YourWishes/cglm
1
0
Fork 0
mirror of https://github.com/recp/cglm.git synced 2026-02-17 03:39:05 +00:00
Code Issues Packages Projects Releases Wiki Activity

arrm, neon: impove hadd performance

Browse Source
This commit is contained in:
Recep Aslantas
2021-05-07 01:46:24 +03:00
parent d0ab3aaa2e
commit 7f9585ca72
1 changed files with 7 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

9
include/cglm/simd/arm.h
View File

@@ -47,8 +47,13 @@ glmm_abs(float32x4_t v) {
static inline static inline
float32x4_t float32x4_t
glmm_vhadd(float32x4_t v) { glmm_vhadd(float32x4_t v) {
v = vaddq_f32(v, vrev64q_f32(v)); return vaddq_f32(vaddq_f32(glmm_splat_x(v), glmm_splat_y(v)),
return vaddq_f32(v, vcombine_f32(vget_high_f32(v), vget_low_f32(v))); vaddq_f32(glmm_splat_z(v), glmm_splat_w(v)));
/*
this seems slower:
v = vaddq_f32(v, vrev64q_f32(v));
return vaddq_f32(v, vcombine_f32(vget_high_f32(v), vget_low_f32(v)));
*/
} }
static inline static inline