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

neon: move neon-scale to simd header

Browse Source
This commit is contained in:
Recep Aslantas
2020-08-29 11:32:44 +03:00
parent a05b282fad
commit 54f805a62d
2 changed files with 14 additions and 6 deletions
Download Patch File Download Diff File Expand all files Collapse all files

7
include/cglm/mat4.h
View File

@@ -536,12 +536,7 @@ glm_mat4_scale(mat4 m, float s) {
#if defined( __SSE__ ) || defined( __SSE2__ )
glm_mat4_scale_sse2(m, s);
#elif defined(CGLM_NEON_FP)
float32x4_t v0;
v0 = vdupq_n_f32(s);
vst1q_f32(m[0], vmulq_f32(vld1q_f32(m[0]), v0));
vst1q_f32(m[1], vmulq_f32(vld1q_f32(m[1]), v0));
vst1q_f32(m[2], vmulq_f32(vld1q_f32(m[2]), v0));
vst1q_f32(m[3], vmulq_f32(vld1q_f32(m[3]), v0));
glm_mat4_scale_neon(m, s);
#else
glm_mat4_scale_p(m, s);
#endif

13
include/cglm/simd/neon/mat4.h
View File

@@ -12,6 +12,19 @@
#include "../../common.h"
#include "../intrin.h"
CGLM_INLINE
void
glm_mat4_scale_neon(mat4 m, float s) {
float32x4_t v0;
v0 = vdupq_n_f32(s);
vst1q_f32(m[0], vmulq_f32(vld1q_f32(m[0]), v0));
vst1q_f32(m[1], vmulq_f32(vld1q_f32(m[1]), v0));
vst1q_f32(m[2], vmulq_f32(vld1q_f32(m[2]), v0));
vst1q_f32(m[3], vmulq_f32(vld1q_f32(m[3]), v0));
}
CGLM_INLINE
void
glm_mat4_mul_neon(mat4 m1, mat4 m2, mat4 dest) {