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>

1 files changed, 2 insertions, 2 deletions

diff --git a/src/core/CL/ICLKernel.cpp b/src/core/CL/ICLKernel.cpp
index 1c6963f3f1..9ba17d0e03 100644
--- a/src/core/CL/ICLKernel.cpp
+++ b/src/core/CL/ICLKernel.cpp
@@ -105,8 +105,8 @@ void ICLKernel::add_tensor_argument(unsigned &idx, const ICLTensor *tensor, cons
 
     for(unsigned int d = 0; d < dimension_size; ++d)
     {
-        _kernel.setArg<cl_uint>(idx++, strides[d]);
-        _kernel.setArg<cl_uint>(idx++, strides[d] * window[d].step());
+        _kernel.setArg<cl_uint>(idx++, window.is_broadcasted(d) ? 0 : strides[d]);
+        _kernel.setArg<cl_uint>(idx++, window.is_broadcasted(d) ? 0 : (strides[d] * window[d].step()));
     }
 
     _kernel.setArg<cl_uint>(idx++, offset_first_element);