diff options
author | Manuel Bottini <manuel.bottini@arm.com> | 2019-12-10 15:28:40 +0000 |
---|---|---|
committer | Georgios Pinitas <georgios.pinitas@arm.com> | 2020-01-09 11:38:00 +0000 |
commit | 8481d833783589e70191c6388c93685b4fc4a0b8 (patch) | |
tree | 98e171bf013ad86bfe021bcc5c5a03e8634094d1 /arm_compute/core/CL/kernels/CLDeconvolutionReshapeOutputKernel.h | |
parent | a35980546c00ae1647ce033b061530607a5ad1e4 (diff) | |
download | ComputeLibrary-8481d833783589e70191c6388c93685b4fc4a0b8.tar.gz |
COMPMID-2753: Add support for QASYMM8_SIGNED in CL kernels/functions
Change-Id: I7ed2d43f33458ba0571323f6fa9dc2e45fcd672a
Signed-off-by: Manuel Bottini <manuel.bottini@arm.com>
Reviewed-on: https://review.mlplatform.org/c/2516
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Michele Di Giorgio <michele.digiorgio@arm.com>
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>
Diffstat (limited to 'arm_compute/core/CL/kernels/CLDeconvolutionReshapeOutputKernel.h')
-rw-r--r-- | arm_compute/core/CL/kernels/CLDeconvolutionReshapeOutputKernel.h | 6 |
1 files changed, 3 insertions, 3 deletions
diff --git a/arm_compute/core/CL/kernels/CLDeconvolutionReshapeOutputKernel.h b/arm_compute/core/CL/kernels/CLDeconvolutionReshapeOutputKernel.h index cbc368fef9..6c90bd6c7f 100644 --- a/arm_compute/core/CL/kernels/CLDeconvolutionReshapeOutputKernel.h +++ b/arm_compute/core/CL/kernels/CLDeconvolutionReshapeOutputKernel.h @@ -1,5 +1,5 @@ /* - * Copyright (c) 2019 ARM Limited. + * Copyright (c) 2019-2020 ARM Limited. * * SPDX-License-Identifier: MIT * @@ -59,7 +59,7 @@ public: /** Initialise the kernel's source and destination. * - * @param[in] input Input tensor. Supported data types: F16/F32. + * @param[in] input Input tensor. Supported data types: QASYMM8/QASYMM8_SIGNED/S32/F16/F32. * @param[in] bias Bias tensor to be added directly during the reshape operation. Supported data types: same as @p input. Supported data layouts: same as @p input. * @param[out] output Output tensor with the following shape: [stride_x * (input_width - 1) + filter_width - 2 * padx, stride_y * (input_height - 1) + filter_height - 2 * pady, ofms, batch_size] * Supported data types: same as @p input. Supported data layouts: same as @p input. @@ -71,7 +71,7 @@ public: /** Static function to check if given info will lead to a valid configuration of @ref CLDeconvolutionReshapeOutputKernel. * - * @param[in] input GEMM output tensor info to be reshaped. Supported data types: F16/F32. + * @param[in] input GEMM output tensor info to be reshaped. Supported data types: QASYMM8/QASYMM8_SIGNED/S32/F16/F32. * @param[in] bias (Optional) Optional bias tensor info to be added directly during the reshape operation. Supported data types: same as @p input. Supported data layouts: same as @p input. * @param[in] output Reshaped output tensor info. Supported data types: same as @p input. Supported data layouts: same as @p input. * @param[in] input_info Original input tensor info. Supported data types: same as @p input. Supported data layouts: same as @p input. |