prepared driver/level3 functions for UNROLL values, that are not a power of two

2017-01-09 10:38:15 +01:00
parent c61a7cd293
commit a2672d5589
10 changed files with 44 additions and 48 deletions
--- a/driver/level3/syrk_kernel.c
+++ b/driver/level3/syrk_kernel.c
@@ -158,7 +158,7 @@ int CNAME(BLASLONG m, BLASLONG n, BLASLONG k, FLOAT alpha_r,

    int mm, nn;

-    mm = (loop & ~(GEMM_UNROLL_MN - 1));
+    mm = (loop/GEMM_UNROLL_MN) * GEMM_UNROLL_MN;
    nn = MIN(GEMM_UNROLL_MN, n - loop);

 #ifndef LOWER