jasder
/
simdjson
1
0
Fork 0
Code Issues Pull Requests Releases 2 Wiki Activity

Adding analysis by @sebpop from https://github.com/lemire/simdjson/pull/391#issuecomment-565551462

This commit is contained in:
Daniel Lemire 2019-12-13 13:39:15 -05:00
parent fc6133b58f
commit f02babe427
1 changed files with 8 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

9
src/arm64/bitmask.h
View File

@ -16,12 +16,19 @@ namespace simdjson::arm64 {
// For example, prefix_xor(00100100) == 00011100
//
really_inline uint64_t prefix_xor(uint64_t bitmask) {
//
/////////////
// We could do this with PMULL, but it is apparently slow.
//
//#ifdef __ARM_FEATURE_CRYPTO // some ARM processors lack this extension
//return vmull_p64(-1ULL, bitmask);
//#else
// Analysis by @sebpop:
// When diffing the assembly for src/stage1_find_marks.cpp I see that the eors are all spread out
// in between other vector code, so effectively the extra cycles of the sequence do not matter
// because the GPR units are idle otherwise and the critical path is on the FP side.
// Also the PMULL requires two extra fmovs: GPR->FP (3 cycles in N1, 5 cycles in A72 )
// and FP->GPR (2 cycles on N1 and 5 cycles on A72.)
///////////
bitmask ^= bitmask << 1;
bitmask ^= bitmask << 2;
bitmask ^= bitmask << 4;