[llvm] [LLVM][AsmParser] Add support for C style comments (PR #111554)
Rahul Joshi via llvm-commits
llvm-commits at lists.llvm.org
Fri Nov 1 09:08:42 PDT 2024
https://github.com/jurahul updated https://github.com/llvm/llvm-project/pull/111554
>From 43e3a01063173e2e7050fadad8c3339a64f8c447 Mon Sep 17 00:00:00 2001
From: Rahul Joshi <rjoshi at nvidia.com>
Date: Thu, 3 Oct 2024 15:44:17 -0700
Subject: [PATCH] [LLVM][AsmParser] Add support for C style comments
Add support for C style comments in LLVM assembly.
---
llvm/docs/LangRef.rst | 3 +-
llvm/include/llvm/AsmParser/LLLexer.h | 2 +
llvm/lib/AsmParser/LLLexer.cpp | 42 +++++++++++++++++--
llvm/test/Assembler/c-style-comment.ll | 22 ++++++++++
.../Assembler/invalid-c-style-comment0.ll | 6 +++
.../Assembler/invalid-c-style-comment1.ll | 8 ++++
.../Assembler/invalid-c-style-comment2.ll | 7 ++++
7 files changed, 85 insertions(+), 5 deletions(-)
create mode 100644 llvm/test/Assembler/c-style-comment.ll
create mode 100644 llvm/test/Assembler/invalid-c-style-comment0.ll
create mode 100644 llvm/test/Assembler/invalid-c-style-comment1.ll
create mode 100644 llvm/test/Assembler/invalid-c-style-comment2.ll
diff --git a/llvm/docs/LangRef.rst b/llvm/docs/LangRef.rst
index 177924dca4d178..e3c1f8697d53a6 100644
--- a/llvm/docs/LangRef.rst
+++ b/llvm/docs/LangRef.rst
@@ -122,13 +122,14 @@ And the hard way:
.. code-block:: llvm
%0 = add i32 %X, %X ; yields i32:%0
- %1 = add i32 %0, %0 ; yields i32:%1
+ %1 = add i32 %0, %0 /* yields i32:%1 */
%result = add i32 %1, %1
This last way of multiplying ``%X`` by 8 illustrates several important
lexical features of LLVM:
#. Comments are delimited with a '``;``' and go until the end of line.
+ Alternatively, comments can start with ``/*`` and terminate with ``*/``.
#. Unnamed temporaries are created when the result of a computation is
not assigned to a named value.
#. By default, unnamed temporaries are numbered sequentially (using a
diff --git a/llvm/include/llvm/AsmParser/LLLexer.h b/llvm/include/llvm/AsmParser/LLLexer.h
index a9f51fb925f5d5..8e0c5638eef37d 100644
--- a/llvm/include/llvm/AsmParser/LLLexer.h
+++ b/llvm/include/llvm/AsmParser/LLLexer.h
@@ -94,7 +94,9 @@ namespace llvm {
lltok::Kind LexToken();
int getNextChar();
+ int peekNextChar() const;
void SkipLineComment();
+ bool SkipCComment();
lltok::Kind ReadString(lltok::Kind kind);
bool ReadVarName();
diff --git a/llvm/lib/AsmParser/LLLexer.cpp b/llvm/lib/AsmParser/LLLexer.cpp
index 56abd03d623541..43a33a677b2bd4 100644
--- a/llvm/lib/AsmParser/LLLexer.cpp
+++ b/llvm/lib/AsmParser/LLLexer.cpp
@@ -175,17 +175,25 @@ LLLexer::LLLexer(StringRef StartBuf, SourceMgr &SM, SMDiagnostic &Err,
}
int LLLexer::getNextChar() {
- char CurChar = *CurPtr++;
+ int NextChar = peekNextChar();
+ // Keeping CurPtr unchanged at EOF, so that another call to `getNextChar`
+ // returns EOF again.
+ if (NextChar != EOF)
+ ++CurPtr;
+ return NextChar;
+}
+
+int LLLexer::peekNextChar() const {
+ char CurChar = *CurPtr;
switch (CurChar) {
default: return (unsigned char)CurChar;
case 0:
// A nul character in the stream is either the end of the current buffer or
// a random nul in the file. Disambiguate that here.
- if (CurPtr-1 != CurBuf.end())
+ if (CurPtr != CurBuf.end())
return 0; // Just whitespace.
// Otherwise, return end of file.
- --CurPtr; // Another call to lex will return EOF again.
return EOF;
}
}
@@ -200,7 +208,6 @@ lltok::Kind LLLexer::LexToken() {
// Handle letters: [a-zA-Z_]
if (isalpha(static_cast<unsigned char>(CurChar)) || CurChar == '_')
return LexIdentifier();
-
return lltok::Error;
case EOF: return lltok::Eof;
case 0:
@@ -251,6 +258,12 @@ lltok::Kind LLLexer::LexToken() {
case ',': return lltok::comma;
case '*': return lltok::star;
case '|': return lltok::bar;
+ case '/':
+ if (peekNextChar() != '*')
+ return lltok::Error;
+ if (SkipCComment())
+ return lltok::Error;
+ continue;
}
}
}
@@ -262,6 +275,27 @@ void LLLexer::SkipLineComment() {
}
}
+/// SkipCComment - This skips C-style /**/ comments. Returns true if there
+/// was an error.
+bool LLLexer::SkipCComment() {
+ getNextChar(); // skip the star.
+
+ while (true) {
+ int CurChar = getNextChar();
+ switch (CurChar) {
+ case EOF:
+ LexError("unterminated comment");
+ return true;
+ case '*':
+ // End of the comment?
+ if (peekNextChar() == '/') {
+ getNextChar(); // Eat the '/'.
+ return false;
+ }
+ }
+ }
+}
+
/// Lex all tokens that start with an @ character.
/// GlobalVar @\"[^\"]*\"
/// GlobalVar @[-a-zA-Z$._][-a-zA-Z$._0-9]*
diff --git a/llvm/test/Assembler/c-style-comment.ll b/llvm/test/Assembler/c-style-comment.ll
new file mode 100644
index 00000000000000..9cc17ad90d0bc2
--- /dev/null
+++ b/llvm/test/Assembler/c-style-comment.ll
@@ -0,0 +1,22 @@
+; RUN: llvm-as < %s | llvm-dis | FileCheck %s
+
+/* Simple C style comment */
+
+; CHECK: @B = external global i32
+ at B = external global i32
+
+/* multiline C ctyle comment at "top-level"
+ * This is the second line
+ * and this is third
+ */
+
+
+; CHECK: @foo
+define <4 x i1> @foo(<4 x float> %a, <4 x float> %b) nounwind {
+entry: /* inline comment */
+ %cmp = fcmp olt <4 x float> %a, /* to be ignored */ %b
+ ret <4 x i1> %cmp /* ignore */
+}
+
+/* End of the assembly file */
+
diff --git a/llvm/test/Assembler/invalid-c-style-comment0.ll b/llvm/test/Assembler/invalid-c-style-comment0.ll
new file mode 100644
index 00000000000000..f042cdd151af92
--- /dev/null
+++ b/llvm/test/Assembler/invalid-c-style-comment0.ll
@@ -0,0 +1,6 @@
+; RUN: not llvm-as --disable-output %s 2>&1 | FileCheck %s -DFILE=%s
+
+ at B = external global i32
+
+; CHECK: [[FILE]]:[[@LINE+1]]:1: error: unterminated comment
+/* End of the assembly file
diff --git a/llvm/test/Assembler/invalid-c-style-comment1.ll b/llvm/test/Assembler/invalid-c-style-comment1.ll
new file mode 100644
index 00000000000000..7f2b966238cf49
--- /dev/null
+++ b/llvm/test/Assembler/invalid-c-style-comment1.ll
@@ -0,0 +1,8 @@
+; RUN: not llvm-as --disable-output %s 2>&1 | FileCheck %s -DFILE=%s
+
+ at B = external global i32
+
+/* /* Nested comments not supported */
+
+; CHECK: [[FILE]]:[[@LINE+1]]:1: error: redefinition of global '@B'
+ at B = external global i32
diff --git a/llvm/test/Assembler/invalid-c-style-comment2.ll b/llvm/test/Assembler/invalid-c-style-comment2.ll
new file mode 100644
index 00000000000000..2a759d84682e6e
--- /dev/null
+++ b/llvm/test/Assembler/invalid-c-style-comment2.ll
@@ -0,0 +1,7 @@
+; RUN: not llvm-as --disable-output %s 2>&1 | FileCheck %s -DFILE=%s
+
+ at B = external global i32
+
+; CHECK: [[FILE]]:[[@LINE+1]]:2: error: expected top-level entity
+*/
+
More information about the llvm-commits
mailing list