carbon-language/carbon-lang
1
0
Fork 0
mirror of https://github.com/carbon-language/carbon-lang.git synced 2026-10-05 22:02:55 +01:00
Code Issues Packages Projects Releases 10 Wiki Activity

Switch CARBON_CHECK to a format string API (#4285)

Browse Source 
This switches `DCHECK` and `FATAL` as well.

The goal is to reduce the code size impact of these assertions so that
we can keep more of them enabled. Currently, the largest cost I see from
`CHECK` is not the actual check or the cold code itself, but actually
the failure to inline trivial functions due to the presence of the cold
code. This means that our goal isn't to reduce apparent code size in the
final binary but the LLVM IR cost assessed for these routines in the
inliner, which closely correlates with code size but is a bit different.

As discussed in #4283, experimentation shows that a single function call
with a minimal number of arguments is the lowest cost model for these.
This is easily achieved with a format-string API that internally uses
`llvm::formatv`. This PR is essentially the `CHECK` version of #4283.

However, the check macros are substantially harder to make work with
both format strings and streaming because they also take a condition.
Also, unexpectedly, I was very successful at devising a regular
expression based automated rewrite from the streaming to the format
string form with only low 10s of manual fixes. This includes compacting
strings broken up across lines, etc. Given how well that went, I've
prepared this PR which just directly switches to the format string API
and migrate everything to use it.

One nice side-effect is that the format string approach ends up greatly
simplifying the implementation here as well.

This is ... *shockingly* effective. Parsing speeds up by more than 3%
with just this change. And checking speeds up by **8%** with this change
alone:
```
BM_CompileAPIFileDenseDecls<Phase::Parse>/256      86.3µs ± 1%  82.9µs ± 1%  -3.94%  (p=0.000 n=17+19)
BM_CompileAPIFileDenseDecls<Phase::Parse>/1024      431µs ± 1%   415µs ± 1%  -3.76%  (p=0.000 n=18+19)
BM_CompileAPIFileDenseDecls<Phase::Parse>/4096     1.77ms ± 1%  1.71ms ± 1%  -3.18%  (p=0.000 n=18+19)
BM_CompileAPIFileDenseDecls<Phase::Parse>/16384    7.44ms ± 1%  7.17ms ± 2%  -3.56%  (p=0.000 n=18+20)
BM_CompileAPIFileDenseDecls<Phase::Parse>/65536    30.7ms ± 1%  29.7ms ± 1%  -3.15%  (p=0.000 n=18+20)
BM_CompileAPIFileDenseDecls<Phase::Parse>/262144    131ms ± 1%   127ms ± 1%  -2.81%  (p=0.000 n=18+18)
BM_CompileAPIFileDenseDecls<Phase::Check>/256       878µs ± 2%   800µs ± 1%  -8.91%  (p=0.000 n=19+20)
BM_CompileAPIFileDenseDecls<Phase::Check>/1024     1.88ms ± 2%  1.72ms ± 1%  -8.56%  (p=0.000 n=19+20)
BM_CompileAPIFileDenseDecls<Phase::Check>/4096     5.78ms ± 2%  5.28ms ± 1%  -8.70%  (p=0.000 n=20+18)
BM_CompileAPIFileDenseDecls<Phase::Check>/16384    21.9ms ± 1%  20.1ms ± 1%  -8.02%  (p=0.000 n=18+20)
BM_CompileAPIFileDenseDecls<Phase::Check>/65536    90.4ms ± 2%  83.1ms ± 1%  -8.04%  (p=0.000 n=19+20)
BM_CompileAPIFileDenseDecls<Phase::Check>/262144    381ms ± 2%   352ms ± 1%  -7.79%  (p=0.000 n=19+19)
```

---------

Co-authored-by: Richard Smith <richard@metafoo.co.uk>
Co-authored-by: josh11b <15258583+josh11b@users.noreply.github.com>
This commit is contained in:
Chandler Carruth
2024-09-12 16:42:08 +00:00
committed by GitHub
co-authored by Richard Smith josh11b
parent 35dfa5f03c
commit 4845f40dff
140 changed files with 1234 additions and 1161 deletions
Download Patch File Download Diff File Expand all files Collapse all files
toolchain/lex/lex.cpp
+29 -29
View File
@@ -508,7 +508,7 @@ static auto DispatchNext(Lexer& lexer, llvm::StringRef source_text,
static auto Dispatch##LexMethod(Lexer& lexer, llvm::StringRef source_text, \
ssize_t position) -> void { \
Lexer::LexResult result = lexer.LexMethod(source_text, position); \
CARBON_CHECK(result) << "Failed to form a token!"; \
CARBON_CHECK(result, "Failed to form a token!"); \
[[clang::musttail]] return DispatchNext(lexer, source_text, position); \
}
CARBON_DISPATCH_LEX_TOKEN(LexError)
@@ -527,7 +527,7 @@ CARBON_DISPATCH_LEX_TOKEN(LexStringLiteral)
OneCharTokenKindTable[static_cast<unsigned char>( \
source_text[position])], \
position); \
CARBON_CHECK(result) << "Failed to form a token!"; \
CARBON_CHECK(result, "Failed to form a token!"); \
[[clang::musttail]] return DispatchNext(lexer, source_text, position); \
}
CARBON_DISPATCH_LEX_SYMBOL_TOKEN(LexOneChar)
@@ -855,7 +855,7 @@ auto Lexer::LexCommentOrSlash(llvm::StringRef source_text, ssize_t& position)
// This code path should produce a token, make sure that happens.
LexResult result = LexSymbolToken(source_text, position);
CARBON_CHECK(result) << "Failed to form a token!";
CARBON_CHECK(result, "Failed to form a token!");
}
auto Lexer::LexComment(llvm::StringRef source_text, ssize_t& position) -> void {
@@ -1063,10 +1063,10 @@ auto Lexer::LexOneCharSymbolToken(llvm::StringRef source_text, TokenKind kind,
// Verify in a debug build that the incoming token kind is correct.
CARBON_DCHECK(kind != TokenKind::Error);
CARBON_DCHECK(kind.fixed_spelling().size() == 1);
CARBON_DCHECK(source_text[position] == kind.fixed_spelling().front())
<< "Source text starts with '" << source_text[position]
<< "' instead of the spelling '" << kind.fixed_spelling()
<< "' of the incoming token kind '" << kind << "'";
CARBON_DCHECK(source_text[position] == kind.fixed_spelling().front(),
"Source text starts with '{0}' instead of the spelling '{1}' "
"of the incoming token kind '{2}'",
source_text[position], kind.fixed_spelling(), kind);
TokenIndex token = LexToken(kind, position);
++position;
@@ -1077,10 +1077,10 @@ auto Lexer::LexOpeningSymbolToken(llvm::StringRef source_text, TokenKind kind,
ssize_t& position) -> LexResult {
CARBON_DCHECK(kind.is_opening_symbol());
CARBON_DCHECK(kind.fixed_spelling().size() == 1);
CARBON_DCHECK(source_text[position] == kind.fixed_spelling().front())
<< "Source text starts with '" << source_text[position]
<< "' instead of the spelling '" << kind.fixed_spelling()
<< "' of the incoming token kind '" << kind << "'";
CARBON_DCHECK(source_text[position] == kind.fixed_spelling().front(),
"Source text starts with '{0}' instead of the spelling '{1}' "
"of the incoming token kind '{2}'",
source_text[position], kind.fixed_spelling(), kind);
int32_t byte_offset = position;
++position;
@@ -1096,10 +1096,10 @@ auto Lexer::LexClosingSymbolToken(llvm::StringRef source_text, TokenKind kind,
ssize_t& position) -> LexResult {
CARBON_DCHECK(kind.is_closing_symbol());
CARBON_DCHECK(kind.fixed_spelling().size() == 1);
CARBON_DCHECK(source_text[position] == kind.fixed_spelling().front())
<< "Source text starts with '" << source_text[position]
<< "' instead of the spelling '" << kind.fixed_spelling()
<< "' of the incoming token kind '" << kind << "'";
CARBON_DCHECK(source_text[position] == kind.fixed_spelling().front(),
"Source text starts with '{0}' instead of the spelling '{1}' "
"of the incoming token kind '{2}'",
source_text[position], kind.fixed_spelling(), kind);
int32_t byte_offset = position;
++position;
@@ -1204,7 +1204,7 @@ auto Lexer::LexKeywordOrIdentifier(llvm::StringRef source_text,
// Take the valid characters off the front of the source buffer.
llvm::StringRef identifier_text =
ScanForIdentifierPrefix(source_text.substr(position));
CARBON_CHECK(!identifier_text.empty()) << "Must have at least one character!";
CARBON_CHECK(!identifier_text.empty(), "Must have at least one character!");
position += identifier_text.size();
// Check if the text is a type literal, and if so form such a literal.
@@ -1255,7 +1255,7 @@ auto Lexer::LexHash(llvm::StringRef source_text, ssize_t& position)
// Take the valid characters off the front of the source buffer.
llvm::StringRef identifier_text =
ScanForIdentifierPrefix(source_text.substr(position + 1));
CARBON_CHECK(!identifier_text.empty()) << "Must have at least one character!";
CARBON_CHECK(!identifier_text.empty(), "Must have at least one character!");
position += 1 + identifier_text.size();
// Replace the `r` identifier's value with the raw identifier.
@@ -1359,14 +1359,14 @@ class Lexer::ErrorRecoveryBuffer {
// currently require insertions to be specified in source order, but this
// restriction would be easy to relax.
auto InsertBefore(TokenIndex insert_before, TokenKind kind) -> void {
CARBON_CHECK(insert_before.index > 0)
<< "Cannot insert before the start of file token.";
CARBON_CHECK(insert_before.index <
static_cast<int>(buffer_.token_infos_.size()))
<< "Cannot insert after the end of file token.";
CARBON_CHECK(new_tokens_.empty() ||
new_tokens_.back().first <= insert_before)
<< "Insertions performed out of order.";
CARBON_CHECK(insert_before.index > 0,
"Cannot insert before the start of file token.");
CARBON_CHECK(
insert_before.index < static_cast<int>(buffer_.token_infos_.size()),
"Cannot insert after the end of file token.");
CARBON_CHECK(
new_tokens_.empty() || new_tokens_.back().first <= insert_before,
"Insertions performed out of order.");
// If the `insert_before` token has leading whitespace, mark the
// inserted token as also having leading whitespace. This avoids changing
@@ -1423,12 +1423,12 @@ class Lexer::ErrorRecoveryBuffer {
if (kind.is_opening_symbol()) {
open_groups.push_back(token);
} else if (kind.is_closing_symbol()) {
CARBON_CHECK(!open_groups.empty()) << "Failed to balance brackets";
CARBON_CHECK(!open_groups.empty(), "Failed to balance brackets");
auto opening_token = open_groups.pop_back_val();
CARBON_CHECK(
kind == buffer_.GetTokenInfo(opening_token).kind().closing_symbol())
<< "Failed to balance brackets";
kind == buffer_.GetTokenInfo(opening_token).kind().closing_symbol(),
"Failed to balance brackets");
auto& opening_token_info = buffer_.GetTokenInfo(opening_token);
auto& closing_token_info = buffer_.GetTokenInfo(token);
opening_token_info.set_closing_token_index(token);
@@ -1530,7 +1530,7 @@ auto Lexer::DiagnoseAndFixMismatchedBrackets() -> void {
fixes.ReplaceWithError(token);
}
CARBON_CHECK(!fixes.empty()) << "Didn't find anything to fix";
CARBON_CHECK(!fixes.empty(), "Didn't find anything to fix");
fixes.Apply();
fixes.FixTokenCrossReferences();
}