mirror/opencv
1
0
Fork 0
mirror of https://github.com/opencv/opencv.git synced 2025-06-07 17:44:04 +08:00
Code Issues Actions Packages Projects Releases Wiki Activity

Merge pull request #24043 from zixianweei:use-vaddq_f32-on-arm64

Browse Source 
fix compilation error on Windows ARM, use vaddq_f32 instead of +=
This commit is contained in:
Alexander Smorkalov 2023-07-25 11:41:09 +03:00 committed by GitHub
commit e5e1a3bfde
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 7 additions and 7 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

14
modules/dnn/src/layers/cpu_kernels/conv_block.simd.hpp
View File

@ -452,13 +452,13 @@ void convBlockMR1_F32(int np, const float * a, const float * b, float *c, const
if (init_c)
{
c0 += vld1q_f32(c);
c1 += vld1q_f32(c + 4);
c2 += vld1q_f32(c + 8);
c3 += vld1q_f32(c + 12);
c4 += vld1q_f32(c + 16);
c5 += vld1q_f32(c + 20);
c6 += vld1q_f32(c + 24);
c0 = vaddq_f32(c0, vld1q_f32(c));
c1 = vaddq_f32(c1, vld1q_f32(c + 4));
c2 = vaddq_f32(c2, vld1q_f32(c + 8));
c3 = vaddq_f32(c3, vld1q_f32(c + 12));
c4 = vaddq_f32(c4, vld1q_f32(c + 16));
c5 = vaddq_f32(c5, vld1q_f32(c + 20));
c6 = vaddq_f32(c6, vld1q_f32(c + 24));
}
if (ifMinMaxAct)