diff options
author | Giorgio Arena <giorgio.arena@arm.com> | 2018-08-23 12:00:02 +0100 |
---|---|---|
committer | Anthony Barbier <anthony.barbier@arm.com> | 2018-11-02 16:54:54 +0000 |
commit | 226e4b92b191491ffa57ede66eba1d5d6fcf3b76 (patch) | |
tree | 334705a1e743e3465400208d582cf0b25bf950fa /arm_compute/core/CL | |
parent | 35aea3776449557c438e264bae7af5b1fe0e5ff6 (diff) | |
download | ComputeLibrary-226e4b92b191491ffa57ede66eba1d5d6fcf3b76.tar.gz |
COMPMID-1470 Add auto-init of the output in NECol2im
The output of NECol2Im is already auto-initialized.
This patch is about calling ShapeCalculator instead of computing the shape inside the kernel, adding validate_and_configure_window, and standardize the way convolved dims are passed (now NEON uses Size2D, while CL passes a pair of uint values: using Size2D for both implementations)
Change-Id: I795696e1b6532f57847c3186c1b532c09f5a25da
Reviewed-on: https://eu-gerrit-1.euhpc.arm.com/145345
Tested-by: Jenkins <bsgcomp@arm.com>
Reviewed-by: Michele DiGiorgio <michele.digiorgio@arm.com>
Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com>
Diffstat (limited to 'arm_compute/core/CL')
-rw-r--r-- | arm_compute/core/CL/kernels/CLCol2ImKernel.h | 6 |
1 files changed, 3 insertions, 3 deletions
diff --git a/arm_compute/core/CL/kernels/CLCol2ImKernel.h b/arm_compute/core/CL/kernels/CLCol2ImKernel.h index 2a18ae08c8..948b412ccd 100644 --- a/arm_compute/core/CL/kernels/CLCol2ImKernel.h +++ b/arm_compute/core/CL/kernels/CLCol2ImKernel.h @@ -71,7 +71,7 @@ public: * @param[in] convolved_dims Output convolved dimensions. * @param[in] num_groups (Optional) Number of groups when performing a grouped convolution */ - void configure(const ICLTensor *input, ICLTensor *output, std::pair<unsigned int, unsigned int> convolved_dims, unsigned int num_groups = 1); + void configure(const ICLTensor *input, ICLTensor *output, const Size2D &convolved_dims, unsigned int num_groups = 1); /** Static function to check if given info will lead to a valid configuration of @ref CLCol2ImKernel * * @param[in] input The input tensor to convert. Data types supported: QASYMM8/F16/F32 @@ -82,7 +82,7 @@ public: * * @return a status */ - static Status validate(const ITensorInfo *input, const ITensorInfo *output, std::pair<unsigned int, unsigned int> convolved_dims, unsigned int num_groups = 1); + static Status validate(const ITensorInfo *input, const ITensorInfo *output, const Size2D &convolved_dims, unsigned int num_groups = 1); // Inherited methods overridden: void run(const Window &window, cl::CommandQueue &queue) override; @@ -90,7 +90,7 @@ public: public: const ICLTensor *_input; ICLTensor *_output; - std::pair<unsigned int, unsigned int> _convolved_dims; + Size2D _convolved_dims; }; } // namespace arm_compute #endif /*__ARM_COMPUTE_CLCOL2IMKERNEL_H__ */ |