Fix divide-by-zero compilation error
* CONVERT_TO_TENSOR4D_STRUCT_NO_STEP is implemented and used
in some CL kernels in the way that causes divide-by-zero issue.
- Since the steps are all zeros, the issue might have been
ignored by the compiler.
Resolves: COMPMID-6795
Signed-off-by: Viet-Hoa Do <viet-hoa.do@arm.com>
Change-Id: I0fb38fc62d63671b8abefa39b3d9b3ca6f49c7fe
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/10967
Reviewed-by: Gunes Bayir <gunes.bayir@arm.com>
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Benchmark: Arm Jenkins <bsgcomp@arm.com>
diff --git a/src/core/CL/cl_kernels/common/col2im.cl b/src/core/CL/cl_kernels/common/col2im.cl
index 89054dc..4dc005f 100644
--- a/src/core/CL/cl_kernels/common/col2im.cl
+++ b/src/core/CL/cl_kernels/common/col2im.cl
@@ -1,5 +1,5 @@
/*
- * Copyright (c) 2017-2021 Arm Limited.
+ * Copyright (c) 2017-2021, 2024 Arm Limited.
*
* SPDX-License-Identifier: MIT
*
@@ -67,7 +67,7 @@
TENSOR4D_DECLARATION(dst))
{
Tensor3D src = CONVERT_TO_TENSOR3D_STRUCT(src);
- Tensor4D dst = CONVERT_TO_TENSOR4D_STRUCT_NO_STEP(dst, 0);
+ Tensor4D dst = CONVERT_TO_TENSOR4D_STRUCT_NO_STEP(dst);
const uint xd = get_global_id(1) % WIDTH_OUTPUT; // x coordinate of the destination tensor
const uint yd = get_global_id(1) / WIDTH_OUTPUT; // y coordinate of the destination tensor