diff options
| author | Georgios Pinitas <georgios.pinitas@arm.com> | 2021-04-08 12:25:36 +0100 |
|---|---|---|
| committer | Michele Di Giorgio <michele.digiorgio@arm.com> | 2021-04-08 17:28:15 +0000 |
| commit | 8a1ac6162e2ed07384f5a51162e5c5e347a88c67 (patch) | |
| tree | 99424da10ab04603817b195d7c13f03ce6fb5540 | |
| parent | 4a5f73d36962f254ad630beb70deb1907ba381b9 (diff) | |
| download | ComputeLibrary-8a1ac6162e2ed07384f5a51162e5c5e347a88c67.tar.gz | |
Fix incorrect return statement in gemm_uint8 heuristic selection
Semantic fix that otherwise led to compilation errors when building for
SVE and when MMLA instruction was enabled for int8.
Signed-off-by: Georgios Pinitas <georgios.pinitas@arm.com>
Change-Id: I4852d806789d52c4ed1d3b9132b2f20c2f9b41fa
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/5384
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Michele Di Giorgio <michele.digiorgio@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
| -rw-r--r-- | src/core/NEON/kernels/arm_gemm/gemm_uint8.cpp | 2 |
1 files changed, 1 insertions, 1 deletions
diff --git a/src/core/NEON/kernels/arm_gemm/gemm_uint8.cpp b/src/core/NEON/kernels/arm_gemm/gemm_uint8.cpp index fb41a9fc09..4de3d2b18a 100644 --- a/src/core/NEON/kernels/arm_gemm/gemm_uint8.cpp +++ b/src/core/NEON/kernels/arm_gemm/gemm_uint8.cpp @@ -51,7 +51,7 @@ static const GemmImplementation<uint8_t, uint32_t> gemm_u8_methods[] = { { GemmMethod::GEMM_INTERLEAVED, "sve_interleaved_u8u32_mmla_8x3VL", - [](const GemmArgs &args) { args._ci->has_sve() && return (args._Ksize>8); }, + [](const GemmArgs &args) { return args._ci->has_sve() && (args._Ksize>8); }, [](const GemmArgs &args) { return args._ci->get_cpu_model() != CPUModel::KLEIN; }, [](const GemmArgs &args) { return new GemmInterleaved<cls_sve_interleaved_u8u32_mmla_8x3VL, uint8_t, uint32_t>(args); } }, |