Fix CLDepthwiseConvolutionLayer 3x3 QASYMM8
Fix errors when computing tensors with one element only
- Replace Tensor3D with raw pointers so to get rid of offset to first element for NCHW layout
- Add stronger out of bound constraints for NHWC layout
- Set the border size to the input's padding for NHWC
- Fill the strides == 0 with the largest stride, so to avoid accessing empty strides and multiplying by 0
Resolve COMPMID-4088
Change-Id: I751a4e6d7094b3c42306ff7f53af848fd35f19ac
Signed-off-by: Giorgio Arena <giorgio.arena@arm.com>
Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/5024
Tested-by: Arm Jenkins <bsgcomp@arm.com>
Reviewed-by: Manuel Bottini <manuel.bottini@arm.com>
Reviewed-by: Michele Di Giorgio <michele.digiorgio@arm.com>
Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
diff --git a/src/core/CL/kernels/CLDepthwiseConvolutionLayer3x3NHWCKernel.cpp b/src/core/CL/kernels/CLDepthwiseConvolutionLayer3x3NHWCKernel.cpp
index f553fd1..43c3ff3 100644
--- a/src/core/CL/kernels/CLDepthwiseConvolutionLayer3x3NHWCKernel.cpp
+++ b/src/core/CL/kernels/CLDepthwiseConvolutionLayer3x3NHWCKernel.cpp
@@ -1,5 +1,5 @@
/*
- * Copyright (c) 2018-2020 Arm Limited.
+ * Copyright (c) 2018-2021 Arm Limited.
*
* SPDX-License-Identifier: MIT
*
@@ -233,7 +233,7 @@
if(_is_quantized)
{
- _border_size = BorderSize(is_stride_1 ? 0 : conv_info.pad_left(), 0, std::max(std::max(conv_info.pad_right(), conv_info.pad_bottom()), conv_info.pad_top()), 0);
+ _border_size = BorderSize(input->info()->padding());
// If QASYMM8 and the 8 bit dot product is available, force _num_planes_processed_per_iteration to 1
if(is_dot8_supported)
diff --git a/src/core/CL/kernels/CLGEMMLowpMatrixMultiplyNativeKernel.cpp b/src/core/CL/kernels/CLGEMMLowpMatrixMultiplyNativeKernel.cpp
index 1f89865..5633ee5 100644
--- a/src/core/CL/kernels/CLGEMMLowpMatrixMultiplyNativeKernel.cpp
+++ b/src/core/CL/kernels/CLGEMMLowpMatrixMultiplyNativeKernel.cpp
@@ -1,5 +1,5 @@
/*
- * Copyright (c) 2019-2020 Arm Limited.
+ * Copyright (c) 2019-2021 Arm Limited.
*
* SPDX-License-Identifier: MIT
*
@@ -284,8 +284,8 @@
if(_input1->info()->num_dimensions() < 3)
{
- // The stride_z for matrix B must be zero if we do not slice
- ARM_COMPUTE_ERROR_ON(_input1->info()->strides_in_bytes()[3] != 0);
+ // The stride_w for matrix B must be the same as stride_z if we do not slice
+ ARM_COMPUTE_ERROR_ON(_input1->info()->strides_in_bytes()[3] != _input1->info()->strides_in_bytes()[2]);
}
Window slice = window.first_slice_window_3D();
diff --git a/src/core/CL/kernels/CLGEMMLowpMatrixMultiplyReshapedKernel.cpp b/src/core/CL/kernels/CLGEMMLowpMatrixMultiplyReshapedKernel.cpp
index ded4b29..3043e01 100644
--- a/src/core/CL/kernels/CLGEMMLowpMatrixMultiplyReshapedKernel.cpp
+++ b/src/core/CL/kernels/CLGEMMLowpMatrixMultiplyReshapedKernel.cpp
@@ -1,5 +1,5 @@
/*
- * Copyright (c) 2019-2020 Arm Limited.
+ * Copyright (c) 2019-2021 Arm Limited.
*
* SPDX-License-Identifier: MIT
*
@@ -254,8 +254,8 @@
if(_input1->info()->num_dimensions() < 3)
{
- // The stride_z for matrix B must be zero if we do not slice
- ARM_COMPUTE_ERROR_ON(_input1->info()->strides_in_bytes()[3] != 0);
+ // The stride_w for matrix B must be the same as stride_z if we do not slice
+ ARM_COMPUTE_ERROR_ON(_input1->info()->strides_in_bytes()[3] != _input1->info()->strides_in_bytes()[2]);
}
Window slice = window.first_slice_window_3D();
diff --git a/src/core/CL/kernels/CLGEMMLowpMatrixMultiplyReshapedOnlyRHSKernel.cpp b/src/core/CL/kernels/CLGEMMLowpMatrixMultiplyReshapedOnlyRHSKernel.cpp
index 77cea24..0122e3b 100644
--- a/src/core/CL/kernels/CLGEMMLowpMatrixMultiplyReshapedOnlyRHSKernel.cpp
+++ b/src/core/CL/kernels/CLGEMMLowpMatrixMultiplyReshapedOnlyRHSKernel.cpp
@@ -1,5 +1,5 @@
/*
- * Copyright (c) 2019-2020 Arm Limited.
+ * Copyright (c) 2019-2021 Arm Limited.
*
* SPDX-License-Identifier: MIT
*
@@ -488,8 +488,8 @@
if(_input1->info()->num_dimensions() < 3)
{
- // The stride_z for matrix B must be zero if we do not slice
- ARM_COMPUTE_ERROR_ON(_input1->info()->strides_in_bytes()[3] != 0);
+ // The stride_w for matrix B must be the same as stride_z if we do not slice
+ ARM_COMPUTE_ERROR_ON(_input1->info()->strides_in_bytes()[3] != _input1->info()->strides_in_bytes()[2]);
}
Window slice = window.first_slice_window_3D();
diff --git a/src/core/CL/kernels/CLGEMMMatrixMultiplyKernel.cpp b/src/core/CL/kernels/CLGEMMMatrixMultiplyKernel.cpp
index 2419104..a653e29 100644
--- a/src/core/CL/kernels/CLGEMMMatrixMultiplyKernel.cpp
+++ b/src/core/CL/kernels/CLGEMMMatrixMultiplyKernel.cpp
@@ -1,5 +1,5 @@
/*
- * Copyright (c) 2017-2020 Arm Limited.
+ * Copyright (c) 2017-2021 Arm Limited.
*
* SPDX-License-Identifier: MIT
*
@@ -484,8 +484,8 @@
if(_input1->info()->num_dimensions() < 3)
{
- // The stride_z for matrix B must be zero if we do not slice
- ARM_COMPUTE_ERROR_ON(_input1->info()->strides_in_bytes()[3] != 0);
+ // The stride_w for matrix B must be the same as stride_z if we do not slice
+ ARM_COMPUTE_ERROR_ON(_input1->info()->strides_in_bytes()[3] != _input1->info()->strides_in_bytes()[2]);
}
Window slice = window.first_slice_window_3D();
diff --git a/src/core/CL/kernels/CLGEMMMatrixMultiplyNativeKernel.cpp b/src/core/CL/kernels/CLGEMMMatrixMultiplyNativeKernel.cpp
index 387f1a4..fefcd2f 100644
--- a/src/core/CL/kernels/CLGEMMMatrixMultiplyNativeKernel.cpp
+++ b/src/core/CL/kernels/CLGEMMMatrixMultiplyNativeKernel.cpp
@@ -1,5 +1,5 @@
/*
- * Copyright (c) 2019-2020 Arm Limited.
+ * Copyright (c) 2019-2021 Arm Limited.
*
* SPDX-License-Identifier: MIT
*
@@ -348,8 +348,8 @@
if(_input1->info()->num_dimensions() < 3)
{
- // The stride_z for matrix B must be zero if we do not slice
- ARM_COMPUTE_ERROR_ON(_input1->info()->strides_in_bytes()[3] != 0);
+ // The stride_w for matrix B must be the same as stride_z if we do not slice
+ ARM_COMPUTE_ERROR_ON(_input1->info()->strides_in_bytes()[3] != _input1->info()->strides_in_bytes()[2]);
}
Window slice = window.first_slice_window_3D();
diff --git a/src/core/CL/kernels/CLGEMMMatrixMultiplyReshapedKernel.cpp b/src/core/CL/kernels/CLGEMMMatrixMultiplyReshapedKernel.cpp
index 23e18ba..8a40355 100644
--- a/src/core/CL/kernels/CLGEMMMatrixMultiplyReshapedKernel.cpp
+++ b/src/core/CL/kernels/CLGEMMMatrixMultiplyReshapedKernel.cpp
@@ -1,5 +1,5 @@
/*
- * Copyright (c) 2018-2020 Arm Limited.
+ * Copyright (c) 2018-2021 Arm Limited.
*
* SPDX-License-Identifier: MIT
*
@@ -359,8 +359,8 @@
if(_input1->info()->num_dimensions() < 3)
{
- // The stride_z for matrix B must be zero if we do not slice
- ARM_COMPUTE_ERROR_ON(_input1->info()->strides_in_bytes()[3] != 0);
+ // The stride_w for matrix B must be the same as stride_z if we do not slice
+ ARM_COMPUTE_ERROR_ON(_input1->info()->strides_in_bytes()[3] != _input1->info()->strides_in_bytes()[2]);
}
Window slice = window.first_slice_window_3D();
diff --git a/src/core/CL/kernels/CLGEMMMatrixMultiplyReshapedOnlyRHSKernel.cpp b/src/core/CL/kernels/CLGEMMMatrixMultiplyReshapedOnlyRHSKernel.cpp
index 1f296f8..de986de 100644
--- a/src/core/CL/kernels/CLGEMMMatrixMultiplyReshapedOnlyRHSKernel.cpp
+++ b/src/core/CL/kernels/CLGEMMMatrixMultiplyReshapedOnlyRHSKernel.cpp
@@ -1,5 +1,5 @@
/*
- * Copyright (c) 2019-2020 Arm Limited.
+ * Copyright (c) 2019-2021 Arm Limited.
*
* SPDX-License-Identifier: MIT
*
@@ -352,8 +352,8 @@
if(_input1->info()->num_dimensions() < 3)
{
- // The stride_z for matrix B must be zero if we do not slice
- ARM_COMPUTE_ERROR_ON(_input1->info()->strides_in_bytes()[3] != 0);
+ // The stride_w for matrix B must be the same as stride_z if we do not slice
+ ARM_COMPUTE_ERROR_ON(_input1->info()->strides_in_bytes()[3] != _input1->info()->strides_in_bytes()[2]);
}
const size_t lhs_idx_batch_size = _reinterpret_input_as_3d && !_has_pad_y ? 3u : 2u;