External/cglm
1
0
Fork 0
mirror of https://github.com/recp/cglm.git synced 2025-12-24 20:34:58 +00:00
Code Issues Packages Projects Releases Wiki Activity

avx: implement scale matrix using AVX

Browse Source
This commit is contained in:
Recep Aslantas
2021-04-19 00:11:43 +03:00
parent f3f29bd383
commit 7c81482248
2 changed files with 13 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
include/cglm/mat4.h
View File

@@ -539,7 +539,9 @@ glm_mat4_scale_p(mat4 m, float s) {
CGLM_INLINE
void
glm_mat4_scale(mat4 m, float s) {
#if defined( __SSE__ ) || defined( __SSE2__ )
#ifdef __AVX__
glm_mat4_scale_avx(m, s);
#elif defined( __SSE__ ) || defined( __SSE2__ )
glm_mat4_scale_sse2(m, s);
#elif defined(CGLM_NEON_FP)
glm_mat4_scale_neon(m, s);

10
include/cglm/simd/avx/mat4.h
View File

@@ -14,6 +14,16 @@
#include <immintrin.h>
CGLM_INLINE
void
glm_mat4_scale_avx(mat4 m, float s) {
__m256 y0;
y0 = _mm256_set1_ps(s);
glmm_store256(m[0], _mm256_mul_ps(y0, glmm_load256(m[0])));
glmm_store256(m[2], _mm256_mul_ps(y0, glmm_load256(m[2])));
}
CGLM_INLINE
void
glm_mat4_mul_avx(mat4 m1, mat4 m2, mat4 dest) {