Fix CPU depthwise convolution in case of large padding

* Avoid the assembly kernels to be used when the padding is greater
  than the kernel shape.

Resolves: COMPMID-6280
Signed-off-by: Viet-Hoa Do <viet-hoa.do@arm.com>
Change-Id: Ibe0820018c97f4481bf318397b797ec7b351a1d5
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/9802
Benchmark: Arm Jenkins <bsgcomp@arm.com>
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Jakub Sujak <jakub.sujak@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>

1 files changed, 10 insertions, 0 deletions

diff --git a/src/cpu/kernels/internal/CpuDepthwiseConv2dAssemblyWrapperKernel.cpp b/src/cpu/kernels/internal/CpuDepthwiseConv2dAssemblyWrapperKernel.cpp
index 5360abf5ac..8cda5c6afd 100644
--- a/src/cpu/kernels/internal/CpuDepthwiseConv2dAssemblyWrapperKernel.cpp
+++ b/src/cpu/kernels/internal/CpuDepthwiseConv2dAssemblyWrapperKernel.cpp
@@ -303,6 +303,16 @@ Status CpuDepthwiseConv2dAssemblyWrapperKernel::validate(const ITensorInfo *src,
         ARM_COMPUTE_RETURN_ERROR_ON_MISMATCHING_DIMENSIONS(dst->tensor_shape(), dst_shape);
         ARM_COMPUTE_RETURN_ERROR_ON_MISMATCHING_DATA_TYPES(src, dst);
     }
+
+    // Assembly kernels cannot work with padding greater than the kernel.
+    const auto &padding = info.pad_stride_info;
+    const auto &wei_shape = weights->tensor_shape();
+
+    ARM_COMPUTE_RETURN_ERROR_ON(
+        padding.pad_top() >= wei_shape[2] || padding.pad_bottom() >= wei_shape[2] ||
+        padding.pad_left() >= wei_shape[1] || padding.pad_right() >= wei_shape[1]
+    );
+
     return Status{};
 }