forked from OSchip/llvm-project
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:
parent
134f56e702
commit
d906e731ec
|
@ -1216,65 +1216,22 @@ static void ComputeLineNumbers(DiagnosticsEngine &Diag, ContentCache *FI,
|
|||
|
||||
const unsigned char *Buf = (const unsigned char *)Buffer->getBufferStart();
|
||||
const unsigned char *End = (const unsigned char *)Buffer->getBufferEnd();
|
||||
unsigned Offs = 0;
|
||||
unsigned I = 0;
|
||||
while (true) {
|
||||
// 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__
|
||||
// Try to skip to the next newline using SSE instructions. This is very
|
||||
// performance sensitive for programs with lots of diagnostics and in -E
|
||||
// mode.
|
||||
__m128i CRs = _mm_set1_epi8('\r');
|
||||
__m128i LFs = _mm_set1_epi8('\n');
|
||||
|
||||
// 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);
|
||||
if (Buf[I] == '\n' || Buf[I] == '\r') {
|
||||
// If this is \r\n, skip both characters.
|
||||
if (Buf[I] == '\r' && Buf[I+1] == '\n')
|
||||
++I;
|
||||
++I;
|
||||
LineOffsets.push_back(I);
|
||||
} else {
|
||||
// Otherwise, this is a null. If end of file, exit.
|
||||
if (Buf == End) break;
|
||||
// Otherwise, skip the null.
|
||||
++Offs;
|
||||
++Buf;
|
||||
// Otherwise, this is a NUL. If end of file, exit.
|
||||
if (Buf+I == End) break;
|
||||
++I;
|
||||
}
|
||||
}
|
||||
|
||||
|
|
Loading…
Reference in New Issue