Implement the OpenCL kernel to compute the indirect convolution
- Implement indirect convolution kernel
- Add operator support
- Add test
Resolves COMPMID-5709
Change-Id: I9272304163471a5a40da7fdec204599f3c1d8e32
Signed-off-by: Gian Marco Iodice <gianmarco.iodice@arm.com>
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/8701
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Gunes Bayir <gunes.bayir@arm.com>
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Benchmark: Arm Jenkins <bsgcomp@arm.com>
diff --git a/src/gpu/cl/kernels/ClDirectConv2dKernel.cpp b/src/gpu/cl/kernels/ClDirectConv2dKernel.cpp
index 7816271..d9271e2 100644
--- a/src/gpu/cl/kernels/ClDirectConv2dKernel.cpp
+++ b/src/gpu/cl/kernels/ClDirectConv2dKernel.cpp
@@ -86,6 +86,7 @@
if(data_layout == DataLayout::NHWC)
{
+ ARM_COMPUTE_RETURN_ERROR_ON_MSG(desc.m0 <= 0 || desc.m0 > 8, "M0 can only be greater than 0 and less than or equal to 8");
ARM_COMPUTE_RETURN_ERROR_ON_MSG(desc.n0 != 1 && desc.n0 != 2 && desc.n0 != 3 && desc.n0 != 4 && desc.n0 != 8 && desc.n0 != 16,
"N0 can only be: 1, 2, 3, 4, 8, and 16");
ARM_COMPUTE_RETURN_ERROR_ON_MSG(desc.k0 != 1 && desc.k0 != 2 && desc.k0 != 3 && desc.k0 != 4 && desc.k0 != 8 && desc.k0 != 16,