diff options
| author | Michalis Spyrou <michalis.spyrou@arm.com> | 2020-01-17 11:27:49 +0000 |
|---|---|---|
| committer | Michalis Spyrou <michalis.spyrou@arm.com> | 2020-01-21 16:12:25 +0000 |
| commit | 7317e393de848cb20dd326a45a9efb18a3ee7701 (patch) | |
| tree | c5af35d7986fba95a40b655b2f7408302c2a7c57 /arm_compute/runtime/CL/functions/CLArgMinMaxLayer.h | |
| parent | 74ef1db2263d73d893549cc79418f5be71753d1c (diff) | |
| download | ComputeLibrary-7317e393de848cb20dd326a45a9efb18a3ee7701.tar.gz | |
COMPMID-2941 Add QAsymm8 and S32 support for ArgMinMax to CL
Select operation does not work with any combination of datatypes.
Added a new OpenCL build option, DATA_TYPE_SELECT, in oder to
specify the select result.
Change-Id: I5c73c2a6b1d121288b7f6edba3e0cb1104636844
Signed-off-by: Michalis Spyrou <michalis.spyrou@arm.com>
Reviewed-on: https://review.mlplatform.org/c/2601
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 'arm_compute/runtime/CL/functions/CLArgMinMaxLayer.h')
| -rw-r--r-- | arm_compute/runtime/CL/functions/CLArgMinMaxLayer.h | 6 |
1 files changed, 3 insertions, 3 deletions
diff --git a/arm_compute/runtime/CL/functions/CLArgMinMaxLayer.h b/arm_compute/runtime/CL/functions/CLArgMinMaxLayer.h index 21cded0417..a26fcfda56 100644 --- a/arm_compute/runtime/CL/functions/CLArgMinMaxLayer.h +++ b/arm_compute/runtime/CL/functions/CLArgMinMaxLayer.h @@ -1,5 +1,5 @@ /* - * Copyright (c) 2018-2019 ARM Limited. + * Copyright (c) 2018-2020 ARM Limited. * * SPDX-License-Identifier: MIT * @@ -55,7 +55,7 @@ public: CLArgMinMaxLayer(std::shared_ptr<IMemoryManager> memory_manager = nullptr); /** Set the input and output tensors. * - * @param[in] input Input source tensor. Data types supported: F16/F32. + * @param[in] input Input source tensor. Data types supported: QASYMM8/F16/F32. * @param[in] axis Axis to find max/min index. * @param[out] output Output source tensor. Data types supported: U32/S32. * @param[in] op Reduction operation to perform. Operations supported: ARG_IDX_MAX, ARG_IDX_MIN @@ -63,7 +63,7 @@ public: void configure(const ICLTensor *input, int axis, ICLTensor *output, const ReductionOperation &op); /** Static function to check if given info will lead to a valid configuration of @ref CLArgMinMaxLayer * - * @param[in] input Input source tensor info. Data types supported: F16/F32. + * @param[in] input Input source tensor info. Data types supported: QASYMM8/F16/F32. * @param[in] axis Axis to find max/min index. * @param[in] output Output source tensor info. Data types supported: U32/S32. * @param[in] op Reduction operation to perform. Operations supported: ARG_IDX_MAX, ARG_IDX_MIN |