diff options
| author | Viet-Hoa Do <viet-hoa.do@arm.com> | 2023-04-06 14:48:58 +0100 |
|---|---|---|
| committer | Viet-Hoa Do <viet-hoa.do@arm.com> | 2023-04-13 12:52:42 +0000 |
| commit | 4e84f244548a18e0935502cc443336fc1b8f1454 (patch) | |
| tree | da80b2e13b8213d7a18ccf8bc0f2a69290becb12 /tests/validation/NEON/ConvolutionLayer.cpp | |
| parent | a1b1e41bb261f5613f443fed7071936a360686ed (diff) | |
| download | ComputeLibrary-4e84f244548a18e0935502cc443336fc1b8f1454.tar.gz | |
Increase tolerance for SME kernels
Resolves: COMPMID-5904
Signed-off-by: Viet-Hoa Do <viet-hoa.do@arm.com>
Change-Id: I03bc51a7c5b05cca5db16a39f95e92d72240ab3a
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/9420
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: SiCong Li <sicong.li@arm.com>
Benchmark: Arm Jenkins <bsgcomp@arm.com>
Diffstat (limited to 'tests/validation/NEON/ConvolutionLayer.cpp')
| -rw-r--r-- | tests/validation/NEON/ConvolutionLayer.cpp | 7 |
1 files changed, 7 insertions, 0 deletions
diff --git a/tests/validation/NEON/ConvolutionLayer.cpp b/tests/validation/NEON/ConvolutionLayer.cpp index c2ed336ad5..06fe9f7803 100644 --- a/tests/validation/NEON/ConvolutionLayer.cpp +++ b/tests/validation/NEON/ConvolutionLayer.cpp @@ -81,7 +81,14 @@ const RelativeTolerance<half_float::half> rel_tolerance_f16(half_float::half(0.2 const AbsoluteTolerance<float> abs_tolerance_f16(0.2f); /**< Absolute tolerance for FP16 types */ constexpr float tolerance_num = 0.07f; /**< Tolerance number for the FP16 implementation */ #endif /* __ARM_FEATURE_FP16_VECTOR_ARITHMETIC */ + +#ifdef ARM_COMPUTE_ENABLE_SME +// TODO(COMPMID-6011): SME kernels and the reference model use different rounding mode. +// Temporarily increase the tolerance for quantized data. +constexpr AbsoluteTolerance<float> tolerance_qasymm8(1.0); /**< Tolerance value for comparing reference's output against implementation's output for quantized data types */ +#else // ARM_COMPUTE_ENABLE_SME constexpr AbsoluteTolerance<float> tolerance_qasymm8(0.0); /**< Tolerance value for comparing reference's output against implementation's output for quantized data types */ +#endif // ARM_COMPUTE_ENABLE_SME /** CNN data types */ const auto CNNDataTypes = framework::dataset::make("DataType", |