Re: [PATCH v3] hash: fix SSE comparison

2023-10-10 Thread David Marchand
On Mon, Oct 9, 2023 at 4:33 PM Bruce Richardson wrote: > > On Sat, Oct 07, 2023 at 03:36:34PM +0800, Jieqiang Wang wrote: > > __mm_cmpeq_epi16 returns 0x if the corresponding 16-bit elements are > > equal. In original SSE2 implementation for function compare_signatures, > > it utilizes _mm_mov

Re: [PATCH v3] hash: fix SSE comparison

2023-10-09 Thread Bruce Richardson
On Sat, Oct 07, 2023 at 03:36:34PM +0800, Jieqiang Wang wrote: > __mm_cmpeq_epi16 returns 0x if the corresponding 16-bit elements are > equal. In original SSE2 implementation for function compare_signatures, > it utilizes _mm_movemask_epi8 to create mask from the MSB of each 8-bit > element, wh

[PATCH v3] hash: fix SSE comparison

2023-10-07 Thread Jieqiang Wang
__mm_cmpeq_epi16 returns 0x if the corresponding 16-bit elements are equal. In original SSE2 implementation for function compare_signatures, it utilizes _mm_movemask_epi8 to create mask from the MSB of each 8-bit element, while we should only care about the MSB of lower 8-bit in each 16-bit ele