diff options
| author | Pablo Marquez Tello <pablo.tello@arm.com> | 2023-03-20 16:29:21 +0000 |
|---|---|---|
| committer | Pablo Marquez Tello <pablo.tello@arm.com> | 2023-03-23 12:01:05 +0000 |
| commit | 20cfa45faefbf56f62c8b1aa95dfd0b4f52e5641 (patch) | |
| tree | 7c8b7d17ce04714a8214b89adac5e25cafd2c730 /src/CMakeLists.txt | |
| parent | 251b5145309e941a32c6c7691062544f2fd243fb (diff) | |
| download | ComputeLibrary-20cfa45faefbf56f62c8b1aa95dfd0b4f52e5641.tar.gz | |
Round to nearest with ties to away from zero in Relu
* This patch adds support for rounding modes in vmlaq_qasymm8_signed
which is used to compute Relu for quantized types
* Partially resolves MLCE-1018
Change-Id: I2a267b84745430e1ffe92b8bc79828a39332db18
Signed-off-by: Pablo Marquez Tello <pablo.tello@arm.com>
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/9354
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Gunes Bayir <gunes.bayir@arm.com>
Reviewed-by: Viet-Hoa Do <viet-hoa.do@arm.com>
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Benchmark: Arm Jenkins <bsgcomp@arm.com>
Diffstat (limited to 'src/CMakeLists.txt')
| -rw-r--r-- | src/CMakeLists.txt | 3 |
1 files changed, 3 insertions, 0 deletions
diff --git a/src/CMakeLists.txt b/src/CMakeLists.txt index b056421352..ca07ebf029 100644 --- a/src/CMakeLists.txt +++ b/src/CMakeLists.txt @@ -221,6 +221,9 @@ target_sources( core/NEON/kernels/arm_gemm/kernels/sme2_interleaved_nomerge_bf16fp32_mopa_1VLx4VL/generic.cpp core/NEON/kernels/arm_gemm/kernels/sme2_interleaved_nomerge_bf16fp32_mopa_2VLx2VL/generic.cpp core/NEON/kernels/arm_gemm/kernels/sme2_interleaved_nomerge_bf16fp32_mopa_4VLx1VL/generic.cpp + core/NEON/kernels/arm_gemm/kernels/sme2_interleaved_nomerge_fp16fp32fp16_mopa_1VLx4VL/generic.cpp + core/NEON/kernels/arm_gemm/kernels/sme2_interleaved_nomerge_fp16fp32fp16_mopa_2VLx2VL/generic.cpp + core/NEON/kernels/arm_gemm/kernels/sme2_interleaved_nomerge_fp16fp32fp16_mopa_4VLx1VL/generic.cpp core/NEON/kernels/arm_gemm/kernels/sme2_interleaved_nomerge_fp32_mopa_1VLx4VL/generic.cpp core/NEON/kernels/arm_gemm/kernels/sme2_interleaved_nomerge_fp32_mopa_2VLx2VL/generic.cpp core/NEON/kernels/arm_gemm/kernels/sme2_interleaved_nomerge_fp32_mopa_4VLx1VL/generic.cpp |