldBindings</span><span class="p">[</span><span class="n">i</span><span class="p">];</span>
+
+ <span class="c1">// Return the body computation.</span>
+ <span class="k">return</span> <span class="n">BodyVal</span><span class="p">;</span>
+<span class="p">}</span>
+
+<span class="n">Function</span> <span class="o">*</span><span class="n">PrototypeAST</span><span class="o">::</span><span class="n">codegen</span><span class="p">()</span> <span class="p">{</span>
+ <span class="c1">// Make the function type: double(double,double) etc.</span>
+ <span class="n">std</span><span class="o">::</span><span class="n">vector</span><span class="o"><</span><span class="n">Type</span> <span class="o">*></span> <span class="n">Doubles</span><span class="p">(</span><span class="n">Args</span><span class="p">.</span><span class="n">size</span><span class="p">(),</span>
+ <span class="n">Type</span><span class="o">::</span><span class="n">getDoubleTy</span><span class="p">(</span><span class="n">getGlobalContext</span><span class="p">()));</span>
+ <span class="n">FunctionType</span> <span class="o">*</span><span class="n">FT</span> <span class="o">=</span>
+ <span class="n">FunctionType</span><span class="o">::</span><span class="n">get</span><span class="p">(</span><span class="n">Type</span><span class="o">::</span><span class="n">getDoubleTy</span><span class="p">(</span><span class="n">getGlobalContext</span><span class="p">()),</span> <span class="n">Doubles</span><span class="p">,</span> <span class="nb">false</span><span class="p">);</span>
+
+ <span class="n">Function</span> <span class="o">*</span><span class="n">F</span> <span class="o">=</span>
+ <span class="n">Function</span><span class="o">::</span><span class="n">Create</span><span class="p">(</span><span class="n">FT</span><span class="p">,</span> <span class="n">Function</span><span class="o">::</span><span class="n">ExternalLinkage</span><span class="p">,</span> <span class="n">Name</span><span class="p">,</span> <span class="n">TheModule</span><span class="p">.</span><span class="n">get</span><span class="p">());</span>
+
+ <span class="c1">// Set names for all arguments.</span>
+ <span class="kt">unsigned</span> <span class="n">Idx</span> <span class="o">=</span> <span class="mi">0</span><span class="p">;</span>
+ <span class="k">for</span> <span class="p">(</span><span class="k">auto</span> <span class="o">&</span><span class="n">Arg</span> <span class="o">:</span> <span class="n">F</span><span class="o">-></span><span class="n">args</span><span class="p">())</span>
+ <span class="n">Arg</span><span class="p">.</span><span class="n">setName</span><span class="p">(</span><span class="n">Args</span><span class="p">[</span><span class="n">Idx</span><span class="o">++</span><span class="p">]);</span>
+
+ <span class="k">return</span> <span class="n">F</span><span class="p">;</span>
+<span class="p">}</span>
+
+<span class="n">Function</span> <span class="o">*</span><span class="n">FunctionAST</span><span class="o">::</span><span class="n">codegen</span><span class="p">()</span> <span class="p">{</span>
+ <span class="c1">// Transfer ownership of the prototype to the FunctionProtos map, but keep a</span>
+ <span class="c1">// reference to it for use below.</span>
+ <span class="k">auto</span> <span class="o">&</span><span class="n">P</span> <span class="o">=</span> <span class="o">*</span><span class="n">Proto</span><span class="p">;</span>
+ <span class="n">FunctionProtos</span><span class="p">[</span><span class="n">Proto</span><span class="o">-></span><span class="n">getName</span><span class="p">()]</span> <span class="o">=</span> <span class="n">std</span><span class="o">::</span><span class="n">move</span><span class="p">(</span><span class="n">Proto</span><span class="p">);</span>
+ <span class="n">Function</span> <span class="o">*</span><span class="n">TheFunction</span> <span class="o">=</span> <span class="n">getFunction</span><span class="p">(</span><span class="n">P</span><span class="p">.</span><span class="n">getName</span><span class="p">());</span>
+ <span class="k">if</span> <span class="p">(</span><span class="o">!</span><span class="n">TheFunction</span><span class="p">)</span>
+ <span class="k">return</span> <span class="n">nullptr</span><span class="p">;</span>
+
+ <span class="c1">// If this is an operator, install it.</span>
+ <span class="k">if</span> <span class="p">(</span><span class="n">P</span><span class="p">.</span><span class="n">isBinaryOp</span><span class="p">())</span>
+ <span class="n">BinopPrecedence</span><span class="p">[</span><span class="n">P</span><span class="p">.</span><span class="n">getOperatorName</span><span class="p">()]</span> <span class="o">=</span> <span class="n">P</span><span class="p">.</span><span class="n">getBinaryPrecedence</span><span class="p">();</span>
+
+ <span class="c1">// Create a new basic block to start insertion into.</span>
+ <span class="n">BasicBlock</span> <span class="o">*</span><span class="n">BB</span> <span class="o">=</span> <span class="n">BasicBlock</span><span class="o">::</span><span class="n">Create</span><span class="p">(</span><span class="n">getGlobalContext</span><span class="p">(),</span> <span class="s">"entry"</span><span class="p">,</span> <span class="n">TheFunction</span><span class="p">);</span>
+ <span class="n">Builder</span><span class="p">.</span><span class="n">SetInsertPoint</span><span class="p">(</span><span class="n">BB</span><span class="p">);</span>
+
+ <span class="c1">// Create a subprogram DIE for this function.</span>
+ <span class="n">DIFile</span> <span class="o">*</span><span class="n">Unit</span> <span class="o">=</span> <span class="n">DBuilder</span><span class="o">-></span><span class="n">createFile</span><span class="p">(</span><span class="n">KSDbgInfo</span><span class="p">.</span><span class="n">TheCU</span><span class="o">-></span><span class="n">getFilename</span><span class="p">(),</span>
+ <span class="n">KSDbgInfo</span><span class="p">.</span><span class="n">TheCU</span><span class="o">-></span><span class="n">getDirectory</span><span class="p">());</span>
+ <span class="n">DIScope</span> <span class="o">*</span><span class="n">FContext</span> <span class="o">=</span> <span class="n">Unit</span><span class="p">;</span>
+ <span class="kt">unsigned</span> <span class="n">LineNo</span> <span class="o">=</span> <span class="n">P</span><span class="p">.</span><span class="n">getLine</span><span class="p">();</span>
+ <span class="kt">unsigned</span> <span class="n">ScopeLine</span> <span class="o">=</span> <span class="n">LineNo</span><span class="p">;</span>
+ <span class="n">DISubprogram</span> <span class="o">*</span><span class="n">SP</span> <span class="o">=</span> <span class="n">DBuilder</span><span class="o">-></span><span class="n">createFunction</span><span class="p">(</span>
+ <span class="n">FContext</span><span class="p">,</span> <span class="n">P</span><span class="p">.</span><span class="n">getName</span><span class="p">(),</span> <span class="n">StringRef</span><span class="p">(),</span> <span class="n">Unit</span><span class="p">,</span> <span class="n">LineNo</span><span class="p">,</span>
+ <span class="n">CreateFunctionType</span><span class="p">(</span><span class="n">TheFunction</span><span class="o">-></span><span class="n">arg_size</span><span class="p">(),</span> <span class="n">Unit</span><span class="p">),</span>
+ <span class="nb">false</span> <span class="cm">/* internal linkage */</span><span class="p">,</span> <span class="nb">true</span> <span class="cm">/* definition */</span><span class="p">,</span> <span class="n">ScopeLine</span><span class="p">,</span>
+ <span class="n">DINode</span><span class="o">::</span><span class="n">FlagPrototyped</span><span class="p">,</span> <span class="nb">false</span><span class="p">);</span>
+ <span class="n">TheFunction</span><span class="o">-></span><span class="n">setSubprogram</span><span class="p">(</span><span class="n">SP</span><span class="p">);</span>
+
+ <span class="c1">// Push the current scope.</span>
+ <span class="n">KSDbgInfo</span><span class="p">.</span><span class="n">LexicalBlocks</span><span class="p">.</span><span class="n">push_back</span><span class="p">(</span><span class="n">SP</span><span class="p">);</span>
+
+ <span class="c1">// Unset the location for the prologue emission (leading instructions with no</span>
+ <span class="c1">// location in a function are considered part of the prologue and the debugger</span>
+ <span class="c1">// will run past them when breaking on a function)</span>
+ <span class="n">KSDbgInfo</span><span class="p">.</span><span class="n">emitLocation</span><span class="p">(</span><span class="n">nullptr</span><span class="p">);</span>
+
+ <span class="c1">// Record the function arguments in the NamedValues map.</span>
+ <span class="n">NamedValues</span><span class="p">.</span><span class="n">clear</span><span class="p">();</span>
+ <span class="kt">unsigned</span> <span class="n">ArgIdx</span> <span class="o">=</span> <span class="mi">0</span><span class="p">;</span>
+ <span class="k">for</span> <span class="p">(</span><span class="k">auto</span> <span class="o">&</span><span class="n">Arg</span> <span class="o">:</span> <span class="n">TheFunction</span><span class="o">-></span><span class="n">args</span><span class="p">())</span> <span class="p">{</span>
+ <span class="c1">// Create an alloca for this variable.</span>
+ <span class="n">AllocaInst</span> <span class="o">*</span><span class="n">Alloca</span> <span class="o">=</span> <span class="n">CreateEntryBlockAlloca</span><span class="p">(</span><span class="n">TheFunction</span><span class="p">,</span> <span class="n">Arg</span><span class="p">.</span><span class="n">getName</span><span class="p">());</span>
+
+ <span class="c1">// Create a debug descriptor for the variable.</span>
+ <span class="n">DILocalVariable</span> <span class="o">*</span><span class="n">D</span> <span class="o">=</span> <span class="n">DBuilder</span><span class="o">-></span><span class="n">createParameterVariable</span><span class="p">(</span>
+ <span class="n">SP</span><span class="p">,</span> <span class="n">Arg</span><span class="p">.</span><span class="n">getName</span><span class="p">(),</span> <span class="o">++</span><span class="n">ArgIdx</span><span class="p">,</span> <span class="n">Unit</span><span class="p">,</span> <span class="n">LineNo</span><span class="p">,</span> <span class="n">KSDbgInfo</span><span class="p">.</span><span class="n">getDoubleTy</span><span class="p">(),</span>
+ <span class="nb">true</span><span class="p">);</span>
+
+ <span class="n">DBuilder</span><span class="o">-></span><span class="n">insertDeclare</span><span class="p">(</span><span class="n">Alloca</span><span class="p">,</span> <span class="n">D</span><span class="p">,</span> <span class="n">DBuilder</span><span class="o">-></span><span class="n">createExpression</span><span class="p">(),</span>
+ <span class="n">DebugLoc</span><span class="o">::</span><span class="n">get</span><span class="p">(</span><span class="n">LineNo</span><span class="p">,</span> <span class="mi">0</span><span class="p">,</span> <span class="n">SP</span><span class="p">),</span>
+ <span class="n">Builder</span><span class="p">.</span><span class="n">GetInsertBlock</span><span class="p">());</span>
+
+ <span class="c1">// Store the initial value into the alloca.</span>
+ <span class="n">Builder</span><span class="p">.</span><span class="n">CreateStore</span><span class="p">(</span><span class="o">&</span><span class="n">Arg</span><span class="p">,</span> <span class="n">Alloca</span><span class="p">);</span>
+
+ <span class="c1">// Add arguments to variable symbol table.</span>
+ <span class="n">NamedValues</span><span class="p">[</span><span class="n">Arg</span><span class="p">.</span><span class="n">getName</span><span class="p">()]</span> <span class="o">=</span> <span class="n">Alloca</span><span class="p">;</span>
+ <span class="p">}</span>
+
+ <span class="n">KSDbgInfo</span><span class="p">.</span><span class="n">emitLocation</span><span class="p">(</span><span class="n">Body</span><span class="p">.</span><span class="n">get</span><span class="p">());</span>
+
+ <span class="k">if</span> <span class="p">(</span><span class="n">Value</span> <span class="o">*</span><span class="n">RetVal</span> <span class="o">=</span> <span class="n">Body</span><span class="o">-></span><span class="n">codegen</span><span class="p">())</span> <span class="p">{</span>
+ <span class="c1">// Finish off the function.</span>
+ <span class="n">Builder</span><span class="p">.</span><span class="n">CreateRet</span><span class="p">(</span><span class="n">RetVal</span><span class="p">);</span>
+
+ <span class="c1">// Pop off the lexical block for the function.</span>
+ <span class="n">KSDbgInfo</span><span class="p">.</span><span class="n">LexicalBlocks</span><span class="p">.</span><span class="n">pop_back</span><span class="p">();</span>
+
+ <span class="c1">// Validate the generated code, checking for consistency.</span>
+ <span class="n">verifyFunction</span><span class="p">(</span><span class="o">*</span><span class="n">TheFunction</span><span class="p">);</span>
+
+ <span class="k">return</span> <span class="n">TheFunction</span><span class="p">;</span>
+ <span class="p">}</span>
+
+ <span class="c1">// Error reading body, remove function.</span>
+ <span class="n">TheFunction</span><span class="o">-></span><span class="n">eraseFromParent</span><span class="p">();</span>
+
+ <span class="k">if</span> <span class="p">(</span><span class="n">P</span><span class="p">.</span><span class="n">isBinaryOp</span><span class="p">())</span>
+ <span class="n">BinopPrecedence</span><span class="p">.</span><span class="n">erase</span><span class="p">(</span><span class="n">Proto</span><span class="o">-></span><span class="n">getOperatorName</span><span class="p">());</span>
+
+ <span class="c1">// Pop off the lexical block for the function since we added it</span>
+ <span class="c1">// unconditionally.</span>
+ <span class="n">KSDbgInfo</span><span class="p">.</span><span class="n">LexicalBlocks</span><span class="p">.</span><span class="n">pop_back</span><span class="p">();</span>
+
+ <span class="k">return</span> <span class="n">nullptr</span><span class="p">;</span>
+<span class="p">}</span>
+
+<span class="c1">//===----------------------------------------------------------------------===//</span>
+<span class="c1">// Top-Level parsing and JIT Driver</span>
+<span class="c1">//===----------------------------------------------------------------------===//</span>
+
+<span class="k">static</span> <span class="kt">void</span> <span class="n">InitializeModule</span><span class="p">()</span> <span class="p">{</span>
+ <span class="c1">// Open a new module.</span>
+ <span class="n">TheModule</span> <span class="o">=</span> <span class="n">llvm</span><span class="o">::</span><span class="n">make_unique</span><span class="o"><</span><span class="n">Module</span><span class="o">></span><span class="p">(</span><span class="s">"my cool jit"</span><span class="p">,</span> <span class="n">getGlobalContext</span><span class="p">());</span>
+ <span class="n">TheModule</span><span class="o">-></span><span class="n">setDataLayout</span><span class="p">(</span><span class="n">TheJIT</span><span class="o">-></span><span class="n">getTargetMachine</span><span class="p">().</span><span class="n">createDataLayout</span><span class="p">());</span>
+<span class="p">}</span>
+
+<span class="k">static</span> <span class="kt">void</span> <span class="n">HandleDefinition</span><span class="p">()</span> <span class="p">{</span>
+ <span class="k">if</span> <span class="p">(</span><span class="k">auto</span> <span class="n">FnAST</span> <span class="o">=</span> <span class="n">ParseDefinition</span><span class="p">())</span> <span class="p">{</span>
+ <span class="k">if</span> <span class="p">(</span><span class="o">!</span><span class="n">FnAST</span><span class="o">-></span><span class="n">codegen</span><span class="p">())</span>
+ <span class="n">fprintf</span><span class="p">(</span><span class="n">stderr</span><span class="p">,</span> <span class="s">"Error reading function definition:"</span><span class="p">);</span>
+ <span class="p">}</span> <span class="k">else</span> <span class="p">{</span>
+ <span class="c1">// Skip token for error recovery.</span>
+ <span class="n">getNextToken</span><span class="p">();</span>
+ <span class="p">}</span>
+<span class="p">}</span>
+
+<span class="k">static</span> <span class="kt">void</span> <span class="n">HandleExtern</span><span class="p">()</span> <span class="p">{</span>
+ <span class="k">if</span> <span class="p">(</span><span class="k">auto</span> <span class="n">ProtoAST</span> <span class="o">=</span> <span class="n">ParseExtern</span><span class="p">())</span> <span class="p">{</span>
+ <span class="k">if</span> <span class="p">(</span><span class="o">!</span><span class="n">ProtoAST</span><span class="o">-></span><span class="n">codegen</span><span class="p">())</span>
+ <span class="n">fprintf</span><span class="p">(</span><span class="n">stderr</span><span class="p">,</span> <span class="s">"Error reading extern"</span><span class="p">);</span>
+ <span class="k">else</span>
+ <span class="n">FunctionProtos</span><span class="p">[</span><span class="n">ProtoAST</span><span class="o">-></span><span class="n">getName</span><span class="p">()]</span> <span class="o">=</span> <span class="n">std</span><span class="o">::</span><span class="n">move</span><span class="p">(</span><span class="n">ProtoAST</span><span class="p">);</span>
+ <span class="p">}</span> <span class="k">else</span> <span class="p">{</span>
+ <span class="c1">// Skip token for error recovery.</span>
+ <span class="n">getNextToken</span><span class="p">();</span>
+ <span class="p">}</span>
+<span class="p">}</span>
+
+<span class="k">static</span> <span class="kt">void</span> <span class="n">HandleTopLevelExpression</span><span class="p">()</span> <span class="p">{</span>
+ <span class="c1">// Evaluate a top-level expression into an anonymous function.</span>
+ <span class="k">if</span> <span class="p">(</span><span class="k">auto</span> <span class="n">FnAST</span> <span class="o">=</span> <span class="n">ParseTopLevelExpr</span><span class="p">())</span> <span class="p">{</span>
+ <span class="k">if</span> <span class="p">(</span><span class="o">!</span><span class="n">FnAST</span><span class="o">-></span><span class="n">codegen</span><span class="p">())</span> <span class="p">{</span>
+ <span class="n">fprintf</span><span class="p">(</span><span class="n">stderr</span><span class="p">,</span> <span class="s">"Error generating code for top level expr"</span><span class="p">);</span>
+ <span class="p">}</span>
+ <span class="p">}</span> <span class="k">else</span> <span class="p">{</span>
+ <span class="c1">// Skip token for error recovery.</span>
+ <span class="n">getNextToken</span><span class="p">();</span>
+ <span class="p">}</span>
+<span class="p">}</span>
+
+<span class="c1">/// top ::= definition | external | expression | ';'</span>
+<span class="k">static</span> <span class="kt">void</span> <span class="n">MainLoop</span><span class="p">()</span> <span class="p">{</span>
+ <span class="k">while</span> <span class="p">(</span><span class="mi">1</span><span class="p">)</span> <span class="p">{</span>
+ <span class="k">switch</span> <span class="p">(</span><span class="n">CurTok</span><span class="p">)</span> <span class="p">{</span>
+ <span class="k">case</span> <span class="n">tok_eof</span>:
+ <span class="k">return</span><span class="p">;</span>
+ <span class="k">case</span> <span class="sc">';'</span>: <span class="c1">// ignore top-level semicolons.</span>
+ <span class="n">getNextToken</span><span class="p">();</span>
+ <span class="k">break</span><span class="p">;</span>
+ <span class="k">case</span> <span class="n">tok_def</span>:
+ <span class="n">HandleDefinition</span><span class="p">();</span>
+ <span class="k">break</span><span class="p">;</span>
+ <span class="k">case</span> <span class="n">tok_extern</span>:
+ <span class="n">HandleExtern</span><span class="p">();</span>
+ <span class="k">break</span><span class="p">;</span>
+ <span class="nl">default:</span>
+ <span class="n">HandleTopLevelExpression</span><span class="p">();</span>
+ <span class="k">break</span><span class="p">;</span>
+ <span class="p">}</span>
+ <span class="p">}</span>
+<span class="p">}</span>
+
+<span class="c1">//===----------------------------------------------------------------------===//</span>
+<span class="c1">// "Library" functions that can be "extern'd" from user code.</span>
+<span class="c1">//===----------------------------------------------------------------------===//</span>
+
+<span class="c1">/// putchard - putchar that takes a double and returns 0.</span>
+<span class="k">extern</span> <span class="s">"C"</span> <span class="kt">double</span> <span class="n">putchard</span><span class="p">(</span><span class="kt">double</span> <span class="n">X</span><span class="p">)</span> <span class="p">{</span>
+ <span class="n">fputc</span><span class="p">((</span><span class="kt">char</span><span class="p">)</span><span class="n">X</span><span class="p">,</span> <span class="n">stderr</span><span class="p">);</span>
+ <span class="k">return</span> <span class="mi">0</span><span class="p">;</span>
+<span class="p">}</span>
+
+<span class="c1">/// printd - printf that takes a double prints it as "%f\n", returning 0.</span>
+<span class="k">extern</span> <span class="s">"C"</span> <span class="kt">double</span> <span class="n">printd</span><span class="p">(</span><span class="kt">double</span> <span class="n">X</span><span class="p">)</span> <span class="p">{</span>
+ <span class="n">fprintf</span><span class="p">(</span><span class="n">stderr</span><span class="p">,</span> <span class="s">"%f</span><span class="se">\n</span><span class="s">"</span><span class="p">,</span> <span class="n">X</span><span class="p">);</span>
+ <span class="k">return</span> <span class="mi">0</span><span class="p">;</span>
+<span class="p">}</span>
+
+<span class="c1">//===----------------------------------------------------------------------===//</span>
+<span class="c1">// Main driver code.</span>
+<span class="c1">//===----------------------------------------------------------------------===//</span>
+
+<span class="kt">int</span> <span class="n">main</span><span class="p">()</span> <span class="p">{</span>
+ <span class="n">InitializeNativeTarget</span><span class="p">();</span>
+ <span class="n">InitializeNativeTargetAsmPrinter</span><span class="p">();</span>
+ <span class="n">InitializeNativeTargetAsmParser</span><span class="p">();</span>
+
+ <span class="c1">// Install standard binary operators.</span>
+ <span class="c1">// 1 is lowest precedence.</span>
+ <span class="n">BinopPrecedence</span><span class="p">[</span><span class="sc">'='</span><span class="p">]</span> <span class="o">=</span> <span class="mi">2</span><span class="p">;</span>
+ <span class="n">BinopPrecedence</span><span class="p">[</span><span class="sc">'<'</span><span class="p">]</span> <span class="o">=</span> <span class="mi">10</span><span class="p">;</span>
+ <span class="n">BinopPrecedence</span><span class="p">[</span><span class="sc">'+'</span><span class="p">]</span> <span class="o">=</span> <span class="mi">20</span><span class="p">;</span>
+ <span class="n">BinopPrecedence</span><span class="p">[</span><span class="sc">'-'</span><span class="p">]</span> <span class="o">=</span> <span class="mi">20</span><span class="p">;</span>
+ <span class="n">BinopPrecedence</span><span class="p">[</span><span class="sc">'*'</span><span class="p">]</span> <span class="o">=</span> <span class="mi">40</span><span class="p">;</span> <span class="c1">// highest.</span>
+
+ <span class="c1">// Prime the first token.</span>
+ <span class="n">getNextToken</span><span class="p">();</span>
+
+ <span class="n">TheJIT</span> <span class="o">=</span> <span class="n">llvm</span><span class="o">::</span><span class="n">make_unique</span><span class="o"><</span><span class="n">KaleidoscopeJIT</span><span class="o">></span><span class="p">();</span>
+
+ <span class="n">InitializeModule</span><span class="p">();</span>
+
+ <span class="c1">// Add the current debug info version into the module.</span>
+ <span class="n">TheModule</span><span class="o">-></span><span class="n">addModuleFlag</span><span class="p">(</span><span class="n">Module</span><span class="o">::</span><span class="n">Warning</span><span class="p">,</span> <span class="s">"Debug Info Version"</span><span class="p">,</span>
+ <span class="n">DEBUG_METADATA_VERSION</span><span class="p">);</span>
+
+ <span class="c1">// Darwin only supports dwarf2.</span>
+ <span class="k">if</span> <span class="p">(</span><span class="n">Triple</span><span class="p">(</span><span class="n">sys</span><span class="o">::</span><span class="n">getProcessTriple</span><span class="p">()).</span><span class="n">isOSDarwin</span><span class="p">())</span>
+ <span class="n">TheModule</span><span class="o">-></span><span class="n">addModuleFlag</span><span class="p">(</span><span class="n">llvm</span><span class="o">::</span><span class="n">Module</span><span class="o">::</span><span class="n">Warning</span><span class="p">,</span> <span class="s">"Dwarf Version"</span><span class="p">,</span> <span class="mi">2</span><span class="p">);</span>
+
+ <span class="c1">// Construct the DIBuilder, we do this here because we need the module.</span>
+ <span class="n">DBuilder</span> <span class="o">=</span> <span class="n">llvm</span><span class="o">::</span><span class="n">make_unique</span><span class="o"><</span><span class="n">DIBuilder</span><span class="o">></span><span class="p">(</span><span class="o">*</span><span class="n">TheModule</span><span class="p">);</span>
+
+ <span class="c1">// Create the compile unit for the module.</span>
+ <span class="c1">// Currently down as "fib.ks" as a filename since we're redirecting stdin</span>
+ <span class="c1">// but we'd like actual source locations.</span>
+ <span class="n">KSDbgInfo</span><span class="p">.</span><span class="n">TheCU</span> <span class="o">=</span> <span class="n">DBuilder</span><span class="o">-></span><span class="n">createCompileUnit</span><span class="p">(</span>
+ <span class="n">dwarf</span><span class="o">::</span><span class="n">DW_LANG_C</span><span class="p">,</span> <span class="s">"fib.ks"</span><span class="p">,</span> <span class="s">"."</span><span class="p">,</span> <span class="s">"Kaleidoscope Compiler"</span><span class="p">,</span> <span class="mi">0</span><span class="p">,</span> <span class="s">""</span><span class="p">,</span> <span class="mi">0</span><span class="p">);</span>
+
+ <span class="c1">// Run the main "interpreter loop" now.</span>
+ <span class="n">MainLoop</span><span class="p">();</span>
+
+ <span class="c1">// Finalize the debug info.</span>
+ <span class="n">DBuilder</span><span class="o">-></span><span class="n">finalize</span><span class="p">();</span>
+
+ <span class="c1">// Print out all of the generated code.</span>
+ <span class="n">TheModule</span><span class="o">-></span><span class="n">dump</span><span class="p">();</span>
+
+ <span class="k">return</span> <span class="mi">0</span><span class="p">;</span>
+<span class="p">}</span>
+</pre></div>
+</div>
+<p><a class="reference external" href="LangImpl9.html">Next: Conclusion and other useful LLVM tidbits</a></p>
+</div>
+</div>
+
+
+ </div>
+ </div>
+ <div class="clearer"></div>
+ </div>
+ <div class="related">
+ <h3>Navigation</h3>
+ <ul>
+ <li class="right" style="margin-right: 10px">
+ <a href="../genindex.html" title="General Index"
+ >index</a></li>
+ <li class="right" >
+ <a href="LangImpl9.html" title="9. Kaleidoscope: Conclusion and other useful LLVM tidbits"
+ >next</a> |</li>
+ <li class="right" >
+ <a href="LangImpl7.html" title="7. Kaleidoscope: Extending the Language: Mutable Variables"
+ >previous</a> |</li>
+ <li><a href="http://llvm.org/">LLVM Home</a> | </li>
+ <li><a href="../index.html">Documentation</a>»</li>
+
+ <li><a href="index.html" >LLVM Tutorial: Table of Contents</a> »</li>
+ </ul>
+ </div>
+ <div class="footer">
+ © Copyright 2003-2016, LLVM Project.
+ Last updated on 2016-07-11.
+ Created using <a href="http://sphinx-doc.org/">Sphinx</a> 1.2.2.
+ </div>
+ </body>
+</html>
\ No newline at end of file
Added: www-releases/trunk/3.8.1/docs/tutorial/LangImpl9.html
URL: http://llvm.org/viewvc/llvm-project/www-releases/trunk/3.8.1/docs/tutorial/LangImpl9.html?rev=275092&view=auto
==============================================================================
--- www-releases/trunk/3.8.1/docs/tutorial/LangImpl9.html (added)
+++ www-releases/trunk/3.8.1/docs/tutorial/LangImpl9.html Mon Jul 11 14:36:11 2016
@@ -0,0 +1,347 @@
+
+<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN"
+ "http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd">
+
+
+<html xmlns="http://www.w3.org/1999/xhtml">
+ <head>
+ <meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
+
+ <title>9. Kaleidoscope: Conclusion and other useful LLVM tidbits — LLVM 3.8 documentation</title>
+
+ <link rel="stylesheet" href="../_static/llvm-theme.css" type="text/css" />
+ <link rel="stylesheet" href="../_static/pygments.css" type="text/css" />
+
+ <script type="text/javascript">
+ var DOCUMENTATION_OPTIONS = {
+ URL_ROOT: '../',
+ VERSION: '3.8',
+ COLLAPSE_INDEX: false,
+ FILE_SUFFIX: '.html',
+ HAS_SOURCE: true
+ };
+ </script>
+ <script type="text/javascript" src="../_static/jquery.js"></script>
+ <script type="text/javascript" src="../_static/underscore.js"></script>
+ <script type="text/javascript" src="../_static/doctools.js"></script>
+ <link rel="top" title="LLVM 3.8 documentation" href="../index.html" />
+ <link rel="up" title="LLVM Tutorial: Table of Contents" href="index.html" />
+ <link rel="next" title="1. Kaleidoscope: Tutorial Introduction and the Lexer" href="OCamlLangImpl1.html" />
+ <link rel="prev" title="8. Kaleidoscope: Adding Debug Information" href="LangImpl8.html" />
+<style type="text/css">
+ table.right { float: right; margin-left: 20px; }
+ table.right td { border: 1px solid #ccc; }
+</style>
+
+ </head>
+ <body>
+<div class="logo">
+ <a href="../index.html">
+ <img src="../_static/logo.png"
+ alt="LLVM Logo" width="250" height="88"/></a>
+</div>
+
+ <div class="related">
+ <h3>Navigation</h3>
+ <ul>
+ <li class="right" style="margin-right: 10px">
+ <a href="../genindex.html" title="General Index"
+ accesskey="I">index</a></li>
+ <li class="right" >
+ <a href="OCamlLangImpl1.html" title="1. Kaleidoscope: Tutorial Introduction and the Lexer"
+ accesskey="N">next</a> |</li>
+ <li class="right" >
+ <a href="LangImpl8.html" title="8. Kaleidoscope: Adding Debug Information"
+ accesskey="P">previous</a> |</li>
+ <li><a href="http://llvm.org/">LLVM Home</a> | </li>
+ <li><a href="../index.html">Documentation</a>»</li>
+
+ <li><a href="index.html" accesskey="U">LLVM Tutorial: Table of Contents</a> »</li>
+ </ul>
+ </div>
+
+
+ <div class="document">
+ <div class="documentwrapper">
+ <div class="body">
+
+ <div class="section" id="kaleidoscope-conclusion-and-other-useful-llvm-tidbits">
+<h1>9. Kaleidoscope: Conclusion and other useful LLVM tidbits<a class="headerlink" href="#kaleidoscope-conclusion-and-other-useful-llvm-tidbits" title="Permalink to this headline">¶</a></h1>
+<div class="contents local topic" id="contents">
+<ul class="simple">
+<li><a class="reference internal" href="#tutorial-conclusion" id="id2">Tutorial Conclusion</a></li>
+<li><a class="reference internal" href="#properties-of-the-llvm-ir" id="id3">Properties of the LLVM IR</a><ul>
+<li><a class="reference internal" href="#target-independence" id="id4">Target Independence</a></li>
+<li><a class="reference internal" href="#safety-guarantees" id="id5">Safety Guarantees</a></li>
+<li><a class="reference internal" href="#language-specific-optimizations" id="id6">Language-Specific Optimizations</a></li>
+</ul>
+</li>
+<li><a class="reference internal" href="#tips-and-tricks" id="id7">Tips and Tricks</a><ul>
+<li><a class="reference internal" href="#implementing-portable-offsetof-sizeof" id="id8">Implementing portable offsetof/sizeof</a></li>
+<li><a class="reference internal" href="#garbage-collected-stack-frames" id="id9">Garbage Collected Stack Frames</a></li>
+</ul>
+</li>
+</ul>
+</div>
+<div class="section" id="tutorial-conclusion">
+<h2><a class="toc-backref" href="#id2">9.1. Tutorial Conclusion</a><a class="headerlink" href="#tutorial-conclusion" title="Permalink to this headline">¶</a></h2>
+<p>Welcome to the final chapter of the “<a class="reference external" href="index.html">Implementing a language with
+LLVM</a>” tutorial. In the course of this tutorial, we have
+grown our little Kaleidoscope language from being a useless toy, to
+being a semi-interesting (but probably still useless) toy. :)</p>
+<p>It is interesting to see how far we’ve come, and how little code it has
+taken. We built the entire lexer, parser, AST, code generator, an
+interactive run-loop (with a JIT!), and emitted debug information in
+standalone executables - all in under 1000 lines of (non-comment/non-blank)
+code.</p>
+<p>Our little language supports a couple of interesting features: it
+supports user defined binary and unary operators, it uses JIT
+compilation for immediate evaluation, and it supports a few control flow
+constructs with SSA construction.</p>
+<p>Part of the idea of this tutorial was to show you how easy and fun it
+can be to define, build, and play with languages. Building a compiler
+need not be a scary or mystical process! Now that you’ve seen some of
+the basics, I strongly encourage you to take the code and hack on it.
+For example, try adding:</p>
+<ul class="simple">
+<li><strong>global variables</strong> - While global variables have questional value
+in modern software engineering, they are often useful when putting
+together quick little hacks like the Kaleidoscope compiler itself.
+Fortunately, our current setup makes it very easy to add global
+variables: just have value lookup check to see if an unresolved
+variable is in the global variable symbol table before rejecting it.
+To create a new global variable, make an instance of the LLVM
+<tt class="docutils literal"><span class="pre">GlobalVariable</span></tt> class.</li>
+<li><strong>typed variables</strong> - Kaleidoscope currently only supports variables
+of type double. This gives the language a very nice elegance, because
+only supporting one type means that you never have to specify types.
+Different languages have different ways of handling this. The easiest
+way is to require the user to specify types for every variable
+definition, and record the type of the variable in the symbol table
+along with its Value*.</li>
+<li><strong>arrays, structs, vectors, etc</strong> - Once you add types, you can start
+extending the type system in all sorts of interesting ways. Simple
+arrays are very easy and are quite useful for many different
+applications. Adding them is mostly an exercise in learning how the
+LLVM <a class="reference external" href="../LangRef.html#getelementptr-instruction">getelementptr</a> instruction
+works: it is so nifty/unconventional, it <a class="reference external" href="../GetElementPtr.html">has its own
+FAQ</a>! If you add support for recursive types
+(e.g. linked lists), make sure to read the <a class="reference external" href="../ProgrammersManual.html#TypeResolve">section in the LLVM
+Programmer’s Manual</a> that
+describes how to construct them.</li>
+<li><strong>standard runtime</strong> - Our current language allows the user to access
+arbitrary external functions, and we use it for things like “printd”
+and “putchard”. As you extend the language to add higher-level
+constructs, often these constructs make the most sense if they are
+lowered to calls into a language-supplied runtime. For example, if
+you add hash tables to the language, it would probably make sense to
+add the routines to a runtime, instead of inlining them all the way.</li>
+<li><strong>memory management</strong> - Currently we can only access the stack in
+Kaleidoscope. It would also be useful to be able to allocate heap
+memory, either with calls to the standard libc malloc/free interface
+or with a garbage collector. If you would like to use garbage
+collection, note that LLVM fully supports <a class="reference external" href="../GarbageCollection.html">Accurate Garbage
+Collection</a> including algorithms that
+move objects and need to scan/update the stack.</li>
+<li><strong>exception handling support</strong> - LLVM supports generation of <a class="reference external" href="../ExceptionHandling.html">zero
+cost exceptions</a> which interoperate with
+code compiled in other languages. You could also generate code by
+implicitly making every function return an error value and checking
+it. You could also make explicit use of setjmp/longjmp. There are
+many different ways to go here.</li>
+<li><strong>object orientation, generics, database access, complex numbers,
+geometric programming, ...</strong> - Really, there is no end of crazy
+features that you can add to the language.</li>
+<li><strong>unusual domains</strong> - We’ve been talking about applying LLVM to a
+domain that many people are interested in: building a compiler for a
+specific language. However, there are many other domains that can use
+compiler technology that are not typically considered. For example,
+LLVM has been used to implement OpenGL graphics acceleration,
+translate C++ code to ActionScript, and many other cute and clever
+things. Maybe you will be the first to JIT compile a regular
+expression interpreter into native code with LLVM?</li>
+</ul>
+<p>Have fun - try doing something crazy and unusual. Building a language
+like everyone else always has, is much less fun than trying something a
+little crazy or off the wall and seeing how it turns out. If you get
+stuck or want to talk about it, feel free to email the <a class="reference external" href="http://lists.llvm.org/mailman/listinfo/llvm-dev">llvm-dev mailing
+list</a>: it has lots
+of people who are interested in languages and are often willing to help
+out.</p>
+<p>Before we end this tutorial, I want to talk about some “tips and tricks”
+for generating LLVM IR. These are some of the more subtle things that
+may not be obvious, but are very useful if you want to take advantage of
+LLVM’s capabilities.</p>
+</div>
+<div class="section" id="properties-of-the-llvm-ir">
+<h2><a class="toc-backref" href="#id3">9.2. Properties of the LLVM IR</a><a class="headerlink" href="#properties-of-the-llvm-ir" title="Permalink to this headline">¶</a></h2>
+<p>We have a couple common questions about code in the LLVM IR form - lets
+just get these out of the way right now, shall we?</p>
+<div class="section" id="target-independence">
+<h3><a class="toc-backref" href="#id4">9.2.1. Target Independence</a><a class="headerlink" href="#target-independence" title="Permalink to this headline">¶</a></h3>
+<p>Kaleidoscope is an example of a “portable language”: any program written
+in Kaleidoscope will work the same way on any target that it runs on.
+Many other languages have this property, e.g. lisp, java, haskell,
+javascript, python, etc (note that while these languages are portable,
+not all their libraries are).</p>
+<p>One nice aspect of LLVM is that it is often capable of preserving target
+independence in the IR: you can take the LLVM IR for a
+Kaleidoscope-compiled program and run it on any target that LLVM
+supports, even emitting C code and compiling that on targets that LLVM
+doesn’t support natively. You can trivially tell that the Kaleidoscope
+compiler generates target-independent code because it never queries for
+any target-specific information when generating code.</p>
+<p>The fact that LLVM provides a compact, target-independent,
+representation for code gets a lot of people excited. Unfortunately,
+these people are usually thinking about C or a language from the C
+family when they are asking questions about language portability. I say
+“unfortunately”, because there is really no way to make (fully general)
+C code portable, other than shipping the source code around (and of
+course, C source code is not actually portable in general either - ever
+port a really old application from 32- to 64-bits?).</p>
+<p>The problem with C (again, in its full generality) is that it is heavily
+laden with target specific assumptions. As one simple example, the
+preprocessor often destructively removes target-independence from the
+code when it processes the input text:</p>
+<div class="highlight-c"><div class="highlight"><pre><span class="cp">#ifdef __i386__</span>
+ <span class="kt">int</span> <span class="n">X</span> <span class="o">=</span> <span class="mi">1</span><span class="p">;</span>
+<span class="cp">#else</span>
+ <span class="kt">int</span> <span class="n">X</span> <span class="o">=</span> <span class="mi">42</span><span class="p">;</span>
+<span class="cp">#endif</span>
+</pre></div>
+</div>
+<p>While it is possible to engineer more and more complex solutions to
+problems like this, it cannot be solved in full generality in a way that
+is better than shipping the actual source code.</p>
+<p>That said, there are interesting subsets of C that can be made portable.
+If you are willing to fix primitive types to a fixed size (say int =
+32-bits, and long = 64-bits), don’t care about ABI compatibility with
+existing binaries, and are willing to give up some other minor features,
+you can have portable code. This can make sense for specialized domains
+such as an in-kernel language.</p>
+</div>
+<div class="section" id="safety-guarantees">
+<h3><a class="toc-backref" href="#id5">9.2.2. Safety Guarantees</a><a class="headerlink" href="#safety-guarantees" title="Permalink to this headline">¶</a></h3>
+<p>Many of the languages above are also “safe” languages: it is impossible
+for a program written in Java to corrupt its address space and crash the
+process (assuming the JVM has no bugs). Safety is an interesting
+property that requires a combination of language design, runtime
+support, and often operating system support.</p>
+<p>It is certainly possible to implement a safe language in LLVM, but LLVM
+IR does not itself guarantee safety. The LLVM IR allows unsafe pointer
+casts, use after free bugs, buffer over-runs, and a variety of other
+problems. Safety needs to be implemented as a layer on top of LLVM and,
+conveniently, several groups have investigated this. Ask on the <a class="reference external" href="http://lists.llvm.org/mailman/listinfo/llvm-dev">llvm-dev
+mailing list</a> if
+you are interested in more details.</p>
+</div>
+<div class="section" id="language-specific-optimizations">
+<h3><a class="toc-backref" href="#id6">9.2.3. Language-Specific Optimizations</a><a class="headerlink" href="#language-specific-optimizations" title="Permalink to this headline">¶</a></h3>
+<p>One thing about LLVM that turns off many people is that it does not
+solve all the world’s problems in one system (sorry ‘world hunger’,
+someone else will have to solve you some other day). One specific
+complaint is that people perceive LLVM as being incapable of performing
+high-level language-specific optimization: LLVM “loses too much
+information”.</p>
+<p>Unfortunately, this is really not the place to give you a full and
+unified version of “Chris Lattner’s theory of compiler design”. Instead,
+I’ll make a few observations:</p>
+<p>First, you’re right that LLVM does lose information. For example, as of
+this writing, there is no way to distinguish in the LLVM IR whether an
+SSA-value came from a C “int” or a C “long” on an ILP32 machine (other
+than debug info). Both get compiled down to an ‘i32’ value and the
+information about what it came from is lost. The more general issue
+here, is that the LLVM type system uses “structural equivalence” instead
+of “name equivalence”. Another place this surprises people is if you
+have two types in a high-level language that have the same structure
+(e.g. two different structs that have a single int field): these types
+will compile down into a single LLVM type and it will be impossible to
+tell what it came from.</p>
+<p>Second, while LLVM does lose information, LLVM is not a fixed target: we
+continue to enhance and improve it in many different ways. In addition
+to adding new features (LLVM did not always support exceptions or debug
+info), we also extend the IR to capture important information for
+optimization (e.g. whether an argument is sign or zero extended,
+information about pointers aliasing, etc). Many of the enhancements are
+user-driven: people want LLVM to include some specific feature, so they
+go ahead and extend it.</p>
+<p>Third, it is <em>possible and easy</em> to add language-specific optimizations,
+and you have a number of choices in how to do it. As one trivial
+example, it is easy to add language-specific optimization passes that
+“know” things about code compiled for a language. In the case of the C
+family, there is an optimization pass that “knows” about the standard C
+library functions. If you call “exit(0)” in main(), it knows that it is
+safe to optimize that into “return 0;” because C specifies what the
+‘exit’ function does.</p>
+<p>In addition to simple library knowledge, it is possible to embed a
+variety of other language-specific information into the LLVM IR. If you
+have a specific need and run into a wall, please bring the topic up on
+the llvm-dev list. At the very worst, you can always treat LLVM as if it
+were a “dumb code generator” and implement the high-level optimizations
+you desire in your front-end, on the language-specific AST.</p>
+</div>
+</div>
+<div class="section" id="tips-and-tricks">
+<h2><a class="toc-backref" href="#id7">9.3. Tips and Tricks</a><a class="headerlink" href="#tips-and-tricks" title="Permalink to this headline">¶</a></h2>
+<p>There is a variety of useful tips and tricks that you come to know after
+working on/with LLVM that aren’t obvious at first glance. Instead of
+letting everyone rediscover them, this section talks about some of these
+issues.</p>
+<div class="section" id="implementing-portable-offsetof-sizeof">
+<h3><a class="toc-backref" href="#id8">9.3.1. Implementing portable offsetof/sizeof</a><a class="headerlink" href="#implementing-portable-offsetof-sizeof" title="Permalink to this headline">¶</a></h3>
+<p>One interesting thing that comes up, if you are trying to keep the code
+generated by your compiler “target independent”, is that you often need
+to know the size of some LLVM type or the offset of some field in an
+llvm structure. For example, you might need to pass the size of a type
+into a function that allocates memory.</p>
+<p>Unfortunately, this can vary widely across targets: for example the
+width of a pointer is trivially target-specific. However, there is a
+<a class="reference external" href="http://nondot.org/sabre/LLVMNotes/SizeOf-OffsetOf-VariableSizedStructs.txt">clever way to use the getelementptr
+instruction</a>
+that allows you to compute this in a portable way.</p>
+</div>
+<div class="section" id="garbage-collected-stack-frames">
+<h3><a class="toc-backref" href="#id9">9.3.2. Garbage Collected Stack Frames</a><a class="headerlink" href="#garbage-collected-stack-frames" title="Permalink to this headline">¶</a></h3>
+<p>Some languages want to explicitly manage their stack frames, often so
+that they are garbage collected or to allow easy implementation of
+closures. There are often better ways to implement these features than
+explicit stack frames, but <a class="reference external" href="http://nondot.org/sabre/LLVMNotes/ExplicitlyManagedStackFrames.txt">LLVM does support
+them,</a>
+if you want. It requires your front-end to convert the code into
+<a class="reference external" href="http://en.wikipedia.org/wiki/Continuation-passing_style">Continuation Passing
+Style</a> and
+the use of tail calls (which LLVM also supports).</p>
+</div>
+</div>
+</div>
+
+
+ </div>
+ </div>
+ <div class="clearer"></div>
+ </div>
+ <div class="related">
+ <h3>Navigation</h3>
+ <ul>
+ <li class="right" style="margin-right: 10px">
+ <a href="../genindex.html" title="General Index"
+ >index</a></li>
+ <li class="right" >
+ <a href="OCamlLangImpl1.html" title="1. Kaleidoscope: Tutorial Introduction and the Lexer"
+ >next</a> |</li>
+ <li class="right" >
+ <a href="LangImpl8.html" title="8. Kaleidoscope: Adding Debug Information"
+ >previous</a> |</li>
+ <li><a href="http://llvm.org/">LLVM Home</a> | </li>
+ <li><a href="../index.html">Documentation</a>»</li>
+
+ <li><a href="index.html" >LLVM Tutorial: Table of Contents</a> »</li>
+ </ul>
+ </div>
+ <div class="footer">
+ © Copyright 2003-2016, LLVM Project.
+ Last updated on 2016-07-11.
+ Created using <a href="http://sphinx-doc.org/">Sphinx</a> 1.2.2.
+ </div>
+ </body>
+</html>
\ No newline at end of file
Added: www-releases/trunk/3.8.1/docs/tutorial/OCamlLangImpl1.html
URL: http://llvm.org/viewvc/llvm-project/www-releases/trunk/3.8.1/docs/tutorial/OCamlLangImpl1.html?rev=275092&view=auto
==============================================================================
--- www-releases/trunk/3.8.1/docs/tutorial/OCamlLangImpl1.html (added)
+++ www-releases/trunk/3.8.1/docs/tutorial/OCamlLangImpl1.html Mon Jul 11 14:36:11 2016
@@ -0,0 +1,358 @@
+
+<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN"
+ "http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd">
+
+
+<html xmlns="http://www.w3.org/1999/xhtml">
+ <head>
+ <meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
+
+ <title>1. Kaleidoscope: Tutorial Introduction and the Lexer — LLVM 3.8 documentation</title>
+
+ <link rel="stylesheet" href="../_static/llvm-theme.css" type="text/css" />
+ <link rel="stylesheet" href="../_static/pygments.css" type="text/css" />
+
+ <script type="text/javascript">
+ var DOCUMENTATION_OPTIONS = {
+ URL_ROOT: '../',
+ VERSION: '3.8',
+ COLLAPSE_INDEX: false,
+ FILE_SUFFIX: '.html',
+ HAS_SOURCE: true
+ };
+ </script>
+ <script type="text/javascript" src="../_static/jquery.js"></script>
+ <script type="text/javascript" src="../_static/underscore.js"></script>
+ <script type="text/javascript" src="../_static/doctools.js"></script>
+ <link rel="top" title="LLVM 3.8 documentation" href="../index.html" />
+ <link rel="up" title="LLVM Tutorial: Table of Contents" href="index.html" />
+ <link rel="next" title="2. Kaleidoscope: Implementing a Parser and AST" href="OCamlLangImpl2.html" />
+ <link rel="prev" title="9. Kaleidoscope: Conclusion and other useful LLVM tidbits" href="LangImpl9.html" />
+<style type="text/css">
+ table.right { float: right; margin-left: 20px; }
+ table.right td { border: 1px solid #ccc; }
+</style>
+
+ </head>
+ <body>
+<div class="logo">
+ <a href="../index.html">
+ <img src="../_static/logo.png"
+ alt="LLVM Logo" width="250" height="88"/></a>
+</div>
+
+ <div class="related">
+ <h3>Navigation</h3>
+ <ul>
+ <li class="right" style="margin-right: 10px">
+ <a href="../genindex.html" title="General Index"
+ accesskey="I">index</a></li>
+ <li class="right" >
+ <a href="OCamlLangImpl2.html" title="2. Kaleidoscope: Implementing a Parser and AST"
+ accesskey="N">next</a> |</li>
+ <li class="right" >
+ <a href="LangImpl9.html" title="9. Kaleidoscope: Conclusion and other useful LLVM tidbits"
+ accesskey="P">previous</a> |</li>
+ <li><a href="http://llvm.org/">LLVM Home</a> | </li>
+ <li><a href="../index.html">Documentation</a>»</li>
+
+ <li><a href="index.html" accesskey="U">LLVM Tutorial: Table of Contents</a> »</li>
+ </ul>
+ </div>
+
+
+ <div class="document">
+ <div class="documentwrapper">
+ <div class="body">
+
+ <div class="section" id="kaleidoscope-tutorial-introduction-and-the-lexer">
+<h1>1. Kaleidoscope: Tutorial Introduction and the Lexer<a class="headerlink" href="#kaleidoscope-tutorial-introduction-and-the-lexer" title="Permalink to this headline">¶</a></h1>
+<div class="contents local topic" id="contents">
+<ul class="simple">
+<li><a class="reference internal" href="#tutorial-introduction" id="id1">Tutorial Introduction</a></li>
+<li><a class="reference internal" href="#the-basic-language" id="id2">The Basic Language</a></li>
+<li><a class="reference internal" href="#the-lexer" id="id3">The Lexer</a></li>
+</ul>
+</div>
+<div class="section" id="tutorial-introduction">
+<h2><a class="toc-backref" href="#id1">1.1. Tutorial Introduction</a><a class="headerlink" href="#tutorial-introduction" title="Permalink to this headline">¶</a></h2>
+<p>Welcome to the “Implementing a language with LLVM” tutorial. This
+tutorial runs through the implementation of a simple language, showing
+how fun and easy it can be. This tutorial will get you up and started as
+well as help to build a framework you can extend to other languages. The
+code in this tutorial can also be used as a playground to hack on other
+LLVM specific things.</p>
+<p>The goal of this tutorial is to progressively unveil our language,
+describing how it is built up over time. This will let us cover a fairly
+broad range of language design and LLVM-specific usage issues, showing
+and explaining the code for it all along the way, without overwhelming
+you with tons of details up front.</p>
+<p>It is useful to point out ahead of time that this tutorial is really
+about teaching compiler techniques and LLVM specifically, <em>not</em> about
+teaching modern and sane software engineering principles. In practice,
+this means that we’ll take a number of shortcuts to simplify the
+exposition. For example, the code leaks memory, uses global variables
+all over the place, doesn’t use nice design patterns like
+<a class="reference external" href="http://en.wikipedia.org/wiki/Visitor_pattern">visitors</a>, etc... but
+it is very simple. If you dig in and use the code as a basis for future
+projects, fixing these deficiencies shouldn’t be hard.</p>
+<p>I’ve tried to put this tutorial together in a way that makes chapters
+easy to skip over if you are already familiar with or are uninterested
+in the various pieces. The structure of the tutorial is:</p>
+<ul class="simple">
+<li><a class="reference external" href="#language">Chapter #1</a>: Introduction to the Kaleidoscope
+language, and the definition of its Lexer - This shows where we are
+going and the basic functionality that we want it to do. In order to
+make this tutorial maximally understandable and hackable, we choose
+to implement everything in Objective Caml instead of using lexer and
+parser generators. LLVM obviously works just fine with such tools,
+feel free to use one if you prefer.</li>
+<li><a class="reference external" href="OCamlLangImpl2.html">Chapter #2</a>: Implementing a Parser and
+AST - With the lexer in place, we can talk about parsing techniques
+and basic AST construction. This tutorial describes recursive descent
+parsing and operator precedence parsing. Nothing in Chapters 1 or 2
+is LLVM-specific, the code doesn’t even link in LLVM at this point.
+:)</li>
+<li><a class="reference external" href="OCamlLangImpl3.html">Chapter #3</a>: Code generation to LLVM IR -
+With the AST ready, we can show off how easy generation of LLVM IR
+really is.</li>
+<li><a class="reference external" href="OCamlLangImpl4.html">Chapter #4</a>: Adding JIT and Optimizer
+Support - Because a lot of people are interested in using LLVM as a
+JIT, we’ll dive right into it and show you the 3 lines it takes to
+add JIT support. LLVM is also useful in many other ways, but this is
+one simple and “sexy” way to shows off its power. :)</li>
+<li><a class="reference external" href="OCamlLangImpl5.html">Chapter #5</a>: Extending the Language:
+Control Flow - With the language up and running, we show how to
+extend it with control flow operations (if/then/else and a ‘for’
+loop). This gives us a chance to talk about simple SSA construction
+and control flow.</li>
+<li><a class="reference external" href="OCamlLangImpl6.html">Chapter #6</a>: Extending the Language:
+User-defined Operators - This is a silly but fun chapter that talks
+about extending the language to let the user program define their own
+arbitrary unary and binary operators (with assignable precedence!).
+This lets us build a significant piece of the “language” as library
+routines.</li>
+<li><a class="reference external" href="OCamlLangImpl7.html">Chapter #7</a>: Extending the Language:
+Mutable Variables - This chapter talks about adding user-defined
+local variables along with an assignment operator. The interesting
+part about this is how easy and trivial it is to construct SSA form
+in LLVM: no, LLVM does <em>not</em> require your front-end to construct SSA
+form!</li>
+<li><a class="reference external" href="OCamlLangImpl8.html">Chapter #8</a>: Conclusion and other useful
+LLVM tidbits - This chapter wraps up the series by talking about
+potential ways to extend the language, but also includes a bunch of
+pointers to info about “special topics” like adding garbage
+collection support, exceptions, debugging, support for “spaghetti
+stacks”, and a bunch of other tips and tricks.</li>
+</ul>
+<p>By the end of the tutorial, we’ll have written a bit less than 700 lines
+of non-comment, non-blank, lines of code. With this small amount of
+code, we’ll have built up a very reasonable compiler for a non-trivial
+language including a hand-written lexer, parser, AST, as well as code
+generation support with a JIT compiler. While other systems may have
+interesting “hello world” tutorials, I think the breadth of this
+tutorial is a great testament to the strengths of LLVM and why you
+should consider it if you’re interested in language or compiler design.</p>
+<p>A note about this tutorial: we expect you to extend the language and
+play with it on your own. Take the code and go crazy hacking away at it,
+compilers don’t need to be scary creatures - it can be a lot of fun to
+play with languages!</p>
+</div>
+<div class="section" id="the-basic-language">
+<h2><a class="toc-backref" href="#id2">1.2. The Basic Language</a><a class="headerlink" href="#the-basic-language" title="Permalink to this headline">¶</a></h2>
+<p>This tutorial will be illustrated with a toy language that we’ll call
+“<a class="reference external" href="http://en.wikipedia.org/wiki/Kaleidoscope">Kaleidoscope</a>” (derived
+from “meaning beautiful, form, and view”). Kaleidoscope is a procedural
+language that allows you to define functions, use conditionals, math,
+etc. Over the course of the tutorial, we’ll extend Kaleidoscope to
+support the if/then/else construct, a for loop, user defined operators,
+JIT compilation with a simple command line interface, etc.</p>
+<p>Because we want to keep things simple, the only datatype in Kaleidoscope
+is a 64-bit floating point type (aka ‘float’ in O’Caml parlance). As
+such, all values are implicitly double precision and the language
+doesn’t require type declarations. This gives the language a very nice
+and simple syntax. For example, the following simple example computes
+<a class="reference external" href="http://en.wikipedia.org/wiki/Fibonacci_number">Fibonacci numbers:</a></p>
+<div class="highlight-python"><div class="highlight"><pre># Compute the x'th fibonacci number.
+def fib(x)
+ if x < 3 then
+ 1
+ else
+ fib(x-1)+fib(x-2)
+
+# This expression will compute the 40th number.
+fib(40)
+</pre></div>
+</div>
+<p>We also allow Kaleidoscope to call into standard library functions (the
+LLVM JIT makes this completely trivial). This means that you can use the
+‘extern’ keyword to define a function before you use it (this is also
+useful for mutually recursive functions). For example:</p>
+<div class="highlight-python"><div class="highlight"><pre>extern sin(arg);
+extern cos(arg);
+extern atan2(arg1 arg2);
+
+atan2(sin(.4), cos(42))
+</pre></div>
+</div>
+<p>A more interesting example is included in Chapter 6 where we write a
+little Kaleidoscope application that <a class="reference external" href="OCamlLangImpl6.html#kicking-the-tires">displays a Mandelbrot
+Set</a> at various levels of magnification.</p>
+<p>Lets dive into the implementation of this language!</p>
+</div>
+<div class="section" id="the-lexer">
+<h2><a class="toc-backref" href="#id3">1.3. The Lexer</a><a class="headerlink" href="#the-lexer" title="Permalink to this headline">¶</a></h2>
+<p>When it comes to implementing a language, the first thing needed is the
+ability to process a text file and recognize what it says. The
+traditional way to do this is to use a
+“<a class="reference external" href="http://en.wikipedia.org/wiki/Lexical_analysis">lexer</a>” (aka
+‘scanner’) to break the input up into “tokens”. Each token returned by
+the lexer includes a token code and potentially some metadata (e.g. the
+numeric value of a number). First, we define the possibilities:</p>
+<div class="highlight-ocaml"><div class="highlight"><pre><span class="c">(* The lexer returns these 'Kwd' if it is an unknown character, otherwise one of</span>
+<span class="c"> * these others for known things. *)</span>
+<span class="k">type</span> <span class="n">token</span> <span class="o">=</span>
+ <span class="c">(* commands *)</span>
+ <span class="o">|</span> <span class="nc">Def</span> <span class="o">|</span> <span class="nc">Extern</span>
+
+ <span class="c">(* primary *)</span>
+ <span class="o">|</span> <span class="nc">Ident</span> <span class="k">of</span> <span class="kt">string</span> <span class="o">|</span> <span class="nc">Number</span> <span class="k">of</span> <span class="kt">float</span>
+
+ <span class="c">(* unknown *)</span>
+ <span class="o">|</span> <span class="nc">Kwd</span> <span class="k">of</span> <span class="kt">char</span>
+</pre></div>
+</div>
+<p>Each token returned by our lexer will be one of the token variant
+values. An unknown character like ‘+’ will be returned as
+<tt class="docutils literal"><span class="pre">Token.Kwd</span> <span class="pre">'+'</span></tt>. If the curr token is an identifier, the value will be
+<tt class="docutils literal"><span class="pre">Token.Ident</span> <span class="pre">s</span></tt>. If the current token is a numeric literal (like 1.0),
+the value will be <tt class="docutils literal"><span class="pre">Token.Number</span> <span class="pre">1.0</span></tt>.</p>
+<p>The actual implementation of the lexer is a collection of functions
+driven by a function named <tt class="docutils literal"><span class="pre">Lexer.lex</span></tt>. The <tt class="docutils literal"><span class="pre">Lexer.lex</span></tt> function is
+called to return the next token from standard input. We will use
+<a class="reference external" href="http://caml.inria.fr/pub/docs/manual-camlp4/index.html">Camlp4</a> to
+simplify the tokenization of the standard input. Its definition starts
+as:</p>
+<div class="highlight-ocaml"><div class="highlight"><pre><span class="c">(*===----------------------------------------------------------------------===</span>
+<span class="c"> * Lexer</span>
+<span class="c"> *===----------------------------------------------------------------------===*)</span>
+
+<span class="k">let</span> <span class="k">rec</span> <span class="n">lex</span> <span class="o">=</span> <span class="n">parser</span>
+ <span class="c">(* Skip any whitespace. *)</span>
+ <span class="o">|</span> <span class="o">[<</span> <span class="k">'</span> <span class="o">(</span><span class="sc">' '</span> <span class="o">|</span> <span class="sc">'\n'</span> <span class="o">|</span> <span class="sc">'\r'</span> <span class="o">|</span> <span class="sc">'\t'</span><span class="o">);</span> <span class="n">stream</span> <span class="o">>]</span> <span class="o">-></span> <span class="n">lex</span> <span class="n">stream</span>
+</pre></div>
+</div>
+<p><tt class="docutils literal"><span class="pre">Lexer.lex</span></tt> works by recursing over a <tt class="docutils literal"><span class="pre">char</span> <span class="pre">Stream.t</span></tt> to read
+characters one at a time from the standard input. It eats them as it
+recognizes them and stores them in in a <tt class="docutils literal"><span class="pre">Token.token</span></tt> variant. The
+first thing that it has to do is ignore whitespace between tokens. This
+is accomplished with the recursive call above.</p>
+<p>The next thing <tt class="docutils literal"><span class="pre">Lexer.lex</span></tt> needs to do is recognize identifiers and
+specific keywords like “def”. Kaleidoscope does this with a pattern
+match and a helper function.</p>
+<div class="highlight-ocaml"><div class="highlight"><pre> <span class="c">(* identifier: [a-zA-Z][a-zA-Z0-9] *)</span>
+ <span class="o">|</span> <span class="o">[<</span> <span class="k">'</span> <span class="o">(</span><span class="sc">'A'</span> <span class="o">..</span> <span class="sc">'Z'</span> <span class="o">|</span> <span class="sc">'a'</span> <span class="o">..</span> <span class="sc">'z'</span> <span class="k">as</span> <span class="n">c</span><span class="o">);</span> <span class="n">stream</span> <span class="o">>]</span> <span class="o">-></span>
+ <span class="k">let</span> <span class="n">buffer</span> <span class="o">=</span> <span class="nn">Buffer</span><span class="p">.</span><span class="n">create</span> <span class="mi">1</span> <span class="k">in</span>
+ <span class="nn">Buffer</span><span class="p">.</span><span class="n">add_char</span> <span class="n">buffer</span> <span class="n">c</span><span class="o">;</span>
+ <span class="n">lex_ident</span> <span class="n">buffer</span> <span class="n">stream</span>
+
+<span class="o">...</span>
+
+<span class="ow">and</span> <span class="n">lex_ident</span> <span class="n">buffer</span> <span class="o">=</span> <span class="n">parser</span>
+ <span class="o">|</span> <span class="o">[<</span> <span class="k">'</span> <span class="o">(</span><span class="sc">'A'</span> <span class="o">..</span> <span class="sc">'Z'</span> <span class="o">|</span> <span class="sc">'a'</span> <span class="o">..</span> <span class="sc">'z'</span> <span class="o">|</span> <span class="sc">'0'</span> <span class="o">..</span> <span class="sc">'9'</span> <span class="k">as</span> <span class="n">c</span><span class="o">);</span> <span class="n">stream</span> <span class="o">>]</span> <span class="o">-></span>
+ <span class="nn">Buffer</span><span class="p">.</span><span class="n">add_char</span> <span class="n">buffer</span> <span class="n">c</span><span class="o">;</span>
+ <span class="n">lex_ident</span> <span class="n">buffer</span> <span class="n">stream</span>
+ <span class="o">|</span> <span class="o">[<</span> <span class="n">stream</span><span class="o">=</span><span class="n">lex</span> <span class="o">>]</span> <span class="o">-></span>
+ <span class="k">match</span> <span class="nn">Buffer</span><span class="p">.</span><span class="n">contents</span> <span class="n">buffer</span> <span class="k">with</span>
+ <span class="o">|</span> <span class="s2">"def"</span> <span class="o">-></span> <span class="o">[<</span> <span class="k">'</span><span class="nn">Token</span><span class="p">.</span><span class="nc">Def</span><span class="o">;</span> <span class="n">stream</span> <span class="o">>]</span>
+ <span class="o">|</span> <span class="s2">"extern"</span> <span class="o">-></span> <span class="o">[<</span> <span class="k">'</span><span class="nn">Token</span><span class="p">.</span><span class="nc">Extern</span><span class="o">;</span> <span class="n">stream</span> <span class="o">>]</span>
+ <span class="o">|</span> <span class="n">id</span> <span class="o">-></span> <span class="o">[<</span> <span class="k">'</span><span class="nn">Token</span><span class="p">.</span><span class="nc">Ident</span> <span class="n">id</span><span class="o">;</span> <span class="n">stream</span> <span class="o">>]</span>
+</pre></div>
+</div>
+<p>Numeric values are similar:</p>
+<div class="highlight-ocaml"><div class="highlight"><pre> <span class="c">(* number: [0-9.]+ *)</span>
+ <span class="o">|</span> <span class="o">[<</span> <span class="k">'</span> <span class="o">(</span><span class="sc">'0'</span> <span class="o">..</span> <span class="sc">'9'</span> <span class="k">as</span> <span class="n">c</span><span class="o">);</span> <span class="n">stream</span> <span class="o">>]</span> <span class="o">-></span>
+ <span class="k">let</span> <span class="n">buffer</span> <span class="o">=</span> <span class="nn">Buffer</span><span class="p">.</span><span class="n">create</span> <span class="mi">1</span> <span class="k">in</span>
+ <span class="nn">Buffer</span><span class="p">.</span><span class="n">add_char</span> <span class="n">buffer</span> <span class="n">c</span><span class="o">;</span>
+ <span class="n">lex_number</span> <span class="n">buffer</span> <span class="n">stream</span>
+
+<span class="o">...</span>
+
+<span class="ow">and</span> <span class="n">lex_number</span> <span class="n">buffer</span> <span class="o">=</span> <span class="n">parser</span>
+ <span class="o">|</span> <span class="o">[<</span> <span class="k">'</span> <span class="o">(</span><span class="sc">'0'</span> <span class="o">..</span> <span class="sc">'9'</span> <span class="o">|</span> <span class="sc">'.'</span> <span class="k">as</span> <span class="n">c</span><span class="o">);</span> <span class="n">stream</span> <span class="o">>]</span> <span class="o">-></span>
+ <span class="nn">Buffer</span><span class="p">.</span><span class="n">add_char</span> <span class="n">buffer</span> <span class="n">c</span><span class="o">;</span>
+ <span class="n">lex_number</span> <span class="n">buffer</span> <span class="n">stream</span>
+ <span class="o">|</span> <span class="o">[<</span> <span class="n">stream</span><span class="o">=</span><span class="n">lex</span> <span class="o">>]</span> <span class="o">-></span>
+ <span class="o">[<</span> <span class="k">'</span><span class="nn">Token</span><span class="p">.</span><span class="nc">Number</span> <span class="o">(</span><span class="n">float_of_string</span> <span class="o">(</span><span class="nn">Buffer</span><span class="p">.</span><span class="n">contents</span> <span class="n">buffer</span><span class="o">));</span> <span class="n">stream</span> <span class="o">>]</span>
+</pre></div>
+</div>
+<p>This is all pretty straight-forward code for processing input. When
+reading a numeric value from input, we use the ocaml <tt class="docutils literal"><span class="pre">float_of_string</span></tt>
+function to convert it to a numeric value that we store in
+<tt class="docutils literal"><span class="pre">Token.Number</span></tt>. Note that this isn’t doing sufficient error checking:
+it will raise <tt class="docutils literal"><span class="pre">Failure</span></tt> if the string “1.23.45.67”. Feel free to
+extend it :). Next we handle comments:</p>
+<div class="highlight-ocaml"><div class="highlight"><pre> <span class="c">(* Comment until end of line. *)</span>
+ <span class="o">|</span> <span class="o">[<</span> <span class="k">'</span> <span class="o">(</span><span class="sc">'#'</span><span class="o">);</span> <span class="n">stream</span> <span class="o">>]</span> <span class="o">-></span>
+ <span class="n">lex_comment</span> <span class="n">stream</span>
+
+<span class="o">...</span>
+
+<span class="ow">and</span> <span class="n">lex_comment</span> <span class="o">=</span> <span class="n">parser</span>
+ <span class="o">|</span> <span class="o">[<</span> <span class="k">'</span> <span class="o">(</span><span class="sc">'\n'</span><span class="o">);</span> <span class="n">stream</span><span class="o">=</span><span class="n">lex</span> <span class="o">>]</span> <span class="o">-></span> <span class="n">stream</span>
+ <span class="o">|</span> <span class="o">[<</span> <span class="k">'</span><span class="n">c</span><span class="o">;</span> <span class="n">e</span><span class="o">=</span><span class="n">lex_comment</span> <span class="o">>]</span> <span class="o">-></span> <span class="n">e</span>
+ <span class="o">|</span> <span class="o">[<</span> <span class="o">>]</span> <span class="o">-></span> <span class="o">[<</span> <span class="o">>]</span>
+</pre></div>
+</div>
+<p>We handle comments by skipping to the end of the line and then return
+the next token. Finally, if the input doesn’t match one of the above
+cases, it is either an operator character like ‘+’ or the end of the
+file. These are handled with this code:</p>
+<div class="highlight-ocaml"><div class="highlight"><pre><span class="c">(* Otherwise, just return the character as its ascii value. *)</span>
+<span class="o">|</span> <span class="o">[<</span> <span class="k">'</span><span class="n">c</span><span class="o">;</span> <span class="n">stream</span> <span class="o">>]</span> <span class="o">-></span>
+ <span class="o">[<</span> <span class="k">'</span><span class="nn">Token</span><span class="p">.</span><span class="nc">Kwd</span> <span class="n">c</span><span class="o">;</span> <span class="n">lex</span> <span class="n">stream</span> <span class="o">>]</span>
+
+<span class="c">(* end of stream. *)</span>
+<span class="o">|</span> <span class="o">[<</span> <span class="o">>]</span> <span class="o">-></span> <span class="o">[<</span> <span class="o">>]</span>
+</pre></div>
+</div>
+<p>With this, we have the complete lexer for the basic Kaleidoscope
+language (the <a class="reference external" href="OCamlLangImpl2.html#full-code-listing">full code listing</a> for the
+Lexer is available in the <a class="reference external" href="OCamlLangImpl2.html">next chapter</a> of the
+tutorial). Next we’ll <a class="reference external" href="OCamlLangImpl2.html">build a simple parser that uses this to build an
+Abstract Syntax Tree</a>. When we have that, we’ll
+include a driver so that you can use the lexer and parser together.</p>
+<p><a class="reference external" href="OCamlLangImpl2.html">Next: Implementing a Parser and AST</a></p>
+</div>
+</div>
+
+
+ </div>
+ </div>
+ <div class="clearer"></div>
+ </div>
+ <div class="related">
+ <h3>Navigation</h3>
+ <ul>
+ <li class="right" style="margin-right: 10px">
+ <a href="../genindex.html" title="General Index"
+ >index</a></li>
+ <li class="right" >
+ <a href="OCamlLangImpl2.html" title="2. Kaleidoscope: Implementing a Parser and AST"
+ >next</a> |</li>
+ <li class="right" >
+ <a href="LangImpl9.html" title="9. Kaleidoscope: Conclusion and other useful LLVM tidbits"
+ >previous</a> |</li>
+ <li><a href="http://llvm.org/">LLVM Home</a> | </li>
+ <li><a href="../index.html">Documentation</a>»</li>
+
+ <li><a href="index.html" >LLVM Tutorial: Table of Contents</a> »</li>
+ </ul>
+ </div>
+ <div class="footer">
+ © Copyright 2003-2016, LLVM Project.
+ Last updated on 2016-07-11.
+ Created using <a href="http://sphinx-doc.org/">Sphinx</a> 1.2.2.
+ </div>
+ </body>
+</html>
\ No newline at end of file
Added: www-releases/trunk/3.8.1/docs/tutorial/OCamlLangImpl2.html
URL: http://llvm.org/viewvc/llvm-project/www-releases/trunk/3.8.1/docs/tutorial/OCamlLangImpl2.html?rev=275092&view=auto
==============================================================================
--- www-releases/trunk/3.8.1/docs/tutorial/OCamlLangImpl2.html (added)
+++ www-releases/trunk/3.8.1/docs/tutorial/OCamlLangImpl2.html Mon Jul 11 14:36:11 2016
@@ -0,0 +1,936 @@
+
+<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN"
+ "http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd">
+
+
+<html xmlns="http://www.w3.org/1999/xhtml">
+ <head>
+ <meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
+
+ <title>2. Kaleidoscope: Implementing a Parser and AST — LLVM 3.8 documentation</title>
+
+ <link rel="stylesheet" href="../_static/llvm-theme.css" type="text/css" />
+ <link rel="stylesheet" href="../_static/pygments.css" type="text/css" />
+
+ <script type="text/javascript">
+ var DOCUMENTATION_OPTIONS = {
+ URL_ROOT: '../',
+ VERSION: '3.8',
+ COLLAPSE_INDEX: false,
+ FILE_SUFFIX: '.html',
+ HAS_SOURCE: true
+ };
+ </script>
+ <script type="text/javascript" src="../_static/jquery.js"></script>
+ <script type="text/javascript" src="../_static/underscore.js"></script>
+ <script type="text/javascript" src="../_static/doctools.js"></script>
+ <link rel="top" title="LLVM 3.8 documentation" href="../index.html" />
+ <link rel="up" title="LLVM Tutorial: Table of Contents" href="index.html" />
+ <link rel="next" title="3. Kaleidoscope: Code generation to LLVM IR" href="OCamlLangImpl3.html" />
+ <link rel="prev" title="1. Kaleidoscope: Tutorial Introduction and the Lexer" href="OCamlLangImpl1.html" />
+<style type="text/css">
+ table.right { float: right; margin-left: 20px; }
+ table.right td { border: 1px solid #ccc; }
+</style>
+
+ </head>
+ <body>
+<div class="logo">
+ <a href="../index.html">
+ <img src="../_static/logo.png"
+ alt="LLVM Logo" width="250" height="88"/></a>
+</div>
+
+ <div class="related">
+ <h3>Navigation</h3>
+ <ul>
+ <li class="right" style="margin-right: 10px">
+ <a href="../genindex.html" title="General Index"
+ accesskey="I">index</a></li>
+ <li class="right" >
+ <a href="OCamlLangImpl3.html" title="3. Kaleidoscope: Code generation to LLVM IR"
+ accesskey="N">next</a> |</li>
+ <li class="right" >
+ <a href="OCamlLangImpl1.html" title="1. Kaleidoscope: Tutorial Introduction and the Lexer"
+ accesskey="P">previous</a> |</li>
+ <li><a href="http://llvm.org/">LLVM Home</a> | </li>
+ <li><a href="../index.html">Documentation</a>»</li>
+
+ <li><a href="index.html" accesskey="U">LLVM Tutorial: Table of Contents</a> »</li>
+ </ul>
+ </div>
+
+
+ <div class="document">
+ <div class="documentwrapper">
+ <div class="body">
+
+ <div class="section" id="kaleidoscope-implementing-a-parser-and-ast">
+<h1>2. Kaleidoscope: Implementing a Parser and AST<a class="headerlink" href="#kaleidoscope-implementing-a-parser-and-ast" title="Permalink to this headline">¶</a></h1>
+<div class="contents local topic" id="contents">
+<ul class="simple">
+<li><a class="reference internal" href="#chapter-2-introduction" id="id2">Chapter 2 Introduction</a></li>
+<li><a class="reference internal" href="#the-abstract-syntax-tree-ast" id="id3">The Abstract Syntax Tree (AST)</a></li>
+<li><a class="reference internal" href="#parser-basics" id="id4">Parser Basics</a></li>
+<li><a class="reference internal" href="#basic-expression-parsing" id="id5">Basic Expression Parsing</a></li>
+<li><a class="reference internal" href="#binary-expression-parsing" id="id6">Binary Expression Parsing</a></li>
+<li><a class="reference internal" href="#parsing-the-rest" id="id7">Parsing the Rest</a></li>
+<li><a class="reference internal" href="#the-driver" id="id8">The Driver</a></li>
+<li><a class="reference internal" href="#conclusions" id="id9">Conclusions</a></li>
+<li><a class="reference internal" href="#full-code-listing" id="id10">Full Code Listing</a></li>
+</ul>
+</div>
+<div class="section" id="chapter-2-introduction">
+<h2><a class="toc-backref" href="#id2">2.1. Chapter 2 Introduction</a><a class="headerlink" href="#chapter-2-introduction" title="Permalink to this headline">¶</a></h2>
+<p>Welcome to Chapter 2 of the “<a class="reference external" href="index.html">Implementing a language with LLVM in
+Objective Caml</a>” tutorial. This chapter shows you how to
+use the lexer, built in <a class="reference external" href="OCamlLangImpl1.html">Chapter 1</a>, to build a
+full <a class="reference external" href="http://en.wikipedia.org/wiki/Parsing">parser</a> for our
+Kaleidoscope language. Once we have a parser, we’ll define and build an
+<a class="reference external" href="http://en.wikipedia.org/wiki/Abstract_syntax_tree">Abstract Syntax
+Tree</a> (AST).</p>
+<p>The parser we will build uses a combination of <a class="reference external" href="http://en.wikipedia.org/wiki/Recursive_descent_parser">Recursive Descent
+Parsing</a> and
+<a class="reference external" href="http://en.wikipedia.org/wiki/Operator-precedence_parser">Operator-Precedence
+Parsing</a> to
+parse the Kaleidoscope language (the latter for binary expressions and
+the former for everything else). Before we get to parsing though, lets
+talk about the output of the parser: the Abstract Syntax Tree.</p>
+</div>
+<div class="section" id="the-abstract-syntax-tree-ast">
+<h2><a class="toc-backref" href="#id3">2.2. The Abstract Syntax Tree (AST)</a><a class="headerlink" href="#the-abstract-syntax-tree-ast" title="Permalink to this headline">¶</a></h2>
+<p>The AST for a program captures its behavior in such a way that it is
+easy for later stages of the compiler (e.g. code generation) to
+interpret. We basically want one object for each construct in the
+language, and the AST should closely model the language. In
+Kaleidoscope, we have expressions, a prototype, and a function object.
+We’ll start with expressions first:</p>
+<div class="highlight-ocaml"><div class="highlight"><pre><span class="c">(* expr - Base type for all expression nodes. *)</span>
+<span class="k">type</span> <span class="n">expr</span> <span class="o">=</span>
+ <span class="c">(* variant for numeric literals like "1.0". *)</span>
+ <span class="o">|</span> <span class="nc">Number</span> <span class="k">of</span> <span class="kt">float</span>
+</pre></div>
+</div>
+<p>The code above shows the definition of the base ExprAST class and one
+subclass which we use for numeric literals. The important thing to note
+about this code is that the Number variant captures the numeric value of
+the literal as an instance variable. This allows later phases of the
+compiler to know what the stored numeric value is.</p>
+<p>Right now we only create the AST, so there are no useful functions on
+them. It would be very easy to add a function to pretty print the code,
+for example. Here are the other expression AST node definitions that
+we’ll use in the basic form of the Kaleidoscope language:</p>
+<div class="highlight-ocaml"><div class="highlight"><pre><span class="c">(* variant for referencing a variable, like "a". *)</span>
+<span class="o">|</span> <span class="nc">Variable</span> <span class="k">of</span> <span class="kt">string</span>
+
+<span class="c">(* variant for a binary operator. *)</span>
+<span class="o">|</span> <span class="nc">Binary</span> <span class="k">of</span> <span class="kt">char</span> <span class="o">*</span> <span class="n">expr</span> <span class="o">*</span> <span class="n">expr</span>
+
+<span class="c">(* variant for function calls. *)</span>
+<span class="o">|</span> <span class="nc">Call</span> <span class="k">of</span> <span class="kt">string</span> <span class="o">*</span> <span class="n">expr</span> <span class="kt">array</span>
+</pre></div>
+</div>
+<p>This is all (intentionally) rather straight-forward: variables capture
+the variable name, binary operators capture their opcode (e.g. ‘+’), and
+calls capture a function name as well as a list of any argument
+expressions. One thing that is nice about our AST is that it captures
+the language features without talking about the syntax of the language.
+Note that there is no discussion about precedence of binary operators,
+lexical structure, etc.</p>
+<p>For our basic language, these are all of the expression nodes we’ll
+define. Because it doesn’t have conditional control flow, it isn’t
+Turing-complete; we’ll fix that in a later installment. The two things
+we need next are a way to talk about the interface to a function, and a
+way to talk about functions themselves:</p>
+<div class="highlight-ocaml"><div class="highlight"><pre><span class="c">(* proto - This type represents the "prototype" for a function, which captures</span>
+<span class="c"> * its name, and its argument names (thus implicitly the number of arguments the</span>
+<span class="c"> * function takes). *)</span>
+<span class="k">type</span> <span class="n">proto</span> <span class="o">=</span> <span class="nc">Prototype</span> <span class="k">of</span> <span class="kt">string</span> <span class="o">*</span> <span class="kt">string</span> <span class="kt">array</span>
+
+<span class="c">(* func - This type represents a function definition itself. *)</span>
+<span class="k">type</span> <span class="n">func</span> <span class="o">=</span> <span class="nc">Function</span> <span class="k">of</span> <span class="n">proto</span> <span class="o">*</span> <span class="n">expr</span>
+</pre></div>
+</div>
+<p>In Kaleidoscope, functions are typed with just a count of their
+arguments. Since all values are double precision floating point, the
+type of each argument doesn’t need to be stored anywhere. In a more
+aggressive and realistic language, the “expr” variants would probably
+have a type field.</p>
+<p>With this scaffolding, we can now talk about parsing expressions and
+function bodies in Kaleidoscope.</p>
+</div>
+<div class="section" id="parser-basics">
+<h2><a class="toc-backref" href="#id4">2.3. Parser Basics</a><a class="headerlink" href="#parser-basics" title="Permalink to this headline">¶</a></h2>
+<p>Now that we have an AST to build, we need to define the parser code to
+build it. The idea here is that we want to parse something like “x+y”
+(which is returned as three tokens by the lexer) into an AST that could
+be generated with calls like this:</p>
+<div class="highlight-ocaml"><div class="highlight"><pre><span class="k">let</span> <span class="n">x</span> <span class="o">=</span> <span class="nc">Variable</span> <span class="s2">"x"</span> <span class="k">in</span>
+<span class="k">let</span> <span class="n">y</span> <span class="o">=</span> <span class="nc">Variable</span> <span class="s2">"y"</span> <span class="k">in</span>
+<span class="k">let</span> <span class="n">result</span> <span class="o">=</span> <span class="nc">Binary</span> <span class="o">(</span><span class="sc">'+'</span><span class="o">,</span> <span class="n">x</span><span class="o">,</span> <span class="n">y</span><span class="o">)</span> <span class="k">in</span>
+<span class="o">...</span>
+</pre></div>
+</div>
+<p>The error handling routines make use of the builtin <tt class="docutils literal"><span class="pre">Stream.Failure</span></tt>
+and <tt class="docutils literal"><span class="pre">Stream.Error``s.</span> <span class="pre">``Stream.Failure</span></tt> is raised when the parser is
+unable to find any matching token in the first position of a pattern.
+<tt class="docutils literal"><span class="pre">Stream.Error</span></tt> is raised when the first token matches, but the rest do
+not. The error recovery in our parser will not be the best and is not
+particular user-friendly, but it will be enough for our tutorial. These
+exceptions make it easier to handle errors in routines that have various
+return types.</p>
+<p>With these basic types and exceptions, we can implement the first piece
+of our grammar: numeric literals.</p>
+</div>
+<div class="section" id="basic-expression-parsing">
+<h2><a class="toc-backref" href="#id5">2.4. Basic Expression Parsing</a><a class="headerlink" href="#basic-expression-parsing" title="Permalink to this headline">¶</a></h2>
+<p>We start with numeric literals, because they are the simplest to
+process. For each production in our grammar, we’ll define a function
+which parses that production. We call this class of expressions
+“primary” expressions, for reasons that will become more clear <a class="reference external" href="OCamlLangImpl6.html#user-defined-unary-operators">later in
+the tutorial</a>. In order to parse an
+arbitrary primary expression, we need to determine what sort of
+expression it is. For numeric literals, we have:</p>
+<div class="highlight-ocaml"><div class="highlight"><pre><span class="c">(* primary</span>
+<span class="c"> * ::= identifier</span>
+<span class="c"> * ::= numberexpr</span>
+<span class="c"> * ::= parenexpr *)</span>
+<span class="n">parse_primary</span> <span class="o">=</span> <span class="n">parser</span>
+ <span class="c">(* numberexpr ::= number *)</span>
+ <span class="o">|</span> <span class="o">[<</span> <span class="k">'</span><span class="nn">Token</span><span class="p">.</span><span class="nc">Number</span> <span class="n">n</span> <span class="o">>]</span> <span class="o">-></span> <span class="nn">Ast</span><span class="p">.</span><span class="nc">Number</span> <span class="n">n</span>
+</pre></div>
+</div>
+<p>This routine is very simple: it expects to be called when the current
+token is a <tt class="docutils literal"><span class="pre">Token.Number</span></tt> token. It takes the current number value,
+creates a <tt class="docutils literal"><span class="pre">Ast.Number</span></tt> node, advances the lexer to the next token, and
+finally returns.</p>
+<p>There are some interesting aspects to this. The most important one is
+that this routine eats all of the tokens that correspond to the
+production and returns the lexer buffer with the next token (which is
+not part of the grammar production) ready to go. This is a fairly
+standard way to go for recursive descent parsers. For a better example,
+the parenthesis operator is defined like this:</p>
+<div class="highlight-ocaml"><div class="highlight"><pre><span class="c">(* parenexpr ::= '(' expression ')' *)</span>
+<span class="o">|</span> <span class="o">[<</span> <span class="k">'</span><span class="nn">Token</span><span class="p">.</span><span class="nc">Kwd</span> <span class="sc">'('</span><span class="o">;</span> <span class="n">e</span><span class="o">=</span><span class="n">parse_expr</span><span class="o">;</span> <span class="k">'</span><span class="nn">Token</span><span class="p">.</span><span class="nc">Kwd</span> <span class="sc">')'</span> <span class="o">??</span> <span class="s2">"expected ')'"</span> <span class="o">>]</span> <span class="o">-></span> <span class="n">e</span>
+</pre></div>
+</div>
+<p>This function illustrates a number of interesting things about the
+parser:</p>
+<p>1) It shows how we use the <tt class="docutils literal"><span class="pre">Stream.Error</span></tt> exception. When called, this
+function expects that the current token is a ‘(‘ token, but after
+parsing the subexpression, it is possible that there is no ‘)’ waiting.
+For example, if the user types in “(4 x” instead of “(4)”, the parser
+should emit an error. Because errors can occur, the parser needs a way
+to indicate that they happened. In our parser, we use the camlp4
+shortcut syntax <tt class="docutils literal"><span class="pre">token</span> <span class="pre">??</span> <span class="pre">"parse</span> <span class="pre">error"</span></tt>, where if the token before
+the <tt class="docutils literal"><span class="pre">??</span></tt> does not match, then <tt class="docutils literal"><span class="pre">Stream.Error</span> <span class="pre">"parse</span> <span class="pre">error"</span></tt> will be
+raised.</p>
+<p>2) Another interesting aspect of this function is that it uses recursion
+by calling <tt class="docutils literal"><span class="pre">Parser.parse_primary</span></tt> (we will soon see that
+<tt class="docutils literal"><span class="pre">Parser.parse_primary</span></tt> can call <tt class="docutils literal"><span class="pre">Parser.parse_primary</span></tt>). This is
+powerful because it allows us to handle recursive grammars, and keeps
+each production very simple. Note that parentheses do not cause
+construction of AST nodes themselves. While we could do it this way, the
+most important role of parentheses are to guide the parser and provide
+grouping. Once the parser constructs the AST, parentheses are not
+needed.</p>
+<p>The next simple production is for handling variable references and
+function calls:</p>
+<div class="highlight-ocaml"><div class="highlight"><pre><span class="c">(* identifierexpr</span>
+<span class="c"> * ::= identifier</span>
+<span class="c"> * ::= identifier '(' argumentexpr ')' *)</span>
+<span class="o">|</span> <span class="o">[<</span> <span class="k">'</span><span class="nn">Token</span><span class="p">.</span><span class="nc">Ident</span> <span class="n">id</span><span class="o">;</span> <span class="n">stream</span> <span class="o">>]</span> <span class="o">-></span>
+ <span class="k">let</span> <span class="k">rec</span> <span class="n">parse_args</span> <span class="n">accumulator</span> <span class="o">=</span> <span class="n">parser</span>
+ <span class="o">|</span> <span class="o">[<</span> <span class="n">e</span><span class="o">=</span><span class="n">parse_expr</span><span class="o">;</span> <span class="n">stream</span> <span class="o">>]</span> <span class="o">-></span>
+ <span class="k">begin</span> <span class="n">parser</span>
+ <span class="o">|</span> <span class="o">[<</span> <span class="k">'</span><span class="nn">Token</span><span class="p">.</span><span class="nc">Kwd</span> <span class="sc">','</span><span class="o">;</span> <span class="n">e</span><span class="o">=</span><span class="n">parse_args</span> <span class="o">(</span><span class="n">e</span> <span class="o">::</span> <span class="n">accumulator</span><span class="o">)</span> <span class="o">>]</span> <span class="o">-></span> <span class="n">e</span>
+ <span class="o">|</span> <span class="o">[<</span> <span class="o">>]</span> <span class="o">-></span> <span class="n">e</span> <span class="o">::</span> <span class="n">accumulator</span>
+ <span class="k">end</span> <span class="n">stream</span>
+ <span class="o">|</span> <span class="o">[<</span> <span class="o">>]</span> <span class="o">-></span> <span class="n">accumulator</span>
+ <span class="k">in</span>
+ <span class="k">let</span> <span class="k">rec</span> <span class="n">parse_ident</span> <span class="n">id</span> <span class="o">=</span> <span class="n">parser</span>
+ <span class="c">(* Call. *)</span>
+ <span class="o">|</span> <span class="o">[<</span> <span class="k">'</span><span class="nn">Token</span><span class="p">.</span><span class="nc">Kwd</span> <span class="sc">'('</span><span class="o">;</span>
+ <span class="n">args</span><span class="o">=</span><span class="n">parse_args</span> <span class="bp">[]</span><span class="o">;</span>
+ <span class="k">'</span><span class="nn">Token</span><span class="p">.</span><span class="nc">Kwd</span> <span class="sc">')'</span> <span class="o">??</span> <span class="s2">"expected ')'"</span><span class="o">>]</span> <span class="o">-></span>
+ <span class="nn">Ast</span><span class="p">.</span><span class="nc">Call</span> <span class="o">(</span><span class="n">id</span><span class="o">,</span> <span class="nn">Array</span><span class="p">.</span><span class="n">of_list</span> <span class="o">(</span><span class="nn">List</span><span class="p">.</span><span class="n">rev</span> <span class="n">args</span><span class="o">))</span>
+
+ <span class="c">(* Simple variable ref. *)</span>
+ <span class="o">|</span> <span class="o">[<</span> <span class="o">>]</span> <span class="o">-></span> <span class="nn">Ast</span><span class="p">.</span><span class="nc">Variable</span> <span class="n">id</span>
+ <span class="k">in</span>
+ <span class="n">parse_ident</span> <span class="n">id</span> <span class="n">stream</span>
+</pre></div>
+</div>
+<p>This routine follows the same style as the other routines. (It expects
+to be called if the current token is a <tt class="docutils literal"><span class="pre">Token.Ident</span></tt> token). It also
+has recursion and error handling. One interesting aspect of this is that
+it uses <em>look-ahead</em> to determine if the current identifier is a stand
+alone variable reference or if it is a function call expression. It
+handles this by checking to see if the token after the identifier is a
+‘(‘ token, constructing either a <tt class="docutils literal"><span class="pre">Ast.Variable</span></tt> or <tt class="docutils literal"><span class="pre">Ast.Call</span></tt> node
+as appropriate.</p>
+<p>We finish up by raising an exception if we received a token we didn’t
+expect:</p>
+<div class="highlight-ocaml"><div class="highlight"><pre><span class="o">|</span> <span class="o">[<</span> <span class="o">>]</span> <span class="o">-></span> <span class="k">raise</span> <span class="o">(</span><span class="nn">Stream</span><span class="p">.</span><span class="nc">Error</span> <span class="s2">"unknown token when expecting an expression."</span><span class="o">)</span>
+</pre></div>
+</div>
+<p>Now that basic expressions are handled, we need to handle binary
+expressions. They are a bit more complex.</p>
+</div>
+<div class="section" id="binary-expression-parsing">
+<h2><a class="toc-backref" href="#id6">2.5. Binary Expression Parsing</a><a class="headerlink" href="#binary-expression-parsing" title="Permalink to this headline">¶</a></h2>
+<p>Binary expressions are significantly harder to parse because they are
+often ambiguous. For example, when given the string “x+y*z”, the parser
+can choose to parse it as either “(x+y)*z” or “x+(y*z)”. With common
+definitions from mathematics, we expect the later parse, because “*”
+(multiplication) has higher <em>precedence</em> than “+” (addition).</p>
+<p>There are many ways to handle this, but an elegant and efficient way is
+to use <a class="reference external" href="http://en.wikipedia.org/wiki/Operator-precedence_parser">Operator-Precedence
+Parsing</a>.
+This parsing technique uses the precedence of binary operators to guide
+recursion. To start with, we need a table of precedences:</p>
+<div class="highlight-ocaml"><div class="highlight"><pre><span class="c">(* binop_precedence - This holds the precedence for each binary operator that is</span>
+<span class="c"> * defined *)</span>
+<span class="k">let</span> <span class="n">binop_precedence</span><span class="o">:(</span><span class="kt">char</span><span class="o">,</span> <span class="kt">int</span><span class="o">)</span> <span class="nn">Hashtbl</span><span class="p">.</span><span class="n">t</span> <span class="o">=</span> <span class="nn">Hashtbl</span><span class="p">.</span><span class="n">create</span> <span class="mi">10</span>
+
+<span class="c">(* precedence - Get the precedence of the pending binary operator token. *)</span>
+<span class="k">let</span> <span class="n">precedence</span> <span class="n">c</span> <span class="o">=</span> <span class="k">try</span> <span class="nn">Hashtbl</span><span class="p">.</span><span class="n">find</span> <span class="n">binop_precedence</span> <span class="n">c</span> <span class="k">with</span> <span class="nc">Not_found</span> <span class="o">-></span> <span class="o">-</span><span class="mi">1</span>
+
+<span class="o">...</span>
+
+<span class="k">let</span> <span class="n">main</span> <span class="bp">()</span> <span class="o">=</span>
+ <span class="c">(* Install standard binary operators.</span>
+<span class="c"> * 1 is the lowest precedence. *)</span>
+ <span class="nn">Hashtbl</span><span class="p">.</span><span class="n">add</span> <span class="nn">Parser</span><span class="p">.</span><span class="n">binop_precedence</span> <span class="sc">'<'</span> <span class="mi">10</span><span class="o">;</span>
+ <span class="nn">Hashtbl</span><span class="p">.</span><span class="n">add</span> <span class="nn">Parser</span><span class="p">.</span><span class="n">binop_precedence</span> <span class="sc">'+'</span> <span class="mi">20</span><span class="o">;</span>
+ <span class="nn">Hashtbl</span><span class="p">.</span><span class="n">add</span> <span class="nn">Parser</span><span class="p">.</span><span class="n">binop_precedence</span> <span class="sc">'-'</span> <span class="mi">20</span><span class="o">;</span>
+ <span class="nn">Hashtbl</span><span class="p">.</span><span class="n">add</span> <span class="nn">Parser</span><span class="p">.</span><span class="n">binop_precedence</span> <span class="sc">'*'</span> <span class="mi">40</span><span class="o">;</span> <span class="c">(* highest. *)</span>
+ <span class="o">...</span>
+</pre></div>
+</div>
+<p>For the basic form of Kaleidoscope, we will only support 4 binary
+operators (this can obviously be extended by you, our brave and intrepid
+reader). The <tt class="docutils literal"><span class="pre">Parser.precedence</span></tt> function returns the precedence for
+the current token, or -1 if the token is not a binary operator. Having a
+<tt class="docutils literal"><span class="pre">Hashtbl.t</span></tt> makes it easy to add new operators and makes it clear that
+the algorithm doesn’t depend on the specific operators involved, but it
+would be easy enough to eliminate the <tt class="docutils literal"><span class="pre">Hashtbl.t</span></tt> and do the
+comparisons in the <tt class="docutils literal"><span class="pre">Parser.precedence</span></tt> function. (Or just use a
+fixed-size array).</p>
+<p>With the helper above defined, we can now start parsing binary
+expressions. The basic idea of operator precedence parsing is to break
+down an expression with potentially ambiguous binary operators into
+pieces. Consider, for example, the expression “a+b+(c+d)*e*f+g”.
+Operator precedence parsing considers this as a stream of primary
+expressions separated by binary operators. As such, it will first parse
+the leading primary expression “a”, then it will see the pairs [+, b]
+[+, (c+d)] [*, e] [*, f] and [+, g]. Note that because parentheses are
+primary expressions, the binary expression parser doesn’t need to worry
+about nested subexpressions like (c+d) at all.</p>
+<p>To start, an expression is a primary expression potentially followed by
+a sequence of [binop,primaryexpr] pairs:</p>
+<div class="highlight-ocaml"><div class="highlight"><pre><span class="c">(* expression</span>
+<span class="c"> * ::= primary binoprhs *)</span>
+<span class="ow">and</span> <span class="n">parse_expr</span> <span class="o">=</span> <span class="n">parser</span>
+ <span class="o">|</span> <span class="o">[<</span> <span class="n">lhs</span><span class="o">=</span><span class="n">parse_primary</span><span class="o">;</span> <span class="n">stream</span> <span class="o">>]</span> <span class="o">-></span> <span class="n">parse_bin_rhs</span> <span class="mi">0</span> <span class="n">lhs</span> <span class="n">stream</span>
+</pre></div>
+</div>
+<p><tt class="docutils literal"><span class="pre">Parser.parse_bin_rhs</span></tt> is the function that parses the sequence of
+pairs for us. It takes a precedence and a pointer to an expression for
+the part that has been parsed so far. Note that “x” is a perfectly valid
+expression: As such, “binoprhs” is allowed to be empty, in which case it
+returns the expression that is passed into it. In our example above, the
+code passes the expression for “a” into <tt class="docutils literal"><span class="pre">Parser.parse_bin_rhs</span></tt> and the
+current token is “+”.</p>
+<p>The precedence value passed into <tt class="docutils literal"><span class="pre">Parser.parse_bin_rhs</span></tt> indicates the
+<em>minimal operator precedence</em> that the function is allowed to eat. For
+example, if the current pair stream is [+, x] and
+<tt class="docutils literal"><span class="pre">Parser.parse_bin_rhs</span></tt> is passed in a precedence of 40, it will not
+consume any tokens (because the precedence of ‘+’ is only 20). With this
+in mind, <tt class="docutils literal"><span class="pre">Parser.parse_bin_rhs</span></tt> starts with:</p>
+<div class="highlight-ocaml"><div class="highlight"><pre><span class="c">(* binoprhs</span>
+<span class="c"> * ::= ('+' primary)* *)</span>
+<span class="ow">and</span> <span class="n">parse_bin_rhs</span> <span class="n">expr_prec</span> <span class="n">lhs</span> <span class="n">stream</span> <span class="o">=</span>
+ <span class="k">match</span> <span class="nn">Stream</span><span class="p">.</span><span class="n">peek</span> <span class="n">stream</span> <span class="k">with</span>
+ <span class="c">(* If this is a binop, find its precedence. *)</span>
+ <span class="o">|</span> <span class="nc">Some</span> <span class="o">(</span><span class="nn">Token</span><span class="p">.</span><span class="nc">Kwd</span> <span class="n">c</span><span class="o">)</span> <span class="k">when</span> <span class="nn">Hashtbl</span><span class="p">.</span><span class="n">mem</span> <span class="n">binop_precedence</span> <span class="n">c</span> <span class="o">-></span>
+ <span class="k">let</span> <span class="n">token_prec</span> <span class="o">=</span> <span class="n">precedence</span> <span class="n">c</span> <span class="k">in</span>
+
+ <span class="c">(* If this is a binop that binds at least as tightly as the current binop,</span>
+<span class="c"> * consume it, otherwise we are done. *)</span>
+ <span class="k">if</span> <span class="n">token_prec</span> <span class="o"><</span> <span class="n">expr_prec</span> <span class="k">then</span> <span class="n">lhs</span> <span class="k">else</span> <span class="k">begin</span>
+</pre></div>
+</div>
+<p>This code gets the precedence of the current token and checks to see if
+if is too low. Because we defined invalid tokens to have a precedence of
+-1, this check implicitly knows that the pair-stream ends when the token
+stream runs out of binary operators. If this check succeeds, we know
+that the token is a binary operator and that it will be included in this
+expression:</p>
+<div class="highlight-ocaml"><div class="highlight"><pre><span class="c">(* Eat the binop. *)</span>
+<span class="nn">Stream</span><span class="p">.</span><span class="n">junk</span> <span class="n">stream</span><span class="o">;</span>
+
+<span class="c">(* Parse the primary expression after the binary operator *)</span>
+<span class="k">let</span> <span class="n">rhs</span> <span class="o">=</span> <span class="n">parse_primary</span> <span class="n">stream</span> <span class="k">in</span>
+
+<span class="c">(* Okay, we know this is a binop. *)</span>
+<span class="k">let</span> <span class="n">rhs</span> <span class="o">=</span>
+ <span class="k">match</span> <span class="nn">Stream</span><span class="p">.</span><span class="n">peek</span> <span class="n">stream</span> <span class="k">with</span>
+ <span class="o">|</span> <span class="nc">Some</span> <span class="o">(</span><span class="nn">Token</span><span class="p">.</span><span class="nc">Kwd</span> <span class="n">c2</span><span class="o">)</span> <span class="o">-></span>
+</pre></div>
+</div>
+<p>As such, this code eats (and remembers) the binary operator and then
+parses the primary expression that follows. This builds up the whole
+pair, the first of which is [+, b] for the running example.</p>
+<p>Now that we parsed the left-hand side of an expression and one pair of
+the RHS sequence, we have to decide which way the expression associates.
+In particular, we could have “(a+b) binop unparsed” or “a + (b binop
+unparsed)”. To determine this, we look ahead at “binop” to determine its
+precedence and compare it to BinOp’s precedence (which is ‘+’ in this
+case):</p>
+<div class="highlight-ocaml"><div class="highlight"><pre><span class="c">(* If BinOp binds less tightly with rhs than the operator after</span>
+<span class="c"> * rhs, let the pending operator take rhs as its lhs. *)</span>
+<span class="k">let</span> <span class="n">next_prec</span> <span class="o">=</span> <span class="n">precedence</span> <span class="n">c2</span> <span class="k">in</span>
+<span class="k">if</span> <span class="n">token_prec</span> <span class="o"><</span> <span class="n">next_prec</span>
+</pre></div>
+</div>
+<p>If the precedence of the binop to the right of “RHS” is lower or equal
+to the precedence of our current operator, then we know that the
+parentheses associate as “(a+b) binop ...”. In our example, the current
+operator is “+” and the next operator is “+”, we know that they have the
+same precedence. In this case we’ll create the AST node for “a+b”, and
+then continue parsing:</p>
+<div class="highlight-ocaml"><div class="highlight"><pre> <span class="o">...</span> <span class="k">if</span> <span class="n">body</span> <span class="n">omitted</span> <span class="o">...</span>
+ <span class="k">in</span>
+
+ <span class="c">(* Merge lhs/rhs. *)</span>
+ <span class="k">let</span> <span class="n">lhs</span> <span class="o">=</span> <span class="nn">Ast</span><span class="p">.</span><span class="nc">Binary</span> <span class="o">(</span><span class="n">c</span><span class="o">,</span> <span class="n">lhs</span><span class="o">,</span> <span class="n">rhs</span><span class="o">)</span> <span class="k">in</span>
+ <span class="n">parse_bin_rhs</span> <span class="n">expr_prec</span> <span class="n">lhs</span> <span class="n">stream</span>
+<span class="k">end</span>
+</pre></div>
+</div>
+<p>In our example above, this will turn “a+b+” into “(a+b)” and execute the
+next iteration of the loop, with “+” as the current token. The code
+above will eat, remember, and parse “(c+d)” as the primary expression,
+which makes the current pair equal to [+, (c+d)]. It will then evaluate
+the ‘if’ conditional above with “*” as the binop to the right of the
+primary. In this case, the precedence of “*” is higher than the
+precedence of “+” so the if condition will be entered.</p>
+<p>The critical question left here is “how can the if condition parse the
+right hand side in full”? In particular, to build the AST correctly for
+our example, it needs to get all of “(c+d)*e*f” as the RHS expression
+variable. The code to do this is surprisingly simple (code from the
+above two blocks duplicated for context):</p>
+<div class="highlight-ocaml"><div class="highlight"><pre> <span class="k">match</span> <span class="nn">Stream</span><span class="p">.</span><span class="n">peek</span> <span class="n">stream</span> <span class="k">with</span>
+ <span class="o">|</span> <span class="nc">Some</span> <span class="o">(</span><span class="nn">Token</span><span class="p">.</span><span class="nc">Kwd</span> <span class="n">c2</span><span class="o">)</span> <span class="o">-></span>
+ <span class="c">(* If BinOp binds less tightly with rhs than the operator after</span>
+<span class="c"> * rhs, let the pending operator take rhs as its lhs. *)</span>
+ <span class="k">if</span> <span class="n">token_prec</span> <span class="o"><</span> <span class="n">precedence</span> <span class="n">c2</span>
+ <span class="k">then</span> <span class="n">parse_bin_rhs</span> <span class="o">(</span><span class="n">token_prec</span> <span class="o">+</span> <span class="mi">1</span><span class="o">)</span> <span class="n">rhs</span> <span class="n">stream</span>
+ <span class="k">else</span> <span class="n">rhs</span>
+ <span class="o">|</span> <span class="o">_</span> <span class="o">-></span> <span class="n">rhs</span>
+ <span class="k">in</span>
+
+ <span class="c">(* Merge lhs/rhs. *)</span>
+ <span class="k">let</span> <span class="n">lhs</span> <span class="o">=</span> <span class="nn">Ast</span><span class="p">.</span><span class="nc">Binary</span> <span class="o">(</span><span class="n">c</span><span class="o">,</span> <span class="n">lhs</span><span class="o">,</span> <span class="n">rhs</span><span class="o">)</span> <span class="k">in</span>
+ <span class="n">parse_bin_rhs</span> <span class="n">expr_prec</span> <span class="n">lhs</span> <span class="n">stream</span>
+<span class="k">end</span>
+</pre></div>
+</div>
+<p>At this point, we know that the binary operator to the RHS of our
+primary has higher precedence than the binop we are currently parsing.
+As such, we know that any sequence of pairs whose operators are all
+higher precedence than “+” should be parsed together and returned as
+“RHS”. To do this, we recursively invoke the <tt class="docutils literal"><span class="pre">Parser.parse_bin_rhs</span></tt>
+function specifying “token_prec+1” as the minimum precedence required
+for it to continue. In our example above, this will cause it to return
+the AST node for “(c+d)*e*f” as RHS, which is then set as the RHS of
+the ‘+’ expression.</p>
+<p>Finally, on the next iteration of the while loop, the “+g” piece is
+parsed and added to the AST. With this little bit of code (14
+non-trivial lines), we correctly handle fully general binary expression
+parsing in a very elegant way. This was a whirlwind tour of this code,
+and it is somewhat subtle. I recommend running through it with a few
+tough examples to see how it works.</p>
+<p>This wraps up handling of expressions. At this point, we can point the
+parser at an arbitrary token stream and build an expression from it,
+stopping at the first token that is not part of the expression. Next up
+we need to handle function definitions, etc.</p>
+</div>
+<div class="section" id="parsing-the-rest">
+<h2><a class="toc-backref" href="#id7">2.6. Parsing the Rest</a><a class="headerlink" href="#parsing-the-rest" title="Permalink to this headline">¶</a></h2>
+<p>The next thing missing is handling of function prototypes. In
+Kaleidoscope, these are used both for ‘extern’ function declarations as
+well as function body definitions. The code to do this is
+straight-forward and not very interesting (once you’ve survived
+expressions):</p>
+<div class="highlight-ocaml"><div class="highlight"><pre><span class="c">(* prototype</span>
+<span class="c"> * ::= id '(' id* ')' *)</span>
+<span class="k">let</span> <span class="n">parse_prototype</span> <span class="o">=</span>
+ <span class="k">let</span> <span class="k">rec</span> <span class="n">parse_args</span> <span class="n">accumulator</span> <span class="o">=</span> <span class="n">parser</span>
+ <span class="o">|</span> <span class="o">[<</span> <span class="k">'</span><span class="nn">Token</span><span class="p">.</span><span class="nc">Ident</span> <span class="n">id</span><span class="o">;</span> <span class="n">e</span><span class="o">=</span><span class="n">parse_args</span> <span class="o">(</span><span class="n">id</span><span class="o">::</span><span class="n">accumulator</span><span class="o">)</span> <span class="o">>]</span> <span class="o">-></span> <span class="n">e</span>
+ <span class="o">|</span> <span class="o">[<</span> <span class="o">>]</span> <span class="o">-></span> <span class="n">accumulator</span>
+ <span class="k">in</span>
+
+ <span class="n">parser</span>
+ <span class="o">|</span> <span class="o">[<</span> <span class="k">'</span><span class="nn">Token</span><span class="p">.</span><span class="nc">Ident</span> <span class="n">id</span><span class="o">;</span>
+ <span class="k">'</span><span class="nn">Token</span><span class="p">.</span><span class="nc">Kwd</span> <span class="sc">'('</span> <span class="o">??</span> <span class="s2">"expected '(' in prototype"</span><span class="o">;</span>
+ <span class="n">args</span><span class="o">=</span><span class="n">parse_args</span> <span class="bp">[]</span><span class="o">;</span>
+ <span class="k">'</span><span class="nn">Token</span><span class="p">.</span><span class="nc">Kwd</span> <span class="sc">')'</span> <span class="o">??</span> <span class="s2">"expected ')' in prototype"</span> <span class="o">>]</span> <span class="o">-></span>
+ <span class="c">(* success. *)</span>
+ <span class="nn">Ast</span><span class="p">.</span><span class="nc">Prototype</span> <span class="o">(</span><span class="n">id</span><span class="o">,</span> <span class="nn">Array</span><span class="p">.</span><span class="n">of_list</span> <span class="o">(</span><span class="nn">List</span><span class="p">.</span><span class="n">rev</span> <span class="n">args</span><span class="o">))</span>
+
+ <span class="o">|</span> <span class="o">[<</span> <span class="o">>]</span> <span class="o">-></span>
+ <span class="k">raise</span> <span class="o">(</span><span class="nn">Stream</span><span class="p">.</span><span class="nc">Error</span> <span class="s2">"expected function name in prototype"</span><span class="o">)</span>
+</pre></div>
+</div>
+<p>Given this, a function definition is very simple, just a prototype plus
+an expression to implement the body:</p>
+<div class="highlight-ocaml"><div class="highlight"><pre><span class="c">(* definition ::= 'def' prototype expression *)</span>
+<span class="k">let</span> <span class="n">parse_definition</span> <span class="o">=</span> <span class="n">parser</span>
+ <span class="o">|</span> <span class="o">[<</span> <span class="k">'</span><span class="nn">Token</span><span class="p">.</span><span class="nc">Def</span><span class="o">;</span> <span class="n">p</span><span class="o">=</span><span class="n">parse_prototype</span><span class="o">;</span> <span class="n">e</span><span class="o">=</span><span class="n">parse_expr</span> <span class="o">>]</span> <span class="o">-></span>
+ <span class="nn">Ast</span><span class="p">.</span><span class="nc">Function</span> <span class="o">(</span><span class="n">p</span><span class="o">,</span> <span class="n">e</span><span class="o">)</span>
+</pre></div>
+</div>
+<p>In addition, we support ‘extern’ to declare functions like ‘sin’ and
+‘cos’ as well as to support forward declaration of user functions. These
+‘extern’s are just prototypes with no body:</p>
+<div class="highlight-ocaml"><div class="highlight"><pre><span class="c">(* external ::= 'extern' prototype *)</span>
+<span class="k">let</span> <span class="n">parse_extern</span> <span class="o">=</span> <span class="n">parser</span>
+ <span class="o">|</span> <span class="o">[<</span> <span class="k">'</span><span class="nn">Token</span><span class="p">.</span><span class="nc">Extern</span><span class="o">;</span> <span class="n">e</span><span class="o">=</span><span class="n">parse_prototype</span> <span class="o">>]</span> <span class="o">-></span> <span class="n">e</span>
+</pre></div>
+</div>
+<p>Finally, we’ll also let the user type in arbitrary top-level expressions
+and evaluate them on the fly. We will handle this by defining anonymous
+nullary (zero argument) functions for them:</p>
+<div class="highlight-ocaml"><div class="highlight"><pre><span class="c">(* toplevelexpr ::= expression *)</span>
+<span class="k">let</span> <span class="n">parse_toplevel</span> <span class="o">=</span> <span class="n">parser</span>
+ <span class="o">|</span> <span class="o">[<</span> <span class="n">e</span><span class="o">=</span><span class="n">parse_expr</span> <span class="o">>]</span> <span class="o">-></span>
+ <span class="c">(* Make an anonymous proto. *)</span>
+ <span class="nn">Ast</span><span class="p">.</span><span class="nc">Function</span> <span class="o">(</span><span class="nn">Ast</span><span class="p">.</span><span class="nc">Prototype</span> <span class="o">(</span><span class="s2">""</span><span class="o">,</span> <span class="o">[||]),</span> <span class="n">e</span><span class="o">)</span>
+</pre></div>
+</div>
+<p>Now that we have all the pieces, let’s build a little driver that will
+let us actually <em>execute</em> this code we’ve built!</p>
+</div>
+<div class="section" id="the-driver">
+<h2><a class="toc-backref" href="#id8">2.7. The Driver</a><a class="headerlink" href="#the-driver" title="Permalink to this headline">¶</a></h2>
+<p>The driver for this simply invokes all of the parsing pieces with a
+top-level dispatch loop. There isn’t much interesting here, so I’ll just
+include the top-level loop. See <a class="reference external" href="#full-code-listing">below</a> for full code in the
+“Top-Level Parsing” section.</p>
+<div class="highlight-ocaml"><div class="highlight"><pre><span class="c">(* top ::= definition | external | expression | ';' *)</span>
+<span class="k">let</span> <span class="k">rec</span> <span class="n">main_loop</span> <span class="n">stream</span> <span class="o">=</span>
+ <span class="k">match</span> <span class="nn">Stream</span><span class="p">.</span><span class="n">peek</span> <span class="n">stream</span> <span class="k">with</span>
+ <span class="o">|</span> <span class="nc">None</span> <span class="o">-></span> <span class="bp">()</span>
+
+ <span class="c">(* ignore top-level semicolons. *)</span>
+ <span class="o">|</span> <span class="nc">Some</span> <span class="o">(</span><span class="nn">Token</span><span class="p">.</span><span class="nc">Kwd</span> <span class="sc">';'</span><span class="o">)</span> <span class="o">-></span>
+ <span class="nn">Stream</span><span class="p">.</span><span class="n">junk</span> <span class="n">stream</span><span class="o">;</span>
+ <span class="n">main_loop</span> <span class="n">stream</span>
+
+ <span class="o">|</span> <span class="nc">Some</span> <span class="n">token</span> <span class="o">-></span>
+ <span class="k">begin</span>
+ <span class="k">try</span> <span class="k">match</span> <span class="n">token</span> <span class="k">with</span>
+ <span class="o">|</span> <span class="nn">Token</span><span class="p">.</span><span class="nc">Def</span> <span class="o">-></span>
+ <span class="n">ignore</span><span class="o">(</span><span class="nn">Parser</span><span class="p">.</span><span class="n">parse_definition</span> <span class="n">stream</span><span class="o">);</span>
+ <span class="n">print_endline</span> <span class="s2">"parsed a function definition."</span><span class="o">;</span>
+ <span class="o">|</span> <span class="nn">Token</span><span class="p">.</span><span class="nc">Extern</span> <span class="o">-></span>
+ <span class="n">ignore</span><span class="o">(</span><span class="nn">Parser</span><span class="p">.</span><span class="n">parse_extern</span> <span class="n">stream</span><span class="o">);</span>
+ <span class="n">print_endline</span> <span class="s2">"parsed an extern."</span><span class="o">;</span>
+ <span class="o">|</span> <span class="o">_</span> <span class="o">-></span>
+ <span class="c">(* Evaluate a top-level expression into an anonymous function. *)</span>
+ <span class="n">ignore</span><span class="o">(</span><span class="nn">Parser</span><span class="p">.</span><span class="n">parse_toplevel</span> <span class="n">stream</span><span class="o">);</span>
+ <span class="n">print_endline</span> <span class="s2">"parsed a top-level expr"</span><span class="o">;</span>
+ <span class="k">with</span> <span class="nn">Stream</span><span class="p">.</span><span class="nc">Error</span> <span class="n">s</span> <span class="o">-></span>
+ <span class="c">(* Skip token for error recovery. *)</span>
+ <span class="nn">Stream</span><span class="p">.</span><span class="n">junk</span> <span class="n">stream</span><span class="o">;</span>
+ <span class="n">print_endline</span> <span class="n">s</span><span class="o">;</span>
+ <span class="k">end</span><span class="o">;</span>
+ <span class="n">print_string</span> <span class="s2">"ready> "</span><span class="o">;</span> <span class="n">flush</span> <span class="n">stdout</span><span class="o">;</span>
+ <span class="n">main_loop</span> <span class="n">stream</span>
+</pre></div>
+</div>
+<p>The most interesting part of this is that we ignore top-level
+semicolons. Why is this, you ask? The basic reason is that if you type
+“4 + 5” at the command line, the parser doesn’t know whether that is the
+end of what you will type or not. For example, on the next line you
+could type “def foo...” in which case 4+5 is the end of a top-level
+expression. Alternatively you could type “* 6”, which would continue
+the expression. Having top-level semicolons allows you to type “4+5;”,
+and the parser will know you are done.</p>
+</div>
+<div class="section" id="conclusions">
+<h2><a class="toc-backref" href="#id9">2.8. Conclusions</a><a class="headerlink" href="#conclusions" title="Permalink to this headline">¶</a></h2>
+<p>With just under 300 lines of commented code (240 lines of non-comment,
+non-blank code), we fully defined our minimal language, including a
+lexer, parser, and AST builder. With this done, the executable will
+validate Kaleidoscope code and tell us if it is grammatically invalid.
+For example, here is a sample interaction:</p>
+<div class="highlight-bash"><div class="highlight"><pre>$ ./toy.byte
+ready> def foo(x y) x+foo(y, 4.0);
+Parsed a function definition.
+ready> def foo(x y) x+y y;
+Parsed a function definition.
+Parsed a top-level expr
+ready> def foo(x y) x+y );
+Parsed a function definition.
+Error: unknown token when expecting an expression
+ready> extern sin(a);
+ready> Parsed an extern
+ready> ^D
+$
+</pre></div>
+</div>
+<p>There is a lot of room for extension here. You can define new AST nodes,
+extend the language in many ways, etc. In the <a class="reference external" href="OCamlLangImpl3.html">next
+installment</a>, we will describe how to generate
+LLVM Intermediate Representation (IR) from the AST.</p>
+</div>
+<div class="section" id="full-code-listing">
+<h2><a class="toc-backref" href="#id10">2.9. Full Code Listing</a><a class="headerlink" href="#full-code-listing" title="Permalink to this headline">¶</a></h2>
+<p>Here is the complete code listing for this and the previous chapter.
+Note that it is fully self-contained: you don’t need LLVM or any
+external libraries at all for this. (Besides the ocaml standard
+libraries, of course.) To build this, just compile with:</p>
+<div class="highlight-bash"><div class="highlight"><pre><span class="c"># Compile</span>
+ocamlbuild toy.byte
+<span class="c"># Run</span>
+./toy.byte
+</pre></div>
+</div>
+<p>Here is the code:</p>
+<dl class="docutils">
+<dt>_tags:</dt>
+<dd><div class="first last highlight-python"><div class="highlight"><pre><{lexer,parser}.ml>: use_camlp4, pp(camlp4of)
+</pre></div>
+</div>
+</dd>
+<dt>token.ml:</dt>
+<dd><div class="first last highlight-ocaml"><div class="highlight"><pre><span class="c">(*===----------------------------------------------------------------------===</span>
+<span class="c"> * Lexer Tokens</span>
+<span class="c"> *===----------------------------------------------------------------------===*)</span>
+
+<span class="c">(* The lexer returns these 'Kwd' if it is an unknown character, otherwise one of</span>
+<span class="c"> * these others for known things. *)</span>
+<span class="k">type</span> <span class="n">token</span> <span class="o">=</span>
+ <span class="c">(* commands *)</span>
+ <span class="o">|</span> <span class="nc">Def</span> <span class="o">|</span> <span class="nc">Extern</span>
+
+ <span class="c">(* primary *)</span>
+ <span class="o">|</span> <span class="nc">Ident</span> <span class="k">of</span> <span class="kt">string</span> <span class="o">|</span> <span class="nc">Number</span> <span class="k">of</span> <span class="kt">float</span>
+
+ <span class="c">(* unknown *)</span>
+ <span class="o">|</span> <span class="nc">Kwd</span> <span class="k">of</span> <span class="kt">char</span>
+</pre></div>
+</div>
+</dd>
+<dt>lexer.ml:</dt>
+<dd><div class="first last highlight-ocaml"><div class="highlight"><pre><span class="c">(*===----------------------------------------------------------------------===</span>
+<span class="c"> * Lexer</span>
+<span class="c"> *===----------------------------------------------------------------------===*)</span>
+
+<span class="k">let</span> <span class="k">rec</span> <span class="n">lex</span> <span class="o">=</span> <span class="n">parser</span>
+ <span class="c">(* Skip any whitespace. *)</span>
+ <span class="o">|</span> <span class="o">[<</span> <span class="k">'</span> <span class="o">(</span><span class="sc">' '</span> <span class="o">|</span> <span class="sc">'\n'</span> <span class="o">|</span> <span class="sc">'\r'</span> <span class="o">|</span> <span class="sc">'\t'</span><span class="o">);</span> <span class="n">stream</span> <span class="o">>]</span> <span class="o">-></span> <span class="n">lex</span> <span class="n">stream</span>
+
+ <span class="c">(* identifier: [a-zA-Z][a-zA-Z0-9] *)</span>
+ <span class="o">|</span> <span class="o">[<</span> <span class="k">'</span> <span class="o">(</span><span class="sc">'A'</span> <span class="o">..</span> <span class="sc">'Z'</span> <span class="o">|</span> <span class="sc">'a'</span> <span class="o">..</span> <span class="sc">'z'</span> <span class="k">as</span> <span class="n">c</span><span class="o">);</span> <span class="n">stream</span> <span class="o">>]</span> <span class="o">-></span>
+ <span class="k">let</span> <span class="n">buffer</span> <span class="o">=</span> <span class="nn">Buffer</span><span class="p">.</span><span class="n">create</span> <span class="mi">1</span> <span class="k">in</span>
+ <span class="nn">Buffer</span><span class="p">.</span><span class="n">add_char</span> <span class="n">buffer</span> <span class="n">c</span><span class="o">;</span>
+ <span class="n">lex_ident</span> <span class="n">buffer</span> <span class="n">stream</span>
+
+ <span class="c">(* number: [0-9.]+ *)</span>
+ <span class="o">|</span> <span class="o">[<</span> <span class="k">'</span> <span class="o">(</span><span class="sc">'0'</span> <span class="o">..</span> <span class="sc">'9'</span> <span class="k">as</span> <span class="n">c</span><span class="o">);</span> <span class="n">stream</span> <span class="o">>]</span> <span class="o">-></span>
+ <span class="k">let</span> <span class="n">buffer</span> <span class="o">=</span> <span class="nn">Buffer</span><span class="p">.</span><span class="n">create</span> <span class="mi">1</span> <span class="k">in</span>
+ <span class="nn">Buffer</span><span class="p">.</span><span class="n">add_char</span> <span class="n">buffer</span> <span class="n">c</span><span class="o">;</span>
+ <span class="n">lex_number</span> <span class="n">buffer</span> <span class="n">stream</span>
+
+ <span class="c">(* Comment until end of line. *)</span>
+ <span class="o">|</span> <span class="o">[<</span> <span class="k">'</span> <span class="o">(</span><span class="sc">'#'</span><span class="o">);</span> <span class="n">stream</span> <span class="o">>]</span> <span class="o">-></span>
+ <span class="n">lex_comment</span> <span class="n">stream</span>
+
+ <span class="c">(* Otherwise, just return the character as its ascii value. *)</span>
+ <span class="o">|</span> <span class="o">[<</span> <span class="k">'</span><span class="n">c</span><span class="o">;</span> <span class="n">stream</span> <span class="o">>]</span> <span class="o">-></span>
+ <span class="o">[<</span> <span class="k">'</span><span class="nn">Token</span><span class="p">.</span><span class="nc">Kwd</span> <span class="n">c</span><span class="o">;</span> <span class="n">lex</span> <span class="n">stream</span> <span class="o">>]</span>
+
+ <span class="c">(* end of stream. *)</span>
+ <span class="o">|</span> <span class="o">[<</span> <span class="o">>]</span> <span class="o">-></span> <span class="o">[<</span> <span class="o">>]</span>
+
+<span class="ow">and</span> <span class="n">lex_number</span> <span class="n">buffer</span> <span class="o">=</span> <span class="n">parser</span>
+ <span class="o">|</span> <span class="o">[<</span> <span class="k">'</span> <span class="o">(</span><span class="sc">'0'</span> <span class="o">..</span> <span class="sc">'9'</span> <span class="o">|</span> <span class="sc">'.'</span> <span class="k">as</span> <span class="n">c</span><span class="o">);</span> <span class="n">stream</span> <span class="o">>]</span> <span class="o">-></span>
+ <span class="nn">Buffer</span><span class="p">.</span><span class="n">add_char</span> <span class="n">buffer</span> <span class="n">c</span><span class="o">;</span>
+ <span class="n">lex_number</span> <span class="n">buffer</span> <span class="n">stream</span>
+ <span class="o">|</span> <span class="o">[<</span> <span class="n">stream</span><span class="o">=</span><span class="n">lex</span> <span class="o">>]</span> <span class="o">-></span>
+ <span class="o">[<</span> <span class="k">'</span><span class="nn">Token</span><span class="p">.</span><span class="nc">Number</span> <span class="o">(</span><span class="n">float_of_string</span> <span class="o">(</span><span class="nn">Buffer</span><span class="p">.</span><span class="n">contents</span> <span class="n">buffer</span><span class="o">));</span> <span class="n">stream</span> <span class="o">>]</span>
+
+<span class="ow">and</span> <span class="n">lex_ident</span> <span class="n">buffer</span> <span class="o">=</span> <span class="n">parser</span>
+ <span class="o">|</span> <span class="o">[<</span> <span class="k">'</span> <span class="o">(</span><span class="sc">'A'</span> <span class="o">..</span> <span class="sc">'Z'</span> <span class="o">|</span> <span class="sc">'a'</span> <span class="o">..</span> <span class="sc">'z'</span> <span class="o">|</span> <span class="sc">'0'</span> <span class="o">..</span> <span class="sc">'9'</span> <span class="k">as</span> <span class="n">c</span><span class="o">);</span> <span class="n">stream</span> <span class="o">>]</span> <span class="o">-></span>
+ <span class="nn">Buffer</span><span class="p">.</span><span class="n">add_char</span> <span class="n">buffer</span> <span class="n">c</span><span class="o">;</span>
+ <span class="n">lex_ident</span> <span class="n">buffer</span> <span class="n">stream</span>
+ <span class="o">|</span> <span class="o">[<</span> <span class="n">stream</span><span class="o">=</span><span class="n">lex</span> <span class="o">>]</span> <span class="o">-></span>
+ <span class="k">match</span> <span class="nn">Buffer</span><span class="p">.</span><span class="n">contents</span> <span class="n">buffer</span> <span class="k">with</span>
+ <span class="o">|</span> <span class="s2">"def"</span> <span class="o">-></span> <span class="o">[<</span> <span class="k">'</span><span class="nn">Token</span><span class="p">.</span><span class="nc">Def</span><span class="o">;</span> <span class="n">stream</span> <span class="o">>]</span>
+ <span class="o">|</span> <span class="s2">"extern"</span> <span class="o">-></span> <span class="o">[<</span> <span class="k">'</span><span class="nn">Token</span><span class="p">.</span><span class="nc">Extern</span><span class="o">;</span> <span class="n">stream</span> <span class="o">>]</span>
+ <span class="o">|</span> <span class="n">id</span> <span class="o">-></span> <span class="o">[<</span> <span class="k">'</span><span class="nn">Token</span><span class="p">.</span><span class="nc">Ident</span> <span class="n">id</span><span class="o">;</span> <span class="n">stream</span> <span class="o">>]</span>
+
+<span class="ow">and</span> <span class="n">lex_comment</span> <span class="o">=</span> <span class="n">parser</span>
+ <span class="o">|</span> <span class="o">[<</span> <span class="k">'</span> <span class="o">(</span><span class="sc">'\n'</span><span class="o">);</span> <span class="n">stream</span><span class="o">=</span><span class="n">lex</span> <span class="o">>]</span> <span class="o">-></span> <span class="n">stream</span>
+ <span class="o">|</span> <span class="o">[<</span> <span class="k">'</span><span class="n">c</span><span class="o">;</span> <span class="n">e</span><span class="o">=</span><span class="n">lex_comment</span> <span class="o">>]</span> <span class="o">-></span> <span class="n">e</span>
+ <span class="o">|</span> <span class="o">[<</span> <span class="o">>]</span> <span class="o">-></span> <span class="o">[<</span> <span class="o">>]</span>
+</pre></div>
+</div>
+</dd>
+<dt>ast.ml:</dt>
+<dd><div class="first last highlight-ocaml"><div class="highlight"><pre><span class="c">(*===----------------------------------------------------------------------===</span>
+<span class="c"> * Abstract Syntax Tree (aka Parse Tree)</span>
+<span class="c"> *===----------------------------------------------------------------------===*)</span>
+
+<span class="c">(* expr - Base type for all expression nodes. *)</span>
+<span class="k">type</span> <span class="n">expr</span> <span class="o">=</span>
+ <span class="c">(* variant for numeric literals like "1.0". *)</span>
+ <span class="o">|</span> <span class="nc">Number</span> <span class="k">of</span> <span class="kt">float</span>
+
+ <span class="c">(* variant for referencing a variable, like "a". *)</span>
+ <span class="o">|</span> <span class="nc">Variable</span> <span class="k">of</span> <span class="kt">string</span>
+
+ <span class="c">(* variant for a binary operator. *)</span>
+ <span class="o">|</span> <span class="nc">Binary</span> <span class="k">of</span> <span class="kt">char</span> <span class="o">*</span> <span class="n">expr</span> <span class="o">*</span> <span class="n">expr</span>
+
+ <span class="c">(* variant for function calls. *)</span>
+ <span class="o">|</span> <span class="nc">Call</span> <span class="k">of</span> <span class="kt">string</span> <span class="o">*</span> <span class="n">expr</span> <span class="kt">array</span>
+
+<span class="c">(* proto - This type represents the "prototype" for a function, which captures</span>
+<span class="c"> * its name, and its argument names (thus implicitly the number of arguments the</span>
+<span class="c"> * function takes). *)</span>
+<span class="k">type</span> <span class="n">proto</span> <span class="o">=</span> <span class="nc">Prototype</span> <span class="k">of</span> <span class="kt">string</span> <span class="o">*</span> <span class="kt">string</span> <span class="kt">array</span>
+
+<span class="c">(* func - This type represents a function definition itself. *)</span>
+<span class="k">type</span> <span class="n">func</span> <span class="o">=</span> <span class="nc">Function</span> <span class="k">of</span> <span class="n">proto</span> <span class="o">*</span> <span class="n">expr</span>
+</pre></div>
+</div>
+</dd>
+<dt>parser.ml:</dt>
+<dd><div class="first last highlight-ocaml"><div class="highlight"><pre><span class="c">(*===---------------------------------------------------------------------===</span>
+<span class="c"> * Parser</span>
+<span class="c"> *===---------------------------------------------------------------------===*)</span>
+
+<span class="c">(* binop_precedence - This holds the precedence for each binary operator that is</span>
+<span class="c"> * defined *)</span>
+<span class="k">let</span> <span class="n">binop_precedence</span><span class="o">:(</span><span class="kt">char</span><span class="o">,</span> <span class="kt">int</span><span class="o">)</span> <span class="nn">Hashtbl</span><span class="p">.</span><span class="n">t</span> <span class="o">=</span> <span class="nn">Hashtbl</span><span class="p">.</span><span class="n">create</span> <span class="mi">10</span>
+
+<span class="c">(* precedence - Get the precedence of the pending binary operator token. *)</span>
+<span class="k">let</span> <span class="n">precedence</span> <span class="n">c</span> <span class="o">=</span> <span class="k">try</span> <span class="nn">Hashtbl</span><span class="p">.</span><span class="n">find</span> <span class="n">binop_precedence</span> <span class="n">c</span> <span class="k">with</span> <span class="nc">Not_found</span> <span class="o">-></span> <span class="o">-</span><span class="mi">1</span>
+
+<span class="c">(* primary</span>
+<span class="c"> * ::= identifier</span>
+<span class="c"> * ::= numberexpr</span>
+<span class="c"> * ::= parenexpr *)</span>
+<span class="k">let</span> <span class="k">rec</span> <span class="n">parse_primary</span> <span class="o">=</span> <span class="n">parser</span>
+ <span class="c">(* numberexpr ::= number *)</span>
+ <span class="o">|</span> <span class="o">[<</span> <span class="k">'</span><span class="nn">Token</span><span class="p">.</span><span class="nc">Number</span> <span class="n">n</span> <span class="o">>]</span> <span class="o">-></span> <span class="nn">Ast</span><span class="p">.</span><span class="nc">Number</span> <span class="n">n</span>
+
+ <span class="c">(* parenexpr ::= '(' expression ')' *)</span>
+ <span class="o">|</span> <span class="o">[<</span> <span class="k">'</span><span class="nn">Token</span><span class="p">.</span><span class="nc">Kwd</span> <span class="sc">'('</span><span class="o">;</span> <span class="n">e</span><span class="o">=</span><span class="n">parse_expr</span><span class="o">;</span> <span class="k">'</span><span class="nn">Token</span><span class="p">.</span><span class="nc">Kwd</span> <span class="sc">')'</span> <span class="o">??</span> <span class="s2">"expected ')'"</span> <span class="o">>]</span> <span class="o">-></span> <span class="n">e</span>
+
+ <span class="c">(* identifierexpr</span>
+<span class="c"> * ::= identifier</span>
+<span class="c"> * ::= identifier '(' argumentexpr ')' *)</span>
+ <span class="o">|</span> <span class="o">[<</span> <span class="k">'</span><span class="nn">Token</span><span class="p">.</span><span class="nc">Ident</span> <span class="n">id</span><span class="o">;</span> <span class="n">stream</span> <span class="o">>]</span> <span class="o">-></span>
+ <span class="k">let</span> <span class="k">rec</span> <span class="n">parse_args</span> <span class="n">accumulator</span> <span class="o">=</span> <span class="n">parser</span>
+ <span class="o">|</span> <span class="o">[<</span> <span class="n">e</span><span class="o">=</span><span class="n">parse_expr</span><span class="o">;</span> <span class="n">stream</span> <span class="o">>]</span> <span class="o">-></span>
+ <span class="k">begin</span> <span class="n">parser</span>
+ <span class="o">|</span> <span class="o">[<</span> <span class="k">'</span><span class="nn">Token</span><span class="p">.</span><span class="nc">Kwd</span> <span class="sc">','</span><span class="o">;</span> <span class="n">e</span><span class="o">=</span><span class="n">parse_args</span> <span class="o">(</span><span class="n">e</span> <span class="o">::</span> <span class="n">accumulator</span><span class="o">)</span> <span class="o">>]</span> <span class="o">-></span> <span class="n">e</span>
+ <span class="o">|</span> <span class="o">[<</span> <span class="o">>]</span> <span class="o">-></span> <span class="n">e</span> <span class="o">::</span> <span class="n">accumulator</span>
+ <span class="k">end</span> <span class="n">stream</span>
+ <span class="o">|</span> <span class="o">[<</span> <span class="o">>]</span> <span class="o">-></span> <span class="n">accumulator</span>
+ <span class="k">in</span>
+ <span class="k">let</span> <span class="k">rec</span> <span class="n">parse_ident</span> <span class="n">id</span> <span class="o">=</span> <span class="n">parser</span>
+ <span class="c">(* Call. *)</span>
+ <span class="o">|</span> <span class="o">[<</span> <span class="k">'</span><span class="nn">Token</span><span class="p">.</span><span class="nc">Kwd</span> <span class="sc">'('</span><span class="o">;</span>
+ <span class="n">args</span><span class="o">=</span><span class="n">parse_args</span> <span class="bp">[]</span><span class="o">;</span>
+ <span class="k">'</span><span class="nn">Token</span><span class="p">.</span><span class="nc">Kwd</span> <span class="sc">')'</span> <span class="o">??</span> <span class="s2">"expected ')'"</span><span class="o">>]</span> <span class="o">-></span>
+ <span class="nn">Ast</span><span class="p">.</span><span class="nc">Call</span> <span class="o">(</span><span class="n">id</span><span class="o">,</span> <span class="nn">Array</span><span class="p">.</span><span class="n">of_list</span> <span class="o">(</span><span class="nn">List</span><span class="p">.</span><span class="n">rev</span> <span class="n">args</span><span class="o">))</span>
+
+ <span class="c">(* Simple variable ref. *)</span>
+ <span class="o">|</span> <span class="o">[<</span> <span class="o">>]</span> <span class="o">-></span> <span class="nn">Ast</span><span class="p">.</span><span class="nc">Variable</span> <span class="n">id</span>
+ <span class="k">in</span>
+ <span class="n">parse_ident</span> <span class="n">id</span> <span class="n">stream</span>
+
+ <span class="o">|</span> <span class="o">[<</span> <span class="o">>]</span> <span class="o">-></span> <span class="k">raise</span> <span class="o">(</span><span class="nn">Stream</span><span class="p">.</span><span class="nc">Error</span> <span class="s2">"unknown token when expecting an expression."</span><span class="o">)</span>
+
+<span class="c">(* binoprhs</span>
+<span class="c"> * ::= ('+' primary)* *)</span>
+<span class="ow">and</span> <span class="n">parse_bin_rhs</span> <span class="n">expr_prec</span> <span class="n">lhs</span> <span class="n">stream</span> <span class="o">=</span>
+ <span class="k">match</span> <span class="nn">Stream</span><span class="p">.</span><span class="n">peek</span> <span class="n">stream</span> <span class="k">with</span>
+ <span class="c">(* If this is a binop, find its precedence. *)</span>
+ <span class="o">|</span> <span class="nc">Some</span> <span class="o">(</span><span class="nn">Token</span><span class="p">.</span><span class="nc">Kwd</span> <span class="n">c</span><span class="o">)</span> <span class="k">when</span> <span class="nn">Hashtbl</span><span class="p">.</span><span class="n">mem</span> <span class="n">binop_precedence</span> <span class="n">c</span> <span class="o">-></span>
+ <span class="k">let</span> <span class="n">token_prec</span> <span class="o">=</span> <span class="n">precedence</span> <span class="n">c</span> <span class="k">in</span>
+
+ <span class="c">(* If this is a binop that binds at least as tightly as the current binop,</span>
+<span class="c"> * consume it, otherwise we are done. *)</span>
+ <span class="k">if</span> <span class="n">token_prec</span> <span class="o"><</span> <span class="n">expr_prec</span> <span class="k">then</span> <span class="n">lhs</span> <span class="k">else</span> <span class="k">begin</span>
+ <span class="c">(* Eat the binop. *)</span>
+ <span class="nn">Stream</span><span class="p">.</span><span class="n">junk</span> <span class="n">stream</span><span class="o">;</span>
+
+ <span class="c">(* Parse the primary expression after the binary operator. *)</span>
+ <span class="k">let</span> <span class="n">rhs</span> <span class="o">=</span> <span class="n">parse_primary</span> <span class="n">stream</span> <span class="k">in</span>
+
+ <span class="c">(* Okay, we know this is a binop. *)</span>
+ <span class="k">let</span> <span class="n">rhs</span> <span class="o">=</span>
+ <span class="k">match</span> <span class="nn">Stream</span><span class="p">.</span><span class="n">peek</span> <span class="n">stream</span> <span class="k">with</span>
+ <span class="o">|</span> <span class="nc">Some</span> <span class="o">(</span><span class="nn">Token</span><span class="p">.</span><span class="nc">Kwd</span> <span class="n">c2</span><span class="o">)</span> <span class="o">-></span>
+ <span class="c">(* If BinOp binds less tightly with rhs than the operator after</span>
+<span class="c"> * rhs, let the pending operator take rhs as its lhs. *)</span>
+ <span class="k">let</span> <span class="n">next_prec</span> <span class="o">=</span> <span class="n">precedence</span> <span class="n">c2</span> <span class="k">in</span>
+ <span class="k">if</span> <span class="n">token_prec</span> <span class="o"><</span> <span class="n">next_prec</span>
+ <span class="k">then</span> <span class="n">parse_bin_rhs</span> <span class="o">(</span><span class="n">token_prec</span> <span class="o">+</span> <span class="mi">1</span><span class="o">)</span> <span class="n">rhs</span> <span class="n">stream</span>
+ <span class="k">else</span> <span class="n">rhs</span>
+ <span class="o">|</span> <span class="o">_</span> <span class="o">-></span> <span class="n">rhs</span>
+ <span class="k">in</span>
+
+ <span class="c">(* Merge lhs/rhs. *)</span>
+ <span class="k">let</span> <span class="n">lhs</span> <span class="o">=</span> <span class="nn">Ast</span><span class="p">.</span><span class="nc">Binary</span> <span class="o">(</span><span class="n">c</span><span class="o">,</span> <span class="n">lhs</span><span class="o">,</span> <span class="n">rhs</span><span class="o">)</span> <span class="k">in</span>
+ <span class="n">parse_bin_rhs</span> <span class="n">expr_prec</span> <span class="n">lhs</span> <span class="n">stream</span>
+ <span class="k">end</span>
+ <span class="o">|</span> <span class="o">_</span> <span class="o">-></span> <span class="n">lhs</span>
+
+<span class="c">(* expression</span>
+<span class="c"> * ::= primary binoprhs *)</span>
+<span class="ow">and</span> <span class="n">parse_expr</span> <span class="o">=</span> <span class="n">parser</span>
+ <span class="o">|</span> <span class="o">[<</span> <span class="n">lhs</span><span class="o">=</span><span class="n">parse_primary</span><span class="o">;</span> <span class="n">stream</span> <span class="o">>]</span> <span class="o">-></span> <span class="n">parse_bin_rhs</span> <span class="mi">0</span> <span class="n">lhs</span> <span class="n">stream</span>
+
+<span class="c">(* prototype</span>
+<span class="c"> * ::= id '(' id* ')' *)</span>
+<span class="k">let</span> <span class="n">parse_prototype</span> <span class="o">=</span>
+ <span class="k">let</span> <span class="k">rec</span> <span class="n">parse_args</span> <span class="n">accumulator</span> <span class="o">=</span> <span class="n">parser</span>
+ <span class="o">|</span> <span class="o">[<</span> <span class="k">'</span><span class="nn">Token</span><span class="p">.</span><span class="nc">Ident</span> <span class="n">id</span><span class="o">;</span> <span class="n">e</span><span class="o">=</span><span class="n">parse_args</span> <span class="o">(</span><span class="n">id</span><span class="o">::</span><span class="n">accumulator</span><span class="o">)</span> <span class="o">>]</span> <span class="o">-></span> <span class="n">e</span>
+ <span class="o">|</span> <span class="o">[<</span> <span class="o">>]</span> <span class="o">-></span> <span class="n">accumulator</span>
+ <span class="k">in</span>
+
+ <span class="n">parser</span>
+ <span class="o">|</span> <span class="o">[<</span> <span class="k">'</span><span class="nn">Token</span><span class="p">.</span><span class="nc">Ident</span> <span class="n">id</span><span class="o">;</span>
+ <span class="k">'</span><span class="nn">Token</span><span class="p">.</span><span class="nc">Kwd</span> <span class="sc">'('</span> <span class="o">??</span> <span class="s2">"expected '(' in prototype"</span><span class="o">;</span>
+ <span class="n">args</span><span class="o">=</span><span class="n">parse_args</span> <span class="bp">[]</span><span class="o">;</span>
+ <span class="k">'</span><span class="nn">Token</span><span class="p">.</span><span class="nc">Kwd</span> <span class="sc">')'</span> <span class="o">??</span> <span class="s2">"expected ')' in prototype"</span> <span class="o">>]</span> <span class="o">-></span>
+ <span class="c">(* success. *)</span>
+ <span class="nn">Ast</span><span class="p">.</span><span class="nc">Prototype</span> <span class="o">(</span><span class="n">id</span><span class="o">,</span> <span class="nn">Array</span><span class="p">.</span><span class="n">of_list</span> <span class="o">(</span><span class="nn">List</span><span class="p">.</span><span class="n">rev</span> <span class="n">args</span><span class="o">))</span>
+
+ <span class="o">|</span> <span class="o">[<</span> <span class="o">>]</span> <span class="o">-></span>
+ <span class="k">raise</span> <span class="o">(</span><span class="nn">Stream</span><span class="p">.</span><span class="nc">Error</span> <span class="s2">"expected function name in prototype"</span><span class="o">)</span>
+
+<span class="c">(* definition ::= 'def' prototype expression *)</span>
+<span class="k">let</span> <span class="n">parse_definition</span> <span class="o">=</span> <span class="n">parser</span>
+ <span class="o">|</span> <span class="o">[<</span> <span class="k">'</span><span class="nn">Token</span><span class="p">.</span><span class="nc">Def</span><span class="o">;</span> <span class="n">p</span><span class="o">=</span><span class="n">parse_prototype</span><span class="o">;</span> <span class="n">e</span><span class="o">=</span><span class="n">parse_expr</span> <span class="o">>]</span> <span class="o">-></span>
+ <span class="nn">Ast</span><span class="p">.</span><span class="nc">Function</span> <span class="o">(</span><span class="n">p</span><span class="o">,</span> <span class="n">e</span><span class="o">)</span>
+
+<span class="c">(* toplevelexpr ::= expression *)</span>
+<span class="k">let</span> <span class="n">parse_toplevel</span> <span class="o">=</span> <span class="n">parser</span>
+ <span class="o">|</span> <span class="o">[<</span> <span class="n">e</span><span class="o">=</span><span class="n">parse_expr</span> <span class="o">>]</span> <span class="o">-></span>
+ <span class="c">(* Make an anonymous proto. *)</span>
+ <span class="nn">Ast</span><span class="p">.</span><span class="nc">Function</span> <span class="o">(</span><span class="nn">Ast</span><span class="p">.</span><span class="nc">Prototype</span> <span class="o">(</span><span class="s2">""</span><span class="o">,</span> <span class="o">[||]),</span> <span class="n">e</span><span class="o">)</span>
+
+<span class="c">(* external ::= 'extern' prototype *)</span>
+<span class="k">let</span> <span class="n">parse_extern</span> <span class="o">=</span> <span class="n">parser</span>
+ <span class="o">|</span> <span class="o">[<</span> <span class="k">'</span><span class="nn">Token</span><span class="p">.</span><span class="nc">Extern</span><span class="o">;</span> <span class="n">e</span><span class="o">=</span><span class="n">parse_prototype</span> <span class="o">>]</span> <span class="o">-></span> <span class="n">e</span>
+</pre></div>
+</div>
+</dd>
+<dt>toplevel.ml:</dt>
+<dd><div class="first last highlight-ocaml"><div class="highlight"><pre><span class="c">(*===----------------------------------------------------------------------===</span>
+<span class="c"> * Top-Level parsing and JIT Driver</span>
+<span class="c"> *===----------------------------------------------------------------------===*)</span>
+
+<span class="c">(* top ::= definition | external | expression | ';' *)</span>
+<span class="k">let</span> <span class="k">rec</span> <span class="n">main_loop</span> <span class="n">stream</span> <span class="o">=</span>
+ <span class="k">match</span> <span class="nn">Stream</span><span class="p">.</span><span class="n">peek</span> <span class="n">stream</span> <span class="k">with</span>
+ <span class="o">|</span> <span class="nc">None</span> <span class="o">-></span> <span class="bp">()</span>
+
+ <span class="c">(* ignore top-level semicolons. *)</span>
+ <span class="o">|</span> <span class="nc">Some</span> <span class="o">(</span><span class="nn">Token</span><span class="p">.</span><span class="nc">Kwd</span> <span class="sc">';'</span><span class="o">)</span> <span class="o">-></span>
+ <span class="nn">Stream</span><span class="p">.</span><span class="n">junk</span> <span class="n">stream</span><span class="o">;</span>
+ <span class="n">main_loop</span> <span class="n">stream</span>
+
+ <span class="o">|</span> <span class="nc">Some</span> <span class="n">token</span> <span class="o">-></span>
+ <span class="k">begin</span>
+ <span class="k">try</span> <span class="k">match</span> <span class="n">token</span> <span class="k">with</span>
+ <span class="o">|</span> <span class="nn">Token</span><span class="p">.</span><span class="nc">Def</span> <span class="o">-></span>
+ <span class="n">ignore</span><span class="o">(</span><span class="nn">Parser</span><span class="p">.</span><span class="n">parse_definition</span> <span class="n">stream</span><span class="o">);</span>
+ <span class="n">print_endline</span> <span class="s2">"parsed a function definition."</span><span class="o">;</span>
+ <span class="o">|</span> <span class="nn">Token</span><span class="p">.</span><span class="nc">Extern</span> <span class="o">-></span>
+ <span class="n">ignore</span><span class="o">(</span><span class="nn">Parser</span><span class="p">.</span><span class="n">parse_extern</span> <span class="n">stream</span><span class="o">);</span>
+ <span class="n">print_endline</span> <span class="s2">"parsed an extern."</span><span class="o">;</span>
+ <span class="o">|</span> <span class="o">_</span> <span class="o">-></span>
+ <span class="c">(* Evaluate a top-level expression into an anonymous function. *)</span>
+ <span class="n">ignore</span><span class="o">(</span><span class="nn">Parser</span><span class="p">.</span><span class="n">parse_toplevel</span> <span class="n">stream</span><span class="o">);</span>
+ <span class="n">print_endline</span> <span class="s2">"parsed a top-level expr"</span><span class="o">;</span>
+ <span class="k">with</span> <span class="nn">Stream</span><span class="p">.</span><span class="nc">Error</span> <span class="n">s</span> <span class="o">-></span>
+ <span class="c">(* Skip token for error recovery. *)</span>
+ <span class="nn">Stream</span><span class="p">.</span><span class="n">junk</span> <span class="n">stream</span><span class="o">;</span>
+ <span class="n">print_endline</span> <span class="n">s</span><span class="o">;</span>
+ <span class="k">end</span><span class="o">;</span>
+ <span class="n">print_string</span> <span class="s2">"ready> "</span><span class="o">;</span> <span class="n">flush</span> <span class="n">stdout</span><span class="o">;</span>
+ <span class="n">main_loop</span> <span class="n">stream</span>
+</pre></div>
+</div>
+</dd>
+<dt>toy.ml:</dt>
+<dd><div class="first last highlight-ocaml"><div class="highlight"><pre><span class="c">(*===----------------------------------------------------------------------===</span>
+<span class="c"> * Main driver code.</span>
+<span class="c"> *===----------------------------------------------------------------------===*)</span>
+
+<span class="k">let</span> <span class="n">main</span> <span class="bp">()</span> <span class="o">=</span>
+ <span class="c">(* Install standard binary operators.</span>
+<span class="c"> * 1 is the lowest precedence. *)</span>
+ <span class="nn">Hashtbl</span><span class="p">.</span><span class="n">add</span> <span class="nn">Parser</span><span class="p">.</span><span class="n">binop_precedence</span> <span class="sc">'<'</span> <span class="mi">10</span><span class="o">;</span>
+ <span class="nn">Hashtbl</span><span class="p">.</span><span class="n">add</span> <span class="nn">Parser</span><span class="p">.</span><span class="n">binop_precedence</span> <span class="sc">'+'</span> <span class="mi">20</span><span class="o">;</span>
+ <span class="nn">Hashtbl</span><span class="p">.</span><span class="n">add</span> <span class="nn">Parser</span><span class="p">.</span><span class="n">binop_precedence</span> <span class="sc">'-'</span> <span class="mi">20</span><span class="o">;</span>
+ <span class="nn">Hashtbl</span><span class="p">.</span><span class="n">add</span> <span class="nn">Parser</span><span class="p">.</span><span class="n">binop_precedence</span> <span class="sc">'*'</span> <span class="mi">40</span><span class="o">;</span> <span class="c">(* highest. *)</span>
+
+ <span class="c">(* Prime the first token. *)</span>
+ <span class="n">print_string</span> <span class="s2">"ready> "</span><span class="o">;</span> <span class="n">flush</span> <span class="n">stdout</span><span class="o">;</span>
+ <span class="k">let</span> <span class="n">stream</span> <span class="o">=</span> <span class="nn">Lexer</span><span class="p">.</span><span class="n">lex</span> <span class="o">(</span><span class="nn">Stream</span><span class="p">.</span><span class="n">of_channel</span> <span class="n">stdin</span><span class="o">)</span> <span class="k">in</span>
+
+ <span class="c">(* Run the main "interpreter loop" now. *)</span>
+ <span class="nn">Toplevel</span><span class="p">.</span><span class="n">main_loop</span> <span class="n">stream</span><span class="o">;</span>
+<span class="o">;;</span>
+
+<span class="n">main</span> <span class="bp">()</span>
+</pre></div>
+</div>
+</dd>
+</dl>
+<p><a class="reference external" href="OCamlLangImpl3.html">Next: Implementing Code Generation to LLVM IR</a></p>
+</div>
+</div>
+
+
+ </div>
+ </div>
+ <div class="clearer"></div>
+ </div>
+ <div class="related">
+ <h3>Navigation</h3>
+ <ul>
+ <li class="right" style="margin-right: 10px">
+ <a href="../genindex.html" title="General Index"
+ >index</a></li>
+ <li class="right" >
+ <a href="OCamlLangImpl3.html" title="3. Kaleidoscope: Code generation to LLVM IR"
+ >next</a> |</li>
+ <li class="right" >
+ <a href="OCamlLangImpl1.html" title="1. Kaleidoscope: Tutorial Introduction and the Lexer"
+ >previous</a> |</li>
+ <li><a href="http://llvm.org/">LLVM Home</a> | </li>
+ <li><a href="../index.html">Documentation</a>»</li>
+
+ <li><a href="index.html" >LLVM Tutorial: Table of Contents</a> »</li>
+ </ul>
+ </div>
+ <div class="footer">
+ © Copyright 2003-2016, LLVM Project.
+ Last updated on 2016-07-11.
+ Created using <a href="http://sphinx-doc.org/">Sphinx</a> 1.2.2.
+ </div>
+ </body>
+</html>
\ No newline at end of file
Added: www-releases/trunk/3.8.1/docs/tutorial/OCamlLangImpl3.html
URL: http://llvm.org/viewvc/llvm-project/www-releases/trunk/3.8.1/docs/tutorial/OCamlLangImpl3.html?rev=275092&view=auto
==============================================================================
--- www-releases/trunk/3.8.1/docs/tutorial/OCamlLangImpl3.html (added)
+++ www-releases/trunk/3.8.1/docs/tutorial/OCamlLangImpl3.html Mon Jul 11 14:36:11 2016
@@ -0,0 +1,1003 @@
+
+<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN"
+ "http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd">
+
+
+<html xmlns="http://www.w3.org/1999/xhtml">
+ <head>
+ <meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
+
+ <title>3. Kaleidoscope: Code generation to LLVM IR — LLVM 3.8 documentation</title>
+
+ <link rel="stylesheet" href="../_static/llvm-theme.css" type="text/css" />
+ <link rel="stylesheet" href="../_static/pygments.css" type="text/css" />
+
+ <script type="text/javascript">
+ var DOCUMENTATION_OPTIONS = {
+ URL_ROOT: '../',
+ VERSION: '3.8',
+ COLLAPSE_INDEX: false,
+ FILE_SUFFIX: '.html',
+ HAS_SOURCE: true
+ };
+ </script>
+ <script type="text/javascript" src="../_static/jquery.js"></script>
+ <script type="text/javascript" src="../_static/underscore.js"></script>
+ <script type="text/javascript" src="../_static/doctools.js"></script>
+ <link rel="top" title="LLVM 3.8 documentation" href="../index.html" />
+ <link rel="up" title="LLVM Tutorial: Table of Contents" href="index.html" />
+ <link rel="next" title="4. Kaleidoscope: Adding JIT and Optimizer Support" href="OCamlLangImpl4.html" />
+ <link rel="prev" title="2. Kaleidoscope: Implementing a Parser and AST" href="OCamlLangImpl2.html" />
+<style type="text/css">
+ table.right { float: right; margin-left: 20px; }
+ table.right td { border: 1px solid #ccc; }
+</style>
+
+ </head>
+ <body>
+<div class="logo">
+ <a href="../index.html">
+ <img src="../_static/logo.png"
+ alt="LLVM Logo" width="250" height="88"/></a>
+</div>
+
+ <div class="related">
+ <h3>Navigation</h3>
+ <ul>
+ <li class="right" style="margin-right: 10px">
+ <a href="../genindex.html" title="General Index"
+ accesskey="I">index</a></li>
+ <li class="right" >
+ <a href="OCamlLangImpl4.html" title="4. Kaleidoscope: Adding JIT and Optimizer Support"
+ accesskey="N">next</a> |</li>
+ <li class="right" >
+ <a href="OCamlLangImpl2.html" title="2. Kaleidoscope: Implementing a Parser and AST"
+ accesskey="P">previous</a> |</li>
+ <li><a href="http://llvm.org/">LLVM Home</a> | </li>
+ <li><a href="../index.html">Documentation</a>»</li>
+
+ <li><a href="index.html" accesskey="U">LLVM Tutorial: Table of Contents</a> »</li>
+ </ul>
+ </div>
+
+
+ <div class="document">
+ <div class="documentwrapper">
+ <div class="body">
+
+ <div class="section" id="kaleidoscope-code-generation-to-llvm-ir">
+<h1>3. Kaleidoscope: Code generation to LLVM IR<a class="headerlink" href="#kaleidoscope-code-generation-to-llvm-ir" title="Permalink to this headline">¶</a></h1>
+<div class="contents local topic" id="contents">
+<ul class="simple">
+<li><a class="reference internal" href="#chapter-3-introduction" id="id1">Chapter 3 Introduction</a></li>
+<li><a class="reference internal" href="#code-generation-setup" id="id2">Code Generation Setup</a></li>
+<li><a class="reference internal" href="#expression-code-generation" id="id3">Expression Code Generation</a></li>
+<li><a class="reference internal" href="#function-code-generation" id="id4">Function Code Generation</a></li>
+<li><a class="reference internal" href="#driver-changes-and-closing-thoughts" id="id5">Driver Changes and Closing Thoughts</a></li>
+<li><a class="reference internal" href="#full-code-listing" id="id6">Full Code Listing</a></li>
+</ul>
+</div>
+<div class="section" id="chapter-3-introduction">
+<h2><a class="toc-backref" href="#id1">3.1. Chapter 3 Introduction</a><a class="headerlink" href="#chapter-3-introduction" title="Permalink to this headline">¶</a></h2>
+<p>Welcome to Chapter 3 of the “<a class="reference external" href="index.html">Implementing a language with
+LLVM</a>” tutorial. This chapter shows you how to transform
+the <a class="reference external" href="OCamlLangImpl2.html">Abstract Syntax Tree</a>, built in Chapter 2,
+into LLVM IR. This will teach you a little bit about how LLVM does
+things, as well as demonstrate how easy it is to use. It’s much more
+work to build a lexer and parser than it is to generate LLVM IR code. :)</p>
+<p><strong>Please note</strong>: the code in this chapter and later require LLVM 2.3 or
+LLVM SVN to work. LLVM 2.2 and before will not work with it.</p>
+</div>
+<div class="section" id="code-generation-setup">
+<h2><a class="toc-backref" href="#id2">3.2. Code Generation Setup</a><a class="headerlink" href="#code-generation-setup" title="Permalink to this headline">¶</a></h2>
+<p>In order to generate LLVM IR, we want some simple setup to get started.
+First we define virtual code generation (codegen) methods in each AST
+class:</p>
+<div class="highlight-ocaml"><div class="highlight"><pre><span class="k">let</span> <span class="k">rec</span> <span class="n">codegen_expr</span> <span class="o">=</span> <span class="k">function</span>
+ <span class="o">|</span> <span class="nn">Ast</span><span class="p">.</span><span class="nc">Number</span> <span class="n">n</span> <span class="o">-></span> <span class="o">...</span>
+ <span class="o">|</span> <span class="nn">Ast</span><span class="p">.</span><span class="nc">Variable</span> <span class="n">name</span> <span class="o">-></span> <span class="o">...</span>
+</pre></div>
+</div>
+<p>The <tt class="docutils literal"><span class="pre">Codegen.codegen_expr</span></tt> function says to emit IR for that AST node
+along with all the things it depends on, and they all return an LLVM
+Value object. “Value” is the class used to represent a “<a class="reference external" href="http://en.wikipedia.org/wiki/Static_single_assignment_form">Static Single
+Assignment
+(SSA)</a>
+register” or “SSA value” in LLVM. The most distinct aspect of SSA values
+is that their value is computed as the related instruction executes, and
+it does not get a new value until (and if) the instruction re-executes.
+In other words, there is no way to “change” an SSA value. For more
+information, please read up on <a class="reference external" href="http://en.wikipedia.org/wiki/Static_single_assignment_form">Static Single
+Assignment</a>
+- the concepts are really quite natural once you grok them.</p>
+<p>The second thing we want is an “Error” exception like we used for the
+parser, which will be used to report errors found during code generation
+(for example, use of an undeclared parameter):</p>
+<div class="highlight-ocaml"><div class="highlight"><pre><span class="k">exception</span> <span class="nc">Error</span> <span class="k">of</span> <span class="kt">string</span>
+
+<span class="k">let</span> <span class="n">context</span> <span class="o">=</span> <span class="n">global_context</span> <span class="bp">()</span>
+<span class="k">let</span> <span class="n">the_module</span> <span class="o">=</span> <span class="n">create_module</span> <span class="n">context</span> <span class="s2">"my cool jit"</span>
+<span class="k">let</span> <span class="n">builder</span> <span class="o">=</span> <span class="n">builder</span> <span class="n">context</span>
+<span class="k">let</span> <span class="n">named_values</span><span class="o">:(</span><span class="kt">string</span><span class="o">,</span> <span class="n">llvalue</span><span class="o">)</span> <span class="nn">Hashtbl</span><span class="p">.</span><span class="n">t</span> <span class="o">=</span> <span class="nn">Hashtbl</span><span class="p">.</span><span class="n">create</span> <span class="mi">10</span>
+<span class="k">let</span> <span class="n">double_type</span> <span class="o">=</span> <span class="n">double_type</span> <span class="n">context</span>
+</pre></div>
+</div>
+<p>The static variables will be used during code generation.
+<tt class="docutils literal"><span class="pre">Codgen.the_module</span></tt> is the LLVM construct that contains all of the
+functions and global variables in a chunk of code. In many ways, it is
+the top-level structure that the LLVM IR uses to contain code.</p>
+<p>The <tt class="docutils literal"><span class="pre">Codegen.builder</span></tt> object is a helper object that makes it easy to
+generate LLVM instructions. Instances of the
+<a class="reference external" href="http://llvm.org/doxygen/IRBuilder_8h-source.html">IRBuilder</a>
+class keep track of the current place to insert instructions and has
+methods to create new instructions.</p>
+<p>The <tt class="docutils literal"><span class="pre">Codegen.named_values</span></tt> map keeps track of which values are defined
+in the current scope and what their LLVM representation is. (In other
+words, it is a symbol table for the code). In this form of Kaleidoscope,
+the only things that can be referenced are function parameters. As such,
+function parameters will be in this map when generating code for their
+function body.</p>
+<p>With these basics in place, we can start talking about how to generate
+code for each expression. Note that this assumes that the
+<tt class="docutils literal"><span class="pre">Codgen.builder</span></tt> has been set up to generate code <em>into</em> something.
+For now, we’ll assume that this has already been done, and we’ll just
+use it to emit code.</p>
+</div>
+<div class="section" id="expression-code-generation">
+<h2><a class="toc-backref" href="#id3">3.3. Expression Code Generation</a><a class="headerlink" href="#expression-code-generation" title="Permalink to this headline">¶</a></h2>
+<p>Generating LLVM code for expression nodes is very straightforward: less
+than 30 lines of commented code for all four of our expression nodes.
+First we’ll do numeric literals:</p>
+<div class="highlight-ocaml"><div class="highlight"><pre><span class="o">|</span> <span class="nn">Ast</span><span class="p">.</span><span class="nc">Number</span> <span class="n">n</span> <span class="o">-></span> <span class="n">const_float</span> <span class="n">double_type</span> <span class="n">n</span>
+</pre></div>
+</div>
+<p>In the LLVM IR, numeric constants are represented with the
+<tt class="docutils literal"><span class="pre">ConstantFP</span></tt> class, which holds the numeric value in an <tt class="docutils literal"><span class="pre">APFloat</span></tt>
+internally (<tt class="docutils literal"><span class="pre">APFloat</span></tt> has the capability of holding floating point
+constants of Arbitrary Precision). This code basically just creates
+and returns a <tt class="docutils literal"><span class="pre">ConstantFP</span></tt>. Note that in the LLVM IR that constants
+are all uniqued together and shared. For this reason, the API uses “the
+foo::get(..)” idiom instead of “new foo(..)” or “foo::Create(..)”.</p>
+<div class="highlight-ocaml"><div class="highlight"><pre><span class="o">|</span> <span class="nn">Ast</span><span class="p">.</span><span class="nc">Variable</span> <span class="n">name</span> <span class="o">-></span>
+ <span class="o">(</span><span class="k">try</span> <span class="nn">Hashtbl</span><span class="p">.</span><span class="n">find</span> <span class="n">named_values</span> <span class="n">name</span> <span class="k">with</span>
+ <span class="o">|</span> <span class="nc">Not_found</span> <span class="o">-></span> <span class="k">raise</span> <span class="o">(</span><span class="nc">Error</span> <span class="s2">"unknown variable name"</span><span class="o">))</span>
+</pre></div>
+</div>
+<p>References to variables are also quite simple using LLVM. In the simple
+version of Kaleidoscope, we assume that the variable has already been
+emitted somewhere and its value is available. In practice, the only
+values that can be in the <tt class="docutils literal"><span class="pre">Codegen.named_values</span></tt> map are function
+arguments. This code simply checks to see that the specified name is in
+the map (if not, an unknown variable is being referenced) and returns
+the value for it. In future chapters, we’ll add support for <a class="reference external" href="LangImpl5.html#for-loop-expression">loop
+induction variables</a> in the symbol table, and for
+<a class="reference external" href="LangImpl7.html#user-defined-local-variables">local variables</a>.</p>
+<div class="highlight-ocaml"><div class="highlight"><pre><span class="o">|</span> <span class="nn">Ast</span><span class="p">.</span><span class="nc">Binary</span> <span class="o">(</span><span class="n">op</span><span class="o">,</span> <span class="n">lhs</span><span class="o">,</span> <span class="n">rhs</span><span class="o">)</span> <span class="o">-></span>
+ <span class="k">let</span> <span class="n">lhs_val</span> <span class="o">=</span> <span class="n">codegen_expr</span> <span class="n">lhs</span> <span class="k">in</span>
+ <span class="k">let</span> <span class="n">rhs_val</span> <span class="o">=</span> <span class="n">codegen_expr</span> <span class="n">rhs</span> <span class="k">in</span>
+ <span class="k">begin</span>
+ <span class="k">match</span> <span class="n">op</span> <span class="k">with</span>
+ <span class="o">|</span> <span class="sc">'+'</span> <span class="o">-></span> <span class="n">build_fadd</span> <span class="n">lhs_val</span> <span class="n">rhs_val</span> <span class="s2">"addtmp"</span> <span class="n">builder</span>
+ <span class="o">|</span> <span class="sc">'-'</span> <span class="o">-></span> <span class="n">build_fsub</span> <span class="n">lhs_val</span> <span class="n">rhs_val</span> <span class="s2">"subtmp"</span> <span class="n">builder</span>
+ <span class="o">|</span> <span class="sc">'*'</span> <span class="o">-></span> <span class="n">build_fmul</span> <span class="n">lhs_val</span> <span class="n">rhs_val</span> <span class="s2">"multmp"</span> <span class="n">builder</span>
+ <span class="o">|</span> <span class="sc">'<'</span> <span class="o">-></span>
+ <span class="c">(* Convert bool 0/1 to double 0.0 or 1.0 *)</span>
+ <span class="k">let</span> <span class="n">i</span> <span class="o">=</span> <span class="n">build_fcmp</span> <span class="nn">Fcmp</span><span class="p">.</span><span class="nc">Ult</span> <span class="n">lhs_val</span> <span class="n">rhs_val</span> <span class="s2">"cmptmp"</span> <span class="n">builder</span> <span class="k">in</span>
+ <span class="n">build_uitofp</span> <span class="n">i</span> <span class="n">double_type</span> <span class="s2">"booltmp"</span> <span class="n">builder</span>
+ <span class="o">|</span> <span class="o">_</span> <span class="o">-></span> <span class="k">raise</span> <span class="o">(</span><span class="nc">Error</span> <span class="s2">"invalid binary operator"</span><span class="o">)</span>
+ <span class="k">end</span>
+</pre></div>
+</div>
+<p>Binary operators start to get more interesting. The basic idea here is
+that we recursively emit code for the left-hand side of the expression,
+then the right-hand side, then we compute the result of the binary
+expression. In this code, we do a simple switch on the opcode to create
+the right LLVM instruction.</p>
+<p>In the example above, the LLVM builder class is starting to show its
+value. IRBuilder knows where to insert the newly created instruction,
+all you have to do is specify what instruction to create (e.g. with
+<tt class="docutils literal"><span class="pre">Llvm.create_add</span></tt>), which operands to use (<tt class="docutils literal"><span class="pre">lhs</span></tt> and <tt class="docutils literal"><span class="pre">rhs</span></tt> here)
+and optionally provide a name for the generated instruction.</p>
+<p>One nice thing about LLVM is that the name is just a hint. For instance,
+if the code above emits multiple “addtmp” variables, LLVM will
+automatically provide each one with an increasing, unique numeric
+suffix. Local value names for instructions are purely optional, but it
+makes it much easier to read the IR dumps.</p>
+<p><a class="reference external" href="../LangRef.html#instruction-reference">LLVM instructions</a> are constrained by strict
+rules: for example, the Left and Right operators of an <a class="reference external" href="../LangRef.html#add-instruction">add
+instruction</a> must have the same type, and the
+result type of the add must match the operand types. Because all values
+in Kaleidoscope are doubles, this makes for very simple code for add,
+sub and mul.</p>
+<p>On the other hand, LLVM specifies that the <a class="reference external" href="../LangRef.html#fcmp-instruction">fcmp
+instruction</a> always returns an ‘i1’ value (a
+one bit integer). The problem with this is that Kaleidoscope wants the
+value to be a 0.0 or 1.0 value. In order to get these semantics, we
+combine the fcmp instruction with a <a class="reference external" href="../LangRef.html#uitofp-to-instruction">uitofp
+instruction</a>. This instruction converts its
+input integer into a floating point value by treating the input as an
+unsigned value. In contrast, if we used the <a class="reference external" href="../LangRef.html#sitofp-to-instruction">sitofp
+instruction</a>, the Kaleidoscope ‘<’ operator
+would return 0.0 and -1.0, depending on the input value.</p>
+<div class="highlight-ocaml"><div class="highlight"><pre><span class="o">|</span> <span class="nn">Ast</span><span class="p">.</span><span class="nc">Call</span> <span class="o">(</span><span class="n">callee</span><span class="o">,</span> <span class="n">args</span><span class="o">)</span> <span class="o">-></span>
+ <span class="c">(* Look up the name in the module table. *)</span>
+ <span class="k">let</span> <span class="n">callee</span> <span class="o">=</span>
+ <span class="k">match</span> <span class="n">lookup_function</span> <span class="n">callee</span> <span class="n">the_module</span> <span class="k">with</span>
+ <span class="o">|</span> <span class="nc">Some</span> <span class="n">callee</span> <span class="o">-></span> <span class="n">callee</span>
+ <span class="o">|</span> <span class="nc">None</span> <span class="o">-></span> <span class="k">raise</span> <span class="o">(</span><span class="nc">Error</span> <span class="s2">"unknown function referenced"</span><span class="o">)</span>
+ <span class="k">in</span>
+ <span class="k">let</span> <span class="n">params</span> <span class="o">=</span> <span class="n">params</span> <span class="n">callee</span> <span class="k">in</span>
+
+ <span class="c">(* If argument mismatch error. *)</span>
+ <span class="k">if</span> <span class="nn">Array</span><span class="p">.</span><span class="n">length</span> <span class="n">params</span> <span class="o">==</span> <span class="nn">Array</span><span class="p">.</span><span class="n">length</span> <span class="n">args</span> <span class="k">then</span> <span class="bp">()</span> <span class="k">else</span>
+ <span class="k">raise</span> <span class="o">(</span><span class="nc">Error</span> <span class="s2">"incorrect # arguments passed"</span><span class="o">);</span>
+ <span class="k">let</span> <span class="n">args</span> <span class="o">=</span> <span class="nn">Array</span><span class="p">.</span><span class="n">map</span> <span class="n">codegen_expr</span> <span class="n">args</span> <span class="k">in</span>
+ <span class="n">build_call</span> <span class="n">callee</span> <span class="n">args</span> <span class="s2">"calltmp"</span> <span class="n">builder</span>
+</pre></div>
+</div>
+<p>Code generation for function calls is quite straightforward with LLVM.
+The code above initially does a function name lookup in the LLVM
+Module’s symbol table. Recall that the LLVM Module is the container that
+holds all of the functions we are JIT’ing. By giving each function the
+same name as what the user specifies, we can use the LLVM symbol table
+to resolve function names for us.</p>
+<p>Once we have the function to call, we recursively codegen each argument
+that is to be passed in, and create an LLVM <a class="reference external" href="../LangRef.html#call-instruction">call
+instruction</a>. Note that LLVM uses the native C
+calling conventions by default, allowing these calls to also call into
+standard library functions like “sin” and “cos”, with no additional
+effort.</p>
+<p>This wraps up our handling of the four basic expressions that we have so
+far in Kaleidoscope. Feel free to go in and add some more. For example,
+by browsing the <a class="reference external" href="../LangRef.html">LLVM language reference</a> you’ll find
+several other interesting instructions that are really easy to plug into
+our basic framework.</p>
+</div>
+<div class="section" id="function-code-generation">
+<h2><a class="toc-backref" href="#id4">3.4. Function Code Generation</a><a class="headerlink" href="#function-code-generation" title="Permalink to this headline">¶</a></h2>
+<p>Code generation for prototypes and functions must handle a number of
+details, which make their code less beautiful than expression code
+generation, but allows us to illustrate some important points. First,
+lets talk about code generation for prototypes: they are used both for
+function bodies and external function declarations. The code starts
+with:</p>
+<div class="highlight-ocaml"><div class="highlight"><pre><span class="k">let</span> <span class="n">codegen_proto</span> <span class="o">=</span> <span class="k">function</span>
+ <span class="o">|</span> <span class="nn">Ast</span><span class="p">.</span><span class="nc">Prototype</span> <span class="o">(</span><span class="n">name</span><span class="o">,</span> <span class="n">args</span><span class="o">)</span> <span class="o">-></span>
+ <span class="c">(* Make the function type: double(double,double) etc. *)</span>
+ <span class="k">let</span> <span class="n">doubles</span> <span class="o">=</span> <span class="nn">Array</span><span class="p">.</span><span class="n">make</span> <span class="o">(</span><span class="nn">Array</span><span class="p">.</span><span class="n">length</span> <span class="n">args</span><span class="o">)</span> <span class="n">double_type</span> <span class="k">in</span>
+ <span class="k">let</span> <span class="n">ft</span> <span class="o">=</span> <span class="n">function_type</span> <span class="n">double_type</span> <span class="n">doubles</span> <span class="k">in</span>
+ <span class="k">let</span> <span class="n">f</span> <span class="o">=</span>
+ <span class="k">match</span> <span class="n">lookup_function</span> <span class="n">name</span> <span class="n">the_module</span> <span class="k">with</span>
+</pre></div>
+</div>
+<p>This code packs a lot of power into a few lines. Note first that this
+function returns a “Function*” instead of a “Value*” (although at the
+moment they both are modeled by <tt class="docutils literal"><span class="pre">llvalue</span></tt> in ocaml). Because a
+“prototype” really talks about the external interface for a function
+(not the value computed by an expression), it makes sense for it to
+return the LLVM Function it corresponds to when codegen’d.</p>
+<p>The call to <tt class="docutils literal"><span class="pre">Llvm.function_type</span></tt> creates the <tt class="docutils literal"><span class="pre">Llvm.llvalue</span></tt> that
+should be used for a given Prototype. Since all function arguments in
+Kaleidoscope are of type double, the first line creates a vector of “N”
+LLVM double types. It then uses the <tt class="docutils literal"><span class="pre">Llvm.function_type</span></tt> method to
+create a function type that takes “N” doubles as arguments, returns one
+double as a result, and that is not vararg (that uses the function
+<tt class="docutils literal"><span class="pre">Llvm.var_arg_function_type</span></tt>). Note that Types in LLVM are uniqued
+just like <tt class="docutils literal"><span class="pre">Constant</span></tt>‘s are, so you don’t “new” a type, you “get” it.</p>
+<p>The final line above checks if the function has already been defined in
+<tt class="docutils literal"><span class="pre">Codegen.the_module</span></tt>. If not, we will create it.</p>
+<div class="highlight-ocaml"><div class="highlight"><pre><span class="o">|</span> <span class="nc">None</span> <span class="o">-></span> <span class="n">declare_function</span> <span class="n">name</span> <span class="n">ft</span> <span class="n">the_module</span>
+</pre></div>
+</div>
+<p>This indicates the type and name to use, as well as which module to
+insert into. By default we assume a function has
+<tt class="docutils literal"><span class="pre">Llvm.Linkage.ExternalLinkage</span></tt>. “<a class="reference external" href="../LangRef.html#linkage">external
+linkage</a>” means that the function may be defined
+outside the current module and/or that it is callable by functions
+outside the module. The “<tt class="docutils literal"><span class="pre">name</span></tt>” passed in is the name the user
+specified: this name is registered in “<tt class="docutils literal"><span class="pre">Codegen.the_module</span></tt>“s symbol
+table, which is used by the function call code above.</p>
+<p>In Kaleidoscope, I choose to allow redefinitions of functions in two
+cases: first, we want to allow ‘extern’ing a function more than once, as
+long as the prototypes for the externs match (since all arguments have
+the same type, we just have to check that the number of arguments
+match). Second, we want to allow ‘extern’ing a function and then
+defining a body for it. This is useful when defining mutually recursive
+functions.</p>
+<div class="highlight-ocaml"><div class="highlight"><pre> <span class="c">(* If 'f' conflicted, there was already something named 'name'. If it</span>
+<span class="c"> * has a body, don't allow redefinition or reextern. *)</span>
+ <span class="o">|</span> <span class="nc">Some</span> <span class="n">f</span> <span class="o">-></span>
+ <span class="c">(* If 'f' already has a body, reject this. *)</span>
+ <span class="k">if</span> <span class="nn">Array</span><span class="p">.</span><span class="n">length</span> <span class="o">(</span><span class="n">basic_blocks</span> <span class="n">f</span><span class="o">)</span> <span class="o">==</span> <span class="mi">0</span> <span class="k">then</span> <span class="bp">()</span> <span class="k">else</span>
+ <span class="k">raise</span> <span class="o">(</span><span class="nc">Error</span> <span class="s2">"redefinition of function"</span><span class="o">);</span>
+
+ <span class="c">(* If 'f' took a different number of arguments, reject. *)</span>
+ <span class="k">if</span> <span class="nn">Array</span><span class="p">.</span><span class="n">length</span> <span class="o">(</span><span class="n">params</span> <span class="n">f</span><span class="o">)</span> <span class="o">==</span> <span class="nn">Array</span><span class="p">.</span><span class="n">length</span> <span class="n">args</span> <span class="k">then</span> <span class="bp">()</span> <span class="k">else</span>
+ <span class="k">raise</span> <span class="o">(</span><span class="nc">Error</span> <span class="s2">"redefinition of function with different # args"</span><span class="o">);</span>
+ <span class="n">f</span>
+<span class="k">in</span>
+</pre></div>
+</div>
+<p>In order to verify the logic above, we first check to see if the
+pre-existing function is “empty”. In this case, empty means that it has
+no basic blocks in it, which means it has no body. If it has no body, it
+is a forward declaration. Since we don’t allow anything after a full
+definition of the function, the code rejects this case. If the previous
+reference to a function was an ‘extern’, we simply verify that the
+number of arguments for that definition and this one match up. If not,
+we emit an error.</p>
+<div class="highlight-ocaml"><div class="highlight"><pre><span class="c">(* Set names for all arguments. *)</span>
+<span class="nn">Array</span><span class="p">.</span><span class="n">iteri</span> <span class="o">(</span><span class="k">fun</span> <span class="n">i</span> <span class="n">a</span> <span class="o">-></span>
+ <span class="k">let</span> <span class="n">n</span> <span class="o">=</span> <span class="n">args</span><span class="o">.(</span><span class="n">i</span><span class="o">)</span> <span class="k">in</span>
+ <span class="n">set_value_name</span> <span class="n">n</span> <span class="n">a</span><span class="o">;</span>
+ <span class="nn">Hashtbl</span><span class="p">.</span><span class="n">add</span> <span class="n">named_values</span> <span class="n">n</span> <span class="n">a</span><span class="o">;</span>
+<span class="o">)</span> <span class="o">(</span><span class="n">params</span> <span class="n">f</span><span class="o">);</span>
+<span class="n">f</span>
+</pre></div>
+</div>
+<p>The last bit of code for prototypes loops over all of the arguments in
+the function, setting the name of the LLVM Argument objects to match,
+and registering the arguments in the <tt class="docutils literal"><span class="pre">Codegen.named_values</span></tt> map for
+future use by the <tt class="docutils literal"><span class="pre">Ast.Variable</span></tt> variant. Once this is set up, it
+returns the Function object to the caller. Note that we don’t check for
+conflicting argument names here (e.g. “extern foo(a b a)”). Doing so
+would be very straight-forward with the mechanics we have already used
+above.</p>
+<div class="highlight-ocaml"><div class="highlight"><pre><span class="k">let</span> <span class="n">codegen_func</span> <span class="o">=</span> <span class="k">function</span>
+ <span class="o">|</span> <span class="nn">Ast</span><span class="p">.</span><span class="nc">Function</span> <span class="o">(</span><span class="n">proto</span><span class="o">,</span> <span class="n">body</span><span class="o">)</span> <span class="o">-></span>
+ <span class="nn">Hashtbl</span><span class="p">.</span><span class="n">clear</span> <span class="n">named_values</span><span class="o">;</span>
+ <span class="k">let</span> <span class="n">the_function</span> <span class="o">=</span> <span class="n">codegen_proto</span> <span class="n">proto</span> <span class="k">in</span>
+</pre></div>
+</div>
+<p>Code generation for function definitions starts out simply enough: we
+just codegen the prototype (Proto) and verify that it is ok. We then
+clear out the <tt class="docutils literal"><span class="pre">Codegen.named_values</span></tt> map to make sure that there isn’t
+anything in it from the last function we compiled. Code generation of
+the prototype ensures that there is an LLVM Function object that is
+ready to go for us.</p>
+<div class="highlight-ocaml"><div class="highlight"><pre><span class="c">(* Create a new basic block to start insertion into. *)</span>
+<span class="k">let</span> <span class="n">bb</span> <span class="o">=</span> <span class="n">append_block</span> <span class="n">context</span> <span class="s2">"entry"</span> <span class="n">the_function</span> <span class="k">in</span>
+<span class="n">position_at_end</span> <span class="n">bb</span> <span class="n">builder</span><span class="o">;</span>
+
+<span class="k">try</span>
+ <span class="k">let</span> <span class="n">ret_val</span> <span class="o">=</span> <span class="n">codegen_expr</span> <span class="n">body</span> <span class="k">in</span>
+</pre></div>
+</div>
+<p>Now we get to the point where the <tt class="docutils literal"><span class="pre">Codegen.builder</span></tt> is set up. The
+first line creates a new <a class="reference external" href="http://en.wikipedia.org/wiki/Basic_block">basic
+block</a> (named “entry”),
+which is inserted into <tt class="docutils literal"><span class="pre">the_function</span></tt>. The second line then tells the
+builder that new instructions should be inserted into the end of the new
+basic block. Basic blocks in LLVM are an important part of functions
+that define the <a class="reference external" href="http://en.wikipedia.org/wiki/Control_flow_graph">Control Flow
+Graph</a>. Since we
+don’t have any control flow, our functions will only contain one block
+at this point. We’ll fix this in <a class="reference external" href="OCamlLangImpl5.html">Chapter 5</a> :).</p>
+<div class="highlight-ocaml"><div class="highlight"><pre><span class="k">let</span> <span class="n">ret_val</span> <span class="o">=</span> <span class="n">codegen_expr</span> <span class="n">body</span> <span class="k">in</span>
+
+<span class="c">(* Finish off the function. *)</span>
+<span class="k">let</span> <span class="o">_</span> <span class="o">=</span> <span class="n">build_ret</span> <span class="n">ret_val</span> <span class="n">builder</span> <span class="k">in</span>
+
+<span class="c">(* Validate the generated code, checking for consistency. *)</span>
+<span class="nn">Llvm_analysis</span><span class="p">.</span><span class="n">assert_valid_function</span> <span class="n">the_function</span><span class="o">;</span>
+
+<span class="n">the_function</span>
+</pre></div>
+</div>
+<p>Once the insertion point is set up, we call the <tt class="docutils literal"><span class="pre">Codegen.codegen_func</span></tt>
+method for the root expression of the function. If no error happens,
+this emits code to compute the expression into the entry block and
+returns the value that was computed. Assuming no error, we then create
+an LLVM <a class="reference external" href="../LangRef.html#ret-instruction">ret instruction</a>, which completes the
+function. Once the function is built, we call
+<tt class="docutils literal"><span class="pre">Llvm_analysis.assert_valid_function</span></tt>, which is provided by LLVM. This
+function does a variety of consistency checks on the generated code, to
+determine if our compiler is doing everything right. Using this is
+important: it can catch a lot of bugs. Once the function is finished and
+validated, we return it.</p>
+<div class="highlight-ocaml"><div class="highlight"><pre><span class="k">with</span> <span class="n">e</span> <span class="o">-></span>
+ <span class="n">delete_function</span> <span class="n">the_function</span><span class="o">;</span>
+ <span class="k">raise</span> <span class="n">e</span>
+</pre></div>
+</div>
+<p>The only piece left here is handling of the error case. For simplicity,
+we handle this by merely deleting the function we produced with the
+<tt class="docutils literal"><span class="pre">Llvm.delete_function</span></tt> method. This allows the user to redefine a
+function that they incorrectly typed in before: if we didn’t delete it,
+it would live in the symbol table, with a body, preventing future
+redefinition.</p>
+<p>This code does have a bug, though. Since the <tt class="docutils literal"><span class="pre">Codegen.codegen_proto</span></tt>
+can return a previously defined forward declaration, our code can
+actually delete a forward declaration. There are a number of ways to fix
+this bug, see what you can come up with! Here is a testcase:</p>
+<div class="highlight-python"><div class="highlight"><pre>extern foo(a b); # ok, defines foo.
+def foo(a b) c; # error, 'c' is invalid.
+def bar() foo(1, 2); # error, unknown function "foo"
+</pre></div>
+</div>
+</div>
+<div class="section" id="driver-changes-and-closing-thoughts">
+<h2><a class="toc-backref" href="#id5">3.5. Driver Changes and Closing Thoughts</a><a class="headerlink" href="#driver-changes-and-closing-thoughts" title="Permalink to this headline">¶</a></h2>
+<p>For now, code generation to LLVM doesn’t really get us much, except that
+we can look at the pretty IR calls. The sample code inserts calls to
+Codegen into the “<tt class="docutils literal"><span class="pre">Toplevel.main_loop</span></tt>”, and then dumps out the LLVM
+IR. This gives a nice way to look at the LLVM IR for simple functions.
+For example:</p>
+<div class="highlight-python"><div class="highlight"><pre>ready> 4+5;
+Read top-level expression:
+define double @""() {
+entry:
+ %addtmp = fadd double 4.000000e+00, 5.000000e+00
+ ret double %addtmp
+}
+</pre></div>
+</div>
+<p>Note how the parser turns the top-level expression into anonymous
+functions for us. This will be handy when we add <a class="reference external" href="OCamlLangImpl4.html#adding-a-jit-compiler">JIT
+support</a> in the next chapter. Also note that
+the code is very literally transcribed, no optimizations are being
+performed. We will <a class="reference external" href="OCamlLangImpl4.html#trivial-constant-folding">add
+optimizations</a> explicitly in the
+next chapter.</p>
+<div class="highlight-python"><div class="highlight"><pre>ready> def foo(a b) a*a + 2*a*b + b*b;
+Read function definition:
+define double @foo(double %a, double %b) {
+entry:
+ %multmp = fmul double %a, %a
+ %multmp1 = fmul double 2.000000e+00, %a
+ %multmp2 = fmul double %multmp1, %b
+ %addtmp = fadd double %multmp, %multmp2
+ %multmp3 = fmul double %b, %b
+ %addtmp4 = fadd double %addtmp, %multmp3
+ ret double %addtmp4
+}
+</pre></div>
+</div>
+<p>This shows some simple arithmetic. Notice the striking similarity to the
+LLVM builder calls that we use to create the instructions.</p>
+<div class="highlight-python"><div class="highlight"><pre>ready> def bar(a) foo(a, 4.0) + bar(31337);
+Read function definition:
+define double @bar(double %a) {
+entry:
+ %calltmp = call double @foo(double %a, double 4.000000e+00)
+ %calltmp1 = call double @bar(double 3.133700e+04)
+ %addtmp = fadd double %calltmp, %calltmp1
+ ret double %addtmp
+}
+</pre></div>
+</div>
+<p>This shows some function calls. Note that this function will take a long
+time to execute if you call it. In the future we’ll add conditional
+control flow to actually make recursion useful :).</p>
+<div class="highlight-python"><div class="highlight"><pre>ready> extern cos(x);
+Read extern:
+declare double @cos(double)
+
+ready> cos(1.234);
+Read top-level expression:
+define double @""() {
+entry:
+ %calltmp = call double @cos(double 1.234000e+00)
+ ret double %calltmp
+}
+</pre></div>
+</div>
+<p>This shows an extern for the libm “cos” function, and a call to it.</p>
+<div class="highlight-python"><div class="highlight"><pre>ready> ^D
+; ModuleID = 'my cool jit'
+
+define double @""() {
+entry:
+ %addtmp = fadd double 4.000000e+00, 5.000000e+00
+ ret double %addtmp
+}
+
+define double @foo(double %a, double %b) {
+entry:
+ %multmp = fmul double %a, %a
+ %multmp1 = fmul double 2.000000e+00, %a
+ %multmp2 = fmul double %multmp1, %b
+ %addtmp = fadd double %multmp, %multmp2
+ %multmp3 = fmul double %b, %b
+ %addtmp4 = fadd double %addtmp, %multmp3
+ ret double %addtmp4
+}
+
+define double @bar(double %a) {
+entry:
+ %calltmp = call double @foo(double %a, double 4.000000e+00)
+ %calltmp1 = call double @bar(double 3.133700e+04)
+ %addtmp = fadd double %calltmp, %calltmp1
+ ret double %addtmp
+}
+
+declare double @cos(double)
+
+define double @""() {
+entry:
+ %calltmp = call double @cos(double 1.234000e+00)
+ ret double %calltmp
+}
+</pre></div>
+</div>
+<p>When you quit the current demo, it dumps out the IR for the entire
+module generated. Here you can see the big picture with all the
+functions referencing each other.</p>
+<p>This wraps up the third chapter of the Kaleidoscope tutorial. Up next,
+we’ll describe how to <a class="reference external" href="OCamlLangImpl4.html">add JIT codegen and optimizer
+support</a> to this so we can actually start running
+code!</p>
+</div>
+<div class="section" id="full-code-listing">
+<h2><a class="toc-backref" href="#id6">3.6. Full Code Listing</a><a class="headerlink" href="#full-code-listing" title="Permalink to this headline">¶</a></h2>
+<p>Here is the complete code listing for our running example, enhanced with
+the LLVM code generator. Because this uses the LLVM libraries, we need
+to link them in. To do this, we use the
+<a class="reference external" href="http://llvm.org/cmds/llvm-config.html">llvm-config</a> tool to inform
+our makefile/command line about which options to use:</p>
+<div class="highlight-bash"><div class="highlight"><pre><span class="c"># Compile</span>
+ocamlbuild toy.byte
+<span class="c"># Run</span>
+./toy.byte
+</pre></div>
+</div>
+<p>Here is the code:</p>
+<dl class="docutils">
+<dt>_tags:</dt>
+<dd><div class="first last highlight-python"><div class="highlight"><pre><{lexer,parser}.ml>: use_camlp4, pp(camlp4of)
+<*.{byte,native}>: g++, use_llvm, use_llvm_analysis
+</pre></div>
+</div>
+</dd>
+<dt>myocamlbuild.ml:</dt>
+<dd><div class="first last highlight-ocaml"><div class="highlight"><pre><span class="k">open</span> <span class="nc">Ocamlbuild_plugin</span><span class="o">;;</span>
+
+<span class="n">ocaml_lib</span> <span class="o">~</span><span class="n">extern</span><span class="o">:</span><span class="bp">true</span> <span class="s2">"llvm"</span><span class="o">;;</span>
+<span class="n">ocaml_lib</span> <span class="o">~</span><span class="n">extern</span><span class="o">:</span><span class="bp">true</span> <span class="s2">"llvm_analysis"</span><span class="o">;;</span>
+
+<span class="n">flag</span> <span class="o">[</span><span class="s2">"link"</span><span class="o">;</span> <span class="s2">"ocaml"</span><span class="o">;</span> <span class="s2">"g++"</span><span class="o">]</span> <span class="o">(</span><span class="nc">S</span><span class="o">[</span><span class="nc">A</span><span class="s2">"-cc"</span><span class="o">;</span> <span class="nc">A</span><span class="s2">"g++"</span><span class="o">]);;</span>
+</pre></div>
+</div>
+</dd>
+<dt>token.ml:</dt>
+<dd><div class="first last highlight-ocaml"><div class="highlight"><pre><span class="c">(*===----------------------------------------------------------------------===</span>
+<span class="c"> * Lexer Tokens</span>
+<span class="c"> *===----------------------------------------------------------------------===*)</span>
+
+<span class="c">(* The lexer returns these 'Kwd' if it is an unknown character, otherwise one of</span>
+<span class="c"> * these others for known things. *)</span>
+<span class="k">type</span> <span class="n">token</span> <span class="o">=</span>
+ <span class="c">(* commands *)</span>
+ <span class="o">|</span> <span class="nc">Def</span> <span class="o">|</span> <span class="nc">Extern</span>
+
+ <span class="c">(* primary *)</span>
+ <span class="o">|</span> <span class="nc">Ident</span> <span class="k">of</span> <span class="kt">string</span> <span class="o">|</span> <span class="nc">Number</span> <span class="k">of</span> <span class="kt">float</span>
+
+ <span class="c">(* unknown *)</span>
+ <span class="o">|</span> <span class="nc">Kwd</span> <span class="k">of</span> <span class="kt">char</span>
+</pre></div>
+</div>
+</dd>
+<dt>lexer.ml:</dt>
+<dd><div class="first last highlight-ocaml"><div class="highlight"><pre><span class="c">(*===----------------------------------------------------------------------===</span>
+<span class="c"> * Lexer</span>
+<span class="c"> *===----------------------------------------------------------------------===*)</span>
+
+<span class="k">let</span> <span class="k">rec</span> <span class="n">lex</span> <span class="o">=</span> <span class="n">parser</span>
+ <span class="c">(* Skip any whitespace. *)</span>
+ <span class="o">|</span> <span class="o">[<</span> <span class="k">'</span> <span class="o">(</span><span class="sc">' '</span> <span class="o">|</span> <span class="sc">'\n'</span> <span class="o">|</span> <span class="sc">'\r'</span> <span class="o">|</span> <span class="sc">'\t'</span><span class="o">);</span> <span class="n">stream</span> <span class="o">>]</span> <span class="o">-></span> <span class="n">lex</span> <span class="n">stream</span>
+
+ <span class="c">(* identifier: [a-zA-Z][a-zA-Z0-9] *)</span>
+ <span class="o">|</span> <span class="o">[<</span> <span class="k">'</span> <span class="o">(</span><span class="sc">'A'</span> <span class="o">..</span> <span class="sc">'Z'</span> <span class="o">|</span> <span class="sc">'a'</span> <span class="o">..</span> <span class="sc">'z'</span> <span class="k">as</span> <span class="n">c</span><span class="o">);</span> <span class="n">stream</span> <span class="o">>]</span> <span class="o">-></span>
+ <span class="k">let</span> <span class="n">buffer</span> <span class="o">=</span> <span class="nn">Buffer</span><span class="p">.</span><span class="n">create</span> <span class="mi">1</span> <span class="k">in</span>
+ <span class="nn">Buffer</span><span class="p">.</span><span class="n">add_char</span> <span class="n">buffer</span> <span class="n">c</span><span class="o">;</span>
+ <span class="n">lex_ident</span> <span class="n">buffer</span> <span class="n">stream</span>
+
+ <span class="c">(* number: [0-9.]+ *)</span>
+ <span class="o">|</span> <span class="o">[<</span> <span class="k">'</span> <span class="o">(</span><span class="sc">'0'</span> <span class="o">..</span> <span class="sc">'9'</span> <span class="k">as</span> <span class="n">c</span><span class="o">);</span> <span class="n">stream</span> <span class="o">>]</span> <span class="o">-></span>
+ <span class="k">let</span> <span class="n">buffer</span> <span class="o">=</span> <span class="nn">Buffer</span><span class="p">.</span><span class="n">create</span> <span class="mi">1</span> <span class="k">in</span>
+ <span class="nn">Buffer</span><span class="p">.</span><span class="n">add_char</span> <span class="n">buffer</span> <span class="n">c</span><span class="o">;</span>
+ <span class="n">lex_number</span> <span class="n">buffer</span> <span class="n">stream</span>
+
+ <span class="c">(* Comment until end of line. *)</span>
+ <span class="o">|</span> <span class="o">[<</span> <span class="k">'</span> <span class="o">(</span><span class="sc">'#'</span><span class="o">);</span> <span class="n">stream</span> <span class="o">>]</span> <span class="o">-></span>
+ <span class="n">lex_comment</span> <span class="n">stream</span>
+
+ <span class="c">(* Otherwise, just return the character as its ascii value. *)</span>
+ <span class="o">|</span> <span class="o">[<</span> <span class="k">'</span><span class="n">c</span><span class="o">;</span> <span class="n">stream</span> <span class="o">>]</span> <span class="o">-></span>
+ <span class="o">[<</span> <span class="k">'</span><span class="nn">Token</span><span class="p">.</span><span class="nc">Kwd</span> <span class="n">c</span><span class="o">;</span> <span class="n">lex</span> <span class="n">stream</span> <span class="o">>]</span>
+
+ <span class="c">(* end of stream. *)</span>
+ <span class="o">|</span> <span class="o">[<</span> <span class="o">>]</span> <span class="o">-></span> <span class="o">[<</span> <span class="o">>]</span>
+
+<span class="ow">and</span> <span class="n">lex_number</span> <span class="n">buffer</span> <span class="o">=</span> <span class="n">parser</span>
+ <span class="o">|</span> <span class="o">[<</span> <span class="k">'</span> <span class="o">(</span><span class="sc">'0'</span> <span class="o">..</span> <span class="sc">'9'</span> <span class="o">|</span> <span class="sc">'.'</span> <span class="k">as</span> <span class="n">c</span><span class="o">);</span> <span class="n">stream</span> <span class="o">>]</span> <span class="o">-></span>
+ <span class="nn">Buffer</span><span class="p">.</span><span class="n">add_char</span> <span class="n">buffer</span> <span class="n">c</span><span class="o">;</span>
+ <span class="n">lex_number</span> <span class="n">buffer</span> <span class="n">stream</span>
+ <span class="o">|</span> <span class="o">[<</span> <span class="n">stream</span><span class="o">=</span><span class="n">lex</span> <span class="o">>]</span> <span class="o">-></span>
+ <span class="o">[<</span> <span class="k">'</span><span class="nn">Token</span><span class="p">.</span><span class="nc">Number</span> <span class="o">(</span><span class="n">float_of_string</span> <span class="o">(</span><span class="nn">Buffer</span><span class="p">.</span><span class="n">contents</span> <span class="n">buffer</span><span class="o">));</span> <span class="n">stream</span> <span class="o">>]</span>
+
+<span class="ow">and</span> <span class="n">lex_ident</span> <span class="n">buffer</span> <span class="o">=</span> <span class="n">parser</span>
+ <span class="o">|</span> <span class="o">[<</span> <span class="k">'</span> <span class="o">(</span><span class="sc">'A'</span> <span class="o">..</span> <span class="sc">'Z'</span> <span class="o">|</span> <span class="sc">'a'</span> <span class="o">..</span> <span class="sc">'z'</span> <span class="o">|</span> <span class="sc">'0'</span> <span class="o">..</span> <span class="sc">'9'</span> <span class="k">as</span> <span class="n">c</span><span class="o">);</span> <span class="n">stream</span> <span class="o">>]</span> <span class="o">-></span>
+ <span class="nn">Buffer</span><span class="p">.</span><span class="n">add_char</span> <span class="n">buffer</span> <span class="n">c</span><span class="o">;</span>
+ <span class="n">lex_ident</span> <span class="n">buffer</span> <span class="n">stream</span>
+ <span class="o">|</span> <span class="o">[<</span> <span class="n">stream</span><span class="o">=</span><span class="n">lex</span> <span class="o">>]</span> <span class="o">-></span>
+ <span class="k">match</span> <span class="nn">Buffer</span><span class="p">.</span><span class="n">contents</span> <span class="n">buffer</span> <span class="k">with</span>
+ <span class="o">|</span> <span class="s2">"def"</span> <span class="o">-></span> <span class="o">[<</span> <span class="k">'</span><span class="nn">Token</span><span class="p">.</span><span class="nc">Def</span><span class="o">;</span> <span class="n">stream</span> <span class="o">>]</span>
+ <span class="o">|</span> <span class="s2">"extern"</span> <span class="o">-></span> <span class="o">[<</span> <span class="k">'</span><span class="nn">Token</span><span class="p">.</span><span class="nc">Extern</span><span class="o">;</span> <span class="n">stream</span> <span class="o">>]</span>
+ <span class="o">|</span> <span class="n">id</span> <span class="o">-></span> <span class="o">[<</span> <span class="k">'</span><span class="nn">Token</span><span class="p">.</span><span class="nc">Ident</span> <span class="n">id</span><span class="o">;</span> <span class="n">stream</span> <span class="o">>]</span>
+
+<span class="ow">and</span> <span class="n">lex_comment</span> <span class="o">=</span> <span class="n">parser</span>
+ <span class="o">|</span> <span class="o">[<</span> <span class="k">'</span> <span class="o">(</span><span class="sc">'\n'</span><span class="o">);</span> <span class="n">stream</span><span class="o">=</span><span class="n">lex</span> <span class="o">>]</span> <span class="o">-></span> <span class="n">stream</span>
+ <span class="o">|</span> <span class="o">[<</span> <span class="k">'</span><span class="n">c</span><span class="o">;</span> <span class="n">e</span><span class="o">=</span><span class="n">lex_comment</span> <span class="o">>]</span> <span class="o">-></span> <span class="n">e</span>
+ <span class="o">|</span> <span class="o">[<</span> <span class="o">>]</span> <span class="o">-></span> <span class="o">[<</span> <span class="o">>]</span>
+</pre></div>
+</div>
+</dd>
+<dt>ast.ml:</dt>
+<dd><div class="first last highlight-ocaml"><div class="highlight"><pre><span class="c">(*===----------------------------------------------------------------------===</span>
+<span class="c"> * Abstract Syntax Tree (aka Parse Tree)</span>
+<span class="c"> *===----------------------------------------------------------------------===*)</span>
+
+<span class="c">(* expr - Base type for all expression nodes. *)</span>
+<span class="k">type</span> <span class="n">expr</span> <span class="o">=</span>
+ <span class="c">(* variant for numeric literals like "1.0". *)</span>
+ <span class="o">|</span> <span class="nc">Number</span> <span class="k">of</span> <span class="kt">float</span>
+
+ <span class="c">(* variant for referencing a variable, like "a". *)</span>
+ <span class="o">|</span> <span class="nc">Variable</span> <span class="k">of</span> <span class="kt">string</span>
+
+ <span class="c">(* variant for a binary operator. *)</span>
+ <span class="o">|</span> <span class="nc">Binary</span> <span class="k">of</span> <span class="kt">char</span> <span class="o">*</span> <span class="n">expr</span> <span class="o">*</span> <span class="n">expr</span>
+
+ <span class="c">(* variant for function calls. *)</span>
+ <span class="o">|</span> <span class="nc">Call</span> <span class="k">of</span> <span class="kt">string</span> <span class="o">*</span> <span class="n">expr</span> <span class="kt">array</span>
+
+<span class="c">(* proto - This type represents the "prototype" for a function, which captures</span>
+<span class="c"> * its name, and its argument names (thus implicitly the number of arguments the</span>
+<span class="c"> * function takes). *)</span>
+<span class="k">type</span> <span class="n">proto</span> <span class="o">=</span> <span class="nc">Prototype</span> <span class="k">of</span> <span class="kt">string</span> <span class="o">*</span> <span class="kt">string</span> <span class="kt">array</span>
+
+<span class="c">(* func - This type represents a function definition itself. *)</span>
+<span class="k">type</span> <span class="n">func</span> <span class="o">=</span> <span class="nc">Function</span> <span class="k">of</span> <span class="n">proto</span> <span class="o">*</span> <span class="n">expr</span>
+</pre></div>
+</div>
+</dd>
+<dt>parser.ml:</dt>
+<dd><div class="first last highlight-ocaml"><div class="highlight"><pre><span class="c">(*===---------------------------------------------------------------------===</span>
+<span class="c"> * Parser</span>
+<span class="c"> *===---------------------------------------------------------------------===*)</span>
+
+<span class="c">(* binop_precedence - This holds the precedence for each binary operator that is</span>
+<span class="c"> * defined *)</span>
+<span class="k">let</span> <span class="n">binop_precedence</span><span class="o">:(</span><span class="kt">char</span><span class="o">,</span> <span class="kt">int</span><span class="o">)</span> <span class="nn">Hashtbl</span><span class="p">.</span><span class="n">t</span> <span class="o">=</span> <span class="nn">Hashtbl</span><span class="p">.</span><span class="n">create</span> <span class="mi">10</span>
+
+<span class="c">(* precedence - Get the precedence of the pending binary operator token. *)</span>
+<span class="k">let</span> <span class="n">precedence</span> <span class="n">c</span> <span class="o">=</span> <span class="k">try</span> <span class="nn">Hashtbl</span><span class="p">.</span><span class="n">find</span> <span class="n">binop_precedence</span> <span class="n">c</span> <span class="k">with</span> <span class="nc">Not_found</span> <span class="o">-></span> <span class="o">-</span><span class="mi">1</span>
+
+<span class="c">(* primary</span>
+<span class="c"> * ::= identifier</span>
+<span class="c"> * ::= numberexpr</span>
+<span class="c"> * ::= parenexpr *)</span>
+<span class="k">let</span> <span class="k">rec</span> <span class="n">parse_primary</span> <span class="o">=</span> <span class="n">parser</span>
+ <span class="c">(* numberexpr ::= number *)</span>
+ <span class="o">|</span> <span class="o">[<</span> <span class="k">'</span><span class="nn">Token</span><span class="p">.</span><span class="nc">Number</span> <span class="n">n</span> <span class="o">>]</span> <span class="o">-></span> <span class="nn">Ast</span><span class="p">.</span><span class="nc">Number</span> <span class="n">n</span>
+
+ <span class="c">(* parenexpr ::= '(' expression ')' *)</span>
+ <span class="o">|</span> <span class="o">[<</span> <span class="k">'</span><span class="nn">Token</span><span class="p">.</span><span class="nc">Kwd</span> <span class="sc">'('</span><span class="o">;</span> <span class="n">e</span><span class="o">=</span><span class="n">parse_expr</span><span class="o">;</span> <span class="k">'</span><span class="nn">Token</span><span class="p">.</span><span class="nc">Kwd</span> <span class="sc">')'</span> <span class="o">??</span> <span class="s2">"expected ')'"</span> <span class="o">>]</span> <span class="o">-></span> <span class="n">e</span>
+
+ <span class="c">(* identifierexpr</span>
+<span class="c"> * ::= identifier</span>
+<span class="c"> * ::= identifier '(' argumentexpr ')' *)</span>
+ <span class="o">|</span> <span class="o">[<</span> <span class="k">'</span><span class="nn">Token</span><span class="p">.</span><span class="nc">Ident</span> <span class="n">id</span><span class="o">;</span> <span class="n">stream</span> <span class="o">>]</span> <span class="o">-></span>
+ <span class="k">let</span> <span class="k">rec</span> <span class="n">parse_args</span> <span class="n">accumulator</span> <span class="o">=</span> <span class="n">parser</span>
+ <span class="o">|</span> <span class="o">[<</span> <span class="n">e</span><span class="o">=</span><span class="n">parse_expr</span><span class="o">;</span> <span class="n">stream</span> <span class="o">>]</span> <span class="o">-></span>
+ <span class="k">begin</span> <span class="n">parser</span>
+ <span class="o">|</span> <span class="o">[<</span> <span class="k">'</span><span class="nn">Token</span><span class="p">.</span><span class="nc">Kwd</span> <span class="sc">','</span><span class="o">;</span> <span class="n">e</span><span class="o">=</span><span class="n">parse_args</span> <span class="o">(</span><span class="n">e</span> <span class="o">::</span> <span class="n">accumulator</span><span class="o">)</span> <span class="o">>]</span> <span class="o">-></span> <span class="n">e</span>
+ <span class="o">|</span> <span class="o">[<</span> <span class="o">>]</span> <span class="o">-></span> <span class="n">e</span> <span class="o">::</span> <span class="n">accumulator</span>
+ <span class="k">end</span> <span class="n">stream</span>
+ <span class="o">|</span> <span class="o">[<</span> <span class="o">>]</span> <span class="o">-></span> <span class="n">accumulator</span>
+ <span class="k">in</span>
+ <span class="k">let</span> <span class="k">rec</span> <span class="n">parse_ident</span> <span class="n">id</span> <span class="o">=</span> <span class="n">parser</span>
+ <span class="c">(* Call. *)</span>
+ <span class="o">|</span> <span class="o">[<</span> <span class="k">'</span><span class="nn">Token</span><span class="p">.</span><span class="nc">Kwd</span> <span class="sc">'('</span><span class="o">;</span>
+ <span class="n">args</span><span class="o">=</span><span class="n">parse_args</span> <span class="bp">[]</span><span class="o">;</span>
+ <span class="k">'</span><span class="nn">Token</span><span class="p">.</span><span class="nc">Kwd</span> <span class="sc">')'</span> <span class="o">??</span> <span class="s2">"expected ')'"</span><span class="o">>]</span> <span class="o">-></span>
+ <span class="nn">Ast</span><span class="p">.</span><span class="nc">Call</span> <span class="o">(</span><span class="n">id</span><span class="o">,</span> <span class="nn">Array</span><span class="p">.</span><span class="n">of_list</span> <span class="o">(</span><span class="nn">List</span><span class="p">.</span><span class="n">rev</span> <span class="n">args</span><span class="o">))</span>
+
+ <span class="c">(* Simple variable ref. *)</span>
+ <span class="o">|</span> <span class="o">[<</span> <span class="o">>]</span> <span class="o">-></span> <span class="nn">Ast</span><span class="p">.</span><span class="nc">Variable</span> <span class="n">id</span>
+ <span class="k">in</span>
+ <span class="n">parse_ident</span> <span class="n">id</span> <span class="n">stream</span>
+
+ <span class="o">|</span> <span class="o">[<</span> <span class="o">>]</span> <span class="o">-></span> <span class="k">raise</span> <span class="o">(</span><span class="nn">Stream</span><span class="p">.</span><span class="nc">Error</span> <span class="s2">"unknown token when expecting an expression."</span><span class="o">)</span>
+
+<span class="c">(* binoprhs</span>
+<span class="c"> * ::= ('+' primary)* *)</span>
+<span class="ow">and</span> <span class="n">parse_bin_rhs</span> <span class="n">expr_prec</span> <span class="n">lhs</span> <span class="n">stream</span> <span class="o">=</span>
+ <span class="k">match</span> <span class="nn">Stream</span><span class="p">.</span><span class="n">peek</span> <span class="n">stream</span> <span class="k">with</span>
+ <span class="c">(* If this is a binop, find its precedence. *)</span>
+ <span class="o">|</span> <span class="nc">Some</span> <span class="o">(</span><span class="nn">Token</span><span class="p">.</span><span class="nc">Kwd</span> <span class="n">c</span><span class="o">)</span> <span class="k">when</span> <span class="nn">Hashtbl</span><span class="p">.</span><span class="n">mem</span> <span class="n">binop_precedence</span> <span class="n">c</span> <span class="o">-></span>
+ <span class="k">let</span> <span class="n">token_prec</span> <span class="o">=</span> <span class="n">precedence</span> <span class="n">c</span> <span class="k">in</span>
+
+ <span class="c">(* If this is a binop that binds at least as tightly as the current binop,</span>
+<span class="c"> * consume it, otherwise we are done. *)</span>
+ <span class="k">if</span> <span class="n">token_prec</span> <span class="o"><</span> <span class="n">expr_prec</span> <span class="k">then</span> <span class="n">lhs</span> <span class="k">else</span> <span class="k">begin</span>
+ <span class="c">(* Eat the binop. *)</span>
+ <span class="nn">Stream</span><span class="p">.</span><span class="n">junk</span> <span class="n">stream</span><span class="o">;</span>
+
+ <span class="c">(* Parse the primary expression after the binary operator. *)</span>
+ <span class="k">let</span> <span class="n">rhs</span> <span class="o">=</span> <span class="n">parse_primary</span> <span class="n">stream</span> <span class="k">in</span>
+
+ <span class="c">(* Okay, we know this is a binop. *)</span>
+ <span class="k">let</span> <span class="n">rhs</span> <span class="o">=</span>
+ <span class="k">match</span> <span class="nn">Stream</span><span class="p">.</span><span class="n">peek</span> <span class="n">stream</span> <span class="k">with</span>
+ <span class="o">|</span> <span class="nc">Some</span> <span class="o">(</span><span class="nn">Token</span><span class="p">.</span><span class="nc">Kwd</span> <span class="n">c2</span><span class="o">)</span> <span class="o">-></span>
+ <span class="c">(* If BinOp binds less tightly with rhs than the operator after</span>
+<span class="c"> * rhs, let the pending operator take rhs as its lhs. *)</span>
+ <span class="k">let</span> <span class="n">next_prec</span> <span class="o">=</span> <span class="n">precedence</span> <span class="n">c2</span> <span class="k">in</span>
+ <span class="k">if</span> <span class="n">token_prec</span> <span class="o"><</span> <span class="n">next_prec</span>
+ <span class="k">then</span> <span class="n">parse_bin_rhs</span> <span class="o">(</span><span class="n">token_prec</span> <span class="o">+</span> <span class="mi">1</span><span class="o">)</span> <span class="n">rhs</span> <span class="n">stream</span>
+ <span class="k">else</span> <span class="n">rhs</span>
+ <span class="o">|</span> <span class="o">_</span> <span class="o">-></span> <span class="n">rhs</span>
+ <span class="k">in</span>
+
+ <span class="c">(* Merge lhs/rhs. *)</span>
+ <span class="k">let</span> <span class="n">lhs</span> <span class="o">=</span> <span class="nn">Ast</span><span class="p">.</span><span class="nc">Binary</span> <span class="o">(</span><span class="n">c</span><span class="o">,</span> <span class="n">lhs</span><span class="o">,</span> <span class="n">rhs</span><span class="o">)</span> <span class="k">in</span>
+ <span class="n">parse_bin_rhs</span> <span class="n">expr_prec</span> <span class="n">lhs</span> <span class="n">stream</span>
+ <span class="k">end</span>
+ <span class="o">|</span> <span class="o">_</span> <span class="o">-></span> <span class="n">lhs</span>
+
+<span class="c">(* expression</span>
+<span class="c"> * ::= primary binoprhs *)</span>
+<span class="ow">and</span> <span class="n">parse_expr</span> <span class="o">=</span> <span class="n">parser</span>
+ <span class="o">|</span> <span class="o">[<</span> <span class="n">lhs</span><span class="o">=</span><span class="n">parse_primary</span><span class="o">;</span> <span class="n">stream</span> <span class="o">>]</span> <span class="o">-></span> <span class="n">parse_bin_rhs</span> <span class="mi">0</span> <span class="n">lhs</span> <span class="n">stream</span>
+
+<span class="c">(* prototype</span>
+<span class="c"> * ::= id '(' id* ')' *)</span>
+<span class="k">let</span> <span class="n">parse_prototype</span> <span class="o">=</span>
+ <span class="k">let</span> <span class="k">rec</span> <span class="n">parse_args</span> <span class="n">accumulator</span> <span class="o">=</span> <span class="n">parser</span>
+ <span class="o">|</span> <span class="o">[<</span> <span class="k">'</span><span class="nn">Token</span><span class="p">.</span><span class="nc">Ident</span> <span class="n">id</span><span class="o">;</span> <span class="n">e</span><span class="o">=</span><span class="n">parse_args</span> <span class="o">(</span><span class="n">id</span><span class="o">::</span><span class="n">accumulator</span><span class="o">)</span> <span class="o">>]</span> <span class="o">-></span> <span class="n">e</span>
+ <span class="o">|</span> <span class="o">[<</span> <span class="o">>]</span> <span class="o">-></span> <span class="n">accumulator</span>
+ <span class="k">in</span>
+
+ <span class="n">parser</span>
+ <span class="o">|</span> <span class="o">[<</span> <span class="k">'</span><span class="nn">Token</span><span class="p">.</span><span class="nc">Ident</span> <span class="n">id</span><span class="o">;</span>
+ <span class="k">'</span><span class="nn">Token</span><span class="p">.</span><span class="nc">Kwd</span> <span class="sc">'('</span> <span class="o">??</span> <span class="s2">"expected '(' in prototype"</span><span class="o">;</span>
+ <span class="n">args</span><span class="o">=</span><span class="n">parse_args</span> <span class="bp">[]</span><span class="o">;</span>
+ <span class="k">'</span><span class="nn">Token</span><span class="p">.</span><span class="nc">Kwd</span> <span class="sc">')'</span> <span class="o">??</span> <span class="s2">"expected ')' in prototype"</span> <span class="o">>]</span> <span class="o">-></span>
+ <span class="c">(* success. *)</span>
+ <span class="nn">Ast</span><span class="p">.</span><span class="nc">Prototype</span> <span class="o">(</span><span class="n">id</span><span class="o">,</span> <span class="nn">Array</span><span class="p">.</span><span class="n">of_list</span> <span class="o">(</span><span class="nn">List</span><span class="p">.</span><span class="n">rev</span> <span class="n">args</span><span class="o">))</span>
+
+ <span class="o">|</span> <span class="o">[<</span> <span class="o">>]</span> <span class="o">-></span>
+ <span class="k">raise</span> <span class="o">(</span><span class="nn">Stream</span><span class="p">.</span><span class="nc">Error</span> <span class="s2">"expected function name in prototype"</span><span class="o">)</span>
+
+<span class="c">(* definition ::= 'def' prototype expression *)</span>
+<span class="k">let</span> <span class="n">parse_definition</span> <span class="o">=</span> <span class="n">parser</span>
+ <span class="o">|</span> <span class="o">[<</span> <span class="k">'</span><span class="nn">Token</span><span class="p">.</span><span class="nc">Def</span><span class="o">;</span> <span class="n">p</span><span class="o">=</span><span class="n">parse_prototype</span><span class="o">;</span> <span class="n">e</span><span class="o">=</span><span class="n">parse_expr</span> <span class="o">>]</span> <span class="o">-></span>
+ <span class="nn">Ast</span><span class="p">.</span><span class="nc">Function</span> <span class="o">(</span><span class="n">p</span><span class="o">,</span> <span class="n">e</span><span class="o">)</span>
+
+<span class="c">(* toplevelexpr ::= expression *)</span>
+<span class="k">let</span> <span class="n">parse_toplevel</span> <span class="o">=</span> <span class="n">parser</span>
+ <span class="o">|</span> <span class="o">[<</span> <span class="n">e</span><span class="o">=</span><span class="n">parse_expr</span> <span class="o">>]</span> <span class="o">-></span>
+ <span class="c">(* Make an anonymous proto. *)</span>
+ <span class="nn">Ast</span><span class="p">.</span><span class="nc">Function</span> <span class="o">(</span><span class="nn">Ast</span><span class="p">.</span><span class="nc">Prototype</span> <span class="o">(</span><span class="s2">""</span><span class="o">,</span> <span class="o">[||]),</span> <span class="n">e</span><span class="o">)</span>
+
+<span class="c">(* external ::= 'extern' prototype *)</span>
+<span class="k">let</span> <span class="n">parse_extern</span> <span class="o">=</span> <span class="n">parser</span>
+ <span class="o">|</span> <span class="o">[<</span> <span class="k">'</span><span class="nn">Token</span><span class="p">.</span><span class="nc">Extern</span><span class="o">;</span> <span class="n">e</span><span class="o">=</span><span class="n">parse_prototype</span> <span class="o">>]</span> <span class="o">-></span> <span class="n">e</span>
+</pre></div>
+</div>
+</dd>
+<dt>codegen.ml:</dt>
+<dd><div class="first last highlight-ocaml"><div class="highlight"><pre><span class="c">(*===----------------------------------------------------------------------===</span>
+<span class="c"> * Code Generation</span>
+<span class="c"> *===----------------------------------------------------------------------===*)</span>
+
+<span class="k">open</span> <span class="nc">Llvm</span>
+
+<span class="k">exception</span> <span class="nc">Error</span> <span class="k">of</span> <span class="kt">string</span>
+
+<span class="k">let</span> <span class="n">context</span> <span class="o">=</span> <span class="n">global_context</span> <span class="bp">()</span>
+<span class="k">let</span> <span class="n">the_module</span> <span class="o">=</span> <span class="n">create_module</span> <span class="n">context</span> <span class="s2">"my cool jit"</span>
+<span class="k">let</span> <span class="n">builder</span> <span class="o">=</span> <span class="n">builder</span> <span class="n">context</span>
+<span class="k">let</span> <span class="n">named_values</span><span class="o">:(</span><span class="kt">string</span><span class="o">,</span> <span class="n">llvalue</span><span class="o">)</span> <span class="nn">Hashtbl</span><span class="p">.</span><span class="n">t</span> <span class="o">=</span> <span class="nn">Hashtbl</span><span class="p">.</span><span class="n">create</span> <span class="mi">10</span>
+<span class="k">let</span> <span class="n">double_type</span> <span class="o">=</span> <span class="n">double_type</span> <span class="n">context</span>
+
+<span class="k">let</span> <span class="k">rec</span> <span class="n">codegen_expr</span> <span class="o">=</span> <span class="k">function</span>
+ <span class="o">|</span> <span class="nn">Ast</span><span class="p">.</span><span class="nc">Number</span> <span class="n">n</span> <span class="o">-></span> <span class="n">const_float</span> <span class="n">double_type</span> <span class="n">n</span>
+ <span class="o">|</span> <span class="nn">Ast</span><span class="p">.</span><span class="nc">Variable</span> <span class="n">name</span> <span class="o">-></span>
+ <span class="o">(</span><span class="k">try</span> <span class="nn">Hashtbl</span><span class="p">.</span><span class="n">find</span> <span class="n">named_values</span> <span class="n">name</span> <span class="k">with</span>
+ <span class="o">|</span> <span class="nc">Not_found</span> <span class="o">-></span> <span class="k">raise</span> <span class="o">(</span><span class="nc">Error</span> <span class="s2">"unknown variable name"</span><span class="o">))</span>
+ <span class="o">|</span> <span class="nn">Ast</span><span class="p">.</span><span class="nc">Binary</span> <span class="o">(</span><span class="n">op</span><span class="o">,</span> <span class="n">lhs</span><span class="o">,</span> <span class="n">rhs</span><span class="o">)</span> <span class="o">-></span>
+ <span class="k">let</span> <span class="n">lhs_val</span> <span class="o">=</span> <span class="n">codegen_expr</span> <span class="n">lhs</span> <span class="k">in</span>
+ <span class="k">let</span> <span class="n">rhs_val</span> <span class="o">=</span> <span class="n">codegen_expr</span> <span class="n">rhs</span> <span class="k">in</span>
+ <span class="k">begin</span>
+ <span class="k">match</span> <span class="n">op</span> <span class="k">with</span>
+ <span class="o">|</span> <span class="sc">'+'</span> <span class="o">-></span> <span class="n">build_add</span> <span class="n">lhs_val</span> <span class="n">rhs_val</span> <span class="s2">"addtmp"</span> <span class="n">builder</span>
+ <span class="o">|</span> <span class="sc">'-'</span> <span class="o">-></span> <span class="n">build_sub</span> <span class="n">lhs_val</span> <span class="n">rhs_val</span> <span class="s2">"subtmp"</span> <span class="n">builder</span>
+ <span class="o">|</span> <span class="sc">'*'</span> <span class="o">-></span> <span class="n">build_mul</span> <span class="n">lhs_val</span> <span class="n">rhs_val</span> <span class="s2">"multmp"</span> <span class="n">builder</span>
+ <span class="o">|</span> <span class="sc">'<'</span> <span class="o">-></span>
+ <span class="c">(* Convert bool 0/1 to double 0.0 or 1.0 *)</span>
+ <span class="k">let</span> <span class="n">i</span> <span class="o">=</span> <span class="n">build_fcmp</span> <span class="nn">Fcmp</span><span class="p">.</span><span class="nc">Ult</span> <span class="n">lhs_val</span> <span class="n">rhs_val</span> <span class="s2">"cmptmp"</span> <span class="n">builder</span> <span class="k">in</span>
+ <span class="n">build_uitofp</span> <span class="n">i</span> <span class="n">double_type</span> <span class="s2">"booltmp"</span> <span class="n">builder</span>
+ <span class="o">|</span> <span class="o">_</span> <span class="o">-></span> <span class="k">raise</span> <span class="o">(</span><span class="nc">Error</span> <span class="s2">"invalid binary operator"</span><span class="o">)</span>
+ <span class="k">end</span>
+ <span class="o">|</span> <span class="nn">Ast</span><span class="p">.</span><span class="nc">Call</span> <span class="o">(</span><span class="n">callee</span><span class="o">,</span> <span class="n">args</span><span class="o">)</span> <span class="o">-></span>
+ <span class="c">(* Look up the name in the module table. *)</span>
+ <span class="k">let</span> <span class="n">callee</span> <span class="o">=</span>
+ <span class="k">match</span> <span class="n">lookup_function</span> <span class="n">callee</span> <span class="n">the_module</span> <span class="k">with</span>
+ <span class="o">|</span> <span class="nc">Some</span> <span class="n">callee</span> <span class="o">-></span> <span class="n">callee</span>
+ <span class="o">|</span> <span class="nc">None</span> <span class="o">-></span> <span class="k">raise</span> <span class="o">(</span><span class="nc">Error</span> <span class="s2">"unknown function referenced"</span><span class="o">)</span>
+ <span class="k">in</span>
+ <span class="k">let</span> <span class="n">params</span> <span class="o">=</span> <span class="n">params</span> <span class="n">callee</span> <span class="k">in</span>
+
+ <span class="c">(* If argument mismatch error. *)</span>
+ <span class="k">if</span> <span class="nn">Array</span><span class="p">.</span><span class="n">length</span> <span class="n">params</span> <span class="o">==</span> <span class="nn">Array</span><span class="p">.</span><span class="n">length</span> <span class="n">args</span> <span class="k">then</span> <span class="bp">()</span> <span class="k">else</span>
+ <span class="k">raise</span> <span class="o">(</span><span class="nc">Error</span> <span class="s2">"incorrect # arguments passed"</span><span class="o">);</span>
+ <span class="k">let</span> <span class="n">args</span> <span class="o">=</span> <span class="nn">Array</span><span class="p">.</span><span class="n">map</span> <span class="n">codegen_expr</span> <span class="n">args</span> <span class="k">in</span>
+ <span class="n">build_call</span> <span class="n">callee</span> <span class="n">args</span> <span class="s2">"calltmp"</span> <span class="n">builder</span>
+
+<span class="k">let</span> <span class="n">codegen_proto</span> <span class="o">=</span> <span class="k">function</span>
+ <span class="o">|</span> <span class="nn">Ast</span><span class="p">.</span><span class="nc">Prototype</span> <span class="o">(</span><span class="n">name</span><span class="o">,</span> <span class="n">args</span><span class="o">)</span> <span class="o">-></span>
+ <span class="c">(* Make the function type: double(double,double) etc. *)</span>
+ <span class="k">let</span> <span class="n">doubles</span> <span class="o">=</span> <span class="nn">Array</span><span class="p">.</span><span class="n">make</span> <span class="o">(</span><span class="nn">Array</span><span class="p">.</span><span class="n">length</span> <span class="n">args</span><span class="o">)</span> <span class="n">double_type</span> <span class="k">in</span>
+ <span class="k">let</span> <span class="n">ft</span> <span class="o">=</span> <span class="n">function_type</span> <span class="n">double_type</span> <span class="n">doubles</span> <span class="k">in</span>
+ <span class="k">let</span> <span class="n">f</span> <span class="o">=</span>
+ <span class="k">match</span> <span class="n">lookup_function</span> <span class="n">name</span> <span class="n">the_module</span> <span class="k">with</span>
+ <span class="o">|</span> <span class="nc">None</span> <span class="o">-></span> <span class="n">declare_function</span> <span class="n">name</span> <span class="n">ft</span> <span class="n">the_module</span>
+
+ <span class="c">(* If 'f' conflicted, there was already something named 'name'. If it</span>
+<span class="c"> * has a body, don't allow redefinition or reextern. *)</span>
+ <span class="o">|</span> <span class="nc">Some</span> <span class="n">f</span> <span class="o">-></span>
+ <span class="c">(* If 'f' already has a body, reject this. *)</span>
+ <span class="k">if</span> <span class="n">block_begin</span> <span class="n">f</span> <span class="o"><></span> <span class="nc">At_end</span> <span class="n">f</span> <span class="k">then</span>
+ <span class="k">raise</span> <span class="o">(</span><span class="nc">Error</span> <span class="s2">"redefinition of function"</span><span class="o">);</span>
+
+ <span class="c">(* If 'f' took a different number of arguments, reject. *)</span>
+ <span class="k">if</span> <span class="n">element_type</span> <span class="o">(</span><span class="n">type_of</span> <span class="n">f</span><span class="o">)</span> <span class="o"><></span> <span class="n">ft</span> <span class="k">then</span>
+ <span class="k">raise</span> <span class="o">(</span><span class="nc">Error</span> <span class="s2">"redefinition of function with different # args"</span><span class="o">);</span>
+ <span class="n">f</span>
+ <span class="k">in</span>
+
+ <span class="c">(* Set names for all arguments. *)</span>
+ <span class="nn">Array</span><span class="p">.</span><span class="n">iteri</span> <span class="o">(</span><span class="k">fun</span> <span class="n">i</span> <span class="n">a</span> <span class="o">-></span>
+ <span class="k">let</span> <span class="n">n</span> <span class="o">=</span> <span class="n">args</span><span class="o">.(</span><span class="n">i</span><span class="o">)</span> <span class="k">in</span>
+ <span class="n">set_value_name</span> <span class="n">n</span> <span class="n">a</span><span class="o">;</span>
+ <span class="nn">Hashtbl</span><span class="p">.</span><span class="n">add</span> <span class="n">named_values</span> <span class="n">n</span> <span class="n">a</span><span class="o">;</span>
+ <span class="o">)</span> <span class="o">(</span><span class="n">params</span> <span class="n">f</span><span class="o">);</span>
+ <span class="n">f</span>
+
+<span class="k">let</span> <span class="n">codegen_func</span> <span class="o">=</span> <span class="k">function</span>
+ <span class="o">|</span> <span class="nn">Ast</span><span class="p">.</span><span class="nc">Function</span> <span class="o">(</span><span class="n">proto</span><span class="o">,</span> <span class="n">body</span><span class="o">)</span> <span class="o">-></span>
+ <span class="nn">Hashtbl</span><span class="p">.</span><span class="n">clear</span> <span class="n">named_values</span><span class="o">;</span>
+ <span class="k">let</span> <span class="n">the_function</span> <span class="o">=</span> <span class="n">codegen_proto</span> <span class="n">proto</span> <span class="k">in</span>
+
+ <span class="c">(* Create a new basic block to start insertion into. *)</span>
+ <span class="k">let</span> <span class="n">bb</span> <span class="o">=</span> <span class="n">append_block</span> <span class="n">context</span> <span class="s2">"entry"</span> <span class="n">the_function</span> <span class="k">in</span>
+ <span class="n">position_at_end</span> <span class="n">bb</span> <span class="n">builder</span><span class="o">;</span>
+
+ <span class="k">try</span>
+ <span class="k">let</span> <span class="n">ret_val</span> <span class="o">=</span> <span class="n">codegen_expr</span> <span class="n">body</span> <span class="k">in</span>
+
+ <span class="c">(* Finish off the function. *)</span>
+ <span class="k">let</span> <span class="o">_</span> <span class="o">=</span> <span class="n">build_ret</span> <span class="n">ret_val</span> <span class="n">builder</span> <span class="k">in</span>
+
+ <span class="c">(* Validate the generated code, checking for consistency. *)</span>
+ <span class="nn">Llvm_analysis</span><span class="p">.</span><span class="n">assert_valid_function</span> <span class="n">the_function</span><span class="o">;</span>
+
+ <span class="n">the_function</span>
+ <span class="k">with</span> <span class="n">e</span> <span class="o">-></span>
+ <span class="n">delete_function</span> <span class="n">the_function</span><span class="o">;</span>
+ <span class="k">raise</span> <span class="n">e</span>
+</pre></div>
+</div>
+</dd>
+<dt>toplevel.ml:</dt>
+<dd><div class="first last highlight-ocaml"><div class="highlight"><pre><span class="c">(*===----------------------------------------------------------------------===</span>
+<span class="c"> * Top-Level parsing and JIT Driver</span>
+<span class="c"> *===----------------------------------------------------------------------===*)</span>
+
+<span class="k">open</span> <span class="nc">Llvm</span>
+
+<span class="c">(* top ::= definition | external | expression | ';' *)</span>
+<span class="k">let</span> <span class="k">rec</span> <span class="n">main_loop</span> <span class="n">stream</span> <span class="o">=</span>
+ <span class="k">match</span> <span class="nn">Stream</span><span class="p">.</span><span class="n">peek</span> <span class="n">stream</span> <span class="k">with</span>
+ <span class="o">|</span> <span class="nc">None</span> <span class="o">-></span> <span class="bp">()</span>
+
+ <span class="c">(* ignore top-level semicolons. *)</span>
+ <span class="o">|</span> <span class="nc">Some</span> <span class="o">(</span><span class="nn">Token</span><span class="p">.</span><span class="nc">Kwd</span> <span class="sc">';'</span><span class="o">)</span> <span class="o">-></span>
+ <span class="nn">Stream</span><span class="p">.</span><span class="n">junk</span> <span class="n">stream</span><span class="o">;</span>
+ <span class="n">main_loop</span> <span class="n">stream</span>
+
+ <span class="o">|</span> <span class="nc">Some</span> <span class="n">token</span> <span class="o">-></span>
+ <span class="k">begin</span>
+ <span class="k">try</span> <span class="k">match</span> <span class="n">token</span> <span class="k">with</span>
+ <span class="o">|</span> <span class="nn">Token</span><span class="p">.</span><span class="nc">Def</span> <span class="o">-></span>
+ <span class="k">let</span> <span class="n">e</span> <span class="o">=</span> <span class="nn">Parser</span><span class="p">.</span><span class="n">parse_definition</span> <span class="n">stream</span> <span class="k">in</span>
+ <span class="n">print_endline</span> <span class="s2">"parsed a function definition."</span><span class="o">;</span>
+ <span class="n">dump_value</span> <span class="o">(</span><span class="nn">Codegen</span><span class="p">.</span><span class="n">codegen_func</span> <span class="n">e</span><span class="o">);</span>
+ <span class="o">|</span> <span class="nn">Token</span><span class="p">.</span><span class="nc">Extern</span> <span class="o">-></span>
+ <span class="k">let</span> <span class="n">e</span> <span class="o">=</span> <span class="nn">Parser</span><span class="p">.</span><span class="n">parse_extern</span> <span class="n">stream</span> <span class="k">in</span>
+ <span class="n">print_endline</span> <span class="s2">"parsed an extern."</span><span class="o">;</span>
+ <span class="n">dump_value</span> <span class="o">(</span><span class="nn">Codegen</span><span class="p">.</span><span class="n">codegen_proto</span> <span class="n">e</span><span class="o">);</span>
+ <span class="o">|</span> <span class="o">_</span> <span class="o">-></span>
+ <span class="c">(* Evaluate a top-level expression into an anonymous function. *)</span>
+ <span class="k">let</span> <span class="n">e</span> <span class="o">=</span> <span class="nn">Parser</span><span class="p">.</span><span class="n">parse_toplevel</span> <span class="n">stream</span> <span class="k">in</span>
+ <span class="n">print_endline</span> <span class="s2">"parsed a top-level expr"</span><span class="o">;</span>
+ <span class="n">dump_value</span> <span class="o">(</span><span class="nn">Codegen</span><span class="p">.</span><span class="n">codegen_func</span> <span class="n">e</span><span class="o">);</span>
+ <span class="k">with</span> <span class="nn">Stream</span><span class="p">.</span><span class="nc">Error</span> <span class="n">s</span> <span class="o">|</span> <span class="nn">Codegen</span><span class="p">.</span><span class="nc">Error</span> <span class="n">s</span> <span class="o">-></span>
+ <span class="c">(* Skip token for error recovery. *)</span>
+ <span class="nn">Stream</span><span class="p">.</span><span class="n">junk</span> <span class="n">stream</span><span class="o">;</span>
+ <span class="n">print_endline</span> <span class="n">s</span><span class="o">;</span>
+ <span class="k">end</span><span class="o">;</span>
+ <span class="n">print_string</span> <span class="s2">"ready> "</span><span class="o">;</span> <span class="n">flush</span> <span class="n">stdout</span><span class="o">;</span>
+ <span class="n">main_loop</span> <span class="n">stream</span>
+</pre></div>
+</div>
+</dd>
+<dt>toy.ml:</dt>
+<dd><div class="first last highlight-ocaml"><div class="highlight"><pre><span class="c">(*===----------------------------------------------------------------------===</span>
+<span class="c"> * Main driver code.</span>
+<span class="c"> *===----------------------------------------------------------------------===*)</span>
+
+<span class="k">open</span> <span class="nc">Llvm</span>
+
+<span class="k">let</span> <span class="n">main</span> <span class="bp">()</span> <span class="o">=</span>
+ <span class="c">(* Install standard binary operators.</span>
+<span class="c"> * 1 is the lowest precedence. *)</span>
+ <span class="nn">Hashtbl</span><span class="p">.</span><span class="n">add</span> <span class="nn">Parser</span><span class="p">.</span><span class="n">binop_precedence</span> <span class="sc">'<'</span> <span class="mi">10</span><span class="o">;</span>
+ <span class="nn">Hashtbl</span><span class="p">.</span><span class="n">add</span> <span class="nn">Parser</span><span class="p">.</span><span class="n">binop_precedence</span> <span class="sc">'+'</span> <span class="mi">20</span><span class="o">;</span>
+ <span class="nn">Hashtbl</span><span class="p">.</span><span class="n">add</span> <span class="nn">Parser</span><span class="p">.</span><span class="n">binop_precedence</span> <span class="sc">'-'</span> <span class="mi">20</span><span class="o">;</span>
+ <span class="nn">Hashtbl</span><span class="p">.</span><span class="n">add</span> <span class="nn">Parser</span><span class="p">.</span><span class="n">binop_precedence</span> <span class="sc">'*'</span> <span class="mi">40</span><span class="o">;</span> <span class="c">(* highest. *)</span>
+
+ <span class="c">(* Prime the first token. *)</span>
+ <span class="n">print_string</span> <span class="s2">"ready> "</span><span class="o">;</span> <span class="n">flush</span> <span class="n">stdout</span><span class="o">;</span>
+ <span class="k">let</span> <span class="n">stream</span> <span class="o">=</span> <span class="nn">Lexer</span><span class="p">.</span><span class="n">lex</span> <span class="o">(</span><span class="nn">Stream</span><span class="p">.</span><span class="n">of_channel</span> <span class="n">stdin</span><span class="o">)</span> <span class="k">in</span>
+
+ <span class="c">(* Run the main "interpreter loop" now. *)</span>
+ <span class="nn">Toplevel</span><span class="p">.</span><span class="n">main_loop</span> <span class="n">stream</span><span class="o">;</span>
+
+ <span class="c">(* Print out all the generated code. *)</span>
+ <span class="n">dump_module</span> <span class="nn">Codegen</span><span class="p">.</span><span class="n">the_module</span>
+<span class="o">;;</span>
+
+<span class="n">main</span> <span class="bp">()</span>
+</pre></div>
+</div>
+</dd>
+</dl>
+<p><a class="reference external" href="OCamlLangImpl4.html">Next: Adding JIT and Optimizer Support</a></p>
+</div>
+</div>
+
+
+ </div>
+ </div>
+ <div class="clearer"></div>
+ </div>
+ <div class="related">
+ <h3>Navigation</h3>
+ <ul>
+ <li class="right" style="margin-right: 10px">
+ <a href="../genindex.html" title="General Index"
+ >index</a></li>
+ <li class="right" >
+ <a href="OCamlLangImpl4.html" title="4. Kaleidoscope: Adding JIT and Optimizer Support"
+ >next</a> |</li>
+ <li class="right" >
+ <a href="OCamlLangImpl2.html" title="2. Kaleidoscope: Implementing a Parser and AST"
+ >previous</a> |</li>
+ <li><a href="http://llvm.org/">LLVM Home</a> | </li>
+ <li><a href="../index.html">Documentation</a>»</li>
+
+ <li><a href="index.html" >LLVM Tutorial: Table of Contents</a> »</li>
+ </ul>
+ </div>
+ <div class="footer">
+ © Copyright 2003-2016, LLVM Project.
+ Last updated on 2016-07-11.
+ Created using <a href="http://sphinx-doc.org/">Sphinx</a> 1.2.2.
+ </div>
+ </body>
+</html>
\ No newline at end of file
Added: www-releases/trunk/3.8.1/docs/tutorial/OCamlLangImpl4.html
URL: http://llvm.org/viewvc/llvm-project/www-releases/trunk/3.8.1/docs/tutorial/OCamlLangImpl4.html?rev=275092&view=auto
==============================================================================
--- www-releases/trunk/3.8.1/docs/tutorial/OCamlLangImpl4.html (added)
+++ www-releases/trunk/3.8.1/docs/tutorial/OCamlLangImpl4.html Mon Jul 11 14:36:11 2016
@@ -0,0 +1,968 @@
+
+<!DOCTYPE html PUBLIC "-//W3C//DTD XHTML 1.0 Transitional//EN"
+ "http://www.w3.org/TR/xhtml1/DTD/xhtml1-transitional.dtd">
+
+
+<html xmlns="http://www.w3.org/1999/xhtml">
+ <head>
+ <meta http-equiv="Content-Type" content="text/html; charset=utf-8" />
+
+ <title>4. Kaleidoscope: Adding JIT and Optimizer Support — LLVM 3.8 documentation</title>
+
+ <link rel="stylesheet" href="../_static/llvm-theme.css" type="text/css" />
+ <link rel="stylesheet" href="../_static/pygments.css" type="text/css" />
+
+ <script type="text/javascript">
+ var DOCUMENTATION_OPTIONS = {
+ URL_ROOT: '../',
+ VERSION: '3.8',
+ COLLAPSE_INDEX: false,
+ FILE_SUFFIX: '.html',
+ HAS_SOURCE: true
+ };
+ </script>
+ <script type="text/javascript" src="../_static/jquery.js"></script>
+ <script type="text/javascript" src="../_static/underscore.js"></script>
+ <script type="text/javascript" src="../_static/doctools.js"></script>
+ <link rel="top" title="LLVM 3.8 documentation" href="../index.html" />
+ <link rel="up" title="LLVM Tutorial: Table of Contents" href="index.html" />
+ <link rel="next" title="5. Kaleidoscope: Extending the Language: Control Flow" href="OCamlLangImpl5.html" />
+ <link rel="prev" title="3. Kaleidoscope: Code generation to LLVM IR" href="OCamlLangImpl3.html" />
+<style type="text/css">
+ table.right { float: right; margin-left: 20px; }
+ table.right td { border: 1px solid #ccc; }
+</style>
+
+ </head>
+ <body>
+<div class="logo">
+ <a href="../index.html">
+ <img src="../_static/logo.png"
+ alt="LLVM Logo" width="250" height="88"/></a>
+</div>
+
+ <div class="related">
+ <h3>Navigation</h3>
+ <ul>
+ <li class="right" style="margin-right: 10px">
+ <a href="../genindex.html" title="General Index"
+ accesskey="I">index</a></li>
+ <li class="right" >
+ <a href="OCamlLangImpl5.html" title="5. Kaleidoscope: Extending the Language: Control Flow"
+ accesskey="N">next</a> |</li>
+ <li class="right" >
+ <a href="OCamlLangImpl3.html" title="3. Kaleidoscope: Code generation to LLVM IR"
+ accesskey="P">previous</a> |</li>
+ <li><a href="http://llvm.org/">LLVM Home</a> | </li>
+ <li><a href="../index.html">Documentation</a>»</li>
+
+ <li><a href="index.html" accesskey="U">LLVM Tutorial: Table of Contents</a> »</li>
+ </ul>
+ </div>
+
+
+ <div class="document">
+ <div class="documentwrapper">
+ <div class="body">
+
+ <div class="section" id="kaleidoscope-adding-jit-and-optimizer-support">
+<h1>4. Kaleidoscope: Adding JIT and Optimizer Support<a class="headerlink" href="#kaleidoscope-adding-jit-and-optimizer-support" title="Permalink to this headline">¶</a></h1>
+<div class="contents local topic" id="contents">
+<ul class="simple">
+<li><a class="reference internal" href="#chapter-4-introduction" id="id1">Chapter 4 Introduction</a></li>
+<li><a class="reference internal" href="#trivial-constant-folding" id="id2">Trivial Constant Folding</a></li>
+<li><a class="reference internal" href="#llvm-optimization-passes" id="id3">LLVM Optimization Passes</a></li>
+<li><a class="reference internal" href="#adding-a-jit-compiler" id="id4">Adding a JIT Compiler</a></li>
+<li><a class="reference internal" href="#full-code-listing" id="id5">Full Code Listing</a></li>
+</ul>
+</div>
+<div class="section" id="chapter-4-introduction">
+<h2><a class="toc-backref" href="#id1">4.1. Chapter 4 Introduction</a><a class="headerlink" href="#chapter-4-introduction" title="Permalink to this headline">¶</a></h2>
+<p>Welcome to Chapter 4 of the “<a class="reference external" href="index.html">Implementing a language with
+LLVM</a>” tutorial. Chapters 1-3 described the implementation
+of a simple language and added support for generating LLVM IR. This
+chapter describes two new techniques: adding optimizer support to your
+language, and adding JIT compiler support. These additions will
+demonstrate how to get nice, efficient code for the Kaleidoscope
+language.</p>
+</div>
+<div class="section" id="trivial-constant-folding">
+<h2><a class="toc-backref" href="#id2">4.2. Trivial Constant Folding</a><a class="headerlink" href="#trivial-constant-folding" title="Permalink to this headline">¶</a></h2>
+<p><strong>Note:</strong> the default <tt class="docutils literal"><span class="pre">IRBuilder</span></tt> now always includes the constant
+folding optimisations below.</p>
+<p>Our demonstration for Chapter 3 is elegant and easy to extend.
+Unfortunately, it does not produce wonderful code. For example, when
+compiling simple code, we don’t get obvious optimizations:</p>
+<div class="highlight-python"><div class="highlight"><pre>ready> def test(x) 1+2+x;
+Read function definition:
+define double @test(double %x) {
+entry:
+ %addtmp = fadd double 1.000000e+00, 2.000000e+00
+ %addtmp1 = fadd double %addtmp, %x
+ ret double %addtmp1
+}
+</pre></div>
+</div>
+<p>This code is a very, very literal transcription of the AST built by
+parsing the input. As such, this transcription lacks optimizations like
+constant folding (we’d like to get “<tt class="docutils literal"><span class="pre">add</span> <span class="pre">x,</span> <span class="pre">3.0</span></tt>” in the example
+above) as well as other more important optimizations. Constant folding,
+in particular, is a very common and very important optimization: so much
+so that many language implementors implement constant folding support in
+their AST representation.</p>
+<p>With LLVM, you don’t need this support in the AST. Since all calls to
+build LLVM IR go through the LLVM builder, it would be nice if the
+builder itself checked to see if there was a constant folding
+opportunity when you call it. If so, it could just do the constant fold
+and return the constant instead of creating an instruction. This is
+exactly what the <tt class="docutils literal"><span class="pre">LLVMFoldingBuilder</span></tt> class does.</p>
+<p>All we did was switch from <tt class="docutils literal"><span class="pre">LLVMBuilder</span></tt> to <tt class="docutils literal"><span class="pre">LLVMFoldingBuilder</span></tt>.
+Though we change no other code, we now have all of our instructions
+implicitly constant folded without us having to do anything about it.
+For example, the input above now compiles to:</p>
+<div class="highlight-python"><div class="highlight"><pre>ready> def test(x) 1+2+x;
+Read function definition:
+define double @test(double %x) {
+entry:
+ %addtmp = fadd double 3.000000e+00, %x
+ ret double %addtmp
+}
+</pre></div>
+</div>
+<p>Well, that was easy :). In practice, we recommend always using
+<tt class="docutils literal"><span class="pre">LLVMFoldingBuilder</span></tt> when generating code like this. It has no
+“syntactic overhead” for its use (you don’t have to uglify your compiler
+with constant checks everywhere) and it can dramatically reduce the
+amount of LLVM IR that is generated in some cases (particular for
+languages with a macro preprocessor or that use a lot of constants).</p>
+<p>On the other hand, the <tt class="docutils literal"><span class="pre">LLVMFoldingBuilder</span></tt> is limited by the fact
+that it does all of its analysis inline with the code as it is built. If
+you take a slightly more complex example:</p>
+<div class="highlight-python"><div class="highlight"><pre>ready> def test(x) (1+2+x)*(x+(1+2));
+ready> Read function definition:
+define double @test(double %x) {
+entry:
+ %addtmp = fadd double 3.000000e+00, %x
+ %addtmp1 = fadd double %x, 3.000000e+00
+ %multmp = fmul double %addtmp, %addtmp1
+ ret double %multmp
+}
+</pre></div>
+</div>
+<p>In this case, the LHS and RHS of the multiplication are the same value.
+We’d really like to see this generate “<tt class="docutils literal"><span class="pre">tmp</span> <span class="pre">=</span> <span class="pre">x+3;</span> <span class="pre">result</span> <span class="pre">=</span> <span class="pre">tmp*tmp;</span></tt>”
+instead of computing “<tt class="docutils literal"><span class="pre">x*3</span></tt>” twice.</p>
+<p>Unfortunately, no amount of local analysis will be able to detect and
+correct this. This requires two transformations: reassociation of
+expressions (to make the add’s lexically identical) and Common
+Subexpression Elimination (CSE) to delete the redundant add instruction.
+Fortunately, LLVM provides a broad range of optimizations that you can
+use, in the form of “passes”.</p>
+</div>
+<div class="section" id="llvm-optimization-passes">
+<h2><a class="toc-backref" href="#id3">4.3. LLVM Optimization Passes</a><a class="headerlink" href="#llvm-optimization-passes" title="Permalink to this headline">¶</a></h2>
+<p>LLVM provides many optimization passes, which do many different sorts of
+things and have different tradeoffs. Unlike other systems, LLVM doesn’t
+hold to the mistaken notion that one set of optimizations is right for
+all languages and for all situations. LLVM allows a compiler implementor
+to make complete decisions about what optimizations to use, in which
+order, and in what situation.</p>
+<p>As a concrete example, LLVM supports both “whole module” passes, which
+look across as large of body of code as they can (often a whole file,
+but if run at link time, this can be a substantial portion of the whole
+program). It also supports and includes “per-function” passes which just
+operate on a single function at a time, without looking at other
+functions. For more information on passes and how they are run, see the
+<a class="reference external" href="../WritingAnLLVMPass.html">How to Write a Pass</a> document and the
+<a class="reference external" href="../Passes.html">List of LLVM Passes</a>.</p>
+<p>For Kaleidoscope, we are currently generating functions on the fly, one
+at a time, as the user types them in. We aren’t shooting for the
+ultimate optimization experience in this setting, but we also want to
+catch the easy and quick stuff where possible. As such, we will choose
+to run a few per-function optimizations as the user types the function
+in. If we wanted to make a “static Kaleidoscope compiler”, we would use
+exactly the code we have now, except that we would defer running the
+optimizer until the entire file has been parsed.</p>
+<p>In order to get per-function optimizations going, we need to set up a
+<a class="reference external" href="../WritingAnLLVMPass.html#what-passmanager-does">Llvm.PassManager</a> to hold and
+organize the LLVM optimizations that we want to run. Once we have that,
+we can add a set of optimizations to run. The code looks like this:</p>
+<div class="highlight-ocaml"><div class="highlight"><pre><span class="c">(* Create the JIT. *)</span>
+<span class="k">let</span> <span class="n">the_execution_engine</span> <span class="o">=</span> <span class="nn">ExecutionEngine</span><span class="p">.</span><span class="n">create</span> <span class="nn">Codegen</span><span class="p">.</span><span class="n">the_module</span> <span class="k">in</span>
+<span class="k">let</span> <span class="n">the_fpm</span> <span class="o">=</span> <span class="nn">PassManager</span><span class="p">.</span><span class="n">create_function</span> <span class="nn">Codegen</span><span class="p">.</span><span class="n">the_module</span> <span class="k">in</span>
+
+<span class="c">(* Set up the optimizer pipeline. Start with registering info about how the</span>
+<span class="c"> * target lays out data structures. *)</span>
+<span class="nn">DataLayout</span><span class="p">.</span><span class="n">add</span> <span class="o">(</span><span class="nn">ExecutionEngine</span><span class="p">.</span><span class="n">target_data</span> <span class="n">the_execution_engine</span><span class="o">)</span> <span class="n">the_fpm</span><span class="o">;</span>
+
+<span class="c">(* Do simple "peephole" optimizations and bit-twiddling optzn. *)</span>
+<span class="n">add_instruction_combining</span> <span class="n">the_fpm</span><span class="o">;</span>
+
+<span class="c">(* reassociate expressions. *)</span>
+<span class="n">add_reassociation</span> <span class="n">the_fpm</span><span class="o">;</span>
+
+<span class="c">(* Eliminate Common SubExpressions. *)</span>
+<span class="n">add_gvn</span> <span class="n">the_fpm</span><span class="o">;</span>
+
+<span class="c">(* Simplify the control flow graph (deleting unreachable blocks, etc). *)</span>
+<span class="n">add_cfg_simplification</span> <span class="n">the_fpm</span><span class="o">;</span>
+
+<span class="n">ignore</span> <span class="o">(</span><span class="nn">PassManager</span><span class="p">.</span><span class="n">initialize</span> <span class="n">the_fpm</span><span class="o">);</span>
+
+<span class="c">(* Run the main "interpreter loop" now. *)</span>
+<span class="nn">Toplevel</span><span class="p">.</span><span class="n">main_loop</span> <span class="n">the_fpm</span> <span class="n">the_execution_engine</span> <span class="n">stream</span><span class="o">;</span>
+</pre></div>
+</div>
+<p>The meat of the matter here, is the definition of “<tt class="docutils literal"><span class="pre">the_fpm</span></tt>”. It
+requires a pointer to the <tt class="docutils literal"><span class="pre">the_module</span></tt> to construct itself. Once it is
+set up, we use a series of “add” calls to add a bunch of LLVM passes.
+The first pass is basically boilerplate, it adds a pass so that later
+optimizations know how the data structures in the program are laid out.
+The “<tt class="docutils literal"><span class="pre">the_execution_engine</span></tt>” variable is related to the JIT, which we
+will get to in the next section.</p>
+<p>In this case, we choose to add 4 optimization passes. The passes we
+chose here are a pretty standard set of “cleanup” optimizations that are
+useful for a wide variety of code. I won’t delve into what they do but,
+believe me, they are a good starting place :).</p>
+<p>Once the <tt class="docutils literal"><span class="pre">Llvm.PassManager.</span></tt> is set up, we need to make use of it. We
+do this by running it after our newly created function is constructed
+(in <tt class="docutils literal"><span class="pre">Codegen.codegen_func</span></tt>), but before it is returned to the client:</p>
+<div class="highlight-ocaml"><div class="highlight"><pre><span class="k">let</span> <span class="n">codegen_func</span> <span class="n">the_fpm</span> <span class="o">=</span> <span class="k">function</span>
+ <span class="o">...</span>
+ <span class="k">try</span>
+ <span class="k">let</span> <span class="n">ret_val</span> <span class="o">=</span> <span class="n">codegen_expr</span> <span class="n">body</span> <span class="k">in</span>
+
+ <span class="c">(* Finish off the function. *)</span>
+ <span class="k">let</span> <span class="o">_</span> <span class="o">=</span> <span class="n">build_ret</span> <span class="n">ret_val</span> <span class="n">builder</span> <span class="k">in</span>
+
+ <span class="c">(* Validate the generated code, checking for consistency. *)</span>
+ <span class="nn">Llvm_analysis</span><span class="p">.</span><span class="n">assert_valid_function</span> <span class="n">the_function</span><span class="o">;</span>
+
+ <span class="c">(* Optimize the function. *)</span>
+ <span class="k">let</span> <span class="o">_</span> <span class="o">=</span> <span class="nn">PassManager</span><span class="p">.</span><span class="n">run_function</span> <span class="n">the_function</span> <span class="n">the_fpm</span> <span class="k">in</span>
+
+ <span class="n">the_function</span>
+</pre></div>
+</div>
+<p>As you can see, this is pretty straightforward. The <tt class="docutils literal"><span class="pre">the_fpm</span></tt>
+optimizes and updates the LLVM Function* in place, improving
+(hopefully) its body. With this in place, we can try our test above
+again:</p>
+<div class="highlight-python"><div class="highlight"><pre>ready> def test(x) (1+2+x)*(x+(1+2));
+ready> Read function definition:
+define double @test(double %x) {
+entry:
+ %addtmp = fadd double %x, 3.000000e+00
+ %multmp = fmul double %addtmp, %addtmp
+ ret double %multmp
+}
+</pre></div>
+</div>
+<p>As expected, we now get our nicely optimized code, saving a floating
+point add instruction from every execution of this function.</p>
+<p>LLVM provides a wide variety of optimizations that can be used in
+certain circumstances. Some <a class="reference external" href="../Passes.html">documentation about the various
+passes</a> is available, but it isn’t very complete.
+Another good source of ideas can come from looking at the passes that
+<tt class="docutils literal"><span class="pre">Clang</span></tt> runs to get started. The “<tt class="docutils literal"><span class="pre">opt</span></tt>” tool allows you to
+experiment with passes from the command line, so you can see if they do
+anything.</p>
+<p>Now that we have reasonable code coming out of our front-end, lets talk
+about executing it!</p>
+</div>
+<div class="section" id="adding-a-jit-compiler">
+<h2><a class="toc-backref" href="#id4">4.4. Adding a JIT Compiler</a><a class="headerlink" href="#adding-a-jit-compiler" title="Permalink to this headline">¶</a></h2>
+<p>Code that is available in LLVM IR can have a wide variety of tools
+applied to it. For example, you can run optimizations on it (as we did
+above), you can dump it out in textual or binary forms, you can compile
+the code to an assembly file (.s) for some target, or you can JIT
+compile it. The nice thing about the LLVM IR representation is that it
+is the “common currency” between many different parts of the compiler.</p>
+<p>In this section, we’ll add JIT compiler support to our interpreter. The
+basic idea that we want for Kaleidoscope is to have the user enter
+function bodies as they do now, but immediately evaluate the top-level
+expressions they type in. For example, if they type in “1 + 2;”, we
+should evaluate and print out 3. If they define a function, they should
+be able to call it from the command line.</p>
+<p>In order to do this, we first declare and initialize the JIT. This is
+done by adding a global variable and a call in <tt class="docutils literal"><span class="pre">main</span></tt>:</p>
+<div class="highlight-ocaml"><div class="highlight"><pre><span class="o">...</span>
+<span class="k">let</span> <span class="n">main</span> <span class="bp">()</span> <span class="o">=</span>
+ <span class="o">...</span>
+ <span class="c">(* Create the JIT. *)</span>
+ <span class="k">let</span> <span class="n">the_execution_engine</span> <span class="o">=</span> <span class="nn">ExecutionEngine</span><span class="p">.</span><span class="n">create</span> <span class="nn">Codegen</span><span class="p">.</span><span class="n">the_module</span> <span class="k">in</span>
+ <span class="o">...</span>
+</pre></div>
+</div>
+<p>This creates an abstract “Execution Engine” which can be either a JIT
+compiler or the LLVM interpreter. LLVM will automatically pick a JIT
+compiler for you if one is available for your platform, otherwise it
+will fall back to the interpreter.</p>
+<p>Once the <tt class="docutils literal"><span class="pre">Llvm_executionengine.ExecutionEngine.t</span></tt> is created, the JIT
+is ready to be used. There are a variety of APIs that are useful, but
+the simplest one is the
+“<tt class="docutils literal"><span class="pre">Llvm_executionengine.ExecutionEngine.run_function</span></tt>” function. This
+method JIT compiles the specified LLVM Function and returns a function
+pointer to the generated machine code. In our case, this means that we
+can change the code that parses a top-level expression to look like
+this:</p>
+<div class="highlight-ocaml"><div class="highlight"><pre><span class="c">(* Evaluate a top-level expression into an anonymous function. *)</span>
+<span class="k">let</span> <span class="n">e</span> <span class="o">=</span> <span class="nn">Parser</span><span class="p">.</span><span class="n">parse_toplevel</span> <span class="n">stream</span> <span class="k">in</span>
+<span class="n">print_endline</span> <span class="s2">"parsed a top-level expr"</span><span class="o">;</span>
+<span class="k">let</span> <span class="n">the_function</span> <span class="o">=</span> <span class="nn">Codegen</span><span class="p">.</span><span class="n">codegen_func</span> <span class="n">the_fpm</span> <span class="n">e</span> <span class="k">in</span>
+<span class="n">dump_value</span> <span class="n">the_function</span><span class="o">;</span>
+
+<span class="c">(* JIT the function, returning a function pointer. *)</span>
+<span class="k">let</span> <span class="n">result</span> <span class="o">=</span> <span class="nn">ExecutionEngine</span><span class="p">.</span><span class="n">run_function</span> <span class="n">the_function</span> <span class="o">[||]</span>
+ <span class="n">the_execution_engine</span> <span class="k">in</span>
+
+<span class="n">print_string</span> <span class="s2">"Evaluated to "</span><span class="o">;</span>
+<span class="n">print_float</span> <span class="o">(</span><span class="nn">GenericValue</span><span class="p">.</span><span class="n">as_float</span> <span class="nn">Codegen</span><span class="p">.</span><span class="n">double_type</span> <span class="n">result</span><span class="o">);</span>
+<span class="n">print_newline</span> <span class="bp">()</span><span class="o">;</span>
+</pre></div>
+</div>
+<p>Recall that we compile top-level expressions into a self-contained LLVM
+function that takes no arguments and returns the computed double.
+Because the LLVM JIT compiler matches the native platform ABI, this
+means that you can just cast the result pointer to a function pointer of
+that type and call it directly. This means, there is no difference
+between JIT compiled code and native machine code that is statically
+linked into your application.</p>
+<p>With just these two changes, lets see how Kaleidoscope works now!</p>
+<div class="highlight-python"><div class="highlight"><pre>ready> 4+5;
+define double @""() {
+entry:
+ ret double 9.000000e+00
+}
+
+Evaluated to 9.000000
+</pre></div>
+</div>
+<p>Well this looks like it is basically working. The dump of the function
+shows the “no argument function that always returns double” that we
+synthesize for each top level expression that is typed in. This
+demonstrates very basic functionality, but can we do more?</p>
+<div class="highlight-python"><div class="highlight"><pre>ready> def testfunc(x y) x + y*2;
+Read function definition:
+define double @testfunc(double %x, double %y) {
+entry:
+ %multmp = fmul double %y, 2.000000e+00
+ %addtmp = fadd double %multmp, %x
+ ret double %addtmp
+}
+
+ready> testfunc(4, 10);
+define double @""() {
+entry:
+ %calltmp = call double @testfunc(double 4.000000e+00, double 1.000000e+01)
+ ret double %calltmp
+}
+
+Evaluated to 24.000000
+</pre></div>
+</div>
+<p>This illustrates that we can now call user code, but there is something
+a bit subtle going on here. Note that we only invoke the JIT on the
+anonymous functions that <em>call testfunc</em>, but we never invoked it on
+<em>testfunc</em> itself. What actually happened here is that the JIT scanned
+for all non-JIT’d functions transitively called from the anonymous
+function and compiled all of them before returning from
+<tt class="docutils literal"><span class="pre">run_function</span></tt>.</p>
+<p>The JIT provides a number of other more advanced interfaces for things
+like freeing allocated machine code, rejit’ing functions to update them,
+etc. However, even with this simple code, we get some surprisingly
+powerful capabilities - check this out (I removed the dump of the
+anonymous functions, you should get the idea by now :) :</p>
+<div class="highlight-python"><div class="highlight"><pre>ready> extern sin(x);
+Read extern:
+declare double @sin(double)
+
+ready> extern cos(x);
+Read extern:
+declare double @cos(double)
+
+ready> sin(1.0);
+Evaluated to 0.841471
+
+ready> def foo(x) sin(x)*sin(x) + cos(x)*cos(x);
+Read function definition:
+define double @foo(double %x) {
+entry:
+ %calltmp = call double @sin(double %x)
+ %multmp = fmul double %calltmp, %calltmp
+ %calltmp2 = call double @cos(double %x)
+ %multmp4 = fmul double %calltmp2, %calltmp2
+ %addtmp = fadd double %multmp, %multmp4
+ ret double %addtmp
+}
+
+ready> foo(4.0);
+Evaluated to 1.000000
+</pre></div>
+</div>
+<p>Whoa, how does the JIT know about sin and cos? The answer is
+surprisingly simple: in this example, the JIT started execution of a
+function and got to a function call. It realized that the function was
+not yet JIT compiled and invoked the standard set of routines to resolve
+the function. In this case, there is no body defined for the function,
+so the JIT ended up calling “<tt class="docutils literal"><span class="pre">dlsym("sin")</span></tt>” on the Kaleidoscope
+process itself. Since “<tt class="docutils literal"><span class="pre">sin</span></tt>” is defined within the JIT’s address
+space, it simply patches up calls in the module to call the libm version
+of <tt class="docutils literal"><span class="pre">sin</span></tt> directly.</p>
+<p>The LLVM JIT provides a number of interfaces (look in the
+<tt class="docutils literal"><span class="pre">llvm_executionengine.mli</span></tt> file) for controlling how unknown functions
+get resolved. It allows you to establish explicit mappings between IR
+objects and addresses (useful for LLVM global variables that you want to
+map to static tables, for example), allows you to dynamically decide on
+the fly based on the function name, and even allows you to have the JIT
+compile functions lazily the first time they’re called.</p>
+<p>One interesting application of this is that we can now extend the
+language by writing arbitrary C code to implement operations. For
+example, if we add:</p>
+<div class="highlight-c++"><div class="highlight"><pre><span class="cm">/* putchard - putchar that takes a double and returns 0. */</span>
+<span class="k">extern</span> <span class="s">"C"</span>
+<span class="kt">double</span> <span class="n">putchard</span><span class="p">(</span><span class="kt">double</span> <span class="n">X</span><span class="p">)</span> <span class="p">{</span>
+ <span class="n">putchar</span><span class="p">((</span><span class="kt">char</span><span class="p">)</span><span class="n">X</span><span class="p">);</span>
+ <span class="k">return</span> <span class="mi">0</span><span class="p">;</span>
+<span class="p">}</span>
+</pre></div>
+</div>
+<p>Now we can produce simple output to the console by using things like:
+“<tt class="docutils literal"><span class="pre">extern</span> <span class="pre">putchard(x);</span> <span class="pre">putchard(120);</span></tt>”, which prints a lowercase ‘x’
+on the console (120 is the ASCII code for ‘x’). Similar code could be
+used to implement file I/O, console input, and many other capabilities
+in Kaleidoscope.</p>
+<p>This completes the JIT and optimizer chapter of the Kaleidoscope
+tutorial. At this point, we can compile a non-Turing-complete
+programming language, optimize and JIT compile it in a user-driven way.
+Next up we’ll look into <a class="reference external" href="OCamlLangImpl5.html">extending the language with control flow
+constructs</a>, tackling some interesting LLVM IR
+issues along the way.</p>
+</div>
+<div class="section" id="full-code-listing">
+<h2><a class="toc-backref" href="#id5">4.5. Full Code Listing</a><a class="headerlink" href="#full-code-listing" title="Permalink to this headline">¶</a></h2>
+<p>Here is the complete code listing for our running example, enhanced with
+the LLVM JIT and optimizer. To build this example, use:</p>
+<div class="highlight-bash"><div class="highlight"><pre><span class="c"># Compile</span>
+ocamlbuild toy.byte
+<span class="c"># Run</span>
+./toy.byte
+</pre></div>
+</div>
+<p>Here is the code:</p>
+<dl class="docutils">
+<dt>_tags:</dt>
+<dd><div class="first last highlight-python"><div class="highlight"><pre><{lexer,parser}.ml>: use_camlp4, pp(camlp4of)
+<*.{byte,native}>: g++, use_llvm, use_llvm_analysis
+<*.{byte,native}>: use_llvm_executionengine, use_llvm_target
+<*.{byte,native}>: use_llvm_scalar_opts, use_bindings
+</pre></div>
+</div>
+</dd>
+<dt>myocamlbuild.ml:</dt>
+<dd><div class="first last highlight-ocaml"><div class="highlight"><pre><span class="k">open</span> <span class="nc">Ocamlbuild_plugin</span><span class="o">;;</span>
+
+<span class="n">ocaml_lib</span> <span class="o">~</span><span class="n">extern</span><span class="o">:</span><span class="bp">true</span> <span class="s2">"llvm"</span><span class="o">;;</span>
+<span class="n">ocaml_lib</span> <span class="o">~</span><span class="n">extern</span><span class="o">:</span><span class="bp">true</span> <span class="s2">"llvm_analysis"</span><span class="o">;;</span>
+<span class="n">ocaml_lib</span> <span class="o">~</span><span class="n">extern</span><span class="o">:</span><span class="bp">true</span> <span class="s2">"llvm_executionengine"</span><span class="o">;;</span>
+<span class="n">ocaml_lib</span> <span class="o">~</span><span class="n">extern</span><span class="o">:</span><span class="bp">true</span> <span class="s2">"llvm_target"</span><span class="o">;;</span>
+<span class="n">ocaml_lib</span> <span class="o">~</span><span class="n">extern</span><span class="o">:</span><span class="bp">true</span> <span class="s2">"llvm_scalar_opts"</span><span class="o">;;</span>
+
+<span class="n">flag</span> <span class="o">[</span><span class="s2">"link"</span><span class="o">;</span> <span class="s2">"ocaml"</span><span class="o">;</span> <span class="s2">"g++"</span><span class="o">]</span> <span class="o">(</span><span class="nc">S</span><span class="o">[</span><span class="nc">A</span><span class="s2">"-cc"</span><span class="o">;</span> <span class="nc">A</span><span class="s2">"g++"</span><span class="o">]);;</span>
+<span class="n">dep</span> <span class="o">[</span><span class="s2">"link"</span><span class="o">;</span> <span class="s2">"ocaml"</span><span class="o">;</span> <span class="s2">"use_bindings"</span><span class="o">]</span> <span class="o">[</span><span class="s2">"bindings.o"</span><span class="o">];;</span>
+</pre></div>
+</div>
+</dd>
+<dt>token.ml:</dt>
+<dd><div class="first last highlight-ocaml"><div class="highlight"><pre><span class="c">(*===----------------------------------------------------------------------===</span>
+<span class="c"> * Lexer Tokens</span>
+<span class="c"> *===----------------------------------------------------------------------===*)</span>
+
+<span class="c">(* The lexer returns these 'Kwd' if it is an unknown character, otherwise one of</span>
+<span class="c"> * these others for known things. *)</span>
+<span class="k">type</span> <span class="n">token</span> <span class="o">=</span>
+ <span class="c">(* commands *)</span>
+ <span class="o">|</span> <span class="nc">Def</span> <span class="o">|</span> <span class="nc">Extern</span>
+
+ <span class="c">(* primary *)</span>
+ <span class="o">|</span> <span class="nc">Ident</span> <span class="k">of</span> <span class="kt">string</span> <span class="o">|</span> <span class="nc">Number</span> <span class="k">of</span> <span class="kt">float</span>
+
+ <span class="c">(* unknown *)</span>
+ <span class="o">|</span> <span class="nc">Kwd</span> <span class="k">of</span> <span class="kt">char</span>
+</pre></div>
+</div>
+</dd>
+<dt>lexer.ml:</dt>
+<dd><div class="first last highlight-ocaml"><div class="highlight"><pre><span class="c">(*===----------------------------------------------------------------------===</span>
+<span class="c"> * Lexer</span>
+<span class="c"> *===----------------------------------------------------------------------===*)</span>
+
+<span class="k">let</span> <span class="k">rec</span> <span class="n">lex</span> <span class="o">=</span> <span class="n">parser</span>
+ <span class="c">(* Skip any whitespace. *)</span>
+ <span class="o">|</span> <span class="o">[<</span> <span class="k">'</span> <span class="o">(</span><span class="sc">' '</span> <span class="o">|</span> <span class="sc">'\n'</span> <span class="o">|</span> <span class="sc">'\r'</span> <span class="o">|</span> <span class="sc">'\t'</span><span class="o">);</span> <span class="n">stream</span> <span class="o">>]</span> <span class="o">-></span> <span class="n">lex</span> <span class="n">stream</span>
+
+ <span class="c">(* identifier: [a-zA-Z][a-zA-Z0-9] *)</span>
+ <span class="o">|</span> <span class="o">[<</span> <span class="k">'</span> <span class="o">(</span><span class="sc">'A'</span> <span class="o">..</span> <span class="sc">'Z'</span> <span class="o">|</span> <span class="sc">'a'</span> <span class="o">..</span> <span class="sc">'z'</span> <span class="k">as</span> <span class="n">c</span><span class="o">);</span> <span class="n">stream</span> <span class="o">>]</span> <span class="o">-></span>
+ <span class="k">let</span> <span class="n">buffer</span> <span class="o">=</span> <span class="nn">Buffer</span><span class="p">.</span><span class="n">create</span> <span class="mi">1</span> <span class="k">in</span>
+ <span class="nn">Buffer</span><span class="p">.</span><span class="n">add_char</span> <span class="n">buffer</span> <span class="n">c</span><span class="o">;</span>
+ <span class="n">lex_ident</span> <span class="n">buffer</span> <span class="n">stream</span>
+
+ <span class="c">(* number: [0-9.]+ *)</span>
+ <span class="o">|</span> <span class="o">[<</span> <span class="k">'</span> <span class="o">(</span><span class="sc">'0'</span> <span class="o">..</span> <span class="sc">'9'</span> <span class="k">as</span> <span class="n">c</span><span class="o">);</span> <span class="n">stream</span> <span class="o">>]</span> <span class="o">-></span>
+ <span class="k">let</span> <span class="n">buffer</span> <span class="o">=</span> <span class="nn">Buffer</span><span class="p">.</span><span class="n">create</span> <span class="mi">1</span> <span class="k">in</span>
+ <span class="nn">Buffer</span><span class="p">.</span><span class="n">add_char</span> <span class="n">buffer</span> <span class="n">c</span><span class="o">;</span>
+ <span class="n">lex_number</span> <span class="n">buffer</span> <span class="n">stream</span>
+
+ <span class="c">(* Comment until end of line. *)</span>
+ <span class="o">|</span> <span class="o">[<</span> <span class="k">'</span> <span class="o">(</span><span class="sc">'#'</span><span class="o">);</span> <span class="n">stream</span> <span class="o">>]</span> <span class="o">-></span>
+ <span class="n">lex_comment</span> <span class="n">stream</span>
+
+ <span class="c">(* Otherwise, just return the character as its ascii value. *)</span>
+ <span class="o">|</span> <span class="o">[<</span> <span class="k">'</span><span class="n">c</span><span class="o">;</span> <span class="n">stream</span> <span class="o">>]</span> <span class="o">-></span>
+ <span class="o">[<</span> <span class="k">'</span><span class="nn">Token</span><span class="p">.</span><span class="nc">Kwd</span> <span class="n">c</span><span class="o">;</span> <span class="n">lex</span> <span class="n">stream</span> <span class="o">>]</span>
+
+ <span class="c">(* end of stream. *)</span>
+ <span class="o">|</span> <span class="o">[<</span> <span class="o">>]</span> <span class="o">-></span> <span class="o">[<</span> <span class="o">>]</span>
+
+<span class="ow">and</span> <span class="n">lex_number</span> <span class="n">buffer</span> <span class="o">=</span> <span class="n">parser</span>
+ <span class="o">|</span> <span class="o">[<</span> <span class="k">'</span> <span class="o">(</span><span class="sc">'0'</span> <span class="o">..</span> <span class="sc">'9'</span> <span class="o">|</span> <span class="sc">'.'</span> <span class="k">as</span> <span class="n">c</span><span class="o">);</span> <span class="n">stream</span> <span class="o">>]</span> <span class="o">-></span>
+ <span class="nn">Buffer</span><span class="p">.</span><span class="n">add_char</span> <span class="n">buffer</span> <span class="n">c</span><span class="o">;</span>
+ <span class="n">lex_number</span> <span class="n">buffer</span> <span class="n">stream</span>
+ <span class="o">|</span> <span class="o">[<</span> <span class="n">stream</span><span class="o">=</span><span class="n">lex</span> <span class="o">>]</span> <span class="o">-></span>
+ <span class="o">[<</span> <span class="k">'</span><span class="nn">Token</span><span class="p">.</span><span class="nc">Number</span> <span class="o">(</span><span class="n">float_of_string</span> <span class="o">(</span><span class="nn">Buffer</span><span class="p">.</span><span class="n">contents</span> <span class="n">buffer</span><span class="o">));</span> <span class="n">stream</span> <span class="o">>]</span>
+
+<span class="ow">and</span> <span class="n">lex_ident</span> <span class="n">buffer</span> <span class="o">=</span> <span class="n">parser</span>
+ <span class="o">|</span> <span class="o">[<</span> <span class="k">'</span> <span class="o">(</span><span class="sc">'A'</span> <span class="o">..</span> <span class="sc">'Z'</span> <span class="o">|</span> <span class="sc">'a'</span> <span class="o">..</span> <span class="sc">'z'</span> <span class="o">|</span> <span class="sc">'0'</span> <span class="o">..</span> <span class="sc">'9'</span> <span class="k">as</span> <span class="n">c</span><span class="o">);</span> <span class="n">stream</span> <span class="o">>]</span> <span class="o">-></span>
+ <span class="nn">Buffer</span><span class="p">.</span><span class="n">add_char</span> <span class="n">buffer</span> <span class="n">c</span><span class="o">;</span>
+ <span class="n">lex_ident</span> <span class="n">buffer</span> <span class="n">stream</span>
+ <span class="o">|</span> <span class="o">[<</span> <span class="n">stream</span><span class="o">=</span><span class="n">lex</span> <span class="o">>]</span> <span class="o">-></span>
+ <span class="k">match</span> <span class="nn">Buffer</span><span class="p">.</span><span class="n">contents</span> <span class="n">buffer</span> <span class="k">with</span>
+ <span class="o">|</span> <span class="s2">"def"</span> <span class="o">-></span> <span class="o">[<</span> <span class="k">'</span><span class="nn">Token</span><span class="p">.</span><span class="nc">Def</span><span class="o">;</span> <span class="n">stream</span> <span class="o">>]</span>
+ <span class="o">|</span> <span class="s2">"extern"</span> <span class="o">-></span> <span class="o">[<</span> <span class="k">'</span><span class="nn">Token</span><span class="p">.</span><span class="nc">Extern</span><span class="o">;</span> <span class="n">stream</span> <span class="o">>]</span>
+ <span class="o">|</span> <span class="n">id</span> <span class="o">-></span> <span class="o">[<</span> <span class="k">'</span><span class="nn">Token</span><span class="p">.</span><span class="nc">Ident</span> <span class="n">id</span><span class="o">;</span> <span class="n">stream</span> <span class="o">>]</span>
+
+<span class="ow">and</span> <span class="n">lex_comment</span> <span class="o">=</span> <span class="n">parser</span>
+ <span class="o">|</span> <span class="o">[<</span> <span class="k">'</span> <span class="o">(</span><span class="sc">'\n'</span><span class="o">);</span> <span class="n">stream</span><span class="o">=</span><span class="n">lex</span> <span class="o">>]</span> <span class="o">-></span> <span class="n">stream</span>
+ <span class="o">|</span> <span class="o">[<</span> <span class="k">'</span><span class="n">c</span><span class="o">;</span> <span class="n">e</span><span class="o">=</span><span class="n">lex_comment</span> <span class="o">>]</span> <span class="o">-></span> <span class="n">e</span>
+ <span class="o">|</span> <span class="o">[<</span> <span class="o">>]</span> <span class="o">-></span> <span class="o">[<</span> <span class="o">>]</span>
+</pre></div>
+</div>
+</dd>
+<dt>ast.ml:</dt>
+<dd><div class="first last highlight-ocaml"><div class="highlight"><pre><span class="c">(*===----------------------------------------------------------------------===</span>
+<span class="c"> * Abstract Syntax Tree (aka Parse Tree)</span>
+<span class="c"> *===----------------------------------------------------------------------===*)</span>
+
+<span class="c">(* expr - Base type for all expression nodes. *)</span>
+<span class="k">type</span> <span class="n">expr</span> <span class="o">=</span>
+ <span class="c">(* variant for numeric literals like "1.0". *)</span>
+ <span class="o">|</span> <span class="nc">Number</span> <span class="k">of</span> <span class="kt">float</span>
+
+ <span class="c">(* variant for referencing a variable, like "a". *)</span>
+ <span class="o">|</span> <span class="nc">Variable</span> <span class="k">of</span> <span class="kt">string</span>
+
+ <span class="c">(* variant for a binary operator. *)</span>
+ <span class="o">|</span> <span class="nc">Binary</span> <span class="k">of</span> <span class="kt">char</span> <span class="o">*</span> <span class="n">expr</span> <span class="o">*</span> <span class="n">expr</span>
+
+ <span class="c">(* variant for function calls. *)</span>
+ <span class="o">|</span> <span class="nc">Call</span> <span class="k">of</span> <span class="kt">string</span> <span class="o">*</span> <span class="n">expr</span> <span class="kt">array</span>
+
+<span class="c">(* proto - This type represents the "prototype" for a function, which captures</span>
+<span class="c"> * its name, and its argument names (thus implicitly the number of arguments the</span>
+<span class="c"> * function takes). *)</span>
+<span class="k">type</span> <span class="n">proto</span> <span class="o">=</span> <span class="nc">Prototype</span> <span class="k">of</span> <span class="kt">string</span> <span class="o">*</span> <span class="kt">string</span> <span class="kt">array</span>
+
+<span class="c">(* func - This type represents a function definition itself. *)</span>
+<span class="k">type</span> <span class="n">func</span> <span class="o">=</span> <span class="nc">Function</span> <span class="k">of</span> <span class="n">proto</span> <span class="o">*</span> <span class="n">expr</span>
+</pre></div>
+</div>
+</dd>
+<dt>parser.ml:</dt>
+<dd><div class="first last highlight-ocaml"><div class="highlight"><pre><span class="c">(*===---------------------------------------------------------------------===</span>
+<span class="c"> * Parser</span>
+<span class="c"> *===---------------------------------------------------------------------===*)</span>
+
+<span class="c">(* binop_precedence - This holds the precedence for each binary operator that is</span>
+<span class="c"> * defined *)</span>
+<span class="k">let</span> <span class="n">binop_precedence</span><span class="o">:(</span><span class="kt">char</span><span class="o">,</span> <span class="kt">int</span><span class="o">)</span> <span class="nn">Hashtbl</span><span class="p">.</span><span class="n">t</span> <span class="o">=</span> <span class="nn">Hashtbl</span><span class="p">.</span><span class="n">create</span> <span class="mi">10</span>
+
+<span class="c">(* precedence - Get the precedence of the pending binary operator token. *)</span>
+<span class="k">let</span> <span class="n">precedence</span> <span class="n">c</span> <span class="o">=</span> <span class="k">try</span> <span class="nn">Hashtbl</span><span class="p">.</span><span class="n">find</span> <span class="n">binop_precedence</span> <span class="n">c</span> <span class="k">with</span> <span class="nc">Not_found</span> <span class="o">-></span> <span class="o">-</span><span class="mi">1</span>
+
+<span class="c">(* primary</span>
+<span class="c"> * ::= identifier</span>
+<span class="c"> * ::= numberexpr</span>
+<span class="c"> * ::= parenexpr *)</span>
+<span class="k">let</span> <span class="k">rec</span> <span class="n">parse_primary</span> <span class="o">=</span> <span class="n">parser</span>
+ <span class="c">(* numberexpr ::= number *)</span>
+ <span class="o">|</span> <span class="o">[<</span> <span class="k">'</span><span class="nn">Token</span><span class="p">.</span><span class="nc">Number</span> <span class="n">n</span> <span class="o">>]</span> <span class="o">-></span> <span class="nn">Ast</span><span class="p">.</span><span class="nc">Number</span> <span class="n">n</span>
+
+ <span class="c">(* parenexpr ::= '(' expression ')' *)</span>
+ <span class="o">|</span> <span class="o">[<</span> <span class="k">'</span><span class="nn">Token</span><span class="p">.</span><span class="nc">Kwd</span> <span class="sc">'('</span><span class="o">;</span> <span class="n">e</span><span class="o">=</span><span class="n">parse_expr</span><span class="o">;</span> <span class="k">'</span><span class="nn">Token</span><span class="p">.</span><span class="nc">Kwd</span> <span class="sc">')'</span> <span class="o">??</span> <span class="s2">"expected ')'"</span> <span class="o">>]</span> <span class="o">-></span> <span class="n">e</span>
+
+ <span class="c">(* identifierexpr</span>
+<span class="c"> * ::= identifier</span>
+<span class="c"> * ::= identifier '(' argumentexpr ')' *)</span>
+ <span class="o">|</span> <span class="o">[<</span> <span class="k">'</span><span class="nn">Token</span><span class="p">.</span><span class="nc">Ident</span> <span class="n">id</span><span class="o">;</span> <span class="n">stream</span> <span class="o">>]</span> <span class="o">-></span>
+ <span class="k">let</span> <span class="k">rec</span> <span class="n">parse_args</span> <span class="n">accumulator</span> <span class="o">=</span> <span class="n">parser</span>
+ <span class="o">|</span> <span class="o">[<</span> <span class="n">e</span><span class="o">=</span><span class="n">parse_expr</span><span class="o">;</span> <span class="n">stream</span> <span class="o">>]</span> <span class="o">-></span>
+ <span class="k">begin</span> <span class="n">parser</span>
+ <span class="o">|</span> <span class="o">[<</span> <span class="k">'</span><span class="nn">Token</span><span class="p">.</span><span class="nc">Kwd</span> <span class="sc">','</span><span class="o">;</span> <span class="n">e</span><span class="o">=</span><span class="n">parse_args</span> <span class="o">(</span><span class="n">e</span> <span class="o">::</span> <span class="n">accumulator</span><span class="o">)</span> <span class="o">>]</span> <span class="o">-></span> <span class="n">e</span>
+ <span class="o">|</span> <span class="o">[<</span> <span class="o">>]</span> <span class="o">-></span> <span class="n">e</span> <span class="o">::</span> <span class="n">accumulator</span>
+ <span class="k">end</span> <span class="n">stream</span>
+ <span class="o">|</span> <span class="o">[<</span> <span class="o">>]</span> <span class="o">-></span> <span class="n">accumulator</span>
+ <span class="k">in</span>
+ <span class="k">let</span> <span class="k">rec</span> <span class="n">parse_ident</span> <span class="n">id</span> <span class="o">=</span> <span class="n">parser</span>
+ <span class="c">(* Call. *)</span>
+ <span class="o">|</span> <span class="o">[<</span> <span class="k">'</span><span class="nn">Token</span><span class="p">.</span><span class="nc">Kwd</span> <span class="sc">'('</span><span class="o">;</span>
+ <span class="n">args</span><span class="o">=</span><span class="n">parse_args</span> <span class="bp">[]</span><span class="o">;</span>
+ <span class="k">'</span><span class="nn">Token</span><span class="p">.</span><span class="nc">Kwd</span> <span class="sc">')'</span> <span class="o">??</span> <span class="s2">"expected ')'"</span><span class="o">>]</span> <span class="o">-></span>
+ <span class="nn">Ast</span><span class="p">.</span><span class="nc">Call</span> <span class="o">(</span><span class="n">id</span><span class="o">,</span> <span class="nn">Array</span><span class="p">.</span><span class="n">of_list</span> <span class="o">(</span><span class="nn">List</span><span class="p">.</span><span class="n">rev</span> <span class="n">args</span><span class="o">))</span>
+
+ <span class="c">(* Simple variable ref. *)</span>
+ <span class="o">|</span> <span class="o">[<</span> <span class="o">>]</span> <span class="o">-></span> <span class="nn">Ast</span><span class="p">.</span><span class="nc">Variable</span> <span class="n">id</span>
+ <span class="k">in</span>
+ <span class="n">parse_ident</span> <span class="n">id</span> <span class="n">stream</span>
+
+ <span class="o">|</span> <span class="o">[<</span> <span class="o">>]</span> <span class="o">-></span> <span class="k">raise</span> <span class="o">(</span><span class="nn">Stream</span><span class="p">.</span><span class="nc">Error</span> <span class="s2">"unknown token when expecting an expression."</span><span class="o">)</span>
+
+<span class="c">(* binoprhs</span>
+<span class="c"> * ::= ('+' primary)* *)</span>
+<span class="ow">and</span> <span class="n">parse_bin_rhs</span> <span class="n">expr_prec</span> <span class="n">lhs</span> <span class="n">stream</span> <span class="o">=</span>
+ <span class="k">match</span> <span class="nn">Stream</span><span class="p">.</span><span class="n">peek</span> <span class="n">stream</span> <span class="k">with</span>
+ <span class="c">(* If this is a binop, find its precedence. *)</span>
+ <span class="o">|</span> <span class="nc">Some</span> <span class="o">(</span><span class="nn">Token</span><span class="p">.</span><span class="nc">Kwd</span> <span class="n">c</span><span class="o">)</span> <span class="k">when</span> <span class="nn">Hashtbl</span><span class="p">.</span><span class="n">mem</span> <span class="n">binop_precedence</span> <span class="n">c</span> <span class="o">-></span>
+ <span class="k">let</span> <span class="n">token_prec</span> <span class="o">=</span> <span class="n">precedence</span> <span class="n">c</span> <span class="k">in</span>
+
+ <span class="c">(* If this is a binop that binds at least as tightly as the current binop,</span>
+<span class="c"> * consume it, otherwise we are done. *)</span>
+ <span class="k">if</span> <span class="n">token_prec</span> <span class="o"><</span> <span class="n">expr_prec</span> <span class="k">then</span> <span class="n">lhs</span> <span class="k">else</span> <span class="k">begin</span>
+ <span class="c">(* Eat the binop. *)</span>
+ <span class="nn">Stream</span><span class="p">.</span><span class="n">junk</span> <span class="n">stream</span><span class="o">;</span>
+
+ <span class="c">(* Parse the primary expression after the binary operator. *)</span>
+ <span class="k">let</span> <span class="n">rhs</span> <span class="o">=</span> <span class="n">parse_primary</span> <span class="n">stream</span> <span class="k">in</span>
+
+ <span class="c">(* Okay, we know this is a binop. *)</span>
+ <span class="k">let</span> <span class="n">rhs</span> <span class="o">=</span>
+ <span class="k">match</span> <span class="nn">Stream</span><span class="p">.</span><span class="n">peek</span> <span class="n">stream</span> <span class="k">with</span>
+ <span class="o">|</span> <span class="nc">Some</span> <span class="o">(</span><span class="nn">Token</span><span class="p">.</span><span class="nc">Kwd</span> <span class="n">c2</span><span class="o">)</span> <span class="o">-></span>
+ <span class="c">(* If BinOp binds less tightly with rhs than the operator after</span>
+<span class="c"> * rhs, let the pending operator take rhs as its lhs. *)</span>
+ <span class="k">let</span> <span class="n">next_prec</span> <span class="o">=</span> <span class="n">precedence</span> <span class="n">c2</span> <span class="k">in</span>
+ <span class="k">if</span> <span class="n">token_prec</span> <span class="o"><</span> <span class="n">next_prec</span>
+ <span class="k">then</span> <span class="n">parse_bin_rhs</span> <span class="o">(</span><span class="n">token_prec</span> <span class="o">+</span> <span class="mi">1</span><span class="o">)</span> <span class="n">rhs</span> <span class="n">stream</span>
+ <span class="k">else</span> <span class="n">rhs</span>
+ <span class="o">|</span> <span class="o">_</span> <span class="o">-></span> <span class="n">rhs</span>
+ <span class="k">in</span>
+
+ <span class="c">(* Merge lhs/rhs. *)</span>
+ <span class="k">let</span> <span class="n">lhs</span> <span class="o">=</span> <span class="nn">Ast</span><span class="p">.</span><span class="nc">Binary</span> <span class="o">(</span><span class="n">c</span><span class="o">,</span> <span class="n">lhs</span><span class="o">,</span> <span class="n">rhs</span><span class="o">)</span> <span class="k">in</span>
+ <span class="n">parse_bin_rhs</span> <span class="n">expr_prec</span> <span class="n">lhs</span> <span class="n">stream</span>
+ <span class="k">end</span>
+ <span class="o">|</span> <span class="o">_</span> <span class="o">-></span> <span class="n">lhs</span>
+
+<span class="c">(* expression</span>
+<span class="c"> * ::= primary binoprhs *)</span>
+<span class="ow">and</span> <span class="n">parse_expr</span> <span class="o">=</span> <span class="n">parser</span>
+ <span class="o">|</span> <span class="o">[<</span> <span class="n">lhs</span><span class="o">=</span><span class="n">parse_primary</span><span class="o">;</span> <span class="n">stream</span> <span class="o">>]</span> <span class="o">-></span> <span class="n">parse_bin_rhs</span> <span class="mi">0</span> <span class="n">lhs</span> <span class="n">stream</span>
+
+<span class="c">(* prototype</span>
+<span class="c"> * ::= id '(' id* ')' *)</span>
+<span class="k">let</span> <span class="n">parse_prototype</span> <span class="o">=</span>
+ <span class="k">let</span> <span class="k">rec</span> <span class="n">parse_args</span> <span class="n">accumulator</span> <span class="o">=</span> <span class="n">parser</span>
+ <span class="o">|</span> <span class="o">[<</span> <span class="k">'</span><span class="nn">Token</span><span class="p">.</span><span class="nc">Ident</span> <span class="n">id</span><span class="o">;</span> <span class="n">e</span><span class="o">=</span><span class="n">parse_args</span> <span class="o">(</span><span class="n">id</span><span class="o">::</span><span class="n">accumulator</span><span class="o">)</span> <span class="o">>]</span> <span class="o">-></span> <span class="n">e</span>
+ <span class="o">|</span> <span class="o">[<</span> <span class="o">>]</span> <span class="o">-></span> <span class="n">accumulator</span>
+ <span class="k">in</span>
+
+ <span class="n">parser</span>
+ <span class="o">|</span> <span class="o">[<</span> <span class="k">'</span><span class="nn">Token</span><span class="p">.</span><span class="nc">Ident</span> <span class="n">id</span><span class="o">;</span>
+ <span class="k">'</span><span class="nn">Token</span><span class="p">.</span><span class="nc">Kwd</span> <span class="sc">'('</span> <span class="o">??</span> <span class="s2">"expected '(' in prototype"</span><span class="o">;</span>
+ <span class="n">args</span><span class="o">=</span><span class="n">parse_args</span> <span class="bp">[]</span><span class="o">;</span>
+ <span class="k">'</span><span class="nn">Token</span><span class="p">.</span><span class="nc">Kwd</span> <span class="sc">')'</span> <span class="o">??</span> <span class="s2">"expected ')' in prototype"</span> <span class="o">>]</span> <span class="o">-></span>
+ <span class="c">(* success. *)</span>
+ <span class="nn">Ast</span><span class="p">.</span><span class="nc">Prototype</span> <span class="o">(</span><span class="n">id</span><span class="o">,</span> <span class="nn">Array</span><span class="p">.</span><span class="n">of_list</span> <span class="o">(</span><span class="nn">List</span><span class="p">.</span><span class="n">rev</span> <span class="n">args</span><span class="o">))</span>
+
+ <span class="o">|</span> <span class="o">[<</span> <span class="o">>]</span> <span class="o">-></span>
+ <span class="k">raise</span> <span class="o">(</span><span class="nn">Stream</span><span class="p">.</span><span class="nc">Error</span> <span class="s2">"expected function name in prototype"</span><span class="o">)</span>
+
+<span class="c">(* definition ::= 'def' prototype expression *)</span>
+<span class="k">let</span> <span class="n">parse_definition</span> <span class="o">=</span> <span class="n">parser</span>
+ <span class="o">|</span> <span class="o">[<</span> <span class="k">'</span><span class="nn">Token</span><span class="p">.</span><span class="nc">Def</span><span class="o">;</span> <span class="n">p</span><span class="o">=</span><span class="n">parse_prototype</span><span class="o">;</span> <span class="n">e</span><span class="o">=</span><span class="n">parse_expr</span> <span class="o">>]</span> <span class="o">-></span>
+ <span class="nn">Ast</span><span class="p">.</span><span class="nc">Function</span> <span class="o">(</span><span class="n">p</span><span class="o">,</span> <span class="n">e</span><span class="o">)</span>
+
+<span class="c">(* toplevelexpr ::= expression *)</span>
+<span class="k">let</span> <span class="n">parse_toplevel</span> <span class="o">=</span> <span class="n">parser</span>
+ <span class="o">|</span> <span class="o">[<</span> <span class="n">e</span><span class="o">=</span><span class="n">parse_expr</span> <span class="o">>]</span> <span class="o">-></span>
+ <span class="c">(* Make an anonymous proto. *)</span>
+ <span class="nn">Ast</span><span class="p">.</span><span class="nc">Function</span> <span class="o">(</span><span class="nn">Ast</span><span class="p">.</span><span class="nc">Prototype</span> <span class="o">(</span><span class="s2">""</span><span class="o">,</span> <span class="o">[||]),</span> <span class="n">e</span><span class="o">)</span>
+
+<span class="c">(* external ::= 'extern' prototype *)</span>
+<span class="k">let</span> <span class="n">parse_extern</span> <span class="o">=</span> <span class="n">parser</span>
+ <span class="o">|</span> <span class="o">[<</span> <span class="k">'</span><span class="nn">Token</span><span class="p">.</span><span class="nc">Extern</span><span class="o">;</span> <span class="n">e</span><span class="o">=</span><span class="n">parse_prototype</span> <span class="o">>]</span> <span class="o">-></span> <span class="n">e</span>
+</pre></div>
+</div>
+</dd>
+<dt>codegen.ml:</dt>
+<dd><div class="first last highlight-ocaml"><div class="highlight"><pre><span class="c">(*===----------------------------------------------------------------------===</span>
+<span class="c"> * Code Generation</span>
+<span class="c"> *===----------------------------------------------------------------------===*)</span>
+
+<span class="k">open</span> <span class="nc">Llvm</span>
+
+<span class="k">exception</span> <span class="nc">Error</span> <span class="k">of</span> <span class="kt">string</span>
+
+<span class="k">let</span> <span class="n">context</span> <span class="o">=</span> <span class="n">global_context</span> <span class="bp">()</span>
+<span class="k">let</span> <span class="n">the_module</span> <span class="o">=</span> <span class="n">create_module</span> <span class="n">context</span> <span class="s2">"my cool jit"</span>
+<span class="k">let</span> <span class="n">builder</span> <span class="o">=</span> <span class="n">builder</span> <span class="n">context</span>
+<span class="k">let</span> <span class="n">named_values</span><span class="o">:(</span><span class="kt">string</span><span class="o">,</span> <span class="n">llvalue</span><span class="o">)</span> <span class="nn">Hashtbl</span><span class="p">.</span><span class="n">t</span> <span class="o">=</span> <span class="nn">Hashtbl</span><span class="p">.</span><span class="n">create</span> <span class="mi">10</span>
+<span class="k">let</span> <span class="n">double_type</span> <span class="o">=</span> <span class="n">double_type</span> <span class="n">context</span>
+
+<span class="k">let</span> <span class="k">rec</span> <span class="n">codegen_expr</span> <span class="o">=</span> <span class="k">function</span>
+ <span class="o">|</span> <span class="nn">Ast</span><span class="p">.</span><span class="nc">Number</span> <span class="n">n</span> <span class="o">-></span> <span class="n">const_float</span> <span class="n">double_type</span> <span class="n">n</span>
+ <span class="o">|</span> <span class="nn">Ast</span><span class="p">.</span><span class="nc">Variable</span> <span class="n">name</span> <span class="o">-></span>
+ <span class="o">(</span><span class="k">try</span> <span class="nn">Hashtbl</span><span class="p">.</span><span class="n">find</span> <span class="n">named_values</span> <span class="n">name</span> <span class="k">with</span>
+ <span class="o">|</span> <span class="nc">Not_found</span> <span class="o">-></span> <span class="k">raise</span> <span class="o">(</span><span class="nc">Error</span> <span class="s2">"unknown variable name"</span><span class="o">))</span>
+ <span class="o">|</span> <span class="nn">Ast</span><span class="p">.</span><span class="nc">Binary</span> <span class="o">(</span><span class="n">op</span><span class="o">,</span> <span class="n">lhs</span><span class="o">,</span> <span class="n">rhs</span><span class="o">)</span> <span class="o">-></span>
+ <span class="k">let</span> <span class="n">lhs_val</span> <span class="o">=</span> <span class="n">codegen_expr</span> <span class="n">lhs</span> <span class="k">in</span>
+ <span class="k">let</span> <span class="n">rhs_val</span> <span class="o">=</span> <span class="n">codegen_expr</span> <span class="n">rhs</span> <span class="k">in</span>
+ <span class="k">begin</span>
+ <span class="k">match</span> <span class="n">op</span> <span class="k">with</span>
+ <span class="o">|</span> <span class="sc">'+'</span> <span class="o">-></span> <span class="n">build_add</span> <span class="n">lhs_val</span> <span class="n">rhs_val</span> <span class="s2">"addtmp"</span> <span class="n">builder</span>
+ <span class="o">|</span> <span class="sc">'-'</span> <span class="o">-></span> <span class="n">build_sub</span> <span class="n">lhs_val</span> <span class="n">rhs_val</span> <span class="s2">"subtmp"</span> <span class="n">builder</span>
+ <span class="o">|</span> <span class="sc">'*'</span> <span class="o">-></span> <span class="n">build_mul</span> <span class="n">lhs_val</span> <span class="n">rhs_val</span> <span class="s2">"multmp"</span> <span class="n">builder</span>
+ <span class="o">|</span> <span class="sc">'<'</span> <span class="o">-></span>
+ <span class="c">(* Convert bool 0/1 to double 0.0 or 1.0 *)</span>
+ <span class="k">let</span> <span class="n">i</span> <span class="o">=</span> <span class="n">build_fcmp</span> <span class="nn">Fcmp</span><span class="p">.</span><span class="nc">Ult</span> <span class="n">lhs_val</span> <span class="n">rhs_val</span> <span class="s2">"cmptmp"</span> <span class="n">builder</span> <span class="k">in</span>
+ <span class="n">build_uitofp</span> <span class="n">i</span> <span class="n">double_type</span> <span class="s2">"booltmp"</span> <span class="n">builder</span>
+ <span class="o">|</span> <span class="o">_</span> <span class="o">-></span> <span class="k">raise</span> <span class="o">(</span><span class="nc">Error</span> <span class="s2">"invalid binary operator"</span><span class="o">)</span>
+ <span class="k">end</span>
+ <span class="o">|</span> <span class="nn">Ast</span><span class="p">.</span><span class="nc">Call</span> <span class="o">(</span><span class="n">callee</span><span class="o">,</span> <span class="n">args</span><span class="o">)</span> <span class="o">-></span>
+ <span class="c">(* Look up the name in the module table. *)</span>
+ <span class="k">let</span> <span class="n">callee</span> <span class="o">=</span>
+ <span class="k">match</span> <span class="n">lookup_function</span> <span class="n">callee</span> <span class="n">the_module</span> <span class="k">with</span>
+ <span class="o">|</span> <span class="nc">Some</span> <span class="n">callee</span> <span class="o">-></span> <span class="n">callee</span>
+ <span class="o">|</span> <span class="nc">None</span> <span class="o">-></span> <span class="k">raise</span> <span class="o">(</span><span class="nc">Error</span> <span class="s2">"unknown function referenced"</span><span class="o">)</span>
+ <span class="k">in</span>
+ <span class="k">let</span> <span class="n">params</span> <span class="o">=</span> <span class="n">params</span> <span class="n">callee</span> <span class="k">in</span>
+
+ <span class="c">(* If argument mismatch error. *)</span>
+ <span class="k">if</span> <span class="nn">Array</span><span class="p">.</span><span class="n">length</span> <span class="n">params</span> <span class="o">==</span> <span class="nn">Array</span><span class="p">.</span><span class="n">length</span> <span class="n">args</span> <span class="k">then</span> <span class="bp">()</span> <span class="k">else</span>
+ <span class="k">raise</span> <span class="o">(</span><span class="nc">Error</span> <span class="s2">"incorrect # arguments passed"</span><span class="o">);</span>
+ <span class="k">let</span> <span class="n">args</span> <span class="o">=</span> <span class="nn">Array</span><span class="p">.</span><span class="n">map</span> <span class="n">codegen_expr</span> <span class="n">args</span> <span class="k">in</span>
+ <span class="n">build_call</span> <span class="n">callee</span> <span class="n">args</span> <span class="s2">"calltmp"</span> <span class="n">builder</span>
+
+<span class="k">let</span> <span class="n">codegen_proto</span> <span class="o">=</span> <span class="k">function</span>
+ <span class="o">|</span> <span class="nn">Ast</span><span class="p">.</span><span class="nc">Prototype</span> <span class="o">(</span><span class="n">name</span><span class="o">,</span> <span class="n">args</span><span class="o">)</span> <span class="o">-></span>
+ <span class="c">(* Make the function type: double(double,double) etc. *)</span>
+ <span class="k">let</span> <span class="n">doubles</span> <span class="o">=</span> <span class="nn">Array</span><span class="p">.</span><span class="n">make</span> <span class="o">(</span><span class="nn">Array</span><span class="p">.</span><span class="n">length</span> <span class="n">args</span><span class="o">)</span> <span class="n">double_type</span> <span class="k">in</span>
+ <span class="k">let</span> <span class="n">ft</span> <span class="o">=</span> <span class="n">function_type</span> <span class="n">double_type</span> <span class="n">doubles</span> <span class="k">in</span>
+ <span class="k">let</span> <span class="n">f</span> <span class="o">=</span>
+ <span class="k">match</span> <span class="n">lookup_function</span> <span class="n">name</span> <span class="n">the_module</span> <span class="k">with</span>
+ <span class="o">|</span> <span class="nc">None</span> <span class="o">-></span> <span class="n">declare_function</span> <span class="n">name</span> <span class="n">ft</span> <span class="n">the_module</span>
+
+ <span class="c">(* If 'f' conflicted, there was already something named 'name'. If it</span>
+<span class="c"> * has a body, don't allow redefinition or reextern. *)</span>
+ <span class="o">|</span> <span class="nc">Some</span> <span class="n">f</span> <span class="o">-></span>
+ <span class="c">(* If 'f' already has a body, reject this. *)</span>
+ <span class="k">if</span> <span class="n">block_begin</span> <span class="n">f</span> <span class="o"><></span> <span class="nc">At_end</span> <span class="n">f</span> <span class="k">then</span>
+ <span class="k">raise</span> <span class="o">(</span><span class="nc">Error</span> <span class="s2">"redefinition of function"</span><span class="o">);</span>
+
+ <span class="c">(* If 'f' took a different number of arguments, reject. *)</span>
+ <span class="k">if</span> <span class="n">element_type</span> <span class="o">(</span><span class="n">type_of</span> <span class="n">f</span><span class="o">)</span> <span class="o"><></span> <span class="n">ft</span> <span class="k">then</span>
+ <span class="k">raise</span> <span class="o">(</span><span class="nc">Error</span> <span class="s2">"redefinition of function with different # args"</span><span class="o">);</span>
+ <span class="n">f</span>
+ <span class="k">in</span>
+
+ <span class="c">(* Set names for all arguments. *)</span>
+ <span class="nn">Array</span><span class="p">.</span><span class="n">iteri</span> <span class="o">(</span><span class="k">fun</span> <span class="n">i</span> <span class="n">a</span> <span class="o">-></span>
+ <span class="k">let</span> <span class="n">n</span> <span class="o">=</span> <span class="n">args</span><span class="o">.(</span><span class="n">i</span><span class="o">)</span> <span class="k">in</span>
+ <span class="n">set_value_name</span> <span class="n">n</span> <span class="n">a</span><span class="o">;</span>
+ <span class="nn">Hashtbl</span><span class="p">.</span><span class="n">add</span> <span class="n">named_values</span> <span class="n">n</span> <span class="n">a</span><span class="o">;</span>
+ <span class="o">)</span> <span class="o">(</span><span class="n">params</span> <span class="n">f</span><span class="o">);</span>
+ <span class="n">f</span>
+
+<span class="k">let</span> <span class="n">codegen_func</span> <span class="n">the_fpm</span> <span class="o">=</span> <span class="k">function</span>
+ <span class="o">|</span> <span class="nn">Ast</span><span class="p">.</span><span class="nc">Function</span> <span class="o">(</span><span class="n">proto</span><span class="o">,</span> <span class="n">body</span><span class="o">)</span> <span class="o">-></span>
+ <span class="nn">Hashtbl</span><span class="p">.</span><span class="n">clear</span> <span class="n">named_values</span><span class="o">;</span>
+ <span class="k">let</span> <span class="n">the_function</span> <span class="o">=</span> <span class="n">codegen_proto</span> <span class="n">proto</span> <span class="k">in</span>
+
+ <span class="c">(* Create a new basic block to start insertion into. *)</span>
+ <span class="k">let</span> <span class="n">bb</span> <span class="o">=</span> <span class="n">append_block</span> <span class="n">context</span> <span class="s2">"entry"</span> <span class="n">the_function</span> <span class="k">in</span>
+ <span class="n">position_at_end</span> <span class="n">bb</span> <span class="n">builder</span><span class="o">;</span>
+
+ <span class="k">try</span>
+ <span class="k">let</span> <span class="n">ret_val</span> <span class="o">=</span> <span class="n">codegen_expr</span> <span class="n">body</span> <span class="k">in</span>
+
+ <span class="c">(* Finish off the function. *)</span>
+ <span class="k">let</span> <span class="o">_</span> <span class="o">=</span> <span class="n">build_ret</span> <span class="n">ret_val</span> <span class="n">builder</span> <span class="k">in</span>
+
+ <span class="c">(* Validate the generated code, checking for consistency. *)</span>
+ <span class="nn">Llvm_analysis</span><span class="p">.</span><span class="n">assert_valid_function</span> <span class="n">the_function</span><span class="o">;</span>
+
+ <span class="c">(* Optimize the function. *)</span>
+ <span class="k">let</span> <span class="o">_</span> <span class="o">=</span> <span class="nn">PassManager</span><span class="p">.</span><span class="n">run_function</span> <span class="n">the_function</span> <span class="n">the_fpm</span> <span class="k">in</span>
+
+ <span class="n">the_function</span>
+ <span class="k">with</span> <span class="n">e</span> <span class="o">-></span>
+ <span class="n">delete_function</span> <span class="n">the_function</span><span class="o">;</span>
+ <span class="k">raise</span> <span class="n">e</span>
+</pre></div>
+</div>
+</dd>
+<dt>toplevel.ml:</dt>
+<dd><div class="first last highlight-ocaml"><div class="highlight"><pre><span class="c">(*===----------------------------------------------------------------------===</span>
+<span class="c"> * Top-Level parsing and JIT Driver</span>
+<span class="c"> *===----------------------------------------------------------------------===*)</span>
+
+<span class="k">open</span> <span class="nc">Llvm</span>
+<span class="k">open</span> <span class="nc">Llvm_executionengine</span>
+
+<span class="c">(* top ::= definition | external | expression | ';' *)</span>
+<span class="k">let</span> <span class="k">rec</span> <span class="n">main_loop</span> <span class="n">the_fpm</span> <span class="n">the_execution_engine</span> <span class="n">stream</span> <span class="o">=</span>
+ <span class="k">match</span> <span class="nn">Stream</span><span class="p">.</span><span class="n">peek</span> <span class="n">stream</span> <span class="k">with</span>
+ <span class="o">|</span> <span class="nc">None</span> <span class="o">-></span> <span class="bp">()</span>
+
+ <span class="c">(* ignore top-level semicolons. *)</span>
+ <span class="o">|</span> <span class="nc">Some</span> <span class="o">(</span><span class="nn">Token</span><span class="p">.</span><span class="nc">Kwd</span> <span class="sc">';'</span><span class="o">)</span> <span class="o">-></span>
+ <span class="nn">Stream</span><span class="p">.</span><span class="n">junk</span> <span class="n">stream</span><span class="o">;</span>
+ <span class="n">main_loop</span> <span class="n">the_fpm</span> <span class="n">the_execution_engine</span> <span class="n">stream</span>
+
+ <span class="o">|</span> <span class="nc">Some</span> <span class="n">token</span> <span class="o">-></span>
+ <span class="k">begin</span>
+ <span class="k">try</span> <span class="k">match</span> <span class="n">token</span> <span class="k">with</span>
+ <span class="o">|</span> <span class="nn">Token</span><span class="p">.</span><span class="nc">Def</span> <span class="o">-></span>
+ <span class="k">let</span> <span class="n">e</span> <span class="o">=</span> <span class="nn">Parser</span><span class="p">.</span><span class="n">parse_definition</span> <span class="n">stream</span> <span class="k">in</span>
+ <span class="n">print_endline</span> <span class="s2">"parsed a function definition."</span><span class="o">;</span>
+ <span class="n">dump_value</span> <span class="o">(</span><span class="nn">Codegen</span><span class="p">.</span><span class="n">codegen_func</span> <span class="n">the_fpm</span> <span class="n">e</span><span class="o">);</span>
+ <span class="o">|</span> <span class="nn">Token</span><span class="p">.</span><span class="nc">Extern</span> <span class="o">-></span>
+ <span class="k">let</span> <span class="n">e</span> <span class="o">=</span> <span class="nn">Parser</span><span class="p">.</span><span class="n">parse_extern</span> <span class="n">stream</span> <span class="k">in</span>
+ <span class="n">print_endline</span> <span class="s2">"parsed an extern."</span><span class="o">;</span>
+ <span class="n">dump_value</span> <span class="o">(</span><span class="nn">Codegen</span><span class="p">.</span><span class="n">codegen_proto</span> <span class="n">e</span><span class="o">);</span>
+ <span class="o">|</span> <span class="o">_</span> <span class="o">-></span>
+ <span class="c">(* Evaluate a top-level expression into an anonymous function. *)</span>
+ <span class="k">let</span> <span class="n">e</span> <span class="o">=</span> <span class="nn">Parser</span><span class="p">.</span><span class="n">parse_toplevel</span> <span class="n">stream</span> <span class="k">in</span>
+ <span class="n">print_endline</span> <span class="s2">"parsed a top-level expr"</span><span class="o">;</span>
+ <span class="k">let</span> <span class="n">the_function</span> <span class="o">=</span> <span class="nn">Codegen</span><span class="p">.</span><span class="n">codegen_func</span> <span class="n">the_fpm</span> <span class="n">e</span> <span class="k">in</span>
+ <span class="n">dump_value</span> <span class="n">the_function</span><span class="o">;</span>
+
+ <span class="c">(* JIT the function, returning a function pointer. *)</span>
+ <span class="k">let</span> <span class="n">result</span> <span class="o">=</span> <span class="nn">ExecutionEngine</span><span class="p">.</span><span class="n">run_function</span> <span class="n">the_function</span> <span class="o">[||]</span>
+ <span class="n">the_execution_engine</span> <span class="k">in</span>
+
+ <span class="n">print_string</span> <span class="s2">"Evaluated to "</span><span class="o">;</span>
+ <span class="n">print_float</span> <span class="o">(</span><span class="nn">GenericValue</span><span class="p">.</span><span class="n">as_float</span> <span class="nn">Codegen</span><span class="p">.</span><span class="n">double_type</span> <span class="n">result</span><span class="o">);</span>
+ <span class="n">print_newline</span> <span class="bp">()</span><span class="o">;</span>
+ <span class="k">with</span> <span class="nn">Stream</span><span class="p">.</span><span class="nc">Error</span> <span class="n">s</span> <span class="o">|</span> <span class="nn">Codegen</span><span class="p">.</span><span class="nc">Error</span> <span class="n">s</span> <span class="o">-></span>
+ <span class="c">(* Skip token for error recovery. *)</span>
+ <span class="nn">Stream</span><span class="p">.</span><span class="n">junk</span> <span class="n">stream</span><span class="o">;</span>
+ <span class="n">print_endline</span> <span class="n">s</span><span class="o">;</span>
+ <span class="k">end</span><span class="o">;</span>
+ <span class="n">print_string</span> <span class="s2">"ready> "</span><span class="o">;</span> <span class="n">flush</span> <span class="n">stdout</span><span class="o">;</span>
+ <span class="n">main_loop</span> <span class="n">the_fpm</span> <span class="n">the_execution_engine</span> <span class="n">stream</span>
+</pre></div>
+</div>
+</dd>
+<dt>toy.ml:</dt>
+<dd><div class="first last highlight-ocaml"><div class="highlight"><pre><span class="c">(*===----------------------------------------------------------------------===</span>
+<span class="c"> * Main driver code.</span>
+<span class="c"> *===----------------------------------------------------------------------===*)</span>
+
+<span class="k">open</span> <span class="nc">Llvm</span>
+<span class="k">open</span> <span class="nc">Llvm_executionengine</span>
+<span class="k">open</span> <span class="nc">Llvm_target</span>
+<span class="k">open</span> <span class="nc">Llvm_scalar_opts</span>
+
+<span class="k">let</span> <span class="n">main</span> <span class="bp">()</span> <span class="o">=</span>
+ <span class="n">ignore</span> <span class="o">(</span><span class="n">initialize_native_target</span> <span class="bp">()</span><span class="o">);</span>
+
+ <span class="c">(* Install standard binary operators.</span>
+<span class="c"> * 1 is the lowest precedence. *)</span>
+ <span class="nn">Hashtbl</span><span class="p">.</span><span class="n">add</span> <span class="nn">Parser</span><span class="p">.</span><span class="n">binop_precedence</span> <span class="sc">'<'</span> <span class="mi">10</span><span class="o">;</span>
+ <span class="nn">Hashtbl</span><span class="p">.</span><span class="n">add</span> <span class="nn">Parser</span><span class="p">.</span><span class="n">binop_precedence</span> <span class="sc">'+'</span> <span class="mi">20</span><span class="o">;</span>
+ <span class="nn">Hashtbl</span><span class="p">.</span><span class="n">add</span> <span class="nn">Parser</span><span class="p">.</span><span class="n">binop_precedence</span> <span class="sc">'-'</span> <span class="mi">20</span><span class="o">;</span>
+ <span class="nn">Hashtbl</span><span class="p">.</span><span class="n">add</span> <span class="nn">Parser</span><span class="p">.</span><span class="n">binop_precedence</span> <span class="sc">'*'</span> <span class="mi">40</span><span class="o">;</span> <span class="c">(* highest. *)</span>
+
+ <span class="c">(* Prime the first token. *)</span>
+ <span class="n">print_string</span> <span class="s2">"ready> "</span><span class="o">;</span> <span class="n">flush</span> <span class="n">stdout</span><span class="o">;</span>
+ <span class="k">let</span> <span class="n">stream</span> <span class="o">=</span> <span class="nn">Lexer</span><span class="p">.</span><span class="n">lex</span> <span class="o">(</span><span class="nn">Stream</span><span class="p">.</span><span class="n">of_channel</span> <span class="n">stdin</span><span class="o">)</span> <span class="k">in</span>
+
+ <span class="c">(* Create the JIT. *)</span>
+ <span class="k">let</span> <span class="n">the_execution_engine</span> <span class="o">=</span> <span class="nn">ExecutionEngine</span><span class="p">.</span><span class="n">create</span> <span class="nn">Codegen</span><span class="p">.</span><span class="n">the_module</span> <span class="k">in</span>
+ <span class="k">let</span> <span class="n">the_fpm</span> <span class="o">=</span> <span class="nn">PassManager</span><span class="p">.</span><span class="n">create_function</span> <span class="nn">Codegen</span><span class="p">.</span><span class="n">the_module</span> <span class="k">in</span>
+
+ <span class="c">(* Set up the optimizer pipeline. Start with registering info about how the</span>
+<span class="c"> * target lays out data structures. *)</span>
+ <span class="nn">DataLayout</span><span class="p">.</span><span class="n">add</span> <span class="o">(</span><span class="nn">ExecutionEngine</span><span class="p">.</span><span class="n">target_data</span> <span class="n">the_execution_engine</span><span class="o">)</span> <span class="n">the_fpm</span><span class="o">;</span>
+
+ <span class="c">(* Do simple "peephole" optimizations and bit-twiddling optzn. *)</span>
+ <span class="n">add_instruction_combination</span> <span class="n">the_fpm</span><span class="o">;</span>
+
+ <span class="c">(* reassociate expressions. *)</span>
+ <span class="n">add_reassociation</span> <span class="n">the_fpm</span><span class="o">;</span>
+
+ <span class="c">(* Eliminate Common SubExpressions. *)</span>
+ <span class="n">add_gvn</span> <span class="n">the_fpm</span><span class="o">;</span>
+
+ <span class="c">(* Simplify the control flow graph (deleting unreachable blocks, etc). *)</span>
+ <span class="n">add_cfg_simplification</span> <span class="n">the_fpm</span><span class="o">;</span>
+
+ <span class="n">ignore</span> <span class="o">(</span><span class="nn">PassManager</span><span class="p">.</span><span class="n">initialize</span> <span class="n">the_fpm</span><span class="o">);</span>
+
+ <span class="c">(* Run the main "interpreter loop" now. *)</span>
+ <span class="nn">Toplevel</span><span class="p">.</span><span class="n">main_loop</span> <span class="n">the_fpm</span> <span class="n">the_execution_engine</span> <span class="n">stream</span><span class="o">;</span>
+
+ <span class="c">(* Print out all the generated code. *)</span>
+ <span class="n">dump_module</span> <span class="nn">Codegen</span><span class="p">.</span><span class="n">the_module</span>
+<span class="o">;;</span>
+
+<span class="n">main</span> <span class="bp">()</span>
+</pre></div>
+</div>
+</dd>
+<dt>bindings.c</dt>
+<dd><div class="first last highlight-c"><div class="highlight"><pre><span class="cp">#include <stdio.h></span>
+
+<span class="cm">/* putchard - putchar that takes a double and returns 0. */</span>
+<span class="k">extern</span> <span class="kt">double</span> <span class="nf">putchard</span><span class="p">(</span><span class="kt">double</span> <span class="n">X</span><span class="p">)</span> <span class="p">{</span>
+ <span class="n">putchar</span><span class="p">((</span><span class="kt">char</span><span class="p">)</span><span class="n">X</span><span class="p">);</span>
+ <span class="k">return</span> <span class="mi">0</span><span class="p">;</span>
+<span class="p">}</span>
+</pre></div>
+</div>
+</dd>
+</dl>
+<p><a class="reference external" href="OCamlLangImpl5.html">Next: Extending the language: control flow</a></p>
+</div>
+</div>
+
+
+ </div>
+ </div>
+ <div class="clearer"></div>
+ </div>
+ <div class="related">
+ <h3>Navigation</h3>
+ <ul>
+ <li class="right" style="margin-right: 10px">
+ <a href="../genindex.html" title="General Index"
+ >index</a></li>
+ <li class="right" >
+ <a href="OCamlLangImpl5.html" title="5. Kaleidoscope: Extending the Language: Control Flow"
+ >next</a> |</li>
+ <li class="right" >
+ <a href="OCamlLangImpl3.html" title="3. Kaleidoscope: Code generation to LLVM IR"
+ >previous</a> |</li>
+ <li><a href="http://llvm.org/">LLVM Home</a> | </li>
+ <li><a href="../index.html">Documentation</a>»</li>
+
+ <li><a href="index.html" >LLVM Tutorial: Table of Contents</a> »</li>
+ </ul>
+ </div>
+ <div class="footer">
+ © Copyright 2003-2016, LLVM Project.
+ Last updated on 2016-07-11.
+ Created using <a href="http://sphinx-doc.org/">Sphinx</a> 1.2.2.
+ </div>
+ </body>
+</html>
\ No newline at end of file
More information about the llvm-commits
mailing list