| commit | 4ee8b1599dbaf7634d25607fa5ac96ba3dc6b0f2 | [log] [tgz] |
|---|---|---|
| author | Georgios Pinitas <georgios.pinitas@arm.com> | Fri Jul 16 16:16:43 2021 +0100 |
| committer | Georgios Pinitas <georgios.pinitas@arm.com> | Thu Jul 22 02:25:50 2021 +0000 |
| tree | 2f8362d33cdad4212f4b96995681c68184c759e1 | |
| parent | 59fd7a722e5bc7e85309d6200bc37a772721a719 [diff] [blame] |
Update GEMM assembly kernels - Introduce Fp32 kernels with internal calculations in Bfloat16 when fast_mode is enabled - Improve kernel selection heuristics Signed-off-by: Georgios Pinitas <georgios.pinitas@arm.com> Change-Id: I68a9e7e862b6fd2721b46e0d7cc791091c4ab279 Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/5965 Tested-by: Arm Jenkins <bsgcomp@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
diff --git a/src/core/NEON/kernels/arm_gemm/indirect-interleaves/list.hpp b/src/core/NEON/kernels/arm_gemm/indirect-interleaves/list.hpp index 52b49c0..b13d32c 100644 --- a/src/core/NEON/kernels/arm_gemm/indirect-interleaves/list.hpp +++ b/src/core/NEON/kernels/arm_gemm/indirect-interleaves/list.hpp
@@ -40,6 +40,7 @@ #include "a64_interleave8_block2_bf16_bf16.hpp" #include "a64_interleave8_block2_fp32_fp32.hpp" #include "a64_interleave8_block4_bf16_bf16.hpp" +#include "a64_interleave8_block4_fp32_bf16.hpp" #include "a64_interleave8_block4_s8_s8.hpp" #include "a64_interleave8_block4_s8_s8_summing.hpp" #include "a64_interleave8_block4_u8_u8_summing.hpp"