External/cglm
1
0
Fork 0
mirror of https://github.com/recp/cglm.git synced 2026-01-02 13:49:59 +00:00
Code Issues Packages Projects Releases Wiki Activity

sse: make use of int domain as default behavior if possible ( compiler may ignore it )

Browse Source 
also use AVX's `_mm_permute_ps`for shuffling single vector
This commit is contained in:
Recep Aslantas
2024-04-11 21:57:16 +03:00
parent de66f0a67f
commit 480e1de048
2 changed files with 10 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files

13
include/cglm/simd/x86.h
View File

@@ -20,13 +20,18 @@
#define glmm_128 __m128
#if defined(CGLM_USE_INT_DOMAIN) && defined(__SSE2__)
#ifdef __AVX__
# define glmm_shuff1(xmm, z, y, x, w) \
_mm_castsi128_ps(_mm_shuffle_epi32(_mm_castps_si128(xmm), \
_MM_SHUFFLE(z, y, x, w)))
_mm_permute_ps((xmm), _MM_SHUFFLE(z, y, x, w))
#else
# define glmm_shuff1(xmm, z, y, x, w) \
# if !defined(CGLM_NO_INT_DOMAIN) && defined(__SSE2__)
# define glmm_shuff1(xmm, z, y, x, w) \
_mm_castsi128_ps(_mm_shuffle_epi32(_mm_castps_si128(xmm), \
_MM_SHUFFLE(z, y, x, w)))
# else
# define glmm_shuff1(xmm, z, y, x, w) \
_mm_shuffle_ps(xmm, xmm, _MM_SHUFFLE(z, y, x, w))
# endif
#endif
#define glmm_splat(x, lane) glmm_shuff1(x, lane, lane, lane, lane)