External/cglm
1
0
Fork 0
mirror of https://github.com/recp/cglm.git synced 2025-10-04 01:00:46 +00:00
Code Issues Packages Projects Releases Wiki Activity

make mat4 transpose and scale inline function

Browse Source
This commit is contained in:
Recep Aslantas
2016-09-21 00:23:17 +03:00
parent b2b50076d2
commit ce74bc4a82
2 changed files with 31 additions and 31 deletions
Download Patch File Download Diff File Expand all files Collapse all files

56
include/cglm-mat-simd.h
View File

@@ -10,35 +10,35 @@
#include "cglm-intrin.h"
#define CGLM_MAT_TRANSP_SSE_4x4f(M, D) \
do { \
__m128 r0; \
__m128 r1; \
__m128 r2; \
__m128 r3; \
\
r0 = _mm_load_ps(M[0]); \
r1 = _mm_load_ps(M[1]); \
r2 = _mm_load_ps(M[2]); \
r3 = _mm_load_ps(M[3]); \
\
_MM_TRANSPOSE4_PS(r0, r1, r2, r3); \
\
_mm_store_ps(D[0], r0); \
_mm_store_ps(D[1], r1); \
_mm_store_ps(D[2], r2); \
_mm_store_ps(D[3], r3); \
} while (0)
CGLM_INLINE
void
glm_mat4_scale_sse2(mat4 m, float s){
__m128 x0;
x0 = _mm_set1_ps(s);
#define CGLM_MAT_SCALE_SSE_4x4f(M, S) \
do { \
__m128 xmm0; \
xmm0 = _mm_set1_ps(S); \
_mm_store_ps(M[0], _mm_mul_ps(_mm_load_ps(M[0]), xmm0)); \
_mm_store_ps(M[1], _mm_mul_ps(_mm_load_ps(M[1]), xmm0)); \
_mm_store_ps(M[2], _mm_mul_ps(_mm_load_ps(M[2]), xmm0)); \
_mm_store_ps(M[3], _mm_mul_ps(_mm_load_ps(M[3]), xmm0)); \
} while (0)
_mm_store_ps(m[0], _mm_mul_ps(_mm_load_ps(m[0]), x0));
_mm_store_ps(m[1], _mm_mul_ps(_mm_load_ps(m[1]), x0));
_mm_store_ps(m[2], _mm_mul_ps(_mm_load_ps(m[2]), x0));
_mm_store_ps(m[3], _mm_mul_ps(_mm_load_ps(m[3]), x0));
}
CGLM_INLINE
void
glm_mat4_transp_sse2(mat4 m, mat4 dest){
__m128 r0, r1, r2, r3;
r0 = _mm_load_ps(m[0]);
r1 = _mm_load_ps(m[1]);
r2 = _mm_load_ps(m[2]);
r3 = _mm_load_ps(m[3]);
_MM_TRANSPOSE4_PS(r0, r1, r2, r3);
_mm_store_ps(dest[0], r0);
_mm_store_ps(dest[1], r1);
_mm_store_ps(dest[2], r2);
_mm_store_ps(dest[3], r3);
}
CGLM_INLINE
void

6
include/cglm-mat.h
View File

@@ -90,7 +90,7 @@ CGLM_INLINE
void
glm_mat4_transpose_to(mat4 m, mat4 dest) {
#if defined( __SSE__ ) || defined( __SSE2__ )
CGLM_MAT_TRANSP_SSE_4x4f(m, dest);
glm_mat4_transp_sse2(m, dest);
#else
dest[0][0] = m[0][0];
dest[0][1] = m[1][0];
@@ -118,7 +118,7 @@ CGLM_INLINE
void
glm_mat4_transpose(mat4 m) {
#if defined( __SSE__ ) || defined( __SSE2__ )
CGLM_MAT_TRANSP_SSE_4x4f(m, m);
glm_mat4_transp_sse2(m, m);
#else
mat4 d;
@@ -141,7 +141,7 @@ CGLM_INLINE
void
glm_mat4_scale(mat4 m, float s) {
#if defined( __SSE__ ) || defined( __SSE2__ )
CGLM_MAT_SCALE_SSE_4x4f(m, s);
glm_mat4_scale_sse2(m, s);
#else
glm_mat4_scale_p(m, s);
#endif