[www-releases] r238135 - Add 3.6.1 LLVM Docs.

Tom Stellard thomas.stellard at amd.com
Mon May 25 06:53:05 PDT 2015


Added: www-releases/trunk/3.6.1/docs/tutorial/OCamlLangImpl2.html
URL: http://llvm.org/viewvc/llvm-project/www-releases/trunk/3.6.1/docs/tutorial/OCamlLangImpl2.html?rev=238135&view=auto
==============================================================================
--- www-releases/trunk/3.6.1/docs/tutorial/OCamlLangImpl2.html (added)
+++ www-releases/trunk/3.6.1/docs/tutorial/OCamlLangImpl2.html Mon May 25 08:53:02 2015
@@ -0,0 +1,935 @@
+
+
+<!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 3.6 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:     '3.6',
+        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 3.6 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="https://urldefense.proofpoint.com/v2/url?u=http-3A__llvm.org_&d=AwMDaQ&c=8hUWFZcy2Z-Za5rBPlktOQ&r=mQ4LZ2PUj9hpadE3cDHZnIdEwhEBrbAstXeMaFoB9tg&m=QAGZeXoSMCv0h4wI0rExv_W1lSHAp-_70Lmc3PA5EtM&s=pfiJKhwlj5rZUzKRdDQCg_cdTSO0Ut0YcGMOb-jpeAs&e=">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="https://urldefense.proofpoint.com/v2/url?u=http-3A__en.wikipedia.org_wiki_Parsing&d=AwMDaQ&c=8hUWFZcy2Z-Za5rBPlktOQ&r=mQ4LZ2PUj9hpadE3cDHZnIdEwhEBrbAstXeMaFoB9tg&m=QAGZeXoSMCv0h4wI0rExv_W1lSHAp-_70Lmc3PA5EtM&s=-kqhR8zv3s-2VtA7frk0WI2cuRH74BcxFrOOSCGAWYU&e=">parser</a> for our
+Kaleidoscope language. Once we have a parser, we’ll define and build an
+<a class="reference external" href="https://urldefense.proofpoint.com/v2/url?u=http-3A__en.wikipedia.org_wiki_Abstract-5Fsyntax-5Ftree&d=AwMDaQ&c=8hUWFZcy2Z-Za5rBPlktOQ&r=mQ4LZ2PUj9hpadE3cDHZnIdEwhEBrbAstXeMaFoB9tg&m=QAGZeXoSMCv0h4wI0rExv_W1lSHAp-_70Lmc3PA5EtM&s=Urr9VHaVIjFDTBm_pH3NY95v-PVAz4SmCBEKrpmC4wU&e=">Abstract Syntax
+Tree</a> (AST).</p>
+<p>The parser we will build uses a combination of <a class="reference external" href="https://urldefense.proofpoint.com/v2/url?u=http-3A__en.wikipedia.org_wiki_Recursive-5Fdescent-5Fparser&d=AwMDaQ&c=8hUWFZcy2Z-Za5rBPlktOQ&r=mQ4LZ2PUj9hpadE3cDHZnIdEwhEBrbAstXeMaFoB9tg&m=QAGZeXoSMCv0h4wI0rExv_W1lSHAp-_70Lmc3PA5EtM&s=124Md6Fm9VVYF419ewL8XAw6pOdncHpzJRx95Wwl_q4&e=">Recursive Descent
+Parsing</a> and
+<a class="reference external" href="https://urldefense.proofpoint.com/v2/url?u=http-3A__en.wikipedia.org_wiki_Operator-2Dprecedence-5Fparser&d=AwMDaQ&c=8hUWFZcy2Z-Za5rBPlktOQ&r=mQ4LZ2PUj9hpadE3cDHZnIdEwhEBrbAstXeMaFoB9tg&m=QAGZeXoSMCv0h4wI0rExv_W1lSHAp-_70Lmc3PA5EtM&s=iCMTlV130aXZw14Q-0SijEw7oW9lIbpVttYZmasdhp4&e=">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#unary">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="https://urldefense.proofpoint.com/v2/url?u=http-3A__en.wikipedia.org_wiki_Operator-2Dprecedence-5Fparser&d=AwMDaQ&c=8hUWFZcy2Z-Za5rBPlktOQ&r=mQ4LZ2PUj9hpadE3cDHZnIdEwhEBrbAstXeMaFoB9tg&m=QAGZeXoSMCv0h4wI0rExv_W1lSHAp-_70Lmc3PA5EtM&s=iCMTlV130aXZw14Q-0SijEw7oW9lIbpVttYZmasdhp4&e=">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="#code">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"><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>
+<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"><pre><{lexer,parser}.ml>: use_camlp4, pp(camlp4of)</pre>
+</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="https://urldefense.proofpoint.com/v2/url?u=http-3A__llvm.org_&d=AwMDaQ&c=8hUWFZcy2Z-Za5rBPlktOQ&r=mQ4LZ2PUj9hpadE3cDHZnIdEwhEBrbAstXeMaFoB9tg&m=QAGZeXoSMCv0h4wI0rExv_W1lSHAp-_70Lmc3PA5EtM&s=pfiJKhwlj5rZUzKRdDQCg_cdTSO0Ut0YcGMOb-jpeAs&e=">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 2003-2014, LLVM Project.
+      Last updated on 2015-05-25.
+      Created using <a href="https://urldefense.proofpoint.com/v2/url?u=http-3A__sphinx.pocoo.org_&d=AwMDaQ&c=8hUWFZcy2Z-Za5rBPlktOQ&r=mQ4LZ2PUj9hpadE3cDHZnIdEwhEBrbAstXeMaFoB9tg&m=QAGZeXoSMCv0h4wI0rExv_W1lSHAp-_70Lmc3PA5EtM&s=lSOQQPBONfHSHDEAc1rfzOSlyTiliJLtzc8JrV9lcX4&e=">Sphinx</a> 1.1.3.
+    </div>
+  </body>
+</html>
\ No newline at end of file

Added: www-releases/trunk/3.6.1/docs/tutorial/OCamlLangImpl3.html
URL: http://llvm.org/viewvc/llvm-project/www-releases/trunk/3.6.1/docs/tutorial/OCamlLangImpl3.html?rev=238135&view=auto
==============================================================================
--- www-releases/trunk/3.6.1/docs/tutorial/OCamlLangImpl3.html (added)
+++ www-releases/trunk/3.6.1/docs/tutorial/OCamlLangImpl3.html Mon May 25 08:53:02 2015
@@ -0,0 +1,997 @@
+
+
+<!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 3.6 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:     '3.6',
+        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 3.6 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="https://urldefense.proofpoint.com/v2/url?u=http-3A__llvm.org_&d=AwMDaQ&c=8hUWFZcy2Z-Za5rBPlktOQ&r=mQ4LZ2PUj9hpadE3cDHZnIdEwhEBrbAstXeMaFoB9tg&m=QAGZeXoSMCv0h4wI0rExv_W1lSHAp-_70Lmc3PA5EtM&s=pfiJKhwlj5rZUzKRdDQCg_cdTSO0Ut0YcGMOb-jpeAs&e=">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="https://urldefense.proofpoint.com/v2/url?u=http-3A__en.wikipedia.org_wiki_Static-5Fsingle-5Fassignment-5Fform&d=AwMDaQ&c=8hUWFZcy2Z-Za5rBPlktOQ&r=mQ4LZ2PUj9hpadE3cDHZnIdEwhEBrbAstXeMaFoB9tg&m=QAGZeXoSMCv0h4wI0rExv_W1lSHAp-_70Lmc3PA5EtM&s=Qgsm8Kaurcw7WDxduZweralws7rQvxBwazcKEv-TcGo&e=">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="https://urldefense.proofpoint.com/v2/url?u=http-3A__en.wikipedia.org_wiki_Static-5Fsingle-5Fassignment-5Fform&d=AwMDaQ&c=8hUWFZcy2Z-Za5rBPlktOQ&r=mQ4LZ2PUj9hpadE3cDHZnIdEwhEBrbAstXeMaFoB9tg&m=QAGZeXoSMCv0h4wI0rExv_W1lSHAp-_70Lmc3PA5EtM&s=Qgsm8Kaurcw7WDxduZweralws7rQvxBwazcKEv-TcGo&e=">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
+<tt class="docutils literal"><span class="pre">`IRBuilder</span></tt> <<a class="reference external" href="https://urldefense.proofpoint.com/v2/url?u=http-3A__llvm.org_doxygen_IRBuilder-5F8h-2Dsource.html&d=AwMDaQ&c=8hUWFZcy2Z-Za5rBPlktOQ&r=mQ4LZ2PUj9hpadE3cDHZnIdEwhEBrbAstXeMaFoB9tg&m=QAGZeXoSMCv0h4wI0rExv_W1lSHAp-_70Lmc3PA5EtM&s=59SH77ZtyDsUqwnAAGR4SgfOsECHT7x5kLtru11N5sA&e=">http://llvm.org/doxygen/IRBuilder_8h-source.html</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
+induction variables</a> in the symbol table, and for
+<a class="reference external" href="LangImpl7.html#localvars">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#instref">LLVM instructions</a> are constrained by strict
+rules: for example, the Left and Right operators of an <a class="reference external" href="../LangRef.html#i_add">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#i_fcmp">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#i_uitofp">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#i_sitofp">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#i_call">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="https://urldefense.proofpoint.com/v2/url?u=http-3A__en.wikipedia.org_wiki_Basic-5Fblock&d=AwMDaQ&c=8hUWFZcy2Z-Za5rBPlktOQ&r=mQ4LZ2PUj9hpadE3cDHZnIdEwhEBrbAstXeMaFoB9tg&m=QAGZeXoSMCv0h4wI0rExv_W1lSHAp-_70Lmc3PA5EtM&s=yz-pI4_npa2S_JYeTu9VX-0uBuIDcVVQtSYFVUCmckY&e=">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="https://urldefense.proofpoint.com/v2/url?u=http-3A__en.wikipedia.org_wiki_Control-5Fflow-5Fgraph&d=AwMDaQ&c=8hUWFZcy2Z-Za5rBPlktOQ&r=mQ4LZ2PUj9hpadE3cDHZnIdEwhEBrbAstXeMaFoB9tg&m=QAGZeXoSMCv0h4wI0rExv_W1lSHAp-_70Lmc3PA5EtM&s=kHK5SLpvF7wk8dOXAHNsk_03ju8OnWWqz1RjluqX0Ow&e=">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#i_ret">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"><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 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"><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>
+<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#jit">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#trivialconstfold">add
+optimizations</a> explicitly in the
+next chapter.</p>
+<div class="highlight-python"><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>
+<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"><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>
+<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"><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>
+<p>This shows an extern for the libm “cos” function, and a call to it.</p>
+<div class="highlight-python"><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>
+<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="https://urldefense.proofpoint.com/v2/url?u=http-3A__llvm.org_cmds_llvm-2Dconfig.html&d=AwMDaQ&c=8hUWFZcy2Z-Za5rBPlktOQ&r=mQ4LZ2PUj9hpadE3cDHZnIdEwhEBrbAstXeMaFoB9tg&m=QAGZeXoSMCv0h4wI0rExv_W1lSHAp-_70Lmc3PA5EtM&s=vIMaxUda3QiSyJvHfIvkYuH_39jGOAnZ7zwQFj09TZ0&e=">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"><pre><{lexer,parser}.ml>: use_camlp4, pp(camlp4of)
+<*.{byte,native}>: g++, use_llvm, use_llvm_analysis</pre>
+</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="https://urldefense.proofpoint.com/v2/url?u=http-3A__llvm.org_&d=AwMDaQ&c=8hUWFZcy2Z-Za5rBPlktOQ&r=mQ4LZ2PUj9hpadE3cDHZnIdEwhEBrbAstXeMaFoB9tg&m=QAGZeXoSMCv0h4wI0rExv_W1lSHAp-_70Lmc3PA5EtM&s=pfiJKhwlj5rZUzKRdDQCg_cdTSO0Ut0YcGMOb-jpeAs&e=">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 2003-2014, LLVM Project.
+      Last updated on 2015-05-25.
+      Created using <a href="https://urldefense.proofpoint.com/v2/url?u=http-3A__sphinx.pocoo.org_&d=AwMDaQ&c=8hUWFZcy2Z-Za5rBPlktOQ&r=mQ4LZ2PUj9hpadE3cDHZnIdEwhEBrbAstXeMaFoB9tg&m=QAGZeXoSMCv0h4wI0rExv_W1lSHAp-_70Lmc3PA5EtM&s=lSOQQPBONfHSHDEAc1rfzOSlyTiliJLtzc8JrV9lcX4&e=">Sphinx</a> 1.1.3.
+    </div>
+  </body>
+</html>
\ No newline at end of file

Added: www-releases/trunk/3.6.1/docs/tutorial/OCamlLangImpl4.html
URL: http://llvm.org/viewvc/llvm-project/www-releases/trunk/3.6.1/docs/tutorial/OCamlLangImpl4.html?rev=238135&view=auto
==============================================================================
--- www-releases/trunk/3.6.1/docs/tutorial/OCamlLangImpl4.html (added)
+++ www-releases/trunk/3.6.1/docs/tutorial/OCamlLangImpl4.html Mon May 25 08:53:02 2015
@@ -0,0 +1,961 @@
+
+
+<!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 3.6 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:     '3.6',
+        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 3.6 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="https://urldefense.proofpoint.com/v2/url?u=http-3A__llvm.org_&d=AwMDaQ&c=8hUWFZcy2Z-Za5rBPlktOQ&r=mQ4LZ2PUj9hpadE3cDHZnIdEwhEBrbAstXeMaFoB9tg&m=QAGZeXoSMCv0h4wI0rExv_W1lSHAp-_70Lmc3PA5EtM&s=pfiJKhwlj5rZUzKRdDQCg_cdTSO0Ut0YcGMOb-jpeAs&e=">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"><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>
+<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"><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>
+<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"><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>
+<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#passmanager">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"><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>
+<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"><pre>ready> 4+5;
+define double @""() {
+entry:
+        ret double 9.000000e+00
+}
+
+Evaluated to 9.000000</pre>
+</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"><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>
+<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"><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>
+<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"><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>
+</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="https://urldefense.proofpoint.com/v2/url?u=http-3A__llvm.org_&d=AwMDaQ&c=8hUWFZcy2Z-Za5rBPlktOQ&r=mQ4LZ2PUj9hpadE3cDHZnIdEwhEBrbAstXeMaFoB9tg&m=QAGZeXoSMCv0h4wI0rExv_W1lSHAp-_70Lmc3PA5EtM&s=pfiJKhwlj5rZUzKRdDQCg_cdTSO0Ut0YcGMOb-jpeAs&e=">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 2003-2014, LLVM Project.
+      Last updated on 2015-05-25.
+      Created using <a href="https://urldefense.proofpoint.com/v2/url?u=http-3A__sphinx.pocoo.org_&d=AwMDaQ&c=8hUWFZcy2Z-Za5rBPlktOQ&r=mQ4LZ2PUj9hpadE3cDHZnIdEwhEBrbAstXeMaFoB9tg&m=QAGZeXoSMCv0h4wI0rExv_W1lSHAp-_70Lmc3PA5EtM&s=lSOQQPBONfHSHDEAc1rfzOSlyTiliJLtzc8JrV9lcX4&e=">Sphinx</a> 1.1.3.
+    </div>
+  </body>
+</html>
\ No newline at end of file

Added: www-releases/trunk/3.6.1/docs/tutorial/OCamlLangImpl5.html
URL: http://llvm.org/viewvc/llvm-project/www-releases/trunk/3.6.1/docs/tutorial/OCamlLangImpl5.html?rev=238135&view=auto
==============================================================================
--- www-releases/trunk/3.6.1/docs/tutorial/OCamlLangImpl5.html (added)
+++ www-releases/trunk/3.6.1/docs/tutorial/OCamlLangImpl5.html Mon May 25 08:53:02 2015
@@ -0,0 +1,1389 @@
+
+
+<!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>5. Kaleidoscope: Extending the Language: Control Flow — LLVM 3.6 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:     '3.6',
+        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 3.6 documentation" href="../index.html" />
+    <link rel="up" title="LLVM Tutorial: Table of Contents" href="index.html" />
+    <link rel="next" title="6. Kaleidoscope: Extending the Language: User-defined Operators" href="OCamlLangImpl6.html" />
+    <link rel="prev" title="4. Kaleidoscope: Adding JIT and Optimizer Support" href="OCamlLangImpl4.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="OCamlLangImpl6.html" title="6. Kaleidoscope: Extending the Language: User-defined Operators" + accesskey="N">next</a> |</li>
+        <li class="right" >
+          <a href="OCamlLangImpl4.html" title="4. Kaleidoscope: Adding JIT and Optimizer Support" + accesskey="P">previous</a> |</li>
+  <li><a href="https://urldefense.proofpoint.com/v2/url?u=http-3A__llvm.org_&d=AwMDaQ&c=8hUWFZcy2Z-Za5rBPlktOQ&r=mQ4LZ2PUj9hpadE3cDHZnIdEwhEBrbAstXeMaFoB9tg&m=QAGZeXoSMCv0h4wI0rExv_W1lSHAp-_70Lmc3PA5EtM&s=pfiJKhwlj5rZUzKRdDQCg_cdTSO0Ut0YcGMOb-jpeAs&e=">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-control-flow">
+<h1>5. Kaleidoscope: Extending the Language: Control Flow<a class="headerlink" href="#kaleidoscope-extending-the-language-control-flow" title="Permalink to this headline">¶</a></h1>
+<div class="contents local topic" id="contents">
+<ul class="simple">
+<li><a class="reference internal" href="#chapter-5-introduction" id="id1">Chapter 5 Introduction</a></li>
+<li><a class="reference internal" href="#if-then-else" id="id2">If/Then/Else</a><ul>
+<li><a class="reference internal" href="#lexer-extensions-for-if-then-else" id="id3">Lexer Extensions for If/Then/Else</a></li>
+<li><a class="reference internal" href="#ast-extensions-for-if-then-else" id="id4">AST Extensions for If/Then/Else</a></li>
+<li><a class="reference internal" href="#parser-extensions-for-if-then-else" id="id5">Parser Extensions for If/Then/Else</a></li>
+<li><a class="reference internal" href="#llvm-ir-for-if-then-else" id="id6">LLVM IR for If/Then/Else</a></li>
+<li><a class="reference internal" href="#code-generation-for-if-then-else" id="id7">Code Generation for If/Then/Else</a></li>
+</ul>
+</li>
+<li><a class="reference internal" href="#for-loop-expression" id="id8">‘for’ Loop Expression</a><ul>
+<li><a class="reference internal" href="#lexer-extensions-for-the-for-loop" id="id9">Lexer Extensions for the ‘for’ Loop</a></li>
+<li><a class="reference internal" href="#ast-extensions-for-the-for-loop" id="id10">AST Extensions for the ‘for’ Loop</a></li>
+<li><a class="reference internal" href="#parser-extensions-for-the-for-loop" id="id11">Parser Extensions for the ‘for’ Loop</a></li>
+<li><a class="reference internal" href="#llvm-ir-for-the-for-loop" id="id12">LLVM IR for the ‘for’ Loop</a></li>
+<li><a class="reference internal" href="#code-generation-for-the-for-loop" id="id13">Code Generation for the ‘for’ Loop</a></li>
+</ul>
+</li>
+<li><a class="reference internal" href="#full-code-listing" id="id14">Full Code Listing</a></li>
+</ul>
+</div>
+<div class="section" id="chapter-5-introduction">
+<h2><a class="toc-backref" href="#id1">5.1. Chapter 5 Introduction</a><a class="headerlink" href="#chapter-5-introduction" title="Permalink to this headline">¶</a></h2>
+<p>Welcome to Chapter 5 of the “<a class="reference external" href="index.html">Implementing a language with
+LLVM</a>” tutorial. Parts 1-4 described the implementation of
+the simple Kaleidoscope language and included support for generating
+LLVM IR, followed by optimizations and a JIT compiler. Unfortunately, as
+presented, Kaleidoscope is mostly useless: it has no control flow other
+than call and return. This means that you can’t have conditional
+branches in the code, significantly limiting its power. In this episode
+of “build that compiler”, we’ll extend Kaleidoscope to have an
+if/then/else expression plus a simple ‘for’ loop.</p>
+</div>
+<div class="section" id="if-then-else">
+<h2><a class="toc-backref" href="#id2">5.2. If/Then/Else</a><a class="headerlink" href="#if-then-else" title="Permalink to this headline">¶</a></h2>
+<p>Extending Kaleidoscope to support if/then/else is quite straightforward.
+It basically requires adding lexer support for this “new” concept to the
+lexer, parser, AST, and LLVM code emitter. This example is nice, because
+it shows how easy it is to “grow” a language over time, incrementally
+extending it as new ideas are discovered.</p>
+<p>Before we get going on “how” we add this extension, lets talk about
+“what” we want. The basic idea is that we want to be able to write this
+sort of thing:</p>
+<div class="highlight-python"><pre>def fib(x)
+  if x < 3 then
+    1
+  else
+    fib(x-1)+fib(x-2);</pre>
+</div>
+<p>In Kaleidoscope, every construct is an expression: there are no
+statements. As such, the if/then/else expression needs to return a value
+like any other. Since we’re using a mostly functional form, we’ll have
+it evaluate its conditional, then return the ‘then’ or ‘else’ value
+based on how the condition was resolved. This is very similar to the C
+”?:” expression.</p>
+<p>The semantics of the if/then/else expression is that it evaluates the
+condition to a boolean equality value: 0.0 is considered to be false and
+everything else is considered to be true. If the condition is true, the
+first subexpression is evaluated and returned, if the condition is
+false, the second subexpression is evaluated and returned. Since
+Kaleidoscope allows side-effects, this behavior is important to nail
+down.</p>
+<p>Now that we know what we “want”, lets break this down into its
+constituent pieces.</p>
+<div class="section" id="lexer-extensions-for-if-then-else">
+<h3><a class="toc-backref" href="#id3">5.2.1. Lexer Extensions for If/Then/Else</a><a class="headerlink" href="#lexer-extensions-for-if-then-else" title="Permalink to this headline">¶</a></h3>
+<p>The lexer extensions are straightforward. First we add new variants for
+the relevant tokens:</p>
+<div class="highlight-ocaml"><div class="highlight"><pre><span class="c">(* control *)</span>
+<span class="o">|</span> <span class="nc">If</span> <span class="o">|</span> <span class="nc">Then</span> <span class="o">|</span> <span class="nc">Else</span> <span class="o">|</span> <span class="nc">For</span> <span class="o">|</span> <span class="nc">In</span>
+</pre></div>
+</div>
+<p>Once we have that, we recognize the new keywords in the lexer. This is
+pretty simple stuff:</p>
+<div class="highlight-ocaml"><div class="highlight"><pre><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="s2">"if"</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">If</span><span class="o">;</span> <span class="n">stream</span> <span class="o">>]</span>
+<span class="o">|</span> <span class="s2">"then"</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">Then</span><span class="o">;</span> <span class="n">stream</span> <span class="o">>]</span>
+<span class="o">|</span> <span class="s2">"else"</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">Else</span><span class="o">;</span> <span class="n">stream</span> <span class="o">>]</span>
+<span class="o">|</span> <span class="s2">"for"</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">For</span><span class="o">;</span> <span class="n">stream</span> <span class="o">>]</span>
+<span class="o">|</span> <span class="s2">"in"</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">In</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>
+</div>
+<div class="section" id="ast-extensions-for-if-then-else">
+<h3><a class="toc-backref" href="#id4">5.2.2. AST Extensions for If/Then/Else</a><a class="headerlink" href="#ast-extensions-for-if-then-else" title="Permalink to this headline">¶</a></h3>
+<p>To represent the new expression we add a new AST variant for it:</p>
+<div class="highlight-ocaml"><div class="highlight"><pre><span class="k">type</span> <span class="n">expr</span> <span class="o">=</span>
+  <span class="o">...</span>
+  <span class="c">(* variant for if/then/else. *)</span>
+  <span class="o">|</span> <span class="nc">If</span> <span class="k">of</span> <span class="n">expr</span> <span class="o">*</span> <span class="n">expr</span> <span class="o">*</span> <span class="n">expr</span>
+</pre></div>
+</div>
+<p>The AST variant just has pointers to the various subexpressions.</p>
+</div>
+<div class="section" id="parser-extensions-for-if-then-else">
+<h3><a class="toc-backref" href="#id5">5.2.3. Parser Extensions for If/Then/Else</a><a class="headerlink" href="#parser-extensions-for-if-then-else" title="Permalink to this headline">¶</a></h3>
+<p>Now that we have the relevant tokens coming from the lexer and we have
+the AST node to build, our parsing logic is relatively straightforward.
+First we define a new parsing function:</p>
+<div class="highlight-ocaml"><div class="highlight"><pre><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="o">...</span>
+  <span class="c">(* ifexpr ::= 'if' expr 'then' expr 'else' expr *)</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">If</span><span class="o">;</span> <span class="n">c</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">Then</span> <span class="o">??</span> <span class="s2">"expected 'then'"</span><span class="o">;</span> <span class="n">t</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">Else</span> <span class="o">??</span> <span class="s2">"expected 'else'"</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">If</span> <span class="o">(</span><span class="n">c</span><span class="o">,</span> <span class="n">t</span><span class="o">,</span> <span class="n">e</span><span class="o">)</span>
+</pre></div>
+</div>
+<p>Next we hook it up as a primary expression:</p>
+<div class="highlight-ocaml"><div class="highlight"><pre><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="o">...</span>
+  <span class="c">(* ifexpr ::= 'if' expr 'then' expr 'else' expr *)</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">If</span><span class="o">;</span> <span class="n">c</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">Then</span> <span class="o">??</span> <span class="s2">"expected 'then'"</span><span class="o">;</span> <span class="n">t</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">Else</span> <span class="o">??</span> <span class="s2">"expected 'else'"</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">If</span> <span class="o">(</span><span class="n">c</span><span class="o">,</span> <span class="n">t</span><span class="o">,</span> <span class="n">e</span><span class="o">)</span>
+</pre></div>
+</div>
+</div>
+<div class="section" id="llvm-ir-for-if-then-else">
+<h3><a class="toc-backref" href="#id6">5.2.4. LLVM IR for If/Then/Else</a><a class="headerlink" href="#llvm-ir-for-if-then-else" title="Permalink to this headline">¶</a></h3>
+<p>Now that we have it parsing and building the AST, the final piece is
+adding LLVM code generation support. This is the most interesting part
+of the if/then/else example, because this is where it starts to
+introduce new concepts. All of the code above has been thoroughly
+described in previous chapters.</p>
+<p>To motivate the code we want to produce, lets take a look at a simple
+example. Consider:</p>
+<div class="highlight-python"><pre>extern foo();
+extern bar();
+def baz(x) if x then foo() else bar();</pre>
+</div>
+<p>If you disable optimizations, the code you’ll (soon) get from
+Kaleidoscope looks like this:</p>
+<div class="highlight-llvm"><div class="highlight"><pre><span class="k">declare</span> <span class="kt">double</span> <span class="vg">@foo</span><span class="p">()</span>
+
+<span class="k">declare</span> <span class="kt">double</span> <span class="vg">@bar</span><span class="p">()</span>
+
+<span class="k">define</span> <span class="kt">double</span> <span class="vg">@baz</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">%ifcond</span> <span class="p">=</span> <span class="k">fcmp</span> <span class="k">one</span> <span class="kt">double</span> <span class="nv">%x</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="nv">%calltmp</span> <span class="p">=</span> <span class="k">call</span> <span class="kt">double</span> <span class="vg">@foo</span><span class="p">()</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">%calltmp1</span> <span class="p">=</span> <span class="k">call</span> <span class="kt">double</span> <span class="vg">@bar</span><span class="p">()</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="nv">%calltmp</span><span class="p">,</span> <span class="nv">%then</span> <span class="p">],</span> <span class="p">[</span> <span class="nv">%calltmp1</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>To visualize the control flow graph, you can use a nifty feature of the
+LLVM ‘<a class="reference external" href="https://urldefense.proofpoint.com/v2/url?u=http-3A__llvm.org_cmds_opt.html&d=AwMDaQ&c=8hUWFZcy2Z-Za5rBPlktOQ&r=mQ4LZ2PUj9hpadE3cDHZnIdEwhEBrbAstXeMaFoB9tg&m=QAGZeXoSMCv0h4wI0rExv_W1lSHAp-_70Lmc3PA5EtM&s=kJ9FZ1WaZQuAn6QYsqe-s9Qqy3ejjSg8E6JXP61kcmI&e=">opt</a>‘ tool. If you put this LLVM
+IR into “t.ll” and run “<tt class="docutils literal"><span class="pre">llvm-as</span> <span class="pre"><</span> <span class="pre">t.ll</span> <span class="pre">|</span> <span class="pre">opt</span> <span class="pre">-analyze</span> <span class="pre">-view-cfg</span></tt>”, <a class="reference external" href="../ProgrammersManual.html#ViewGraph">a
+window will pop up</a> and you’ll
+see this graph:</p>
+<div class="figure align-center">
+<img alt="Example CFG" src="../_images/LangImpl5-cfg.png" />
+<p class="caption">Example CFG</p>
+</div>
+<p>Another way to get this is to call
+“<tt class="docutils literal"><span class="pre">Llvm_analysis.view_function_cfg</span> <span class="pre">f</span></tt>” or
+“<tt class="docutils literal"><span class="pre">Llvm_analysis.view_function_cfg_only</span> <span class="pre">f</span></tt>” (where <tt class="docutils literal"><span class="pre">f</span></tt> is a
+“<tt class="docutils literal"><span class="pre">Function</span></tt>”) either by inserting actual calls into the code and
+recompiling or by calling these in the debugger. LLVM has many nice
+features for visualizing various graphs.</p>
+<p>Getting back to the generated code, it is fairly simple: the entry block
+evaluates the conditional expression (“x” in our case here) and compares
+the result to 0.0 with the “<tt class="docutils literal"><span class="pre">fcmp</span> <span class="pre">one</span></tt>” instruction (‘one’ is “Ordered
+and Not Equal”). Based on the result of this expression, the code jumps
+to either the “then” or “else” blocks, which contain the expressions for
+the true/false cases.</p>
+<p>Once the then/else blocks are finished executing, they both branch back
+to the ‘ifcont’ block to execute the code that happens after the
+if/then/else. In this case the only thing left to do is to return to the
+caller of the function. The question then becomes: how does the code
+know which expression to return?</p>
+<p>The answer to this question involves an important SSA operation: the
+<a class="reference external" href="https://urldefense.proofpoint.com/v2/url?u=http-3A__en.wikipedia.org_wiki_Static-5Fsingle-5Fassignment-5Fform&d=AwMDaQ&c=8hUWFZcy2Z-Za5rBPlktOQ&r=mQ4LZ2PUj9hpadE3cDHZnIdEwhEBrbAstXeMaFoB9tg&m=QAGZeXoSMCv0h4wI0rExv_W1lSHAp-_70Lmc3PA5EtM&s=Qgsm8Kaurcw7WDxduZweralws7rQvxBwazcKEv-TcGo&e=">Phi
+operation</a>.
+If you’re not familiar with SSA, <a class="reference external" href="https://urldefense.proofpoint.com/v2/url?u=http-3A__en.wikipedia.org_wiki_Static-5Fsingle-5Fassignment-5Fform&d=AwMDaQ&c=8hUWFZcy2Z-Za5rBPlktOQ&r=mQ4LZ2PUj9hpadE3cDHZnIdEwhEBrbAstXeMaFoB9tg&m=QAGZeXoSMCv0h4wI0rExv_W1lSHAp-_70Lmc3PA5EtM&s=Qgsm8Kaurcw7WDxduZweralws7rQvxBwazcKEv-TcGo&e=">the wikipedia
+article</a>
+is a good introduction and there are various other introductions to it
+available on your favorite search engine. The short version is that
+“execution” of the Phi operation requires “remembering” which block
+control came from. The Phi operation takes on the value corresponding to
+the input control block. In this case, if control comes in from the
+“then” block, it gets the value of “calltmp”. If control comes from the
+“else” block, it gets the value of “calltmp1”.</p>
+<p>At this point, you are probably starting to think “Oh no! This means my
+simple and elegant front-end will have to start generating SSA form in
+order to use LLVM!”. Fortunately, this is not the case, and we strongly
+advise <em>not</em> implementing an SSA construction algorithm in your
+front-end unless there is an amazingly good reason to do so. In
+practice, there are two sorts of values that float around in code
+written for your average imperative programming language that might need
+Phi nodes:</p>
+<ol class="arabic simple">
+<li>Code that involves user variables: <tt class="docutils literal"><span class="pre">x</span> <span class="pre">=</span> <span class="pre">1;</span> <span class="pre">x</span> <span class="pre">=</span> <span class="pre">x</span> <span class="pre">+</span> <span class="pre">1;</span></tt></li>
+<li>Values that are implicit in the structure of your AST, such as the
+Phi node in this case.</li>
+</ol>
+<p>In <a class="reference external" href="OCamlLangImpl7.html">Chapter 7</a> of this tutorial (“mutable
+variables”), we’ll talk about #1 in depth. For now, just believe me that
+you don’t need SSA construction to handle this case. For #2, you have
+the choice of using the techniques that we will describe for #1, or you
+can insert Phi nodes directly, if convenient. In this case, it is really
+really easy to generate the Phi node, so we choose to do it directly.</p>
+<p>Okay, enough of the motivation and overview, lets generate code!</p>
+</div>
+<div class="section" id="code-generation-for-if-then-else">
+<h3><a class="toc-backref" href="#id7">5.2.5. Code Generation for If/Then/Else</a><a class="headerlink" href="#code-generation-for-if-then-else" title="Permalink to this headline">¶</a></h3>
+<p>In order to generate code for this, we implement the <tt class="docutils literal"><span class="pre">Codegen</span></tt> method
+for <tt class="docutils literal"><span class="pre">IfExprAST</span></tt>:</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="o">|</span> <span class="nn">Ast</span><span class="p">.</span><span class="nc">If</span> <span class="o">(</span><span class="n">cond</span><span class="o">,</span> <span class="n">then_</span><span class="o">,</span> <span class="n">else_</span><span class="o">)</span> <span class="o">-></span>
+      <span class="k">let</span> <span class="n">cond</span> <span class="o">=</span> <span class="n">codegen_expr</span> <span class="n">cond</span> <span class="k">in</span>
+
+      <span class="c">(* Convert condition to a bool by comparing equal to 0.0 *)</span>
+      <span class="k">let</span> <span class="n">zero</span> <span class="o">=</span> <span class="n">const_float</span> <span class="n">double_type</span> <span class="mi">0</span><span class="o">.</span><span class="mi">0</span> <span class="k">in</span>
+      <span class="k">let</span> <span class="n">cond_val</span> <span class="o">=</span> <span class="n">build_fcmp</span> <span class="nn">Fcmp</span><span class="p">.</span><span class="nc">One</span> <span class="n">cond</span> <span class="n">zero</span> <span class="s2">"ifcond"</span> <span class="n">builder</span> <span class="k">in</span>
+</pre></div>
+</div>
+<p>This code is straightforward and similar to what we saw before. We emit
+the expression for the condition, then compare that value to zero to get
+a truth value as a 1-bit (bool) value.</p>
+<div class="highlight-ocaml"><div class="highlight"><pre><span class="c">(* Grab the first block so that we might later add the conditional branch</span>
+<span class="c"> * to it at the end of the function. *)</span>
+<span class="k">let</span> <span class="n">start_bb</span> <span class="o">=</span> <span class="n">insertion_block</span> <span class="n">builder</span> <span class="k">in</span>
+<span class="k">let</span> <span class="n">the_function</span> <span class="o">=</span> <span class="n">block_parent</span> <span class="n">start_bb</span> <span class="k">in</span>
+
+<span class="k">let</span> <span class="n">then_bb</span> <span class="o">=</span> <span class="n">append_block</span> <span class="n">context</span> <span class="s2">"then"</span> <span class="n">the_function</span> <span class="k">in</span>
+<span class="n">position_at_end</span> <span class="n">then_bb</span> <span class="n">builder</span><span class="o">;</span>
+</pre></div>
+</div>
+<p>As opposed to the <a class="reference external" href="LangImpl5.html">C++ tutorial</a>, we have to build our
+basic blocks bottom up since we can’t have dangling BasicBlocks. We
+start off by saving a pointer to the first block (which might not be the
+entry block), which we’ll need to build a conditional branch later. We
+do this by asking the <tt class="docutils literal"><span class="pre">builder</span></tt> for the current BasicBlock. The fourth
+line gets the current Function object that is being built. It gets this
+by the <tt class="docutils literal"><span class="pre">start_bb</span></tt> for its “parent” (the function it is currently
+embedded into).</p>
+<p>Once it has that, it creates one block. It is automatically appended
+into the function’s list of blocks.</p>
+<div class="highlight-ocaml"><div class="highlight"><pre><span class="c">(* Emit 'then' value. *)</span>
+<span class="n">position_at_end</span> <span class="n">then_bb</span> <span class="n">builder</span><span class="o">;</span>
+<span class="k">let</span> <span class="n">then_val</span> <span class="o">=</span> <span class="n">codegen_expr</span> <span class="n">then_</span> <span class="k">in</span>
+
+<span class="c">(* Codegen of 'then' can change the current block, update then_bb for the</span>
+<span class="c"> * phi. We create a new name because one is used for the phi node, and the</span>
+<span class="c"> * other is used for the conditional branch. *)</span>
+<span class="k">let</span> <span class="n">new_then_bb</span> <span class="o">=</span> <span class="n">insertion_block</span> <span class="n">builder</span> <span class="k">in</span>
+</pre></div>
+</div>
+<p>We move the builder to start inserting into the “then” block. Strictly
+speaking, this call moves the insertion point to be at the end of the
+specified block. However, since the “then” block is empty, it also
+starts out by inserting at the beginning of the block. :)</p>
+<p>Once the insertion point is set, we recursively codegen the “then”
+expression from the AST.</p>
+<p>The final line here is quite subtle, but is very important. The basic
+issue is that when we create the Phi node in the merge block, we need to
+set up the block/value pairs that indicate how the Phi will work.
+Importantly, the Phi node expects to have an entry for each predecessor
+of the block in the CFG. Why then, are we getting the current block when
+we just set it to ThenBB 5 lines above? The problem is that the “Then”
+expression may actually itself change the block that the Builder is
+emitting into if, for example, it contains a nested “if/then/else”
+expression. Because calling Codegen recursively could arbitrarily change
+the notion of the current block, we are required to get an up-to-date
+value for code that will set up the Phi node.</p>
+<div class="highlight-ocaml"><div class="highlight"><pre><span class="c">(* Emit 'else' value. *)</span>
+<span class="k">let</span> <span class="n">else_bb</span> <span class="o">=</span> <span class="n">append_block</span> <span class="n">context</span> <span class="s2">"else"</span> <span class="n">the_function</span> <span class="k">in</span>
+<span class="n">position_at_end</span> <span class="n">else_bb</span> <span class="n">builder</span><span class="o">;</span>
+<span class="k">let</span> <span class="n">else_val</span> <span class="o">=</span> <span class="n">codegen_expr</span> <span class="n">else_</span> <span class="k">in</span>
+
+<span class="c">(* Codegen of 'else' can change the current block, update else_bb for the</span>
+<span class="c"> * phi. *)</span>
+<span class="k">let</span> <span class="n">new_else_bb</span> <span class="o">=</span> <span class="n">insertion_block</span> <span class="n">builder</span> <span class="k">in</span>
+</pre></div>
+</div>
+<p>Code generation for the ‘else’ block is basically identical to codegen
+for the ‘then’ block.</p>
+<div class="highlight-ocaml"><div class="highlight"><pre><span class="c">(* Emit merge block. *)</span>
+<span class="k">let</span> <span class="n">merge_bb</span> <span class="o">=</span> <span class="n">append_block</span> <span class="n">context</span> <span class="s2">"ifcont"</span> <span class="n">the_function</span> <span class="k">in</span>
+<span class="n">position_at_end</span> <span class="n">merge_bb</span> <span class="n">builder</span><span class="o">;</span>
+<span class="k">let</span> <span class="n">incoming</span> <span class="o">=</span> <span class="o">[(</span><span class="n">then_val</span><span class="o">,</span> <span class="n">new_then_bb</span><span class="o">);</span> <span class="o">(</span><span class="n">else_val</span><span class="o">,</span> <span class="n">new_else_bb</span><span class="o">)]</span> <span class="k">in</span>
+<span class="k">let</span> <span class="n">phi</span> <span class="o">=</span> <span class="n">build_phi</span> <span class="n">incoming</span> <span class="s2">"iftmp"</span> <span class="n">builder</span> <span class="k">in</span>
+</pre></div>
+</div>
+<p>The first two lines here are now familiar: the first adds the “merge”
+block to the Function object. The second block changes the insertion
+point so that newly created code will go into the “merge” block. Once
+that is done, we need to create the PHI node and set up the block/value
+pairs for the PHI.</p>
+<div class="highlight-ocaml"><div class="highlight"><pre><span class="c">(* Return to the start block to add the conditional branch. *)</span>
+<span class="n">position_at_end</span> <span class="n">start_bb</span> <span class="n">builder</span><span class="o">;</span>
+<span class="n">ignore</span> <span class="o">(</span><span class="n">build_cond_br</span> <span class="n">cond_val</span> <span class="n">then_bb</span> <span class="n">else_bb</span> <span class="n">builder</span><span class="o">);</span>
+</pre></div>
+</div>
+<p>Once the blocks are created, we can emit the conditional branch that
+chooses between them. Note that creating new blocks does not implicitly
+affect the IRBuilder, so it is still inserting into the block that the
+condition went into. This is why we needed to save the “start” block.</p>
+<div class="highlight-ocaml"><div class="highlight"><pre><span class="c">(* Set a unconditional branch at the end of the 'then' block and the</span>
+<span class="c"> * 'else' block to the 'merge' block. *)</span>
+<span class="n">position_at_end</span> <span class="n">new_then_bb</span> <span class="n">builder</span><span class="o">;</span> <span class="n">ignore</span> <span class="o">(</span><span class="n">build_br</span> <span class="n">merge_bb</span> <span class="n">builder</span><span class="o">);</span>
+<span class="n">position_at_end</span> <span class="n">new_else_bb</span> <span class="n">builder</span><span class="o">;</span> <span class="n">ignore</span> <span class="o">(</span><span class="n">build_br</span> <span class="n">merge_bb</span> <span class="n">builder</span><span class="o">);</span>
+
+<span class="c">(* Finally, set the builder to the end of the merge block. *)</span>
+<span class="n">position_at_end</span> <span class="n">merge_bb</span> <span class="n">builder</span><span class="o">;</span>
+
+<span class="n">phi</span>
+</pre></div>
+</div>
+<p>To finish off the blocks, we create an unconditional branch to the merge
+block. One interesting (and very important) aspect of the LLVM IR is
+that it <a class="reference external" href="../LangRef.html#functionstructure">requires all basic blocks to be
+“terminated”</a> with a <a class="reference external" href="../LangRef.html#terminators">control flow
+instruction</a> such as return or branch.
+This means that all control flow, <em>including fall throughs</em> must be made
+explicit in the LLVM IR. If you violate this rule, the verifier will
+emit an error.</p>
+<p>Finally, the CodeGen function returns the phi node as the value computed
+by the if/then/else expression. In our example above, this returned
+value will feed into the code for the top-level function, which will
+create the return instruction.</p>
+<p>Overall, we now have the ability to execute conditional code in
+Kaleidoscope. With this extension, Kaleidoscope is a fairly complete
+language that can calculate a wide variety of numeric functions. Next up
+we’ll add another useful expression that is familiar from non-functional
+languages...</p>
+</div>
+</div>
+<div class="section" id="for-loop-expression">
+<h2><a class="toc-backref" href="#id8">5.3. ‘for’ Loop Expression</a><a class="headerlink" href="#for-loop-expression" title="Permalink to this headline">¶</a></h2>
+<p>Now that we know how to add basic control flow constructs to the
+language, we have the tools to add more powerful things. Lets add
+something more aggressive, a ‘for’ expression:</p>
+<div class="highlight-python"><pre>extern putchard(char);
+def printstar(n)
+  for i = 1, i < n, 1.0 in
+    putchard(42);  # ascii 42 = '*'
+
+# print 100 '*' characters
+printstar(100);</pre>
+</div>
+<p>This expression defines a new variable (“i” in this case) which iterates
+from a starting value, while the condition (“i < n” in this case) is
+true, incrementing by an optional step value (“1.0” in this case). If
+the step value is omitted, it defaults to 1.0. While the loop is true,
+it executes its body expression. Because we don’t have anything better
+to return, we’ll just define the loop as always returning 0.0. In the
+future when we have mutable variables, it will get more useful.</p>
+<p>As before, lets talk about the changes that we need to Kaleidoscope to
+support this.</p>
+<div class="section" id="lexer-extensions-for-the-for-loop">
+<h3><a class="toc-backref" href="#id9">5.3.1. Lexer Extensions for the ‘for’ Loop</a><a class="headerlink" href="#lexer-extensions-for-the-for-loop" title="Permalink to this headline">¶</a></h3>
+<p>The lexer extensions are the same sort of thing as for if/then/else:</p>
+<div class="highlight-ocaml"><div class="highlight"><pre><span class="o">...</span> <span class="k">in</span> <span class="nn">Token</span><span class="p">.</span><span class="n">token</span> <span class="o">...</span>
+<span class="c">(* control *)</span>
+<span class="o">|</span> <span class="nc">If</span> <span class="o">|</span> <span class="nc">Then</span> <span class="o">|</span> <span class="nc">Else</span>
+<span class="o">|</span> <span class="nc">For</span> <span class="o">|</span> <span class="nn">In</span>
+
+<span class="p">...</span> <span class="n">in</span> <span class="nn">Lexer</span><span class="p">.</span><span class="n">lex_ident</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="s2">"if"</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">If</span><span class="o">;</span> <span class="n">stream</span> <span class="o">>]</span>
+    <span class="o">|</span> <span class="s2">"then"</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">Then</span><span class="o">;</span> <span class="n">stream</span> <span class="o">>]</span>
+    <span class="o">|</span> <span class="s2">"else"</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">Else</span><span class="o">;</span> <span class="n">stream</span> <span class="o">>]</span>
+    <span class="o">|</span> <span class="s2">"for"</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">For</span><span class="o">;</span> <span class="n">stream</span> <span class="o">>]</span>
+    <span class="o">|</span> <span class="s2">"in"</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">In</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>
+</div>
+<div class="section" id="ast-extensions-for-the-for-loop">
+<h3><a class="toc-backref" href="#id10">5.3.2. AST Extensions for the ‘for’ Loop</a><a class="headerlink" href="#ast-extensions-for-the-for-loop" title="Permalink to this headline">¶</a></h3>
+<p>The AST variant is just as simple. It basically boils down to capturing
+the variable name and the constituent expressions in the node.</p>
+<div class="highlight-ocaml"><div class="highlight"><pre><span class="k">type</span> <span class="n">expr</span> <span class="o">=</span>
+  <span class="o">...</span>
+  <span class="c">(* variant for for/in. *)</span>
+  <span class="o">|</span> <span class="nc">For</span> <span class="k">of</span> <span class="kt">string</span> <span class="o">*</span> <span class="n">expr</span> <span class="o">*</span> <span class="n">expr</span> <span class="o">*</span> <span class="n">expr</span> <span class="n">option</span> <span class="o">*</span> <span class="n">expr</span>
+</pre></div>
+</div>
+</div>
+<div class="section" id="parser-extensions-for-the-for-loop">
+<h3><a class="toc-backref" href="#id11">5.3.3. Parser Extensions for the ‘for’ Loop</a><a class="headerlink" href="#parser-extensions-for-the-for-loop" title="Permalink to this headline">¶</a></h3>
+<p>The parser code is also fairly standard. The only interesting thing here
+is handling of the optional step value. The parser code handles it by
+checking to see if the second comma is present. If not, it sets the step
+value to null in the AST node:</p>
+<div class="highlight-ocaml"><div class="highlight"><pre><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="o">...</span>
+  <span class="c">(* forexpr</span>
+<span class="c">        ::= 'for' identifier '=' expr ',' expr (',' expr)? 'in' 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">For</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="s2">"expected identifier after for"</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 '=' after for"</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="n">start</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 ',' after for"</span><span class="o">;</span>
+             <span class="n">end_</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">let</span> <span class="n">step</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">step</span><span class="o">=</span><span class="n">parse_expr</span> <span class="o">>]</span> <span class="o">-></span> <span class="nc">Some</span> <span class="n">step</span>
+              <span class="o">|</span> <span class="o">[<</span> <span class="o">>]</span> <span class="o">-></span> <span class="nc">None</span>
+              <span class="k">end</span> <span class="n">stream</span>
+            <span class="k">in</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">In</span><span class="o">;</span> <span class="n">body</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">For</span> <span class="o">(</span><span class="n">id</span><span class="o">,</span> <span class="n">start</span><span class="o">,</span> <span class="n">end_</span><span class="o">,</span> <span class="n">step</span><span class="o">,</span> <span class="n">body</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 'in' after for"</span><span class="o">)</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="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 '=' after for"</span><span class="o">)</span>
+      <span class="k">end</span> <span class="n">stream</span>
+</pre></div>
+</div>
+</div>
+<div class="section" id="llvm-ir-for-the-for-loop">
+<h3><a class="toc-backref" href="#id12">5.3.4. LLVM IR for the ‘for’ Loop</a><a class="headerlink" href="#llvm-ir-for-the-for-loop" title="Permalink to this headline">¶</a></h3>
+<p>Now we get to the good part: the LLVM IR we want to generate for this
+thing. With the simple example above, we get this LLVM IR (note that
+this dump is generated with optimizations disabled for clarity):</p>
+<div class="highlight-llvm"><div class="highlight"><pre><span class="k">declare</span> <span class="kt">double</span> <span class="vg">@putchard</span><span class="p">(</span><span class="kt">double</span><span class="p">)</span>
+
+<span class="k">define</span> <span class="kt">double</span> <span class="vg">@printstar</span><span class="p">(</span><span class="kt">double</span> <span class="nv">%n</span><span class="p">)</span> <span class="p">{</span>
+<span class="nl">entry:</span>
+        <span class="c">; initial value = 1.0 (inlined into phi)</span>
+  <span class="k">br</span> <span class="kt">label</span> <span class="nv">%loop</span>
+
+<span class="nl">loop:</span>    <span class="c">; preds = %loop, %entry</span>
+  <span class="nv">%i</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">%entry</span> <span class="p">],</span> <span class="p">[</span> <span class="nv">%nextvar</span><span class="p">,</span> <span class="nv">%loop</span> <span class="p">]</span>
+        <span class="c">; body</span>
+  <span class="nv">%calltmp</span> <span class="p">=</span> <span class="k">call</span> <span class="kt">double</span> <span class="vg">@putchard</span><span class="p">(</span><span class="kt">double</span> <span class="m">4.200000e+01</span><span class="p">)</span>
+        <span class="c">; increment</span>
+  <span class="nv">%nextvar</span> <span class="p">=</span> <span class="k">fadd</span> <span class="kt">double</span> <span class="nv">%i</span><span class="p">,</span> <span class="m">1.000000e+00</span>
+
+        <span class="c">; termination test</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">%i</span><span class="p">,</span> <span class="nv">%n</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">%loopcond</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">%loopcond</span><span class="p">,</span> <span class="kt">label</span> <span class="nv">%loop</span><span class="p">,</span> <span class="kt">label</span> <span class="nv">%afterloop</span>
+
+<span class="nl">afterloop:</span>    <span class="c">; preds = %loop</span>
+        <span class="c">; loop always returns 0.0</span>
+  <span class="k">ret</span> <span class="kt">double</span> <span class="m">0.000000e+00</span>
+<span class="p">}</span>
+</pre></div>
+</div>
+<p>This loop contains all the same constructs we saw before: a phi node,
+several expressions, and some basic blocks. Lets see how this fits
+together.</p>
+</div>
+<div class="section" id="code-generation-for-the-for-loop">
+<h3><a class="toc-backref" href="#id13">5.3.5. Code Generation for the ‘for’ Loop</a><a class="headerlink" href="#code-generation-for-the-for-loop" title="Permalink to this headline">¶</a></h3>
+<p>The first part of Codegen is very simple: we just output the start
+expression for the loop value:</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="o">|</span> <span class="nn">Ast</span><span class="p">.</span><span class="nc">For</span> <span class="o">(</span><span class="n">var_name</span><span class="o">,</span> <span class="n">start</span><span class="o">,</span> <span class="n">end_</span><span class="o">,</span> <span class="n">step</span><span class="o">,</span> <span class="n">body</span><span class="o">)</span> <span class="o">-></span>
+      <span class="c">(* Emit the start code first, without 'variable' in scope. *)</span>
+      <span class="k">let</span> <span class="n">start_val</span> <span class="o">=</span> <span class="n">codegen_expr</span> <span class="n">start</span> <span class="k">in</span>
+</pre></div>
+</div>
+<p>With this out of the way, the next step is to set up the LLVM basic
+block for the start of the loop body. In the case above, the whole loop
+body is one block, but remember that the body code itself could consist
+of multiple blocks (e.g. if it contains an if/then/else or a for/in
+expression).</p>
+<div class="highlight-ocaml"><div class="highlight"><pre><span class="c">(* Make the new basic block for the loop header, inserting after current</span>
+<span class="c"> * block. *)</span>
+<span class="k">let</span> <span class="n">preheader_bb</span> <span class="o">=</span> <span class="n">insertion_block</span> <span class="n">builder</span> <span class="k">in</span>
+<span class="k">let</span> <span class="n">the_function</span> <span class="o">=</span> <span class="n">block_parent</span> <span class="n">preheader_bb</span> <span class="k">in</span>
+<span class="k">let</span> <span class="n">loop_bb</span> <span class="o">=</span> <span class="n">append_block</span> <span class="n">context</span> <span class="s2">"loop"</span> <span class="n">the_function</span> <span class="k">in</span>
+
+<span class="c">(* Insert an explicit fall through from the current block to the</span>
+<span class="c"> * loop_bb. *)</span>
+<span class="n">ignore</span> <span class="o">(</span><span class="n">build_br</span> <span class="n">loop_bb</span> <span class="n">builder</span><span class="o">);</span>
+</pre></div>
+</div>
+<p>This code is similar to what we saw for if/then/else. Because we will
+need it to create the Phi node, we remember the block that falls through
+into the loop. Once we have that, we create the actual block that starts
+the loop and create an unconditional branch for the fall-through between
+the two blocks.</p>
+<div class="highlight-ocaml"><div class="highlight"><pre><span class="c">(* Start insertion in loop_bb. *)</span>
+<span class="n">position_at_end</span> <span class="n">loop_bb</span> <span class="n">builder</span><span class="o">;</span>
+
+<span class="c">(* Start the PHI node with an entry for start. *)</span>
+<span class="k">let</span> <span class="n">variable</span> <span class="o">=</span> <span class="n">build_phi</span> <span class="o">[(</span><span class="n">start_val</span><span class="o">,</span> <span class="n">preheader_bb</span><span class="o">)]</span> <span class="n">var_name</span> <span class="n">builder</span> <span class="k">in</span>
+</pre></div>
+</div>
+<p>Now that the “preheader” for the loop is set up, we switch to emitting
+code for the loop body. To begin with, we move the insertion point and
+create the PHI node for the loop induction variable. Since we already
+know the incoming value for the starting value, we add it to the Phi
+node. Note that the Phi will eventually get a second value for the
+backedge, but we can’t set it up yet (because it doesn’t exist!).</p>
+<div class="highlight-ocaml"><div class="highlight"><pre><span class="c">(* Within the loop, the variable is defined equal to the PHI node. If it</span>
+<span class="c"> * shadows an existing variable, we have to restore it, so save it</span>
+<span class="c"> * now. *)</span>
+<span class="k">let</span> <span class="n">old_val</span> <span class="o">=</span>
+  <span class="k">try</span> <span class="nc">Some</span> <span class="o">(</span><span class="nn">Hashtbl</span><span class="p">.</span><span class="n">find</span> <span class="n">named_values</span> <span class="n">var_name</span><span class="o">)</span> <span class="k">with</span> <span class="nc">Not_found</span> <span class="o">-></span> <span class="nc">None</span>
+<span class="k">in</span>
+<span class="nn">Hashtbl</span><span class="p">.</span><span class="n">add</span> <span class="n">named_values</span> <span class="n">var_name</span> <span class="n">variable</span><span class="o">;</span>
+
+<span class="c">(* Emit the body of the loop.  This, like any other expr, can change the</span>
+<span class="c"> * current BB.  Note that we ignore the value computed by the body, but</span>
+<span class="c"> * don't allow an error *)</span>
+<span class="n">ignore</span> <span class="o">(</span><span class="n">codegen_expr</span> <span class="n">body</span><span class="o">);</span>
+</pre></div>
+</div>
+<p>Now the code starts to get more interesting. Our ‘for’ loop introduces a
+new variable to the symbol table. This means that our symbol table can
+now contain either function arguments or loop variables. To handle this,
+before we codegen the body of the loop, we add the loop variable as the
+current value for its name. Note that it is possible that there is a
+variable of the same name in the outer scope. It would be easy to make
+this an error (emit an error and return null if there is already an
+entry for VarName) but we choose to allow shadowing of variables. In
+order to handle this correctly, we remember the Value that we are
+potentially shadowing in <tt class="docutils literal"><span class="pre">old_val</span></tt> (which will be None if there is no
+shadowed variable).</p>
+<p>Once the loop variable is set into the symbol table, the code
+recursively codegen’s the body. This allows the body to use the loop
+variable: any references to it will naturally find it in the symbol
+table.</p>
+<div class="highlight-ocaml"><div class="highlight"><pre><span class="c">(* Emit the step value. *)</span>
+<span class="k">let</span> <span class="n">step_val</span> <span class="o">=</span>
+  <span class="k">match</span> <span class="n">step</span> <span class="k">with</span>
+  <span class="o">|</span> <span class="nc">Some</span> <span class="n">step</span> <span class="o">-></span> <span class="n">codegen_expr</span> <span class="n">step</span>
+  <span class="c">(* If not specified, use 1.0. *)</span>
+  <span class="o">|</span> <span class="nc">None</span> <span class="o">-></span> <span class="n">const_float</span> <span class="n">double_type</span> <span class="mi">1</span><span class="o">.</span><span class="mi">0</span>
+<span class="k">in</span>
+
+<span class="k">let</span> <span class="n">next_var</span> <span class="o">=</span> <span class="n">build_add</span> <span class="n">variable</span> <span class="n">step_val</span> <span class="s2">"nextvar"</span> <span class="n">builder</span> <span class="k">in</span>
+</pre></div>
+</div>
+<p>Now that the body is emitted, we compute the next value of the iteration
+variable by adding the step value, or 1.0 if it isn’t present.
+‘<tt class="docutils literal"><span class="pre">next_var</span></tt>‘ will be the value of the loop variable on the next
+iteration of the loop.</p>
+<div class="highlight-ocaml"><div class="highlight"><pre><span class="c">(* Compute the end condition. *)</span>
+<span class="k">let</span> <span class="n">end_cond</span> <span class="o">=</span> <span class="n">codegen_expr</span> <span class="n">end_</span> <span class="k">in</span>
+
+<span class="c">(* Convert condition to a bool by comparing equal to 0.0. *)</span>
+<span class="k">let</span> <span class="n">zero</span> <span class="o">=</span> <span class="n">const_float</span> <span class="n">double_type</span> <span class="mi">0</span><span class="o">.</span><span class="mi">0</span> <span class="k">in</span>
+<span class="k">let</span> <span class="n">end_cond</span> <span class="o">=</span> <span class="n">build_fcmp</span> <span class="nn">Fcmp</span><span class="p">.</span><span class="nc">One</span> <span class="n">end_cond</span> <span class="n">zero</span> <span class="s2">"loopcond"</span> <span class="n">builder</span> <span class="k">in</span>
+</pre></div>
+</div>
+<p>Finally, we evaluate the exit value of the loop, to determine whether
+the loop should exit. This mirrors the condition evaluation for the
+if/then/else statement.</p>
+<div class="highlight-ocaml"><div class="highlight"><pre><span class="c">(* Create the "after loop" block and insert it. *)</span>
+<span class="k">let</span> <span class="n">loop_end_bb</span> <span class="o">=</span> <span class="n">insertion_block</span> <span class="n">builder</span> <span class="k">in</span>
+<span class="k">let</span> <span class="n">after_bb</span> <span class="o">=</span> <span class="n">append_block</span> <span class="n">context</span> <span class="s2">"afterloop"</span> <span class="n">the_function</span> <span class="k">in</span>
+
+<span class="c">(* Insert the conditional branch into the end of loop_end_bb. *)</span>
+<span class="n">ignore</span> <span class="o">(</span><span class="n">build_cond_br</span> <span class="n">end_cond</span> <span class="n">loop_bb</span> <span class="n">after_bb</span> <span class="n">builder</span><span class="o">);</span>
+
+<span class="c">(* Any new code will be inserted in after_bb. *)</span>
+<span class="n">position_at_end</span> <span class="n">after_bb</span> <span class="n">builder</span><span class="o">;</span>
+</pre></div>
+</div>
+<p>With the code for the body of the loop complete, we just need to finish
+up the control flow for it. This code remembers the end block (for the
+phi node), then creates the block for the loop exit (“afterloop”). Based
+on the value of the exit condition, it creates a conditional branch that
+chooses between executing the loop again and exiting the loop. Any
+future code is emitted in the “afterloop” block, so it sets the
+insertion position to it.</p>
+<div class="highlight-ocaml"><div class="highlight"><pre><span class="c">(* Add a new entry to the PHI node for the backedge. *)</span>
+<span class="n">add_incoming</span> <span class="o">(</span><span class="n">next_var</span><span class="o">,</span> <span class="n">loop_end_bb</span><span class="o">)</span> <span class="n">variable</span><span class="o">;</span>
+
+<span class="c">(* Restore the unshadowed variable. *)</span>
+<span class="k">begin</span> <span class="k">match</span> <span class="n">old_val</span> <span class="k">with</span>
+<span class="o">|</span> <span class="nc">Some</span> <span class="n">old_val</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">var_name</span> <span class="n">old_val</span>
+<span class="o">|</span> <span class="nc">None</span> <span class="o">-></span> <span class="bp">()</span>
+<span class="k">end</span><span class="o">;</span>
+
+<span class="c">(* for expr always returns 0.0. *)</span>
+<span class="n">const_null</span> <span class="n">double_type</span>
+</pre></div>
+</div>
+<p>The final code handles various cleanups: now that we have the
+“<tt class="docutils literal"><span class="pre">next_var</span></tt>” value, we can add the incoming value to the loop PHI
+node. After that, we remove the loop variable from the symbol table, so
+that it isn’t in scope after the for loop. Finally, code generation of
+the for loop always returns 0.0, so that is what we return from
+<tt class="docutils literal"><span class="pre">Codegen.codegen_expr</span></tt>.</p>
+<p>With this, we conclude the “adding control flow to Kaleidoscope” chapter
+of the tutorial. In this chapter we added two control flow constructs,
+and used them to motivate a couple of aspects of the LLVM IR that are
+important for front-end implementors to know. In the next chapter of our
+saga, we will get a bit crazier and add <a class="reference external" href="OCamlLangImpl6.html">user-defined
+operators</a> to our poor innocent language.</p>
+</div>
+</div>
+<div class="section" id="full-code-listing">
+<h2><a class="toc-backref" href="#id14">5.4. 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>
+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"><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>
+</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>
+
+  <span class="c">(* control *)</span>
+  <span class="o">|</span> <span class="nc">If</span> <span class="o">|</span> <span class="nc">Then</span> <span class="o">|</span> <span class="nc">Else</span>
+  <span class="o">|</span> <span class="nc">For</span> <span class="o">|</span> <span class="nc">In</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="s2">"if"</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">If</span><span class="o">;</span> <span class="n">stream</span> <span class="o">>]</span>
+      <span class="o">|</span> <span class="s2">"then"</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">Then</span><span class="o">;</span> <span class="n">stream</span> <span class="o">>]</span>
+      <span class="o">|</span> <span class="s2">"else"</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">Else</span><span class="o">;</span> <span class="n">stream</span> <span class="o">>]</span>
+      <span class="o">|</span> <span class="s2">"for"</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">For</span><span class="o">;</span> <span class="n">stream</span> <span class="o">>]</span>
+      <span class="o">|</span> <span class="s2">"in"</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">In</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">(* variant for if/then/else. *)</span>
+  <span class="o">|</span> <span class="nc">If</span> <span class="k">of</span> <span class="n">expr</span> <span class="o">*</span> <span class="n">expr</span> <span class="o">*</span> <span class="n">expr</span>
+
+  <span class="c">(* variant for for/in. *)</span>
+  <span class="o">|</span> <span class="nc">For</span> <span class="k">of</span> <span class="kt">string</span> <span class="o">*</span> <span class="n">expr</span> <span class="o">*</span> <span class="n">expr</span> <span class="o">*</span> <span class="n">expr</span> <span class="n">option</span> <span class="o">*</span> <span class="n">expr</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="c"> *   ::= ifexpr</span>
+<span class="c"> *   ::= forexpr *)</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="c">(* ifexpr ::= 'if' expr 'then' expr 'else' expr *)</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">If</span><span class="o">;</span> <span class="n">c</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">Then</span> <span class="o">??</span> <span class="s2">"expected 'then'"</span><span class="o">;</span> <span class="n">t</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">Else</span> <span class="o">??</span> <span class="s2">"expected 'else'"</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">If</span> <span class="o">(</span><span class="n">c</span><span class="o">,</span> <span class="n">t</span><span class="o">,</span> <span class="n">e</span><span class="o">)</span>
+
+  <span class="c">(* forexpr</span>
+<span class="c">        ::= 'for' identifier '=' expr ',' expr (',' expr)? 'in' 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">For</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="s2">"expected identifier after for"</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 '=' after for"</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="n">start</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 ',' after for"</span><span class="o">;</span>
+             <span class="n">end_</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">let</span> <span class="n">step</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">step</span><span class="o">=</span><span class="n">parse_expr</span> <span class="o">>]</span> <span class="o">-></span> <span class="nc">Some</span> <span class="n">step</span>
+              <span class="o">|</span> <span class="o">[<</span> <span class="o">>]</span> <span class="o">-></span> <span class="nc">None</span>
+              <span class="k">end</span> <span class="n">stream</span>
+            <span class="k">in</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">In</span><span class="o">;</span> <span class="n">body</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">For</span> <span class="o">(</span><span class="n">id</span><span class="o">,</span> <span class="n">start</span><span class="o">,</span> <span class="n">end_</span><span class="o">,</span> <span class="n">step</span><span class="o">,</span> <span class="n">body</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 'in' after for"</span><span class="o">)</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="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 '=' after for"</span><span class="o">)</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="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="o">|</span> <span class="nn">Ast</span><span class="p">.</span><span class="nc">If</span> <span class="o">(</span><span class="n">cond</span><span class="o">,</span> <span class="n">then_</span><span class="o">,</span> <span class="n">else_</span><span class="o">)</span> <span class="o">-></span>
+      <span class="k">let</span> <span class="n">cond</span> <span class="o">=</span> <span class="n">codegen_expr</span> <span class="n">cond</span> <span class="k">in</span>
+
+      <span class="c">(* Convert condition to a bool by comparing equal to 0.0 *)</span>
+      <span class="k">let</span> <span class="n">zero</span> <span class="o">=</span> <span class="n">const_float</span> <span class="n">double_type</span> <span class="mi">0</span><span class="o">.</span><span class="mi">0</span> <span class="k">in</span>
+      <span class="k">let</span> <span class="n">cond_val</span> <span class="o">=</span> <span class="n">build_fcmp</span> <span class="nn">Fcmp</span><span class="p">.</span><span class="nc">One</span> <span class="n">cond</span> <span class="n">zero</span> <span class="s2">"ifcond"</span> <span class="n">builder</span> <span class="k">in</span>
+
+      <span class="c">(* Grab the first block so that we might later add the conditional branch</span>
+<span class="c">       * to it at the end of the function. *)</span>
+      <span class="k">let</span> <span class="n">start_bb</span> <span class="o">=</span> <span class="n">insertion_block</span> <span class="n">builder</span> <span class="k">in</span>
+      <span class="k">let</span> <span class="n">the_function</span> <span class="o">=</span> <span class="n">block_parent</span> <span class="n">start_bb</span> <span class="k">in</span>
+
+      <span class="k">let</span> <span class="n">then_bb</span> <span class="o">=</span> <span class="n">append_block</span> <span class="n">context</span> <span class="s2">"then"</span> <span class="n">the_function</span> <span class="k">in</span>
+
+      <span class="c">(* Emit 'then' value. *)</span>
+      <span class="n">position_at_end</span> <span class="n">then_bb</span> <span class="n">builder</span><span class="o">;</span>
+      <span class="k">let</span> <span class="n">then_val</span> <span class="o">=</span> <span class="n">codegen_expr</span> <span class="n">then_</span> <span class="k">in</span>
+
+      <span class="c">(* Codegen of 'then' can change the current block, update then_bb for the</span>
+<span class="c">       * phi. We create a new name because one is used for the phi node, and the</span>
+<span class="c">       * other is used for the conditional branch. *)</span>
+      <span class="k">let</span> <span class="n">new_then_bb</span> <span class="o">=</span> <span class="n">insertion_block</span> <span class="n">builder</span> <span class="k">in</span>
+
+      <span class="c">(* Emit 'else' value. *)</span>
+      <span class="k">let</span> <span class="n">else_bb</span> <span class="o">=</span> <span class="n">append_block</span> <span class="n">context</span> <span class="s2">"else"</span> <span class="n">the_function</span> <span class="k">in</span>
+      <span class="n">position_at_end</span> <span class="n">else_bb</span> <span class="n">builder</span><span class="o">;</span>
+      <span class="k">let</span> <span class="n">else_val</span> <span class="o">=</span> <span class="n">codegen_expr</span> <span class="n">else_</span> <span class="k">in</span>
+
+      <span class="c">(* Codegen of 'else' can change the current block, update else_bb for the</span>
+<span class="c">       * phi. *)</span>
+      <span class="k">let</span> <span class="n">new_else_bb</span> <span class="o">=</span> <span class="n">insertion_block</span> <span class="n">builder</span> <span class="k">in</span>
+
+      <span class="c">(* Emit merge block. *)</span>
+      <span class="k">let</span> <span class="n">merge_bb</span> <span class="o">=</span> <span class="n">append_block</span> <span class="n">context</span> <span class="s2">"ifcont"</span> <span class="n">the_function</span> <span class="k">in</span>
+      <span class="n">position_at_end</span> <span class="n">merge_bb</span> <span class="n">builder</span><span class="o">;</span>
+      <span class="k">let</span> <span class="n">incoming</span> <span class="o">=</span> <span class="o">[(</span><span class="n">then_val</span><span class="o">,</span> <span class="n">new_then_bb</span><span class="o">);</span> <span class="o">(</span><span class="n">else_val</span><span class="o">,</span> <span class="n">new_else_bb</span><span class="o">)]</span> <span class="k">in</span>
+      <span class="k">let</span> <span class="n">phi</span> <span class="o">=</span> <span class="n">build_phi</span> <span class="n">incoming</span> <span class="s2">"iftmp"</span> <span class="n">builder</span> <span class="k">in</span>
+
+      <span class="c">(* Return to the start block to add the conditional branch. *)</span>
+      <span class="n">position_at_end</span> <span class="n">start_bb</span> <span class="n">builder</span><span class="o">;</span>
+      <span class="n">ignore</span> <span class="o">(</span><span class="n">build_cond_br</span> <span class="n">cond_val</span> <span class="n">then_bb</span> <span class="n">else_bb</span> <span class="n">builder</span><span class="o">);</span>
+
+      <span class="c">(* Set a unconditional branch at the end of the 'then' block and the</span>
+<span class="c">       * 'else' block to the 'merge' block. *)</span>
+      <span class="n">position_at_end</span> <span class="n">new_then_bb</span> <span class="n">builder</span><span class="o">;</span> <span class="n">ignore</span> <span class="o">(</span><span class="n">build_br</span> <span class="n">merge_bb</span> <span class="n">builder</span><span class="o">);</span>
+      <span class="n">position_at_end</span> <span class="n">new_else_bb</span> <span class="n">builder</span><span class="o">;</span> <span class="n">ignore</span> <span class="o">(</span><span class="n">build_br</span> <span class="n">merge_bb</span> <span class="n">builder</span><span class="o">);</span>
+
+      <span class="c">(* Finally, set the builder to the end of the merge block. *)</span>
+      <span class="n">position_at_end</span> <span class="n">merge_bb</span> <span class="n">builder</span><span class="o">;</span>
+
+      <span class="n">phi</span>
+  <span class="o">|</span> <span class="nn">Ast</span><span class="p">.</span><span class="nc">For</span> <span class="o">(</span><span class="n">var_name</span><span class="o">,</span> <span class="n">start</span><span class="o">,</span> <span class="n">end_</span><span class="o">,</span> <span class="n">step</span><span class="o">,</span> <span class="n">body</span><span class="o">)</span> <span class="o">-></span>
+      <span class="c">(* Emit the start code first, without 'variable' in scope. *)</span>
+      <span class="k">let</span> <span class="n">start_val</span> <span class="o">=</span> <span class="n">codegen_expr</span> <span class="n">start</span> <span class="k">in</span>
+
+      <span class="c">(* Make the new basic block for the loop header, inserting after current</span>
+<span class="c">       * block. *)</span>
+      <span class="k">let</span> <span class="n">preheader_bb</span> <span class="o">=</span> <span class="n">insertion_block</span> <span class="n">builder</span> <span class="k">in</span>
+      <span class="k">let</span> <span class="n">the_function</span> <span class="o">=</span> <span class="n">block_parent</span> <span class="n">preheader_bb</span> <span class="k">in</span>
+      <span class="k">let</span> <span class="n">loop_bb</span> <span class="o">=</span> <span class="n">append_block</span> <span class="n">context</span> <span class="s2">"loop"</span> <span class="n">the_function</span> <span class="k">in</span>
+
+      <span class="c">(* Insert an explicit fall through from the current block to the</span>
+<span class="c">       * loop_bb. *)</span>
+      <span class="n">ignore</span> <span class="o">(</span><span class="n">build_br</span> <span class="n">loop_bb</span> <span class="n">builder</span><span class="o">);</span>
+
+      <span class="c">(* Start insertion in loop_bb. *)</span>
+      <span class="n">position_at_end</span> <span class="n">loop_bb</span> <span class="n">builder</span><span class="o">;</span>
+
+      <span class="c">(* Start the PHI node with an entry for start. *)</span>
+      <span class="k">let</span> <span class="n">variable</span> <span class="o">=</span> <span class="n">build_phi</span> <span class="o">[(</span><span class="n">start_val</span><span class="o">,</span> <span class="n">preheader_bb</span><span class="o">)]</span> <span class="n">var_name</span> <span class="n">builder</span> <span class="k">in</span>
+
+      <span class="c">(* Within the loop, the variable is defined equal to the PHI node. If it</span>
+<span class="c">       * shadows an existing variable, we have to restore it, so save it</span>
+<span class="c">       * now. *)</span>
+      <span class="k">let</span> <span class="n">old_val</span> <span class="o">=</span>
+        <span class="k">try</span> <span class="nc">Some</span> <span class="o">(</span><span class="nn">Hashtbl</span><span class="p">.</span><span class="n">find</span> <span class="n">named_values</span> <span class="n">var_name</span><span class="o">)</span> <span class="k">with</span> <span class="nc">Not_found</span> <span class="o">-></span> <span class="nc">None</span>
+      <span class="k">in</span>
+      <span class="nn">Hashtbl</span><span class="p">.</span><span class="n">add</span> <span class="n">named_values</span> <span class="n">var_name</span> <span class="n">variable</span><span class="o">;</span>
+
+      <span class="c">(* Emit the body of the loop.  This, like any other expr, can change the</span>
+<span class="c">       * current BB.  Note that we ignore the value computed by the body, but</span>
+<span class="c">       * don't allow an error *)</span>
+      <span class="n">ignore</span> <span class="o">(</span><span class="n">codegen_expr</span> <span class="n">body</span><span class="o">);</span>
+
+      <span class="c">(* Emit the step value. *)</span>
+      <span class="k">let</span> <span class="n">step_val</span> <span class="o">=</span>
+        <span class="k">match</span> <span class="n">step</span> <span class="k">with</span>
+        <span class="o">|</span> <span class="nc">Some</span> <span class="n">step</span> <span class="o">-></span> <span class="n">codegen_expr</span> <span class="n">step</span>
+        <span class="c">(* If not specified, use 1.0. *)</span>
+        <span class="o">|</span> <span class="nc">None</span> <span class="o">-></span> <span class="n">const_float</span> <span class="n">double_type</span> <span class="mi">1</span><span class="o">.</span><span class="mi">0</span>
+      <span class="k">in</span>
+
+      <span class="k">let</span> <span class="n">next_var</span> <span class="o">=</span> <span class="n">build_add</span> <span class="n">variable</span> <span class="n">step_val</span> <span class="s2">"nextvar"</span> <span class="n">builder</span> <span class="k">in</span>
+
+      <span class="c">(* Compute the end condition. *)</span>
+      <span class="k">let</span> <span class="n">end_cond</span> <span class="o">=</span> <span class="n">codegen_expr</span> <span class="n">end_</span> <span class="k">in</span>
+
+      <span class="c">(* Convert condition to a bool by comparing equal to 0.0. *)</span>
+      <span class="k">let</span> <span class="n">zero</span> <span class="o">=</span> <span class="n">const_float</span> <span class="n">double_type</span> <span class="mi">0</span><span class="o">.</span><span class="mi">0</span> <span class="k">in</span>
+      <span class="k">let</span> <span class="n">end_cond</span> <span class="o">=</span> <span class="n">build_fcmp</span> <span class="nn">Fcmp</span><span class="p">.</span><span class="nc">One</span> <span class="n">end_cond</span> <span class="n">zero</span> <span class="s2">"loopcond"</span> <span class="n">builder</span> <span class="k">in</span>
+
+      <span class="c">(* Create the "after loop" block and insert it. *)</span>
+      <span class="k">let</span> <span class="n">loop_end_bb</span> <span class="o">=</span> <span class="n">insertion_block</span> <span class="n">builder</span> <span class="k">in</span>
+      <span class="k">let</span> <span class="n">after_bb</span> <span class="o">=</span> <span class="n">append_block</span> <span class="n">context</span> <span class="s2">"afterloop"</span> <span class="n">the_function</span> <span class="k">in</span>
+
+      <span class="c">(* Insert the conditional branch into the end of loop_end_bb. *)</span>
+      <span class="n">ignore</span> <span class="o">(</span><span class="n">build_cond_br</span> <span class="n">end_cond</span> <span class="n">loop_bb</span> <span class="n">after_bb</span> <span class="n">builder</span><span class="o">);</span>
+
+      <span class="c">(* Any new code will be inserted in after_bb. *)</span>
+      <span class="n">position_at_end</span> <span class="n">after_bb</span> <span class="n">builder</span><span class="o">;</span>
+
+      <span class="c">(* Add a new entry to the PHI node for the backedge. *)</span>
+      <span class="n">add_incoming</span> <span class="o">(</span><span class="n">next_var</span><span class="o">,</span> <span class="n">loop_end_bb</span><span class="o">)</span> <span class="n">variable</span><span class="o">;</span>
+
+      <span class="c">(* Restore the unshadowed variable. *)</span>
+      <span class="k">begin</span> <span class="k">match</span> <span class="n">old_val</span> <span class="k">with</span>
+      <span class="o">|</span> <span class="nc">Some</span> <span class="n">old_val</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">var_name</span> <span class="n">old_val</span>
+      <span class="o">|</span> <span class="nc">None</span> <span class="o">-></span> <span class="bp">()</span>
+      <span class="k">end</span><span class="o">;</span>
+
+      <span class="c">(* for expr always returns 0.0. *)</span>
+      <span class="n">const_null</span> <span class="n">double_type</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="OCamlLangImpl6.html">Next: Extending the language: user-defined
+operators</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="OCamlLangImpl6.html" title="6. Kaleidoscope: Extending the Language: User-defined Operators" +>next</a> |</li>
+        <li class="right" >
+          <a href="OCamlLangImpl4.html" title="4. Kaleidoscope: Adding JIT and Optimizer Support" +>previous</a> |</li>
+  <li><a href="https://urldefense.proofpoint.com/v2/url?u=http-3A__llvm.org_&d=AwMDaQ&c=8hUWFZcy2Z-Za5rBPlktOQ&r=mQ4LZ2PUj9hpadE3cDHZnIdEwhEBrbAstXeMaFoB9tg&m=QAGZeXoSMCv0h4wI0rExv_W1lSHAp-_70Lmc3PA5EtM&s=pfiJKhwlj5rZUzKRdDQCg_cdTSO0Ut0YcGMOb-jpeAs&e=">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 2003-2014, LLVM Project.
+      Last updated on 2015-05-25.
+      Created using <a href="https://urldefense.proofpoint.com/v2/url?u=http-3A__sphinx.pocoo.org_&d=AwMDaQ&c=8hUWFZcy2Z-Za5rBPlktOQ&r=mQ4LZ2PUj9hpadE3cDHZnIdEwhEBrbAstXeMaFoB9tg&m=QAGZeXoSMCv0h4wI0rExv_W1lSHAp-_70Lmc3PA5EtM&s=lSOQQPBONfHSHDEAc1rfzOSlyTiliJLtzc8JrV9lcX4&e=">Sphinx</a> 1.1.3.
+    </div>
+  </body>
+</html>
\ No newline at end of file

Added: www-releases/trunk/3.6.1/docs/tutorial/OCamlLangImpl6.html
URL: http://llvm.org/viewvc/llvm-project/www-releases/trunk/3.6.1/docs/tutorial/OCamlLangImpl6.html?rev=238135&view=auto
==============================================================================
--- www-releases/trunk/3.6.1/docs/tutorial/OCamlLangImpl6.html (added)
+++ www-releases/trunk/3.6.1/docs/tutorial/OCamlLangImpl6.html Mon May 25 08:53:02 2015
@@ -0,0 +1,1485 @@
+
+
+<!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 3.6 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:     '3.6',
+        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 3.6 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="OCamlLangImpl7.html" />
+    <link rel="prev" title="5. Kaleidoscope: Extending the Language: Control Flow" href="OCamlLangImpl5.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="OCamlLangImpl7.html" title="7. Kaleidoscope: Extending the Language: Mutable Variables" + accesskey="N">next</a> |</li>
+        <li class="right" >
+          <a href="OCamlLangImpl5.html" title="5. Kaleidoscope: Extending the Language: Control Flow" + accesskey="P">previous</a> |</li>
+  <li><a href="https://urldefense.proofpoint.com/v2/url?u=http-3A__llvm.org_&d=AwMDaQ&c=8hUWFZcy2Z-Za5rBPlktOQ&r=mQ4LZ2PUj9hpadE3cDHZnIdEwhEBrbAstXeMaFoB9tg&m=QAGZeXoSMCv0h4wI0rExv_W1lSHAp-_70Lmc3PA5EtM&s=pfiJKhwlj5rZUzKRdDQCg_cdTSO0Ut0YcGMOb-jpeAs&e=">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="#example">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="OCamlLangImpl2.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"><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>
+<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-ocaml"><div class="highlight"><pre><span class="k">type</span> <span class="n">token</span> <span class="o">=</span>
+  <span class="o">...</span>
+  <span class="c">(* operators *)</span>
+  <span class="o">|</span> <span class="nc">Binary</span> <span class="o">|</span> <span class="nn">Unary</span>
+
+<span class="p">...</span>
+
+<span class="n">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="s2">"for"</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">For</span><span class="o">;</span> <span class="n">stream</span> <span class="o">>]</span>
+      <span class="o">|</span> <span class="s2">"in"</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">In</span><span class="o">;</span> <span class="n">stream</span> <span class="o">>]</span>
+      <span class="o">|</span> <span class="s2">"binary"</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">Binary</span><span class="o">;</span> <span class="n">stream</span> <span class="o">>]</span>
+      <span class="o">|</span> <span class="s2">"unary"</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">Unary</span><span class="o">;</span> <span class="n">stream</span> <span class="o">>]</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="OCamlLangImpl5.html#iflexer">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">Ast.Prototype</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">Ast.Prototype</span></tt> AST node like
+this:</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="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="o">|</span> <span class="nc">BinOpPrototype</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="o">*</span> <span class="kt">int</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-ocaml"><div class="highlight"><pre><span class="c">(* prototype</span>
+<span class="c"> *   ::= id '(' id* ')'</span>
+<span class="c"> *   ::= binary LETTER number? (id, id)</span>
+<span class="c"> *   ::= unary LETTER number? (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="k">let</span> <span class="n">parse_operator</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">Unary</span> <span class="o">>]</span> <span class="o">-></span> <span class="s2">"unary"</span><span class="o">,</span> <span class="mi">1</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">Binary</span> <span class="o">>]</span> <span class="o">-></span> <span class="s2">"binary"</span><span class="o">,</span> <span class="mi">2</span>
+  <span class="k">in</span>
+  <span class="k">let</span> <span class="n">parse_binary_precedence</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">Number</span> <span class="n">n</span> <span class="o">>]</span> <span class="o">-></span> <span class="n">int_of_float</span> <span class="n">n</span>
+    <span class="o">|</span> <span class="o">[<</span> <span class="o">>]</span> <span class="o">-></span> <span class="mi">30</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="n">prefix</span><span class="o">,</span> <span class="n">kind</span><span class="o">)=</span><span class="n">parse_operator</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">op</span> <span class="o">??</span> <span class="s2">"expected an operator"</span><span class="o">;</span>
+       <span class="c">(* Read the precedence if present. *)</span>
+       <span class="n">binary_precedence</span><span class="o">=</span><span class="n">parse_binary_precedence</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="k">let</span> <span class="n">name</span> <span class="o">=</span> <span class="n">prefix</span> <span class="o">^</span> <span class="o">(</span><span class="nn">String</span><span class="p">.</span><span class="n">make</span> <span class="mi">1</span> <span class="n">op</span><span class="o">)</span> <span class="k">in</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">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="k">in</span>
+
+      <span class="c">(* Verify right number of arguments for operator. *)</span>
+      <span class="k">if</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">kind</span>
+      <span class="k">then</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">"invalid number of operands for operator"</span><span class="o">)</span>
+      <span class="k">else</span>
+        <span class="k">if</span> <span class="n">kind</span> <span class="o">==</span> <span class="mi">1</span> <span class="k">then</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="k">else</span>
+          <span class="nn">Ast</span><span class="p">.</span><span class="nc">BinOpPrototype</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="n">binary_precedence</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>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">name</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-ocaml"><div class="highlight"><pre><span class="k">let</span> <span class="n">codegen_expr</span> <span class="o">=</span> <span class="k">function</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="c">(* If it wasn't a builtin binary operator, it must be a user defined</span>
+<span class="c">             * one. Emit a call to it. *)</span>
+            <span class="k">let</span> <span class="n">callee</span> <span class="o">=</span> <span class="s2">"binary"</span> <span class="o">^</span> <span class="o">(</span><span class="nn">String</span><span class="p">.</span><span class="n">make</span> <span class="mi">1</span> <span class="n">op</span><span class="o">)</span> <span class="k">in</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">"binary operator not found!"</span><span class="o">)</span>
+            <span class="k">in</span>
+            <span class="n">build_call</span> <span class="n">callee</span> <span class="o">[|</span><span class="n">lhs_val</span><span class="o">;</span> <span class="n">rhs_val</span><span class="o">|]</span> <span class="s2">"binop"</span> <span class="n">builder</span>
+      <span class="k">end</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-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="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">(* If this is an operator, install it. *)</span>
+      <span class="k">begin</span> <span class="k">match</span> <span class="n">proto</span> <span class="k">with</span>
+      <span class="o">|</span> <span class="nn">Ast</span><span class="p">.</span><span class="nc">BinOpPrototype</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="n">prec</span><span class="o">)</span> <span class="o">-></span>
+          <span class="k">let</span> <span class="n">op</span> <span class="o">=</span> <span class="n">name</span><span class="o">.[</span><span class="nn">String</span><span class="p">.</span><span class="n">length</span> <span class="n">name</span> <span class="o">-</span> <span class="mi">1</span><span class="o">]</span> <span class="k">in</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="n">op</span> <span class="n">prec</span><span class="o">;</span>
+      <span class="o">|</span> <span class="o">_</span> <span class="o">-></span> <span class="bp">()</span>
+      <span class="k">end</span><span class="o">;</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="o">...</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-ocaml"><div class="highlight"><pre><span class="k">type</span> <span class="n">expr</span> <span class="o">=</span>
+  <span class="o">...</span>
+  <span class="c">(* variant for a unary operator. *)</span>
+  <span class="o">|</span> <span class="nc">Unary</span> <span class="k">of</span> <span class="kt">char</span> <span class="o">*</span> <span class="n">expr</span>
+  <span class="o">...</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-ocaml"><div class="highlight"><pre><span class="c">(* unary</span>
+<span class="c"> *   ::= primary</span>
+<span class="c"> *   ::= '!' unary *)</span>
+<span class="ow">and</span> <span class="n">parse_unary</span> <span class="o">=</span> <span class="n">parser</span>
+  <span class="c">(* If this is a unary operator, read it. *)</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">op</span> <span class="k">when</span> <span class="n">op</span> <span class="o">!=</span> <span class="sc">'('</span> <span class="o">&&</span> <span class="n">op</span> <span class="o">!=</span> <span class="sc">')'</span><span class="o">;</span> <span class="n">operand</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">Unary</span> <span class="o">(</span><span class="n">op</span><span class="o">,</span> <span class="n">operand</span><span class="o">)</span>
+
+  <span class="c">(* If the current token is not an operator, it must be a primary expr. *)</span>
+  <span class="o">|</span> <span class="o">[<</span> <span class="n">stream</span> <span class="o">>]</span> <span class="o">-></span> <span class="n">parse_primary</span> <span class="n">stream</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 <tt class="docutils literal"><span class="pre">parse_unary</span></tt> instead:</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="o">...</span>
+        <span class="c">(* Parse the unary expression after the binary operator. *)</span>
+        <span class="k">let</span> <span class="n">rhs</span> <span class="o">=</span> <span class="n">parse_unary</span> <span class="n">stream</span> <span class="k">in</span>
+        <span class="o">...</span>
+
+<span class="o">...</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_unary</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>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-ocaml"><div class="highlight"><pre><span class="c">(* prototype</span>
+<span class="c"> *   ::= id '(' id* ')'</span>
+<span class="c"> *   ::= binary LETTER number? (id, id)</span>
+<span class="c"> *   ::= unary LETTER number? (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="k">let</span> <span class="n">parse_operator</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">Unary</span> <span class="o">>]</span> <span class="o">-></span> <span class="s2">"unary"</span><span class="o">,</span> <span class="mi">1</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">Binary</span> <span class="o">>]</span> <span class="o">-></span> <span class="s2">"binary"</span><span class="o">,</span> <span class="mi">2</span>
+  <span class="k">in</span>
+  <span class="k">let</span> <span class="n">parse_binary_precedence</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">Number</span> <span class="n">n</span> <span class="o">>]</span> <span class="o">-></span> <span class="n">int_of_float</span> <span class="n">n</span>
+    <span class="o">|</span> <span class="o">[<</span> <span class="o">>]</span> <span class="o">-></span> <span class="mi">30</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="n">prefix</span><span class="o">,</span> <span class="n">kind</span><span class="o">)=</span><span class="n">parse_operator</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">op</span> <span class="o">??</span> <span class="s2">"expected an operator"</span><span class="o">;</span>
+       <span class="c">(* Read the precedence if present. *)</span>
+       <span class="n">binary_precedence</span><span class="o">=</span><span class="n">parse_binary_precedence</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="k">let</span> <span class="n">name</span> <span class="o">=</span> <span class="n">prefix</span> <span class="o">^</span> <span class="o">(</span><span class="nn">String</span><span class="p">.</span><span class="n">make</span> <span class="mi">1</span> <span class="n">op</span><span class="o">)</span> <span class="k">in</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">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="k">in</span>
+
+      <span class="c">(* Verify right number of arguments for operator. *)</span>
+      <span class="k">if</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">kind</span>
+      <span class="k">then</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">"invalid number of operands for operator"</span><span class="o">)</span>
+      <span class="k">else</span>
+        <span class="k">if</span> <span class="n">kind</span> <span class="o">==</span> <span class="mi">1</span> <span class="k">then</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="k">else</span>
+          <span class="nn">Ast</span><span class="p">.</span><span class="nc">BinOpPrototype</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="n">binary_precedence</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>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-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="o">|</span> <span class="nn">Ast</span><span class="p">.</span><span class="nc">Unary</span> <span class="o">(</span><span class="n">op</span><span class="o">,</span> <span class="n">operand</span><span class="o">)</span> <span class="o">-></span>
+      <span class="k">let</span> <span class="n">operand</span> <span class="o">=</span> <span class="n">codegen_expr</span> <span class="n">operand</span> <span class="k">in</span>
+      <span class="k">let</span> <span class="n">callee</span> <span class="o">=</span> <span class="s2">"unary"</span> <span class="o">^</span> <span class="o">(</span><span class="nn">String</span><span class="p">.</span><span class="n">make</span> <span class="mi">1</span> <span class="n">op</span><span class="o">)</span> <span class="k">in</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 unary operator"</span><span class="o">)</span>
+      <span class="k">in</span>
+      <span class="n">build_call</span> <span class="n">callee</span> <span class="o">[|</span><span class="n">operand</span><span class="o">|]</span> <span class="s2">"unop"</span> <span class="n">builder</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"><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>
+<p>We can also define a bunch of other “primitive” operations, such as:</p>
+<div class="highlight-python"><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);</pre>
+</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"><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>
+<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"><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>
+<p>This “z = z<sup>2</sup> + c” function is a beautiful little creature
+that is the basis for computation of the <a class="reference external" href="https://urldefense.proofpoint.com/v2/url?u=http-3A__en.wikipedia.org_wiki_Mandelbrot-5Fset&d=AwMDaQ&c=8hUWFZcy2Z-Za5rBPlktOQ&r=mQ4LZ2PUj9hpadE3cDHZnIdEwhEBrbAstXeMaFoB9tg&m=QAGZeXoSMCv0h4wI0rExv_W1lSHAp-_70Lmc3PA5EtM&s=wMdSC1EtnypXDZTZSIYxOBlJqMvDwzTnJSkLgeMkNA4&e=">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"><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>
+<p>Given this, we can try plotting out the mandlebrot set! Lets try it out:</p>
+<div class="highlight-python"><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>
+<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="OCamlLangImpl7.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>
+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"><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>
+</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="nc">A</span><span class="s2">"-cclib"</span><span class="o">;</span> <span class="nc">A</span><span class="s2">"-rdynamic"</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>
+
+  <span class="c">(* control *)</span>
+  <span class="o">|</span> <span class="nc">If</span> <span class="o">|</span> <span class="nc">Then</span> <span class="o">|</span> <span class="nc">Else</span>
+  <span class="o">|</span> <span class="nc">For</span> <span class="o">|</span> <span class="nc">In</span>
+
+  <span class="c">(* operators *)</span>
+  <span class="o">|</span> <span class="nc">Binary</span> <span class="o">|</span> <span class="nc">Unary</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="s2">"if"</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">If</span><span class="o">;</span> <span class="n">stream</span> <span class="o">>]</span>
+      <span class="o">|</span> <span class="s2">"then"</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">Then</span><span class="o">;</span> <span class="n">stream</span> <span class="o">>]</span>
+      <span class="o">|</span> <span class="s2">"else"</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">Else</span><span class="o">;</span> <span class="n">stream</span> <span class="o">>]</span>
+      <span class="o">|</span> <span class="s2">"for"</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">For</span><span class="o">;</span> <span class="n">stream</span> <span class="o">>]</span>
+      <span class="o">|</span> <span class="s2">"in"</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">In</span><span class="o">;</span> <span class="n">stream</span> <span class="o">>]</span>
+      <span class="o">|</span> <span class="s2">"binary"</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">Binary</span><span class="o">;</span> <span class="n">stream</span> <span class="o">>]</span>
+      <span class="o">|</span> <span class="s2">"unary"</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">Unary</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 unary operator. *)</span>
+  <span class="o">|</span> <span class="nc">Unary</span> <span class="k">of</span> <span class="kt">char</span> <span class="o">*</span> <span class="n">expr</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">(* variant for if/then/else. *)</span>
+  <span class="o">|</span> <span class="nc">If</span> <span class="k">of</span> <span class="n">expr</span> <span class="o">*</span> <span class="n">expr</span> <span class="o">*</span> <span class="n">expr</span>
+
+  <span class="c">(* variant for for/in. *)</span>
+  <span class="o">|</span> <span class="nc">For</span> <span class="k">of</span> <span class="kt">string</span> <span class="o">*</span> <span class="n">expr</span> <span class="o">*</span> <span class="n">expr</span> <span class="o">*</span> <span class="n">expr</span> <span class="n">option</span> <span class="o">*</span> <span class="n">expr</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="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="o">|</span> <span class="nc">BinOpPrototype</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="o">*</span> <span class="kt">int</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="c"> *   ::= ifexpr</span>
+<span class="c"> *   ::= forexpr *)</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="c">(* ifexpr ::= 'if' expr 'then' expr 'else' expr *)</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">If</span><span class="o">;</span> <span class="n">c</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">Then</span> <span class="o">??</span> <span class="s2">"expected 'then'"</span><span class="o">;</span> <span class="n">t</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">Else</span> <span class="o">??</span> <span class="s2">"expected 'else'"</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">If</span> <span class="o">(</span><span class="n">c</span><span class="o">,</span> <span class="n">t</span><span class="o">,</span> <span class="n">e</span><span class="o">)</span>
+
+  <span class="c">(* forexpr</span>
+<span class="c">        ::= 'for' identifier '=' expr ',' expr (',' expr)? 'in' 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">For</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="s2">"expected identifier after for"</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 '=' after for"</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="n">start</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 ',' after for"</span><span class="o">;</span>
+             <span class="n">end_</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">let</span> <span class="n">step</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">step</span><span class="o">=</span><span class="n">parse_expr</span> <span class="o">>]</span> <span class="o">-></span> <span class="nc">Some</span> <span class="n">step</span>
+              <span class="o">|</span> <span class="o">[<</span> <span class="o">>]</span> <span class="o">-></span> <span class="nc">None</span>
+              <span class="k">end</span> <span class="n">stream</span>
+            <span class="k">in</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">In</span><span class="o">;</span> <span class="n">body</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">For</span> <span class="o">(</span><span class="n">id</span><span class="o">,</span> <span class="n">start</span><span class="o">,</span> <span class="n">end_</span><span class="o">,</span> <span class="n">step</span><span class="o">,</span> <span class="n">body</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 'in' after for"</span><span class="o">)</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="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 '=' after for"</span><span class="o">)</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="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">(* unary</span>
+<span class="c"> *   ::= primary</span>
+<span class="c"> *   ::= '!' unary *)</span>
+<span class="ow">and</span> <span class="n">parse_unary</span> <span class="o">=</span> <span class="n">parser</span>
+  <span class="c">(* If this is a unary operator, read it. *)</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">op</span> <span class="k">when</span> <span class="n">op</span> <span class="o">!=</span> <span class="sc">'('</span> <span class="o">&&</span> <span class="n">op</span> <span class="o">!=</span> <span class="sc">')'</span><span class="o">;</span> <span class="n">operand</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">Unary</span> <span class="o">(</span><span class="n">op</span><span class="o">,</span> <span class="n">operand</span><span class="o">)</span>
+
+  <span class="c">(* If the current token is not an operator, it must be a primary expr. *)</span>
+  <span class="o">|</span> <span class="o">[<</span> <span class="n">stream</span> <span class="o">>]</span> <span class="o">-></span> <span class="n">parse_primary</span> <span class="n">stream</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 unary expression after the binary operator. *)</span>
+        <span class="k">let</span> <span class="n">rhs</span> <span class="o">=</span> <span class="n">parse_unary</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_unary</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="c"> *   ::= binary LETTER number? (id, id)</span>
+<span class="c"> *   ::= unary LETTER number? (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="k">let</span> <span class="n">parse_operator</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">Unary</span> <span class="o">>]</span> <span class="o">-></span> <span class="s2">"unary"</span><span class="o">,</span> <span class="mi">1</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">Binary</span> <span class="o">>]</span> <span class="o">-></span> <span class="s2">"binary"</span><span class="o">,</span> <span class="mi">2</span>
+  <span class="k">in</span>
+  <span class="k">let</span> <span class="n">parse_binary_precedence</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">Number</span> <span class="n">n</span> <span class="o">>]</span> <span class="o">-></span> <span class="n">int_of_float</span> <span class="n">n</span>
+    <span class="o">|</span> <span class="o">[<</span> <span class="o">>]</span> <span class="o">-></span> <span class="mi">30</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="n">prefix</span><span class="o">,</span> <span class="n">kind</span><span class="o">)=</span><span class="n">parse_operator</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">op</span> <span class="o">??</span> <span class="s2">"expected an operator"</span><span class="o">;</span>
+       <span class="c">(* Read the precedence if present. *)</span>
+       <span class="n">binary_precedence</span><span class="o">=</span><span class="n">parse_binary_precedence</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="k">let</span> <span class="n">name</span> <span class="o">=</span> <span class="n">prefix</span> <span class="o">^</span> <span class="o">(</span><span class="nn">String</span><span class="p">.</span><span class="n">make</span> <span class="mi">1</span> <span class="n">op</span><span class="o">)</span> <span class="k">in</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">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="k">in</span>
+
+      <span class="c">(* Verify right number of arguments for operator. *)</span>
+      <span class="k">if</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">kind</span>
+      <span class="k">then</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">"invalid number of operands for operator"</span><span class="o">)</span>
+      <span class="k">else</span>
+        <span class="k">if</span> <span class="n">kind</span> <span class="o">==</span> <span class="mi">1</span> <span class="k">then</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="k">else</span>
+          <span class="nn">Ast</span><span class="p">.</span><span class="nc">BinOpPrototype</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="n">binary_precedence</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">Unary</span> <span class="o">(</span><span class="n">op</span><span class="o">,</span> <span class="n">operand</span><span class="o">)</span> <span class="o">-></span>
+      <span class="k">let</span> <span class="n">operand</span> <span class="o">=</span> <span class="n">codegen_expr</span> <span class="n">operand</span> <span class="k">in</span>
+      <span class="k">let</span> <span class="n">callee</span> <span class="o">=</span> <span class="s2">"unary"</span> <span class="o">^</span> <span class="o">(</span><span class="nn">String</span><span class="p">.</span><span class="n">make</span> <span class="mi">1</span> <span class="n">op</span><span class="o">)</span> <span class="k">in</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 unary operator"</span><span class="o">)</span>
+      <span class="k">in</span>
+      <span class="n">build_call</span> <span class="n">callee</span> <span class="o">[|</span><span class="n">operand</span><span class="o">|]</span> <span class="s2">"unop"</span> <span class="n">builder</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="c">(* If it wasn't a builtin binary operator, it must be a user defined</span>
+<span class="c">             * one. Emit a call to it. *)</span>
+            <span class="k">let</span> <span class="n">callee</span> <span class="o">=</span> <span class="s2">"binary"</span> <span class="o">^</span> <span class="o">(</span><span class="nn">String</span><span class="p">.</span><span class="n">make</span> <span class="mi">1</span> <span class="n">op</span><span class="o">)</span> <span class="k">in</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">"binary operator not found!"</span><span class="o">)</span>
+            <span class="k">in</span>
+            <span class="n">build_call</span> <span class="n">callee</span> <span class="o">[|</span><span class="n">lhs_val</span><span class="o">;</span> <span class="n">rhs_val</span><span class="o">|]</span> <span class="s2">"binop"</span> <span class="n">builder</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="o">|</span> <span class="nn">Ast</span><span class="p">.</span><span class="nc">If</span> <span class="o">(</span><span class="n">cond</span><span class="o">,</span> <span class="n">then_</span><span class="o">,</span> <span class="n">else_</span><span class="o">)</span> <span class="o">-></span>
+      <span class="k">let</span> <span class="n">cond</span> <span class="o">=</span> <span class="n">codegen_expr</span> <span class="n">cond</span> <span class="k">in</span>
+
+      <span class="c">(* Convert condition to a bool by comparing equal to 0.0 *)</span>
+      <span class="k">let</span> <span class="n">zero</span> <span class="o">=</span> <span class="n">const_float</span> <span class="n">double_type</span> <span class="mi">0</span><span class="o">.</span><span class="mi">0</span> <span class="k">in</span>
+      <span class="k">let</span> <span class="n">cond_val</span> <span class="o">=</span> <span class="n">build_fcmp</span> <span class="nn">Fcmp</span><span class="p">.</span><span class="nc">One</span> <span class="n">cond</span> <span class="n">zero</span> <span class="s2">"ifcond"</span> <span class="n">builder</span> <span class="k">in</span>
+
+      <span class="c">(* Grab the first block so that we might later add the conditional branch</span>
+<span class="c">       * to it at the end of the function. *)</span>
+      <span class="k">let</span> <span class="n">start_bb</span> <span class="o">=</span> <span class="n">insertion_block</span> <span class="n">builder</span> <span class="k">in</span>
+      <span class="k">let</span> <span class="n">the_function</span> <span class="o">=</span> <span class="n">block_parent</span> <span class="n">start_bb</span> <span class="k">in</span>
+
+      <span class="k">let</span> <span class="n">then_bb</span> <span class="o">=</span> <span class="n">append_block</span> <span class="n">context</span> <span class="s2">"then"</span> <span class="n">the_function</span> <span class="k">in</span>
+
+      <span class="c">(* Emit 'then' value. *)</span>
+      <span class="n">position_at_end</span> <span class="n">then_bb</span> <span class="n">builder</span><span class="o">;</span>
+      <span class="k">let</span> <span class="n">then_val</span> <span class="o">=</span> <span class="n">codegen_expr</span> <span class="n">then_</span> <span class="k">in</span>
+
+      <span class="c">(* Codegen of 'then' can change the current block, update then_bb for the</span>
+<span class="c">       * phi. We create a new name because one is used for the phi node, and the</span>
+<span class="c">       * other is used for the conditional branch. *)</span>
+      <span class="k">let</span> <span class="n">new_then_bb</span> <span class="o">=</span> <span class="n">insertion_block</span> <span class="n">builder</span> <span class="k">in</span>
+
+      <span class="c">(* Emit 'else' value. *)</span>
+      <span class="k">let</span> <span class="n">else_bb</span> <span class="o">=</span> <span class="n">append_block</span> <span class="n">context</span> <span class="s2">"else"</span> <span class="n">the_function</span> <span class="k">in</span>
+      <span class="n">position_at_end</span> <span class="n">else_bb</span> <span class="n">builder</span><span class="o">;</span>
+      <span class="k">let</span> <span class="n">else_val</span> <span class="o">=</span> <span class="n">codegen_expr</span> <span class="n">else_</span> <span class="k">in</span>
+
+      <span class="c">(* Codegen of 'else' can change the current block, update else_bb for the</span>
+<span class="c">       * phi. *)</span>
+      <span class="k">let</span> <span class="n">new_else_bb</span> <span class="o">=</span> <span class="n">insertion_block</span> <span class="n">builder</span> <span class="k">in</span>
+
+      <span class="c">(* Emit merge block. *)</span>
+      <span class="k">let</span> <span class="n">merge_bb</span> <span class="o">=</span> <span class="n">append_block</span> <span class="n">context</span> <span class="s2">"ifcont"</span> <span class="n">the_function</span> <span class="k">in</span>
+      <span class="n">position_at_end</span> <span class="n">merge_bb</span> <span class="n">builder</span><span class="o">;</span>
+      <span class="k">let</span> <span class="n">incoming</span> <span class="o">=</span> <span class="o">[(</span><span class="n">then_val</span><span class="o">,</span> <span class="n">new_then_bb</span><span class="o">);</span> <span class="o">(</span><span class="n">else_val</span><span class="o">,</span> <span class="n">new_else_bb</span><span class="o">)]</span> <span class="k">in</span>
+      <span class="k">let</span> <span class="n">phi</span> <span class="o">=</span> <span class="n">build_phi</span> <span class="n">incoming</span> <span class="s2">"iftmp"</span> <span class="n">builder</span> <span class="k">in</span>
+
+      <span class="c">(* Return to the start block to add the conditional branch. *)</span>
+      <span class="n">position_at_end</span> <span class="n">start_bb</span> <span class="n">builder</span><span class="o">;</span>
+      <span class="n">ignore</span> <span class="o">(</span><span class="n">build_cond_br</span> <span class="n">cond_val</span> <span class="n">then_bb</span> <span class="n">else_bb</span> <span class="n">builder</span><span class="o">);</span>
+
+      <span class="c">(* Set a unconditional branch at the end of the 'then' block and the</span>
+<span class="c">       * 'else' block to the 'merge' block. *)</span>
+      <span class="n">position_at_end</span> <span class="n">new_then_bb</span> <span class="n">builder</span><span class="o">;</span> <span class="n">ignore</span> <span class="o">(</span><span class="n">build_br</span> <span class="n">merge_bb</span> <span class="n">builder</span><span class="o">);</span>
+      <span class="n">position_at_end</span> <span class="n">new_else_bb</span> <span class="n">builder</span><span class="o">;</span> <span class="n">ignore</span> <span class="o">(</span><span class="n">build_br</span> <span class="n">merge_bb</span> <span class="n">builder</span><span class="o">);</span>
+
+      <span class="c">(* Finally, set the builder to the end of the merge block. *)</span>
+      <span class="n">position_at_end</span> <span class="n">merge_bb</span> <span class="n">builder</span><span class="o">;</span>
+
+      <span class="n">phi</span>
+  <span class="o">|</span> <span class="nn">Ast</span><span class="p">.</span><span class="nc">For</span> <span class="o">(</span><span class="n">var_name</span><span class="o">,</span> <span class="n">start</span><span class="o">,</span> <span class="n">end_</span><span class="o">,</span> <span class="n">step</span><span class="o">,</span> <span class="n">body</span><span class="o">)</span> <span class="o">-></span>
+      <span class="c">(* Emit the start code first, without 'variable' in scope. *)</span>
+      <span class="k">let</span> <span class="n">start_val</span> <span class="o">=</span> <span class="n">codegen_expr</span> <span class="n">start</span> <span class="k">in</span>
+
+      <span class="c">(* Make the new basic block for the loop header, inserting after current</span>
+<span class="c">       * block. *)</span>
+      <span class="k">let</span> <span class="n">preheader_bb</span> <span class="o">=</span> <span class="n">insertion_block</span> <span class="n">builder</span> <span class="k">in</span>
+      <span class="k">let</span> <span class="n">the_function</span> <span class="o">=</span> <span class="n">block_parent</span> <span class="n">preheader_bb</span> <span class="k">in</span>
+      <span class="k">let</span> <span class="n">loop_bb</span> <span class="o">=</span> <span class="n">append_block</span> <span class="n">context</span> <span class="s2">"loop"</span> <span class="n">the_function</span> <span class="k">in</span>
+
+      <span class="c">(* Insert an explicit fall through from the current block to the</span>
+<span class="c">       * loop_bb. *)</span>
+      <span class="n">ignore</span> <span class="o">(</span><span class="n">build_br</span> <span class="n">loop_bb</span> <span class="n">builder</span><span class="o">);</span>
+
+      <span class="c">(* Start insertion in loop_bb. *)</span>
+      <span class="n">position_at_end</span> <span class="n">loop_bb</span> <span class="n">builder</span><span class="o">;</span>
+
+      <span class="c">(* Start the PHI node with an entry for start. *)</span>
+      <span class="k">let</span> <span class="n">variable</span> <span class="o">=</span> <span class="n">build_phi</span> <span class="o">[(</span><span class="n">start_val</span><span class="o">,</span> <span class="n">preheader_bb</span><span class="o">)]</span> <span class="n">var_name</span> <span class="n">builder</span> <span class="k">in</span>
+
+      <span class="c">(* Within the loop, the variable is defined equal to the PHI node. If it</span>
+<span class="c">       * shadows an existing variable, we have to restore it, so save it</span>
+<span class="c">       * now. *)</span>
+      <span class="k">let</span> <span class="n">old_val</span> <span class="o">=</span>
+        <span class="k">try</span> <span class="nc">Some</span> <span class="o">(</span><span class="nn">Hashtbl</span><span class="p">.</span><span class="n">find</span> <span class="n">named_values</span> <span class="n">var_name</span><span class="o">)</span> <span class="k">with</span> <span class="nc">Not_found</span> <span class="o">-></span> <span class="nc">None</span>
+      <span class="k">in</span>
+      <span class="nn">Hashtbl</span><span class="p">.</span><span class="n">add</span> <span class="n">named_values</span> <span class="n">var_name</span> <span class="n">variable</span><span class="o">;</span>
+
+      <span class="c">(* Emit the body of the loop.  This, like any other expr, can change the</span>
+<span class="c">       * current BB.  Note that we ignore the value computed by the body, but</span>
+<span class="c">       * don't allow an error *)</span>
+      <span class="n">ignore</span> <span class="o">(</span><span class="n">codegen_expr</span> <span class="n">body</span><span class="o">);</span>
+
+      <span class="c">(* Emit the step value. *)</span>
+      <span class="k">let</span> <span class="n">step_val</span> <span class="o">=</span>
+        <span class="k">match</span> <span class="n">step</span> <span class="k">with</span>
+        <span class="o">|</span> <span class="nc">Some</span> <span class="n">step</span> <span class="o">-></span> <span class="n">codegen_expr</span> <span class="n">step</span>
+        <span class="c">(* If not specified, use 1.0. *)</span>
+        <span class="o">|</span> <span class="nc">None</span> <span class="o">-></span> <span class="n">const_float</span> <span class="n">double_type</span> <span class="mi">1</span><span class="o">.</span><span class="mi">0</span>
+      <span class="k">in</span>
+
+      <span class="k">let</span> <span class="n">next_var</span> <span class="o">=</span> <span class="n">build_add</span> <span class="n">variable</span> <span class="n">step_val</span> <span class="s2">"nextvar"</span> <span class="n">builder</span> <span class="k">in</span>
+
+      <span class="c">(* Compute the end condition. *)</span>
+      <span class="k">let</span> <span class="n">end_cond</span> <span class="o">=</span> <span class="n">codegen_expr</span> <span class="n">end_</span> <span class="k">in</span>
+
+      <span class="c">(* Convert condition to a bool by comparing equal to 0.0. *)</span>
+      <span class="k">let</span> <span class="n">zero</span> <span class="o">=</span> <span class="n">const_float</span> <span class="n">double_type</span> <span class="mi">0</span><span class="o">.</span><span class="mi">0</span> <span class="k">in</span>
+      <span class="k">let</span> <span class="n">end_cond</span> <span class="o">=</span> <span class="n">build_fcmp</span> <span class="nn">Fcmp</span><span class="p">.</span><span class="nc">One</span> <span class="n">end_cond</span> <span class="n">zero</span> <span class="s2">"loopcond"</span> <span class="n">builder</span> <span class="k">in</span>
+
+      <span class="c">(* Create the "after loop" block and insert it. *)</span>
+      <span class="k">let</span> <span class="n">loop_end_bb</span> <span class="o">=</span> <span class="n">insertion_block</span> <span class="n">builder</span> <span class="k">in</span>
+      <span class="k">let</span> <span class="n">after_bb</span> <span class="o">=</span> <span class="n">append_block</span> <span class="n">context</span> <span class="s2">"afterloop"</span> <span class="n">the_function</span> <span class="k">in</span>
+
+      <span class="c">(* Insert the conditional branch into the end of loop_end_bb. *)</span>
+      <span class="n">ignore</span> <span class="o">(</span><span class="n">build_cond_br</span> <span class="n">end_cond</span> <span class="n">loop_bb</span> <span class="n">after_bb</span> <span class="n">builder</span><span class="o">);</span>
+
+      <span class="c">(* Any new code will be inserted in after_bb. *)</span>
+      <span class="n">position_at_end</span> <span class="n">after_bb</span> <span class="n">builder</span><span class="o">;</span>
+
+      <span class="c">(* Add a new entry to the PHI node for the backedge. *)</span>
+      <span class="n">add_incoming</span> <span class="o">(</span><span class="n">next_var</span><span class="o">,</span> <span class="n">loop_end_bb</span><span class="o">)</span> <span class="n">variable</span><span class="o">;</span>
+
+      <span class="c">(* Restore the unshadowed variable. *)</span>
+      <span class="k">begin</span> <span class="k">match</span> <span class="n">old_val</span> <span class="k">with</span>
+      <span class="o">|</span> <span class="nc">Some</span> <span class="n">old_val</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">var_name</span> <span class="n">old_val</span>
+      <span class="o">|</span> <span class="nc">None</span> <span class="o">-></span> <span class="bp">()</span>
+      <span class="k">end</span><span class="o">;</span>
+
+      <span class="c">(* for expr always returns 0.0. *)</span>
+      <span class="n">const_null</span> <span class="n">double_type</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="nn">Ast</span><span class="p">.</span><span class="nc">BinOpPrototype</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="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">(* If this is an operator, install it. *)</span>
+      <span class="k">begin</span> <span class="k">match</span> <span class="n">proto</span> <span class="k">with</span>
+      <span class="o">|</span> <span class="nn">Ast</span><span class="p">.</span><span class="nc">BinOpPrototype</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="n">prec</span><span class="o">)</span> <span class="o">-></span>
+          <span class="k">let</span> <span class="n">op</span> <span class="o">=</span> <span class="n">name</span><span class="o">.[</span><span class="nn">String</span><span class="p">.</span><span class="n">length</span> <span class="n">name</span> <span class="o">-</span> <span class="mi">1</span><span class="o">]</span> <span class="k">in</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="n">op</span> <span class="n">prec</span><span class="o">;</span>
+      <span class="o">|</span> <span class="o">_</span> <span class="o">-></span> <span class="bp">()</span>
+      <span class="k">end</span><span class="o">;</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>
+
+<span class="cm">/* printd - printf that takes a double prints it as "%f\n", returning 0. */</span>
+<span class="k">extern</span> <span class="kt">double</span> <span class="nf">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">printf</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>
+</pre></div>
+</div>
+</dd>
+</dl>
+<p><a class="reference external" href="OCamlLangImpl7.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="OCamlLangImpl7.html" title="7. Kaleidoscope: Extending the Language: Mutable Variables" +>next</a> |</li>
+        <li class="right" >
+          <a href="OCamlLangImpl5.html" title="5. Kaleidoscope: Extending the Language: Control Flow" +>previous</a> |</li>
+  <li><a href="https://urldefense.proofpoint.com/v2/url?u=http-3A__llvm.org_&d=AwMDaQ&c=8hUWFZcy2Z-Za5rBPlktOQ&r=mQ4LZ2PUj9hpadE3cDHZnIdEwhEBrbAstXeMaFoB9tg&m=QAGZeXoSMCv0h4wI0rExv_W1lSHAp-_70Lmc3PA5EtM&s=pfiJKhwlj5rZUzKRdDQCg_cdTSO0Ut0YcGMOb-jpeAs&e=">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 2003-2014, LLVM Project.
+      Last updated on 2015-05-25.
+      Created using <a href="https://urldefense.proofpoint.com/v2/url?u=http-3A__sphinx.pocoo.org_&d=AwMDaQ&c=8hUWFZcy2Z-Za5rBPlktOQ&r=mQ4LZ2PUj9hpadE3cDHZnIdEwhEBrbAstXeMaFoB9tg&m=QAGZeXoSMCv0h4wI0rExv_W1lSHAp-_70Lmc3PA5EtM&s=lSOQQPBONfHSHDEAc1rfzOSlyTiliJLtzc8JrV9lcX4&e=">Sphinx</a> 1.1.3.
+    </div>
+  </body>
+</html>
\ No newline at end of file

Added: www-releases/trunk/3.6.1/docs/tutorial/OCamlLangImpl7.html
URL: http://llvm.org/viewvc/llvm-project/www-releases/trunk/3.6.1/docs/tutorial/OCamlLangImpl7.html?rev=238135&view=auto
==============================================================================
--- www-releases/trunk/3.6.1/docs/tutorial/OCamlLangImpl7.html (added)
+++ www-releases/trunk/3.6.1/docs/tutorial/OCamlLangImpl7.html Mon May 25 08:53:02 2015
@@ -0,0 +1,1749 @@
+
+
+<!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 3.6 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:     '3.6',
+        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 3.6 documentation" href="../index.html" />
+    <link rel="up" title="LLVM Tutorial: Table of Contents" href="index.html" />
+    <link rel="next" title="8. Kaleidoscope: Conclusion and other useful LLVM tidbits" href="OCamlLangImpl8.html" />
+    <link rel="prev" title="6. Kaleidoscope: Extending the Language: User-defined Operators" href="OCamlLangImpl6.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="OCamlLangImpl8.html" title="8. Kaleidoscope: Conclusion and other useful LLVM tidbits" + accesskey="N">next</a> |</li>
+        <li class="right" >
+          <a href="OCamlLangImpl6.html" title="6. Kaleidoscope: Extending the Language: User-defined Operators" + accesskey="P">previous</a> |</li>
+  <li><a href="https://urldefense.proofpoint.com/v2/url?u=http-3A__llvm.org_&d=AwMDaQ&c=8hUWFZcy2Z-Za5rBPlktOQ&r=mQ4LZ2PUj9hpadE3cDHZnIdEwhEBrbAstXeMaFoB9tg&m=QAGZeXoSMCv0h4wI0rExv_W1lSHAp-_70Lmc3PA5EtM&s=pfiJKhwlj5rZUzKRdDQCg_cdTSO0Ut0YcGMOb-jpeAs&e=">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="https://urldefense.proofpoint.com/v2/url?u=http-3A__en.wikipedia.org_wiki_Functional-5Fprogramming&d=AwMDaQ&c=8hUWFZcy2Z-Za5rBPlktOQ&r=mQ4LZ2PUj9hpadE3cDHZnIdEwhEBrbAstXeMaFoB9tg&m=QAGZeXoSMCv0h4wI0rExv_W1lSHAp-_70Lmc3PA5EtM&s=b1zZ_ITHRS6GsWpRSbm1r-lAQhQgGCwZV-LpBKzhhBc&e=">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="https://urldefense.proofpoint.com/v2/url?u=http-3A__en.wikipedia.org_wiki_Static-5Fsingle-5Fassignment-5Fform&d=AwMDaQ&c=8hUWFZcy2Z-Za5rBPlktOQ&r=mQ4LZ2PUj9hpadE3cDHZnIdEwhEBrbAstXeMaFoB9tg&m=QAGZeXoSMCv0h4wI0rExv_W1lSHAp-_70Lmc3PA5EtM&s=Qgsm8Kaurcw7WDxduZweralws7rQvxBwazcKEv-TcGo&e=">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="https://urldefense.proofpoint.com/v2/url?u=http-3A__en.wikipedia.org_wiki_Static-5Fsingle-5Fassignment-5Fform&d=AwMDaQ&c=8hUWFZcy2Z-Za5rBPlktOQ&r=mQ4LZ2PUj9hpadE3cDHZnIdEwhEBrbAstXeMaFoB9tg&m=QAGZeXoSMCv0h4wI0rExv_W1lSHAp-_70Lmc3PA5EtM&s=Qgsm8Kaurcw7WDxduZweralws7rQvxBwazcKEv-TcGo&e=">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#i_alloca">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#t_classifications">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"><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>
+<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">named_values</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">named_values</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
+<tt class="docutils literal"><span class="pre">named_values</span></tt> 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>
+<p><strong>Note:</strong> the ocaml bindings currently model both <tt class="docutils literal"><span class="pre">Value*</span></tt>‘s and
+<tt class="docutils literal"><span class="pre">AllocInst*</span></tt>‘s as <tt class="docutils literal"><span class="pre">Llvm.llvalue</span></tt>‘s, but this may change in the future
+to be more type safe.</p>
+<div class="highlight-ocaml"><div class="highlight"><pre><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>
+</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-ocaml"><div class="highlight"><pre><span class="c">(* Create an alloca instruction in the entry block of the function. This</span>
+<span class="c"> * is used for mutable variables etc. *)</span>
+<span class="k">let</span> <span class="n">create_entry_block_alloca</span> <span class="n">the_function</span> <span class="n">var_name</span> <span class="o">=</span>
+  <span class="k">let</span> <span class="n">builder</span> <span class="o">=</span> <span class="n">builder_at</span> <span class="o">(</span><span class="n">instr_begin</span> <span class="o">(</span><span class="n">entry_block</span> <span class="n">the_function</span><span class="o">))</span> <span class="k">in</span>
+  <span class="n">build_alloca</span> <span class="n">double_type</span> <span class="n">var_name</span> <span class="n">builder</span>
+</pre></div>
+</div>
+<p>This funny looking code creates an <tt class="docutils literal"><span class="pre">Llvm.llbuilder</span></tt> object that is
+pointing at the first instruction 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-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="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="k">let</span> <span class="n">v</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="k">in</span>
+      <span class="c">(* Load the value. *)</span>
+      <span class="n">build_load</span> <span class="n">v</span> <span class="n">name</span> <span class="n">builder</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">codegen_expr</span> <span class="pre">Ast.For</span> <span class="pre">...</span></tt> (see the <a class="reference external" href="#code">full code listing</a>
+for the unabridged code):</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">For</span> <span class="o">(</span><span class="n">var_name</span><span class="o">,</span> <span class="n">start</span><span class="o">,</span> <span class="n">end_</span><span class="o">,</span> <span class="n">step</span><span class="o">,</span> <span class="n">body</span><span class="o">)</span> <span class="o">-></span>
+    <span class="k">let</span> <span class="n">the_function</span> <span class="o">=</span> <span class="n">block_parent</span> <span class="o">(</span><span class="n">insertion_block</span> <span class="n">builder</span><span class="o">)</span> <span class="k">in</span>
+
+    <span class="c">(* Create an alloca for the variable in the entry block. *)</span>
+    <span class="k">let</span> <span class="n">alloca</span> <span class="o">=</span> <span class="n">create_entry_block_alloca</span> <span class="n">the_function</span> <span class="n">var_name</span> <span class="k">in</span>
+
+    <span class="c">(* Emit the start code first, without 'variable' in scope. *)</span>
+    <span class="k">let</span> <span class="n">start_val</span> <span class="o">=</span> <span class="n">codegen_expr</span> <span class="n">start</span> <span class="k">in</span>
+
+    <span class="c">(* Store the value into the alloca. *)</span>
+    <span class="n">ignore</span><span class="o">(</span><span class="n">build_store</span> <span class="n">start_val</span> <span class="n">alloca</span> <span class="n">builder</span><span class="o">);</span>
+
+    <span class="o">...</span>
+
+    <span class="c">(* Within the loop, the variable is defined equal to the PHI node. If it</span>
+<span class="c">     * shadows an existing variable, we have to restore it, so save it</span>
+<span class="c">     * now. *)</span>
+    <span class="k">let</span> <span class="n">old_val</span> <span class="o">=</span>
+      <span class="k">try</span> <span class="nc">Some</span> <span class="o">(</span><span class="nn">Hashtbl</span><span class="p">.</span><span class="n">find</span> <span class="n">named_values</span> <span class="n">var_name</span><span class="o">)</span> <span class="k">with</span> <span class="nc">Not_found</span> <span class="o">-></span> <span class="nc">None</span>
+    <span class="k">in</span>
+    <span class="nn">Hashtbl</span><span class="p">.</span><span class="n">add</span> <span class="n">named_values</span> <span class="n">var_name</span> <span class="n">alloca</span><span class="o">;</span>
+
+    <span class="o">...</span>
+
+    <span class="c">(* Compute the end condition. *)</span>
+    <span class="k">let</span> <span class="n">end_cond</span> <span class="o">=</span> <span class="n">codegen_expr</span> <span class="n">end_</span> <span class="k">in</span>
+
+    <span class="c">(* Reload, increment, and restore the alloca. This handles the case where</span>
+<span class="c">     * the body of the loop mutates the variable. *)</span>
+    <span class="k">let</span> <span class="n">cur_var</span> <span class="o">=</span> <span class="n">build_load</span> <span class="n">alloca</span> <span class="n">var_name</span> <span class="n">builder</span> <span class="k">in</span>
+    <span class="k">let</span> <span class="n">next_var</span> <span class="o">=</span> <span class="n">build_add</span> <span class="n">cur_var</span> <span class="n">step_val</span> <span class="s2">"nextvar"</span> <span class="n">builder</span> <span class="k">in</span>
+    <span class="n">ignore</span><span class="o">(</span><span class="n">build_store</span> <span class="n">next_var</span> <span class="n">alloca</span> <span class="n">builder</span><span class="o">);</span>
+    <span class="o">...</span>
+</pre></div>
+</div>
+<p>This code is virtually identical to the code <a class="reference external" href="OCamlLangImpl5.html#forcodegen">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-ocaml"><div class="highlight"><pre><span class="c">(* Create an alloca for each argument and register the argument in the symbol</span>
+<span class="c"> * table so that references to it will succeed. *)</span>
+<span class="k">let</span> <span class="n">create_argument_allocas</span> <span class="n">the_function</span> <span class="n">proto</span> <span class="o">=</span>
+  <span class="k">let</span> <span class="n">args</span> <span class="o">=</span> <span class="k">match</span> <span class="n">proto</span> <span class="k">with</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">args</span><span class="o">)</span> <span class="o">|</span> <span class="nn">Ast</span><span class="p">.</span><span class="nc">BinOpPrototype</span> <span class="o">(_,</span> <span class="n">args</span><span class="o">,</span> <span class="o">_)</span> <span class="o">-></span> <span class="n">args</span>
+  <span class="k">in</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">ai</span> <span class="o">-></span>
+    <span class="k">let</span> <span class="n">var_name</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="c">(* Create an alloca for this variable. *)</span>
+    <span class="k">let</span> <span class="n">alloca</span> <span class="o">=</span> <span class="n">create_entry_block_alloca</span> <span class="n">the_function</span> <span class="n">var_name</span> <span class="k">in</span>
+
+    <span class="c">(* Store the initial value into the alloca. *)</span>
+    <span class="n">ignore</span><span class="o">(</span><span class="n">build_store</span> <span class="n">ai</span> <span class="n">alloca</span> <span class="n">builder</span><span class="o">);</span>
+
+    <span class="c">(* Add arguments to variable symbol table. *)</span>
+    <span class="nn">Hashtbl</span><span class="p">.</span><span class="n">add</span> <span class="n">named_values</span> <span class="n">var_name</span> <span class="n">alloca</span><span class="o">;</span>
+  <span class="o">)</span> <span class="o">(</span><span class="n">params</span> <span class="n">the_function</span><span class="o">)</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">Codegen.codegen_func</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-ocaml"><div class="highlight"><pre><span class="k">let</span> <span class="n">main</span> <span class="bp">()</span> <span class="o">=</span>
+  <span class="o">...</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">(* Promote allocas to registers. *)</span>
+  <span class="n">add_memory_to_register_promotion</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>
+</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-ocaml"><div class="highlight"><pre><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">2</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">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="o">...</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-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="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="c">(* Special case '=' because we don't want to emit the LHS as an</span>
+<span class="c">           * expression. *)</span>
+          <span class="k">let</span> <span class="n">name</span> <span class="o">=</span>
+            <span class="k">match</span> <span class="n">lhs</span> <span class="k">with</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="n">name</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">"destination of '=' must be a variable"</span><span class="o">)</span>
+          <span class="k">in</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-ocaml"><div class="highlight"><pre>    <span class="c">(* Codegen the rhs. *)</span>
+    <span class="k">let</span> <span class="n">val_</span> <span class="o">=</span> <span class="n">codegen_expr</span> <span class="n">rhs</span> <span class="k">in</span>
+
+    <span class="c">(* Lookup the name. *)</span>
+    <span class="k">let</span> <span class="n">variable</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="k">in</span>
+    <span class="n">ignore</span><span class="o">(</span><span class="n">build_store</span> <span class="n">val_</span> <span class="n">variable</span> <span class="n">builder</span><span class="o">);</span>
+    <span class="n">val_</span>
+<span class="o">|</span> <span class="o">_</span> <span class="o">-></span>
+      <span class="o">...</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"><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>
+<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 other extensions 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-ocaml"><div class="highlight"><pre><span class="k">type</span> <span class="n">token</span> <span class="o">=</span>
+  <span class="o">...</span>
+  <span class="c">(* var definition *)</span>
+  <span class="o">|</span> <span class="nn">Var</span>
+
+<span class="p">...</span>
+
+<span class="n">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="s2">"in"</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">In</span><span class="o">;</span> <span class="n">stream</span> <span class="o">>]</span>
+      <span class="o">|</span> <span class="s2">"binary"</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">Binary</span><span class="o">;</span> <span class="n">stream</span> <span class="o">>]</span>
+      <span class="o">|</span> <span class="s2">"unary"</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">Unary</span><span class="o">;</span> <span class="n">stream</span> <span class="o">>]</span>
+      <span class="o">|</span> <span class="s2">"var"</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">Var</span><span class="o">;</span> <span class="n">stream</span> <span class="o">>]</span>
+      <span class="o">...</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-ocaml"><div class="highlight"><pre><span class="k">type</span> <span class="n">expr</span> <span class="o">=</span>
+  <span class="o">...</span>
+  <span class="c">(* variant for var/in. *)</span>
+  <span class="o">|</span> <span class="nc">Var</span> <span class="k">of</span> <span class="o">(</span><span class="kt">string</span> <span class="o">*</span> <span class="n">expr</span> <span class="n">option</span><span class="o">)</span> <span class="kt">array</span> <span class="o">*</span> <span class="n">expr</span>
+  <span class="o">...</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-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="c"> *   ::= ifexpr</span>
+<span class="c"> *   ::= forexpr</span>
+<span class="c"> *   ::= varexpr *)</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="o">...</span>
+  <span class="c">(* varexpr</span>
+<span class="c">   *   ::= 'var' identifier ('=' expression?</span>
+<span class="c">   *             (',' identifier ('=' expression)?)* 'in' 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">Var</span><span class="o">;</span>
+       <span class="c">(* At least one variable name is required. *)</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="s2">"expected identifier after var"</span><span class="o">;</span>
+       <span class="n">init</span><span class="o">=</span><span class="n">parse_var_init</span><span class="o">;</span>
+       <span class="n">var_names</span><span class="o">=</span><span class="n">parse_var_names</span> <span class="o">[(</span><span class="n">id</span><span class="o">,</span> <span class="n">init</span><span class="o">)];</span>
+       <span class="c">(* At this point, we have to have 'in'. *)</span>
+       <span class="k">'</span><span class="nn">Token</span><span class="p">.</span><span class="nc">In</span> <span class="o">??</span> <span class="s2">"expected 'in' keyword after 'var'"</span><span class="o">;</span>
+       <span class="n">body</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">Var</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">var_names</span><span class="o">),</span> <span class="n">body</span><span class="o">)</span>
+
+<span class="o">...</span>
+
+<span class="ow">and</span> <span class="n">parse_var_init</span> <span class="o">=</span> <span class="n">parser</span>
+  <span class="c">(* read in the optional initializer. *)</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="o">-></span> <span class="nc">Some</span> <span class="n">e</span>
+  <span class="o">|</span> <span class="o">[<</span> <span class="o">>]</span> <span class="o">-></span> <span class="nc">None</span>
+
+<span class="ow">and</span> <span class="n">parse_var_names</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">Kwd</span> <span class="sc">','</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="s2">"expected identifier list after var"</span><span class="o">;</span>
+       <span class="n">init</span><span class="o">=</span><span class="n">parse_var_init</span><span class="o">;</span>
+       <span class="n">e</span><span class="o">=</span><span class="n">parse_var_names</span> <span class="o">((</span><span class="n">id</span><span class="o">,</span> <span class="n">init</span><span class="o">)</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>
+</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-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="o">|</span> <span class="nn">Ast</span><span class="p">.</span><span class="nc">Var</span> <span class="o">(</span><span class="n">var_names</span><span class="o">,</span> <span class="n">body</span><span class="o">)</span>
+      <span class="k">let</span> <span class="n">old_bindings</span> <span class="o">=</span> <span class="n">ref</span> <span class="bp">[]</span> <span class="k">in</span>
+
+      <span class="k">let</span> <span class="n">the_function</span> <span class="o">=</span> <span class="n">block_parent</span> <span class="o">(</span><span class="n">insertion_block</span> <span class="n">builder</span><span class="o">)</span> <span class="k">in</span>
+
+      <span class="c">(* Register all variables and emit their initializer. *)</span>
+      <span class="nn">Array</span><span class="p">.</span><span class="n">iter</span> <span class="o">(</span><span class="k">fun</span> <span class="o">(</span><span class="n">var_name</span><span class="o">,</span> <span class="n">init</span><span class="o">)</span> <span class="o">-></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-ocaml"><div class="highlight"><pre>  <span class="c">(* Emit the initializer before adding the variable to scope, this</span>
+<span class="c">   * prevents the initializer from referencing the variable itself, and</span>
+<span class="c">   * permits stuff like this:</span>
+<span class="c">   *   var a = 1 in</span>
+<span class="c">   *     var a = a in ...   # refers to outer 'a'. *)</span>
+  <span class="k">let</span> <span class="n">init_val</span> <span class="o">=</span>
+    <span class="k">match</span> <span class="n">init</span> <span class="k">with</span>
+    <span class="o">|</span> <span class="nc">Some</span> <span class="n">init</span> <span class="o">-></span> <span class="n">codegen_expr</span> <span class="n">init</span>
+    <span class="c">(* If not specified, use 0.0. *)</span>
+    <span class="o">|</span> <span class="nc">None</span> <span class="o">-></span> <span class="n">const_float</span> <span class="n">double_type</span> <span class="mi">0</span><span class="o">.</span><span class="mi">0</span>
+  <span class="k">in</span>
+
+  <span class="k">let</span> <span class="n">alloca</span> <span class="o">=</span> <span class="n">create_entry_block_alloca</span> <span class="n">the_function</span> <span class="n">var_name</span> <span class="k">in</span>
+  <span class="n">ignore</span><span class="o">(</span><span class="n">build_store</span> <span class="n">init_val</span> <span class="n">alloca</span> <span class="n">builder</span><span class="o">);</span>
+
+  <span class="c">(* Remember the old variable binding so that we can restore the binding</span>
+<span class="c">   * when we unrecurse. *)</span>
+
+  <span class="k">begin</span>
+    <span class="k">try</span>
+      <span class="k">let</span> <span class="n">old_value</span> <span class="o">=</span> <span class="nn">Hashtbl</span><span class="p">.</span><span class="n">find</span> <span class="n">named_values</span> <span class="n">var_name</span> <span class="k">in</span>
+      <span class="n">old_bindings</span> <span class="o">:=</span> <span class="o">(</span><span class="n">var_name</span><span class="o">,</span> <span class="n">old_value</span><span class="o">)</span> <span class="o">::</span> <span class="o">!</span><span class="n">old_bindings</span><span class="o">;</span>
+    <span class="k">with</span> <span class="nc">Not_found</span> <span class="o">></span> <span class="bp">()</span>
+  <span class="k">end</span><span class="o">;</span>
+
+  <span class="c">(* Remember this binding. *)</span>
+  <span class="nn">Hashtbl</span><span class="p">.</span><span class="n">add</span> <span class="n">named_values</span> <span class="n">var_name</span> <span class="n">alloca</span><span class="o">;</span>
+<span class="o">)</span> <span class="n">var_names</span><span class="o">;</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-ocaml"><div class="highlight"><pre><span class="c">(* Codegen the body, now that all vars are in scope. *)</span>
+<span class="k">let</span> <span class="n">body_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>Finally, before returning, we restore the previous variable bindings:</p>
+<div class="highlight-ocaml"><div class="highlight"><pre><span class="c">(* Pop all our variables from scope. *)</span>
+<span class="nn">List</span><span class="p">.</span><span class="n">iter</span> <span class="o">(</span><span class="k">fun</span> <span class="o">(</span><span class="n">var_name</span><span class="o">,</span> <span class="n">old_value</span><span class="o">)</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">var_name</span> <span class="n">old_value</span>
+<span class="o">)</span> <span class="o">!</span><span class="n">old_bindings</span><span class="o">;</span>
+
+<span class="c">(* Return the body computation. *)</span>
+<span class="n">body_val</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>
+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"><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>
+</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="nc">A</span><span class="s2">"-cclib"</span><span class="o">;</span> <span class="nc">A</span><span class="s2">"-rdynamic"</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>
+
+  <span class="c">(* control *)</span>
+  <span class="o">|</span> <span class="nc">If</span> <span class="o">|</span> <span class="nc">Then</span> <span class="o">|</span> <span class="nc">Else</span>
+  <span class="o">|</span> <span class="nc">For</span> <span class="o">|</span> <span class="nc">In</span>
+
+  <span class="c">(* operators *)</span>
+  <span class="o">|</span> <span class="nc">Binary</span> <span class="o">|</span> <span class="nc">Unary</span>
+
+  <span class="c">(* var definition *)</span>
+  <span class="o">|</span> <span class="nc">Var</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>