floraachy
/
OpenBLAS
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Merge pull request #1730 from fenrus75/fix-sdot 

Fix typo in sdot function
This commit is contained in:
Martin Kroeker 2018-08-12 18:17:01 +02:00 committed by GitHub
parent 1ee6d087c3 36add7570a
commit 8c13aa495a
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
1 changed files with 1 additions and 1 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

2
kernel/x86_64/sdot_microk_skylakex-2.c
View File

@ -67,7 +67,7 @@ static void sdot_kernel_16( BLASLONG n, FLOAT *x, FLOAT *y, FLOAT *dot)
accum_0 = _mm512_extractf32x8_ps(accum_05, 0) + _mm512_extractf32x8_ps(accum_05, 1);
accum_1 = _mm512_extractf32x8_ps(accum_15, 0) + _mm512_extractf32x8_ps(accum_15, 1);
accum_2 = _mm512_extractf32x8_ps(accum_25, 0) + _mm512_extractf32x8_ps(accum_25, 1);
accum_3 = _mm512_extractf32x8_ps(accum_35, 0) + _mm512_extractf32x8_ps(accum_35, 1))
accum_3 = _mm512_extractf32x8_ps(accum_35, 0) + _mm512_extractf32x8_ps(accum_35, 1);
#endif
for (; i < n; i += 32) {