Remove OpenCL padding: CLPixelWiseMultiplicationKernel
- Change kernel's vec_size to 16 / sizeof(output)
- Change ICLKernel.cpp to handle broadcast without padding
Resolve COMPMID-3913
Signed-off-by: Giorgio Arena <giorgio.arena@arm.com>
Change-Id: I03e884b250ef5784dc109bff8cf2c96b345d119f
Signed-off-by: Giorgio Arena <giorgio.arena@arm.com>
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/5450
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Michele Di Giorgio <michele.digiorgio@arm.com>
Reviewed-by: Gian Marco Iodice <gianmarco.iodice@arm.com>
diff --git a/src/core/gpu/cl/kernels/ClPixelWiseMultiplicationKernel.h b/src/core/gpu/cl/kernels/ClPixelWiseMultiplicationKernel.h
index 5889b84..5b82726 100644
--- a/src/core/gpu/cl/kernels/ClPixelWiseMultiplicationKernel.h
+++ b/src/core/gpu/cl/kernels/ClPixelWiseMultiplicationKernel.h
@@ -41,7 +41,7 @@
/** Default constructor */
ClPixelWiseMultiplicationKernel() = default;
ARM_COMPUTE_DISALLOW_COPY_ALLOW_MOVE(ClPixelWiseMultiplicationKernel);
- /** Initialise the kernel's src, dst and border mode.
+ /** Initialise the kernel's src and dst.
*
* Valid configurations (Input1,Input2) -> Output :
*
@@ -101,10 +101,6 @@
// Inherited methods overridden:
void run_op(ITensorPack &tensors, const Window &window, cl::CommandQueue &queue) override;
- BorderSize border_size() const override;
-
-public:
- BorderSize _border_size{};
};
/** Interface for the complex pixelwise multiplication kernel. */
@@ -114,7 +110,7 @@
/** Default constructor */
ClComplexPixelWiseMultiplicationKernel() = default;
ARM_COMPUTE_DISALLOW_COPY_ALLOW_MOVE(ClComplexPixelWiseMultiplicationKernel);
- /** Initialise the kernel's src, dst and border mode.
+ /** Initialise the kernel's src and dst.
*
* @param[in] compile_context The compile context to be used.
* @param[in] src1 An src tensor info. Data types supported: F32. Number of channels supported: 2.
@@ -136,10 +132,6 @@
// Inherited methods overridden:
void run_op(ITensorPack &tensors, const Window &window, cl::CommandQueue &queue) override;
- BorderSize border_size() const override;
-
-public:
- BorderSize _border_size{};
};
} // namespace kernels
} // namespace opencl