Merge pull request OpenMathLib#4421 from ChipKerchner/power10Copies_D…

…GEMM Replace two vector loads with one vector pair load and fix endianess of stores - DGEMM PowerPC versions.
martin-frbg · Jan 10, 2024 · 3599f2d · 3599f2d
2 parents 7a6a246 + 5c5c1a1
commit 3599f2d
Show file tree

Hide file tree

Showing 3 changed files with 664 additions and 0 deletions.
diff --git a/kernel/power/dgemm_tcopy_16_power8.S b/kernel/power/dgemm_tcopy_16_power8.S
@@ -107,6 +107,9 @@ USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
 
 #define o0	0
 
+#ifdef POWER10
+#include "dgemm_tcopy_macros_16_power10.S"
+#endif
 #include "dgemm_tcopy_macros_16_power8.S"
 
 #define STACKSIZE 144