Do some tactical inlining across lexer and parser. (#4307)

These are based on looking at our compilation benchmark and looking at
function bodies that seem surprising to not get inlined.

Note that this will have a bit more impact on x86 where function call
overhead (especially due to pushing and popping registers) is a bit
higher than Arm.

For a recent AMD server, this makes parsing around 15% faster, and full
"check" phase 5% faster.

Benchmark results:
```
name                                               old cpu/op   new cpu/op   delta
BM_CompileAPIFileDenseDecls<Phase::Lex>/256        40.2µs ± 2%  37.8µs ± 1%   -5.89%  (p=0.000 n=19+17)
BM_CompileAPIFileDenseDecls<Phase::Lex>/1024        190µs ± 2%   181µs ± 2%   -4.93%  (p=0.000 n=19+18)
BM_CompileAPIFileDenseDecls<Phase::Lex>/4096        779µs ± 1%   745µs ± 2%   -4.29%  (p=0.000 n=19+19)
BM_CompileAPIFileDenseDecls<Phase::Lex>/16384      3.44ms ± 1%  3.32ms ± 3%   -3.32%  (p=0.000 n=19+20)
BM_CompileAPIFileDenseDecls<Phase::Lex>/65536      14.6ms ± 2%  14.3ms ± 3%   -2.46%  (p=0.000 n=19+20)
BM_CompileAPIFileDenseDecls<Phase::Lex>/262144     66.7ms ± 2%  65.0ms ± 4%   -2.52%  (p=0.000 n=19+20)
BM_CompileAPIFileDenseDecls<Phase::Parse>/256      85.7µs ± 2%  71.3µs ± 2%  -16.77%  (p=0.000 n=20+20)
BM_CompileAPIFileDenseDecls<Phase::Parse>/1024      421µs ± 2%   352µs ± 2%  -16.38%  (p=0.000 n=20+20)
BM_CompileAPIFileDenseDecls<Phase::Parse>/4096     1.71ms ± 2%  1.44ms ± 2%  -15.89%  (p=0.000 n=19+20)
BM_CompileAPIFileDenseDecls<Phase::Parse>/16384    7.19ms ± 2%  6.10ms ± 2%  -15.24%  (p=0.000 n=19+20)
BM_CompileAPIFileDenseDecls<Phase::Parse>/65536    29.8ms ± 2%  25.3ms ± 2%  -14.91%  (p=0.000 n=19+20)
BM_CompileAPIFileDenseDecls<Phase::Parse>/262144    127ms ± 2%   109ms ± 2%  -14.28%  (p=0.000 n=20+20)
BM_CompileAPIFileDenseDecls<Phase::Check>/256       785µs ± 1%   752µs ± 1%   -4.13%  (p=0.000 n=20+18)
BM_CompileAPIFileDenseDecls<Phase::Check>/1024     1.71ms ± 1%  1.62ms ± 1%   -5.17%  (p=0.000 n=20+18)
BM_CompileAPIFileDenseDecls<Phase::Check>/4096     5.28ms ± 1%  4.97ms ± 1%   -6.04%  (p=0.000 n=20+19)
BM_CompileAPIFileDenseDecls<Phase::Check>/16384    20.2ms ± 1%  19.0ms ± 2%   -5.98%  (p=0.000 n=20+20)
BM_CompileAPIFileDenseDecls<Phase::Check>/65536    83.8ms ± 1%  78.9ms ± 2%   -5.84%  (p=0.000 n=19+20)
BM_CompileAPIFileDenseDecls<Phase::Check>/262144    354ms ± 1%   335ms ± 1%   -5.41%  (p=0.000 n=19+20)
```
This commit is contained in:
Chandler Carruth
2024-09-15 23:48:19 +00:00
committed by GitHub
parent 580e84513c
commit 06344aeb7c
4 changed files with 44 additions and 48 deletions
-17
View File
@@ -66,16 +66,6 @@ Context::Context(Tree& tree, Lex::TokenizedBuffer& tokens,
tokens_->GetKind(*end_));
}
auto Context::AddLeafNode(NodeKind kind, Lex::TokenIndex token, bool has_error)
-> void {
tree_->node_impls_.push_back(Tree::NodeImpl(kind, has_error, token));
}
auto Context::AddNode(NodeKind kind, Lex::TokenIndex token, bool has_error)
-> void {
tree_->node_impls_.push_back(Tree::NodeImpl(kind, has_error, token));
}
auto Context::ReplacePlaceholderNode(int32_t position, NodeKind kind,
Lex::TokenIndex token, bool has_error)
-> void {
@@ -143,13 +133,6 @@ auto Context::ConsumeChecked(Lex::TokenKind kind) -> Lex::TokenIndex {
return Consume();
}
auto Context::ConsumeIf(Lex::TokenKind kind) -> std::optional<Lex::TokenIndex> {
if (!PositionIs(kind)) {
return std::nullopt;
}
return Consume();
}
auto Context::FindNextOf(std::initializer_list<Lex::TokenKind> desired_kinds)
-> std::optional<Lex::TokenIndex> {
auto new_position = position_;