Merge pull request #5237 from martin-frbg/revert5219

Fix and reinstate the Cooper Lake/Sapphire Rapids microkernel for non-transpose SBGEMV

kernel/x86_64/sbgemv_n.c

@@ -28,9 +28,9 @@ USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
 
 #include "common.h"
 
-//#if defined (COOPERLAKE) || defined (SAPPHIRERAPIDS)
-//#include "sbgemv_n_microk_cooperlake.c"
-//#endif
+#if defined (COOPERLAKE) || defined (SAPPHIRERAPIDS)
+#include "sbgemv_n_microk_cooperlake.c"
+#endif
 
 #define ALIGN64_ALLOC(alloc_size, TYPE, ptr_align, ptr)   \
     ptr = (TYPE *) malloc(sizeof(TYPE)*alloc_size + 63); \

kernel/x86_64/sbgemv_n_microk_cooperlake_template.c

@@ -231,7 +231,7 @@ static int sbgemv_kernel_32xN_lda_direct(BLASLONG m, BLASLONG n, float alpha, bf
         accum512_8  = _mm512_permutex2var_ps(accum512_0, idx_base_0, accum512_1);
         accum512_9  = _mm512_permutex2var_ps(accum512_0, idx_base_1, accum512_1);
 
-        if ((m-tag_m_32x) > 16) {
+        if ((m-tag_m_32x) >= 16) {
             STORE16_COMPLETE_RESULT(accum512_8, y+tag_m_32x+0)
             STORE16_MASK_COMPLETE_RESULT(accum512_9, y+tag_m_32x+16, store_tail_mask)
         } else {