diff options
| author | Teresa Charlin <teresa.charlinreyes@arm.com> | 2021-04-28 10:58:49 +0100 |
|---|---|---|
| committer | Sheri Zhang <sheri.zhang@arm.com> | 2021-04-30 17:18:15 +0000 |
| commit | 62687420901c12be609426f3cf9dee300d25746a (patch) | |
| tree | d9eaf86763aaef2debb4b3ac8ddd6c7064468325 /src/core/CL/cl_kernels/depth_to_space.cl | |
| parent | 50929ef951880469b9d579323d2f9c9f5025327d (diff) | |
| download | ComputeLibrary-62687420901c12be609426f3cf9dee300d25746a.tar.gz | |
Update operator list documentation. Part 2.
All data type and data layout information for the operators are store in the function header files
Signed-off-by: Teresa Charlin <teresa.charlinreyes@arm.com>
Change-Id: I30b564f7eda6bbd99bf3ad36ddb6639ac118eb8b
Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/c/VisualCompute/ComputeLibrary/+/319829
Tested-by: bsgcomp <bsgcomp@arm.com>
Reviewed-by: Michele DiGiorgio <michele.digiorgio@arm.com>
Comments-Addressed: bsgcomp <bsgcomp@arm.com>
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/5531
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: SiCong Li <sicong.li@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Diffstat (limited to 'src/core/CL/cl_kernels/depth_to_space.cl')
| -rw-r--r-- | src/core/CL/cl_kernels/depth_to_space.cl | 10 |
1 files changed, 5 insertions, 5 deletions
diff --git a/src/core/CL/cl_kernels/depth_to_space.cl b/src/core/CL/cl_kernels/depth_to_space.cl index d3231a59a1..f301e64d66 100644 --- a/src/core/CL/cl_kernels/depth_to_space.cl +++ b/src/core/CL/cl_kernels/depth_to_space.cl @@ -1,5 +1,5 @@ /* - * Copyright (c) 2019-2020 Arm Limited. + * Copyright (c) 2019-2021 Arm Limited. * * SPDX-License-Identifier: MIT * @@ -24,10 +24,10 @@ #include "helpers.h" #if defined(DATA_TYPE) && defined(BLOCK_SHAPE) && defined(CHANNEL_SIZE) -/** Batch to space transformation. (NCHW) +/** Depth to space transformation. (NCHW) * * @note Datatype should be given as a preprocessor argument using -DDATA_TYPE=type. e.g. -DDATA_TYPE=float - * @note The input tensor batch size must be passed at compile time using -DCHANNEL_SIZE. e.g. -DCHANNEL_SIZE=2 + * @note The input tensor depth size must be passed at compile time using -DCHANNEL_SIZE. e.g. -DCHANNEL_SIZE=2 * @note The block shape must be passed at compile time using -DBLOCK_SHAPE. e.g. -DBLOCK_SHAPE=2 * * @param[in] input_ptr Pointer to the source tensor. Supported data types: All. @@ -66,10 +66,10 @@ __kernel void depth_to_space_nchw( *((__global DATA_TYPE *)tensor4D_offset(&out, out_x, out_y, z, batch_id)) = *((__global DATA_TYPE *)in.ptr); } -/** Batch to space transformation. (NHWC) +/** Depth to space transformation. (NHWC) * * @note Datatype should be given as a preprocessor argument using -DDATA_TYPE=type. e.g. -DDATA_TYPE=float - * @note The input tensor batch size must be passed at compile time using -DCHANNEL_SIZE. e.g. -DCHANNEL_SIZE=2 + * @note The input tensor depth size must be passed at compile time using -DCHANNEL_SIZE. e.g. -DCHANNEL_SIZE=2 * @note The block shape must be passed at compile time using -DBLOCK_SHAPE. e.g. -DBLOCK_SHAPE=2 * * @param[in] input_ptr Pointer to the source tensor. Supported data types: All. |