External/cglm
1
0
Fork 0
mirror of https://github.com/recp/cglm.git synced 2026-01-03 22:22:11 +00:00
Code Issues Packages Projects Releases Wiki Activity

use non-SIMD scale version for non-SIMD inverse

Browse Source 
* this way is faster, probably mixing manual SSE with compiler result
causes cache misses
This commit is contained in:
Recep Aslantas
2016-09-16 00:56:00 +03:00
parent 8a083c4873
commit 184069361a
1 changed files with 11 additions and 5 deletions
Download Patch File Download Diff File Expand all files Collapse all files

16
include/cglm-mat.h
View File

@@ -126,14 +126,20 @@ glm_mat_transpose_self(mat4 m) {
CGLM_INLINE CGLM_INLINE
void void
glm_mat4_scale(mat4 m, float s) { glm_mat4_scale_p(mat4 m, float s) {
#if defined( __SSE__ ) || defined( __SSE2__ )
CGLM_MAT_SCALE_SSE_4x4f(m, s);
#else
m[0][0] *= s; m[0][1] *= s; m[0][2] *= s; m[0][3] *= s; m[0][0] *= s; m[0][1] *= s; m[0][2] *= s; m[0][3] *= s;
m[1][0] *= s; m[1][1] *= s; m[1][2] *= s; m[1][3] *= s; m[1][0] *= s; m[1][1] *= s; m[1][2] *= s; m[1][3] *= s;
m[2][0] *= s; m[2][1] *= s; m[2][2] *= s; m[2][3] *= s; m[2][0] *= s; m[2][1] *= s; m[2][2] *= s; m[2][3] *= s;
m[3][0] *= s; m[3][1] *= s; m[3][2] *= s; m[3][3] *= s; m[3][0] *= s; m[3][1] *= s; m[3][2] *= s; m[3][3] *= s;
}
CGLM_INLINE
void
glm_mat4_scale(mat4 m, float s) {
#if defined( __SSE__ ) || defined( __SSE2__ )
CGLM_MAT_SCALE_SSE_4x4f(m, s);
#else
glm_mat4_scale_p(m, s);
#endif #endif
} }
@@ -216,7 +222,7 @@ glm_mat4_inv(mat4 mat, mat4 dest) {
det = 1.0f / (a * dest[0][0] + b * dest[1][0] det = 1.0f / (a * dest[0][0] + b * dest[1][0]
+ c * dest[2][0] + d * dest[3][0]); + c * dest[2][0] + d * dest[3][0]);
glm_mat4_scale(dest, det); glm_mat4_scale_p(dest, det);
} }
#endif /* cglm_mat_h */ #endif /* cglm_mat_h */