Disable kernel size 3 in argminmax for axis 0
* Only kernel sizes supported are 2, 4, 8 and 16.
* Resolves COMPMID-6349
Change-Id: I30c85dcb3505d47fe56a2d2a08e9221ff426ee93
Signed-off-by: Pablo Marquez Tello <pablo.tello@arm.com>
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/9890
Reviewed-by: Viet-Hoa Do <viet-hoa.do@arm.com>
Reviewed-by: Jakub Sujak <jakub.sujak@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Benchmark: Arm Jenkins <bsgcomp@arm.com>
diff --git a/src/core/CL/kernels/CLArgMinMaxLayerKernel.cpp b/src/core/CL/kernels/CLArgMinMaxLayerKernel.cpp
index 8438739..3136d69 100644
--- a/src/core/CL/kernels/CLArgMinMaxLayerKernel.cpp
+++ b/src/core/CL/kernels/CLArgMinMaxLayerKernel.cpp
@@ -86,7 +86,9 @@
_op = op;
// Set build options
- const auto vector_size = adjust_vec_size(16U, input->info()->dimension(0));
+ const auto adjusted_vector_size = adjust_vec_size(16U, input->info()->dimension(0));
+ const auto vector_size = (adjusted_vector_size == 3U && axis == 0U) ? 2U : adjusted_vector_size; // the opencl kernel only supports sizes 2, 4, 8 and 16.
+
CLBuildOptions build_opts;
build_opts.add_option("-DDATA_TYPE=" + get_cl_type_from_data_type(input->info()->data_type()));
build_opts.add_option("-DVEC_SIZE_LEFTOVER=" + support::cpp11::to_string(input->info()->dimension(0) % vector_size));