aboutsummaryrefslogtreecommitdiff
path: root/src/runtime/cpu/operators/CpuDepthwiseConv2dAssemblyDispatch.h
diff options
context:
space:
mode:
authorManuel Bottini <manuel.bottini@arm.com>2021-05-24 16:01:32 +0100
committerGeorgios Pinitas <georgios.pinitas@arm.com>2021-06-01 12:52:48 +0000
commitb4bb6a03f717a320b935809fde795b3d6ec5a69f (patch)
tree9c7913282579995d91e79c1a3486605c28dfa595 /src/runtime/cpu/operators/CpuDepthwiseConv2dAssemblyDispatch.h
parent433ea4981675b64c44c8f47f2f4aac6bfcbfc911 (diff)
downloadComputeLibrary-b4bb6a03f717a320b935809fde795b3d6ec5a69f.tar.gz
Rename ported functions
Rename CpuPooling to CpuPool2d Rename CpuPoolingKernel to CpuPool2dKernel Rename CpuPoolingAssemblyWrapperKernel to CpuPool2dAssemblyWrapperKernel Move CpuPool2dAssemblyWrapperKernel in internal subfolder Rename CpuDepthwiseConvolutionNativeKernel to CpuDepthwiseConv2dNativeKernel Rename CpuDepthwiseConvolutionAssemblyDispatch to CpuDepthwiseConv2dAssemblyDispatch Rename CpuDepthwiseConvolution to CpuDepthwiseConv2d Rename CpuDirectConvolutionKernel to CpuDirectConv2dKernel Rename CpuDirectConvolutionOutputStageKernel to CpuDirectConv2dOutputStageKernel Rename CpuDirectConvolution to CpuDirectConv2d Rename ClPoolingKernel to ClPool2dKernel Rename ClPooling to ClPool2d Rename ClDirectConvolutionKernel to ClDirectConv2dKernel Resolves: COMPMID-4405 Change-Id: I8e48f015e4e492a76a7512f5679cb3eb0cd028f6 Signed-off-by: Manuel Bottini <manuel.bottini@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/5708 Reviewed-by: Georgios Pinitas <georgios.pinitas@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com>
Diffstat (limited to 'src/runtime/cpu/operators/CpuDepthwiseConv2dAssemblyDispatch.h')
-rw-r--r--src/runtime/cpu/operators/CpuDepthwiseConv2dAssemblyDispatch.h86
1 files changed, 86 insertions, 0 deletions
diff --git a/src/runtime/cpu/operators/CpuDepthwiseConv2dAssemblyDispatch.h b/src/runtime/cpu/operators/CpuDepthwiseConv2dAssemblyDispatch.h
new file mode 100644
index 0000000000..195942b7fd
--- /dev/null
+++ b/src/runtime/cpu/operators/CpuDepthwiseConv2dAssemblyDispatch.h
@@ -0,0 +1,86 @@
+/*
+ * Copyright (c) 2019-2021 Arm Limited.
+ *
+ * SPDX-License-Identifier: MIT
+ *
+ * Permission is hereby granted, free of charge, to any person obtaining a copy
+ * of this software and associated documentation files (the "Software"), to
+ * deal in the Software without restriction, including without limitation the
+ * rights to use, copy, modify, merge, publish, distribute, sublicense, and/or
+ * sell copies of the Software, and to permit persons to whom the Software is
+ * furnished to do so, subject to the following conditions:
+ *
+ * The above copyright notice and this permission notice shall be included in all
+ * copies or substantial portions of the Software.
+ *
+ * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
+ * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
+ * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
+ * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
+ * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
+ * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
+ * SOFTWARE.
+ */
+#ifndef ARM_COMPUTE_CPU_DEPTHWISECONV2DASSEMBLYDISPATCH_H
+#define ARM_COMPUTE_CPU_DEPTHWISECONV2DASSEMBLYDISPATCH_H
+
+#include "src/core/common/Macros.h"
+#include "src/runtime/cpu/ICpuOperator.h"
+
+namespace arm_compute
+{
+namespace cpu
+{
+/** Depthwise convolution assembly kernel glue */
+class CpuDepthwiseConv2dAssemblyDispatch : public ICpuOperator
+{
+public:
+ /** Default constructor */
+ CpuDepthwiseConv2dAssemblyDispatch();
+ ARM_COMPUTE_DISALLOW_COPY_ALLOW_MOVE(CpuDepthwiseConv2dAssemblyDispatch);
+ /** Default destructor */
+ ~CpuDepthwiseConv2dAssemblyDispatch();
+
+ /** Initialize the function's source, destination, kernels and border_size.
+ *
+ * @note Supports only NHWC format
+ *
+ * @param[in] src Source tensor info. Data type supported: QASYMM8/F16/F32. (Written to only for border filling).
+ * @param[in] weights Weights tensor info. These are 3D tensors with shape [W, H, IFM]. Data type supported: Same as @p src.
+ * @param[in] bias (Optional) Biases tensor info. A 1D tensor with shape [IFM]. Must be nullptr if not needed.
+ * Data type supported: Same as @p src.
+ * @param[out] dst Destination tensor info. Data type supported: same as @p src.
+ * @param[in] info Depthwise convolution meta-data.
+ */
+ void configure(const ITensorInfo *src, const ITensorInfo *weights, const ITensorInfo *bias, ITensorInfo *dst, const ConvolutionInfo &info);
+ /** Static function to check if given info will lead to a valid configuration
+ *
+ * Similar to CpuDepthwiseConv2dAssemblyDispatch::configure()
+ *
+ * @return a status
+ */
+ static Status validate(const ITensorInfo *src, const ITensorInfo *weights, const ITensorInfo *bias, const ITensorInfo *dst, const ConvolutionInfo &info);
+ /** Check if the optimized kernel can be used for the given kernel sizes and strides
+ *
+ * @warning Even if this return true the inputs and outputs might need to get permuted as the only layout supported is NHWC
+ *
+ * @param[in] src Input tensor info.
+ * @param[in] weights Weights tensor info.
+ * @param[in] info Depthwise convolution meta-data.
+ *
+ * @return True if the assembly kernel could be used else false. Note that transformations of input/output could be needed.
+ */
+ static bool is_optimized_supported(const ITensorInfo *src, const ITensorInfo *weights, const ConvolutionInfo &info);
+
+ // Inherited methods overridden:
+ void run(ITensorPack &tensors) override;
+ void prepare(ITensorPack &tensors) override;
+ experimental::MemoryRequirements workspace() const override;
+
+private:
+ struct LocalImpl;
+ std::unique_ptr<LocalImpl> _pImpl;
+};
+} // namespace cpu
+} // namespace arm_compute
+#endif /* ARM_COMPUTE_CPU_DEPTHWISECONV2DASSEMBLYDISPATCH_H */