maxjhandsome
/
llvm-project
forked from OSchip/llvm-project
1
0
Fork 0
Code Issues Pull Requests Packages Releases Wiki Activity

ComputeLineNumbers: delete SSE2 vectorization 

Summary:
SSE2 vectorization was added in 2012, but it is 2018 now and I can't
observe any performance boost (testing clang -E [all Sema/* CodeGen/* with proper -I options]) with the existing _mm_movemask_epi8+countTrailingZeros or the following SSE4.2 (compiling with -msse4.2):

  __m128i C = _mm_setr_epi8('\r','\n',0,0,0,0,0,0,0,0,0,0,0,0,0,0);
  _mm_cmpestri(C, 2, Chunk, 16, _SIDD_UBYTE_OPS | _SIDD_CMP_EQUAL_ANY | _SIDD_POSITIVE_POLARITY | _SIDD_LEAST_SIGNIFICANT)

Delete the vectorization to simplify the code.

Also simplify the code a bit and don't check the line ending sequence \n\r

Reviewers: bkramer, #clang

Reviewed By: bkramer

Subscribers: cfe-commits

Differential Revision: https://reviews.llvm.org/D55484

llvm-svn: 348777
This commit is contained in:
Fangrui Song 2018-12-10 18:10:35 +00:00
parent 134f56e702
commit d906e731ec
1 changed files with 12 additions and 55 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

67
clang/lib/Basic/SourceManager.cpp
View File

@ -1216,65 +1216,22 @@ static void ComputeLineNumbers(DiagnosticsEngine &Diag, ContentCache *FI,
const unsigned char *Buf = (const unsigned char *)Buffer->getBufferStart(); const unsigned char *Buf = (const unsigned char *)Buffer->getBufferStart();
const unsigned char *End = (const unsigned char *)Buffer->getBufferEnd(); const unsigned char *End = (const unsigned char *)Buffer->getBufferEnd();
unsigned Offs = 0; unsigned I = 0;
while (true) { while (true) {
// Skip over the contents of the line. // Skip over the contents of the line.
const unsigned char *NextBuf = (const unsigned char *)Buf; while (Buf[I] != '\n' && Buf[I] != '\r' && Buf[I] != '\0')
++I;
#ifdef __SSE2__ if (Buf[I] == '\n' || Buf[I] == '\r') {
// Try to skip to the next newline using SSE instructions. This is very // If this is \r\n, skip both characters.
// performance sensitive for programs with lots of diagnostics and in -E if (Buf[I] == '\r' && Buf[I+1] == '\n')
// mode. ++I;
__m128i CRs = _mm_set1_epi8('\r'); ++I;
__m128i LFs = _mm_set1_epi8('\n'); LineOffsets.push_back(I);
// First fix up the alignment to 16 bytes.
while (((uintptr_t)NextBuf & 0xF) != 0) {
if (*NextBuf == '\n' || *NextBuf == '\r' || *NextBuf == '\0')
goto FoundSpecialChar;
++NextBuf;
}
// Scan 16 byte chunks for '\r' and '\n'. Ignore '\0'.
while (NextBuf+16 <= End) {
const __m128i Chunk = *(const __m128i*)NextBuf;
__m128i Cmp = _mm_or_si128(_mm_cmpeq_epi8(Chunk, CRs),
_mm_cmpeq_epi8(Chunk, LFs));
unsigned Mask = _mm_movemask_epi8(Cmp);
// If we found a newline, adjust the pointer and jump to the handling code.
if (Mask != 0) {
NextBuf += llvm::countTrailingZeros(Mask);
goto FoundSpecialChar;
}
NextBuf += 16;
}
#endif
while (*NextBuf != '\n' && *NextBuf != '\r' && *NextBuf != '\0')
++NextBuf;
#ifdef __SSE2__
FoundSpecialChar:
#endif
Offs += NextBuf-Buf;
Buf = NextBuf;
if (Buf[0] == '\n' || Buf[0] == '\r') {
// If this is \n\r or \r\n, skip both characters.
if ((Buf[1] == '\n' || Buf[1] == '\r') && Buf[0] != Buf[1]) {
++Offs;
++Buf;
}
++Offs;
++Buf;
LineOffsets.push_back(Offs);
} else { } else {
// Otherwise, this is a null. If end of file, exit. // Otherwise, this is a NUL. If end of file, exit.
if (Buf == End) break; if (Buf+I == End) break;
// Otherwise, skip the null. ++I;
++Offs;
++Buf;
} }
} }