Optimize CLDeconvolution-PART I: bug fixing CLGEMMLowpMatrixMultiplyCore
Change-Id: Ibf80aafc20f5a9feeb76c7c870afd1b83f368f33
Signed-off-by: giuros01 <giuseppe.rossini@arm.com>
Reviewed-on: https://review.mlplatform.org/c/866
Reviewed-by: Michele Di Giorgio <michele.digiorgio@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Tested-by: Arm Jenkins <bsgcomp@arm.com>
diff --git a/src/runtime/CL/functions/CLGEMMLowpMatrixMultiplyCore.cpp b/src/runtime/CL/functions/CLGEMMLowpMatrixMultiplyCore.cpp
index 2a01db7..b254522 100644
--- a/src/runtime/CL/functions/CLGEMMLowpMatrixMultiplyCore.cpp
+++ b/src/runtime/CL/functions/CLGEMMLowpMatrixMultiplyCore.cpp
@@ -332,12 +332,15 @@
// Validate matrix multiply
ARM_COMPUTE_RETURN_ON_ERROR(CLGEMMLowpMatrixMultiplyKernel::validate(matrix_a_info, matrix_b_info, output, false, reshape_info));
}
- // Validate offset contribution kernel
- ARM_COMPUTE_RETURN_ON_ERROR(CLGEMMLowpOffsetContributionKernel::validate(output,
- a_offset == 0 ? nullptr : &info_vector_sum_col,
- b_offset == 0 ? nullptr : &info_vector_sum_row,
- c,
- a_offset, b_offset));
+ if(output->total_size() != 0)
+ {
+ // Validate offset contribution kernel
+ ARM_COMPUTE_RETURN_ON_ERROR(CLGEMMLowpOffsetContributionKernel::validate(output,
+ a_offset == 0 ? nullptr : &info_vector_sum_col,
+ b_offset == 0 ? nullptr : &info_vector_sum_row,
+ c,
+ a_offset, b_offset));
+ }
}
return Status{};