diff options
| author | Georgios Pinitas <georgios.pinitas@arm.com> | 2019-09-30 12:39:40 +0100 |
|---|---|---|
| committer | Georgios Pinitas <georgios.pinitas@arm.com> | 2019-09-30 18:31:55 +0000 |
| commit | ae0fc8612dba6faebf58c3ebbfae8d6e639d432d (patch) | |
| tree | b31ee1085376b86fa33f2c6782b8a54f899116f9 /src/core/NEON/kernels/arm_gemm/transforms/list.hpp | |
| parent | 9637b2e4fc33b2264aa5586dd6b2ed1045db5075 (diff) | |
| download | ComputeLibrary-ae0fc8612dba6faebf58c3ebbfae8d6e639d432d.tar.gz | |
COMPMID-2452: Dot product optimizations on merge/transforms
-Adds optimized gemm transforms for AArch64.
-Optimized gemm merger to only support alpha==1 and (beta==0 || beta=1) cases
Change-Id: I55793b12a0381f4fd53f521d0e57416809904d96
Signed-off-by: Georgios Pinitas <georgios.pinitas@arm.com>
Reviewed-on: https://review.mlplatform.org/c/2003
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Michalis Spyrou <michalis.spyrou@arm.com>
Diffstat (limited to 'src/core/NEON/kernels/arm_gemm/transforms/list.hpp')
| -rw-r--r-- | src/core/NEON/kernels/arm_gemm/transforms/list.hpp | 1 |
1 files changed, 1 insertions, 0 deletions
diff --git a/src/core/NEON/kernels/arm_gemm/transforms/list.hpp b/src/core/NEON/kernels/arm_gemm/transforms/list.hpp index 9cd5983ce0..c0c2ca19d7 100644 --- a/src/core/NEON/kernels/arm_gemm/transforms/list.hpp +++ b/src/core/NEON/kernels/arm_gemm/transforms/list.hpp @@ -26,6 +26,7 @@ #include "a64_block16_interleave4_8bit.hpp" #include "a64_interleave_8way_16bit.hpp" #include "a64_interleave_8way_32bit.hpp" +#include "a64_interleave_8way_block4_8bit.hpp" #include "a64_interleave_8way_half_to_float.hpp" #include "a64_transpose_interleave_12way_16bit.hpp" #include "a64_transpose_interleave_12way_half_to_float.hpp" |