External/cglm
1
0
Fork 0
mirror of https://github.com/recp/cglm.git synced 2025-12-31 12:47:05 +00:00
Code Issues Packages Projects Releases Wiki Activity

arm neon: multiply mat4 with vec4

Browse Source
This commit is contained in:
Recep Aslantas
2020-08-29 11:51:07 +03:00
parent fa01a3077b
commit e34601f578
2 changed files with 24 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
include/cglm/mat4.h
View File

@@ -358,6 +358,8 @@ void
glm_mat4_mulv(mat4 m, vec4 v, vec4 dest) {
#if defined( __SSE__ ) || defined( __SSE2__ )
glm_mat4_mulv_sse2(m, v, dest);
#elif defined(CGLM_NEON_FP)
glm_mat4_mulv_neon(m, v, dest);
#else
vec4 res;
res[0] = m[0][0] * v[0] + m[1][0] * v[1] + m[2][0] * v[2] + m[3][0] * v[3];

22
include/cglm/simd/neon/mat4.h
View File

@@ -79,5 +79,27 @@ glm_mat4_mul_neon(mat4 m1, mat4 m2, mat4 dest) {
vst1q_f32(dest[3], d3);
}
CGLM_INLINE
void
glm_mat4_mulv_neon(mat4 m, vec4 v, vec4 dest) {
float32x4_t l0, l1, l2, l3;
float32x2_t vlo, vhi;
l0 = vld1q_f32(m[0]);
l1 = vld1q_f32(m[1]);
l2 = vld1q_f32(m[2]);
l3 = vld1q_f32(m[3]);
vlo = vld1_f32(&v[0]);
vhi = vld1_f32(&v[2]);
l0 = vmulq_lane_f32(l0, vlo, 0);
l0 = vmlaq_lane_f32(l0, l1, vlo, 1);
l0 = vmlaq_lane_f32(l0, l2, vhi, 0);
l0 = vmlaq_lane_f32(l0, l3, vhi, 1);
vst1q_f32(dest, l0);
}
#endif
#endif /* cglm_mat4_neon_h */