diff options
| author | Michalis Spyrou <michalis.spyrou@arm.com> | 2020-01-22 10:27:06 +0000 |
|---|---|---|
| committer | Michele Di Giorgio <michele.digiorgio@arm.com> | 2020-01-23 09:27:17 +0000 |
| commit | 19bd412fd044197726dbd8c756dbd74a9e33fd2b (patch) | |
| tree | 611072c0419d394ef191705ac82521c8a28a1873 /tests/validation/CL/ReduceMean.cpp | |
| parent | b80c435d65eea7c7befdafaef883da9f66574036 (diff) | |
| download | ComputeLibrary-19bd412fd044197726dbd8c756dbd74a9e33fd2b.tar.gz | |
COMPMID-3022 Fix NEON QASYMM8 Reduction Operation
Use proper offsets in our tests and subtract the
accumulated offsets when we do a SUM operation.
Also change the reference MEAN_SUM impementation to
use floats. As a result the tolerance is increased
to 2.
Change-Id: Icac8b84680bd880fd30dc1dd82d19cce43921eb5
Signed-off-by: Michalis Spyrou <michalis.spyrou@arm.com>
Reviewed-on: https://review.mlplatform.org/c/2616
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Michele Di Giorgio <michele.digiorgio@arm.com>
Diffstat (limited to 'tests/validation/CL/ReduceMean.cpp')
| -rw-r--r-- | tests/validation/CL/ReduceMean.cpp | 4 |
1 files changed, 2 insertions, 2 deletions
diff --git a/tests/validation/CL/ReduceMean.cpp b/tests/validation/CL/ReduceMean.cpp index 1b7400bf53..036ea181ac 100644 --- a/tests/validation/CL/ReduceMean.cpp +++ b/tests/validation/CL/ReduceMean.cpp @@ -1,5 +1,5 @@ /* - * Copyright (c) 2018-2019 ARM Limited. + * Copyright (c) 2018-2020 ARM Limited. * * SPDX-License-Identifier: MIT * @@ -44,7 +44,7 @@ namespace { constexpr AbsoluteTolerance<float> tolerance_f32(0.001f); /**< Tolerance value for comparing reference's output against implementation's output for 32-bit floating-point type */ constexpr AbsoluteTolerance<float> tolerance_f16(0.03f); /**< Tolerance value for comparing reference's output against implementation's output for 16-bit floating-point type */ -constexpr AbsoluteTolerance<uint8_t> tolerance_qasymm8(1); /**< Tolerance value for comparing reference's output against implementation's output for 8-bit asymmetric quantized type */ +constexpr AbsoluteTolerance<uint8_t> tolerance_qasymm8(2); /**< Tolerance value for comparing reference's output against implementation's output for 8-bit asymmetric quantized type */ const auto axis_keep = combine(framework::dataset::make("Axis", { Coordinates(0), Coordinates(1, 0), Coordinates(1, 2), Coordinates(0, 2), Coordinates(1, 3), Coordinates(0, 1, 2, 3) }), framework::dataset::make("KeepDims", { true })); |