From 0e2b6c7f1acd55ffb5350144f4319be4721169f8 Mon Sep 17 00:00:00 2001 From: Chandler Carruth Date: Thu, 12 Oct 2023 22:11:04 -0700 Subject: [PATCH] Optimize runs of horizontal whitespace. (#3288) MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit So, this is a somewhat fun, simple improvement. =] Just use a loop and count runs of whitespace. I didn't even work all that hard to make the loop fast, but it seems great. Makes long runs of indentation more than 2x faster at basically no code complexity. I thought about doing this for vertical whitespace as well but it's not easy to do, and didn't seem worth adding complexity. Huge runs of blank lines aren't nearly as common as lots of indentation. I do have a plan for an analogous optimization for comment blocks, but want to simplify some other code first. We could also make this (hilariously) faster with some judicious use of SIMD or clever use of a string function, but it doesn't seem worth it given how fast the simple loop is already. I didn't work to get a high N count and so there's plenty of noise here, but the benchmark data speaks for itself: ``` BM_ValidKeywords 2.71ms ± 1% 2.75ms ± 1% +1.32% (p=0.016 n=5+5) BM_ValidIdentifiers<1, 64, false> 9.71ms ± 2% 9.74ms ± 1% ~ (p=1.000 n=5+5) BM_ValidIdentifiers<1, 1, true> 3.17ms ± 1% 3.22ms ± 2% ~ (p=0.151 n=5+5) BM_ValidIdentifiers<3, 5, true> 11.5ms ± 2% 11.6ms ± 3% ~ (p=0.548 n=5+5) BM_ValidIdentifiers<3, 16, true> 11.3ms ± 3% 11.6ms ± 3% ~ (p=0.095 n=5+5) BM_ValidIdentifiers<12, 64, true> 12.8ms ± 1% 12.8ms ± 1% ~ (p=1.000 n=5+5) BM_HorizontalWhitespace/1 11.6ms ± 1% 11.7ms ± 2% ~ (p=0.310 n=5+5) BM_HorizontalWhitespace/4 12.9ms ± 1% 11.8ms ± 0% -8.50% (p=0.008 n=5+5) BM_HorizontalWhitespace/16 17.3ms ± 4% 12.5ms ± 1% -27.69% (p=0.008 n=5+5) BM_HorizontalWhitespace/64 28.9ms ± 3% 16.0ms ± 2% -44.88% (p=0.008 n=5+5) BM_HorizontalWhitespace/128 47.6ms ± 3% 21.0ms ± 0% -55.88% (p=0.016 n=5+4) BM_RandomSource 7.92ms ± 1% 7.70ms ± 3% -2.74% (p=0.016 n=5+5) BM_GroupingSymbols/1/0/0 5.92ms ± 2% 5.86ms ± 1% ~ (p=0.310 n=5+5) BM_GroupingSymbols/2/0/0 5.30ms ± 1% 5.01ms ± 1% -5.52% (p=0.008 n=5+5) BM_GroupingSymbols/3/0/0 4.48ms ± 0% 3.95ms ± 1% -11.69% (p=0.008 n=5+5) BM_GroupingSymbols/4/0/0 4.61ms ± 1% 3.73ms ± 1% -19.12% (p=0.008 n=5+5) BM_GroupingSymbols/8/0/0 5.34ms ± 6% 3.05ms ± 1% -42.82% (p=0.008 n=5+5) BM_GroupingSymbols/16/0/0 6.44ms ± 1% 3.20ms ± 2% -50.24% (p=0.008 n=5+5) BM_GroupingSymbols/32/0/0 10.3ms ± 5% 4.2ms ± 1% -59.81% (p=0.008 n=5+5) BM_GroupingSymbols/0/1/0 5.17ms ± 2% 5.17ms ± 1% ~ (p=0.690 n=5+5) BM_GroupingSymbols/0/2/0 4.04ms ± 1% 4.04ms ± 2% ~ (p=1.000 n=5+5) BM_GroupingSymbols/0/3/0 2.89ms ± 1% 2.89ms ± 1% ~ (p=1.000 n=5+5) BM_GroupingSymbols/0/4/0 2.54ms ± 1% 2.55ms ± 1% ~ (p=0.421 n=5+5) BM_GroupingSymbols/0/8/0 1.65ms ± 2% 1.67ms ± 1% ~ (p=0.310 n=5+5) BM_GroupingSymbols/0/16/0 1.18ms ± 1% 1.19ms ± 2% ~ (p=0.222 n=5+5) BM_GroupingSymbols/0/32/0 948µs ± 1% 957µs ± 2% ~ (p=0.310 n=5+5) BM_GroupingSymbols/0/0/1 5.17ms ± 1% 5.16ms ± 2% ~ (p=0.841 n=5+5) BM_GroupingSymbols/0/0/2 4.03ms ± 2% 4.04ms ± 2% ~ (p=0.548 n=5+5) BM_GroupingSymbols/0/0/3 2.89ms ± 1% 2.88ms ± 1% ~ (p=0.841 n=5+5) BM_GroupingSymbols/0/0/4 2.54ms ± 1% 2.54ms ± 2% ~ (p=0.548 n=5+5) BM_GroupingSymbols/0/0/8 1.66ms ± 3% 1.67ms ± 2% ~ (p=0.690 n=5+5) BM_GroupingSymbols/0/0/16 1.19ms ± 1% 1.18ms ± 2% ~ (p=0.548 n=5+5) BM_GroupingSymbols/0/0/32 949µs ± 2% 955µs ± 1% ~ (p=0.310 n=5+5) BM_GroupingSymbols/32/1/0 10.0ms ± 1% 4.0ms ± 1% -59.76% (p=0.008 n=5+5) BM_GroupingSymbols/32/2/0 9.73ms ± 2% 3.92ms ± 2% -59.73% (p=0.008 n=5+5) BM_GroupingSymbols/32/3/0 9.40ms ± 2% 3.84ms ± 3% -59.10% (p=0.008 n=5+5) BM_GroupingSymbols/32/4/0 9.20ms ± 2% 3.74ms ± 1% -59.35% (p=0.008 n=5+5) BM_GroupingSymbols/32/8/0 8.38ms ± 2% 3.50ms ± 1% -58.22% (p=0.008 n=5+5) BM_GroupingSymbols/32/16/0 7.18ms ± 2% 3.06ms ± 3% -57.41% (p=0.008 n=5+5) BM_GroupingSymbols/32/32/0 5.53ms ± 1% 2.44ms ± 2% -55.99% (p=0.008 n=5+5) BM_GroupingSymbols/32/32/1 5.47ms ± 2% 2.40ms ± 2% -56.08% (p=0.008 n=5+5) BM_GroupingSymbols/32/32/2 5.41ms ± 3% 2.40ms ± 2% -55.66% (p=0.008 n=5+5) BM_GroupingSymbols/32/32/3 5.28ms ± 2% 2.37ms ± 2% -55.18% (p=0.008 n=5+5) BM_GroupingSymbols/32/32/4 5.25ms ± 2% 2.34ms ± 2% -55.52% (p=0.008 n=5+5) BM_GroupingSymbols/32/32/8 5.03ms ± 3% 2.25ms ± 1% -55.29% (p=0.008 n=5+5) BM_GroupingSymbols/32/32/16 4.62ms ± 1% 2.15ms ± 3% -53.41% (p=0.008 n=5+5) BM_GroupingSymbols/32/32/32 3.99ms ± 1% 1.86ms ± 1% -53.24% (p=0.008 n=5+5) BM_BlankLines/1 12.8ms ± 1% 12.6ms ± 2% ~ (p=0.310 n=5+5) BM_BlankLines/4 16.0ms ± 3% 15.8ms ± 1% ~ (p=0.310 n=5+5) BM_BlankLines/16 33.1ms ± 2% 32.1ms ± 1% -3.29% (p=0.008 n=5+5) BM_BlankLines/64 84.6ms ± 3% 84.2ms ± 3% ~ (p=0.690 n=5+5) BM_BlankLines/128 159ms ± 4% 155ms ± 3% ~ (p=0.310 n=5+5) BM_CommentLines/1/0/0 14.5ms ± 2% 14.5ms ± 2% ~ (p=0.690 n=5+5) BM_CommentLines/4/0/0 19.0ms ± 1% 19.0ms ± 1% ~ (p=0.548 n=5+5) BM_CommentLines/128/0/0 188ms ± 2% 186ms ± 1% ~ (p=0.151 n=5+5) BM_CommentLines/1/30/0 14.8ms ± 3% 14.7ms ± 2% ~ (p=0.421 n=5+5) BM_CommentLines/4/30/0 21.8ms ± 1% 21.3ms ± 4% ~ (p=0.095 n=5+5) BM_CommentLines/128/30/0 201ms ± 1% 200ms ± 2% ~ (p=0.421 n=5+5) BM_CommentLines/1/70/0 15.5ms ± 3% 15.2ms ± 4% ~ (p=0.095 n=5+5) BM_CommentLines/4/70/0 23.2ms ± 1% 22.5ms ± 2% -2.76% (p=0.008 n=5+5) BM_CommentLines/128/70/0 213ms ± 1% 209ms ± 1% -1.54% (p=0.016 n=5+5) BM_CommentLines/1/0/2 15.3ms ± 1% 14.5ms ± 1% -4.99% (p=0.008 n=5+5) BM_CommentLines/4/0/2 21.4ms ± 1% 20.2ms ± 2% -5.48% (p=0.008 n=5+5) BM_CommentLines/128/0/2 242ms ± 2% 218ms ± 5% -10.13% (p=0.008 n=5+5) BM_CommentLines/1/30/2 15.7ms ± 4% 15.1ms ± 2% -3.37% (p=0.008 n=5+5) BM_CommentLines/4/30/2 24.3ms ± 1% 22.5ms ± 3% -7.42% (p=0.008 n=5+5) BM_CommentLines/128/30/2 268ms ± 2% 240ms ± 3% -10.22% (p=0.008 n=5+5) BM_CommentLines/1/70/2 16.1ms ± 2% 15.3ms ± 3% -5.24% (p=0.008 n=5+5) BM_CommentLines/4/70/2 25.7ms ± 3% 24.0ms ± 3% -6.69% (p=0.008 n=5+5) BM_CommentLines/128/70/2 272ms ± 1% 247ms ± 1% -9.21% (p=0.008 n=5+5) BM_CommentLines/1/0/8 17.2ms ± 5% 14.8ms ± 2% -14.32% (p=0.008 n=5+5) BM_CommentLines/4/0/8 30.4ms ± 2% 20.8ms ± 2% -31.47% (p=0.008 n=5+5) BM_CommentLines/128/0/8 463ms ± 1% 260ms ± 1% -43.89% (p=0.008 n=5+5) BM_CommentLines/1/30/8 17.2ms ± 2% 15.2ms ± 2% -12.01% (p=0.008 n=5+5) BM_CommentLines/4/30/8 32.4ms ± 1% 23.2ms ± 3% -28.61% (p=0.008 n=5+5) BM_CommentLines/128/30/8 498ms ± 3% 287ms ± 2% -42.32% (p=0.008 n=5+5) BM_CommentLines/1/70/8 17.6ms ± 2% 15.5ms ± 3% -11.61% (p=0.008 n=5+5) BM_CommentLines/4/70/8 34.0ms ± 4% 24.7ms ± 3% -27.31% (p=0.008 n=5+5) BM_CommentLines/128/70/8 497ms ± 2% 297ms ± 4% -40.29% (p=0.008 n=5+5) ``` Stacked on top of #3287 -- only the last commit should be reviewed here. --- toolchain/lex/tokenized_buffer.cpp | 14 ++++++++++++-- 1 file changed, 12 insertions(+), 2 deletions(-) diff --git a/toolchain/lex/tokenized_buffer.cpp b/toolchain/lex/tokenized_buffer.cpp index cd62253ba8b3..9a1cf17aba87 100644 --- a/toolchain/lex/tokenized_buffer.cpp +++ b/toolchain/lex/tokenized_buffer.cpp @@ -300,8 +300,18 @@ class [[clang::internal_linkage]] TokenizedBuffer::Lexer { auto LexHorizontalWhitespace(llvm::StringRef& source_text) -> void { CARBON_DCHECK(source_text.front() == ' ' || source_text.front() == '\t'); NoteWhitespace(); - ++current_column_; - source_text = source_text.drop_front(); + // Handle adjacent whitespace quickly. This comes up frequently for example + // due to indentation. We don't expect *huge* runs, so just use a scalar + // loop. While still scalar, this avoids repeated table dispatch and marking + // whitespace. We use `ssize_t` in the loop for performance. + ssize_t ws_count = 1; + ssize_t size = source_text.size(); + while (ws_count < size && + (source_text[ws_count] == ' ' || source_text[ws_count] == '\t')) { + ++ws_count; + } + current_column_ += ws_count; + source_text = source_text.drop_front(ws_count); } auto LexVerticalWhitespace(llvm::StringRef& source_text) -> void {