diff options
| author | Mohammed Suhail Munshi <MohammedSuhail.Munshi@arm.com> | 2024-03-25 15:55:42 +0000 |
|---|---|---|
| committer | Suhail M <MohammedSuhail.Munshi@arm.com> | 2024-04-22 14:44:09 +0000 |
| commit | 7377107378d6c26439320fce78a551e85b5ad36a (patch) | |
| tree | 3aa9c74c59993f9d51924fc123eefa17e3376a79 /src/gpu/cl/kernels/ClScatterKernel.h | |
| parent | 5057ce9e1866ffa0388543d81af32083b5b1c684 (diff) | |
| download | ComputeLibrary-7377107378d6c26439320fce78a551e85b5ad36a.tar.gz | |
Scatter GPU Kernel Implementation for 1D tensors.
Resolves: [COMPMID-6891, COMPMID-6892]
Change-Id: I5b094fff1bff4c4c59cc44f7d6beab0e40133d8e
Signed-off-by: Mohammed Suhail Munshi <MohammedSuhail.Munshi@arm.com>
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/11394
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Gunes Bayir <gunes.bayir@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Benchmark: Arm Jenkins <bsgcomp@arm.com>
Diffstat (limited to 'src/gpu/cl/kernels/ClScatterKernel.h')
| -rw-r--r-- | src/gpu/cl/kernels/ClScatterKernel.h | 13 |
1 files changed, 5 insertions, 8 deletions
diff --git a/src/gpu/cl/kernels/ClScatterKernel.h b/src/gpu/cl/kernels/ClScatterKernel.h index dda614ff3e..d2a41adde9 100644 --- a/src/gpu/cl/kernels/ClScatterKernel.h +++ b/src/gpu/cl/kernels/ClScatterKernel.h @@ -44,15 +44,15 @@ public: ARM_COMPUTE_DISALLOW_COPY_ALLOW_MOVE(ClScatterKernel); /** Initialise the kernel's input and output. * + * @note Negative indices are treated as out of bounds. + * * @param[in] compile_context The compile context to be used. - * @param[in] src Input tensor info for the source matrix. * @param[in] updates Input tensor info for the Update matrix. Data type supported: same as @p src - * @param[in] indices Input tensor info for the Indices matrix. Data type supported: U32. + * @param[in] indices Input tensor info for the Indices matrix. Data type supported: S32. * @param[out] dst Output tensor info. Data type supported: same as @p src * @param[in] info Attributes for Scatter Kernel */ void configure(const ClCompileContext &compile_context, - const ITensorInfo *src, const ITensorInfo *updates, const ITensorInfo *indices, ITensorInfo *dst, @@ -63,11 +63,8 @@ public: * * @return a status */ - static Status validate(const ITensorInfo *src, - const ITensorInfo *updates, - const ITensorInfo *indices, - const ITensorInfo *dst, - const ScatterInfo &info); + static Status + validate(const ITensorInfo *updates, const ITensorInfo *indices, const ITensorInfo *dst, const ScatterInfo &info); // Inherited methods overridden: void run_op(ITensorPack &tensors, const Window &window, cl::CommandQueue &queue) override; |