krak/zstd
krak/zstd
1
0
Fork 0
mirror of https://github.com/facebook/zstd.git synced 2025-03-06 16:56:49 +02:00
Code Issues Releases 1 Activity

improved decompression speed

Browse Source 
while reviewing #1364,
I found a decompression speed improvement.

On my laptop, the new code decompresses +5-6% faster on clang
and +2-3% faster on gcc.

not bad for an accidental optimization...
This commit is contained in:
Yann Collet 2018-10-10 15:48:43 -07:00
parent 8d2c844cf1
commit d3ec23313d
1 changed files with 3 additions and 10 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

13
lib/common/bitstream.h
View File

@ -339,17 +339,8 @@ MEM_STATIC size_t BIT_getUpperBits(size_t bitContainer, U32 const start)
MEM_STATIC size_t BIT_getMiddleBits(size_t bitContainer, U32 const start, U32 const nbBits)
{
#if defined(__BMI__) && defined(__GNUC__) && __GNUC__*1000+__GNUC_MINOR__ >= 4008 /* experimental */
# if defined(__x86_64__)
if (sizeof(bitContainer)==8)
return _bextr_u64(bitContainer, start, nbBits);
else
# endif
return _bextr_u32(bitContainer, start, nbBits);
#else
assert(nbBits < BIT_MASK_SIZE);
return (bitContainer >> start) & BIT_mask[nbBits];
#endif
}
MEM_STATIC size_t BIT_getLowerBits(size_t bitContainer, U32 const nbBits)
@ -366,9 +357,11 @@ MEM_STATIC size_t BIT_getLowerBits(size_t bitContainer, U32 const nbBits)
* @return : value extracted */
MEM_STATIC size_t BIT_lookBits(const BIT_DStream_t* bitD, U32 nbBits)
{
#if defined(__BMI__) && defined(__GNUC__) /* experimental; fails if bitD->bitsConsumed + nbBits > sizeof(bitD->bitContainer)*8 */
#if 1
assert(bitD->bitsConsumed + nbBits <= sizeof(bitD->bitContainer)*8);
return BIT_getMiddleBits(bitD->bitContainer, (sizeof(bitD->bitContainer)*8) - bitD->bitsConsumed - nbBits, nbBits);
#else
/* previous code path, seems slower */
U32 const regMask = sizeof(bitD->bitContainer)*8 - 1;
return ((bitD->bitContainer << (bitD->bitsConsumed & regMask)) >> 1) >> ((regMask-nbBits) & regMask);
#endif