aboutsummaryrefslogtreecommitdiff
path: root/arm_compute/core/CL/kernels/ICLDepthwiseConvolutionLayer3x3Kernel.h
diff options
context:
space:
mode:
authorManuel Bottini <manuel.bottini@arm.com>2020-04-08 10:15:51 +0100
committerManuel Bottini <manuel.bottini@arm.com>2020-04-17 14:10:38 +0000
commit4c6bd514a8d424a29b776754f1b3426fa3a8c339 (patch)
treeed20ea238ae069ab138b62ea6879e0c1b955b606 /arm_compute/core/CL/kernels/ICLDepthwiseConvolutionLayer3x3Kernel.h
parentd2f6d96cdc2ad2169c4abd0a8c4884f61ed6d186 (diff)
downloadComputeLibrary-4c6bd514a8d424a29b776754f1b3426fa3a8c339.tar.gz
COMPMID-3280: Make all ML primitives for CL use the new interface - Part 1
- Only CLKernels have been updated Change-Id: Ife55b847c2e39e712a186eb6ca452503d5b66937 Signed-off-by: Manuel Bottini <manuel.bottini@arm.com> Reviewed-on: https://review.mlplatform.org/c/ml/ComputeLibrary/+/3001 Reviewed-by: Michele Di Giorgio <michele.digiorgio@arm.com> Reviewed-by: Michalis Spyrou <michalis.spyrou@arm.com> Comments-Addressed: Arm Jenkins <bsgcomp@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com>
Diffstat (limited to 'arm_compute/core/CL/kernels/ICLDepthwiseConvolutionLayer3x3Kernel.h')
-rw-r--r--arm_compute/core/CL/kernels/ICLDepthwiseConvolutionLayer3x3Kernel.h23
1 files changed, 22 insertions, 1 deletions
diff --git a/arm_compute/core/CL/kernels/ICLDepthwiseConvolutionLayer3x3Kernel.h b/arm_compute/core/CL/kernels/ICLDepthwiseConvolutionLayer3x3Kernel.h
index 9c62f96f6d..040ca157de 100644
--- a/arm_compute/core/CL/kernels/ICLDepthwiseConvolutionLayer3x3Kernel.h
+++ b/arm_compute/core/CL/kernels/ICLDepthwiseConvolutionLayer3x3Kernel.h
@@ -1,5 +1,5 @@
/*
- * Copyright (c) 2017-2019 ARM Limited.
+ * Copyright (c) 2017-2020 ARM Limited.
*
* SPDX-License-Identifier: MIT
*
@@ -68,6 +68,27 @@ public:
virtual void configure(const ICLTensor *input, const ICLTensor *weights, const ICLTensor *biases, ICLTensor *output, const PadStrideInfo &conv_info,
unsigned int depth_multiplier = 1, ActivationLayerInfo act_info = ActivationLayerInfo(), const Size2D &dilation = Size2D(1U, 1U),
const ICLTensor *output_multipliers = nullptr, const ICLTensor *output_shifts = nullptr) = 0;
+ /** Initialize the function's source, destination, conv and border_size.
+ *
+ * @param[in] compile_context The compile context to be used.
+ * @param[in] input Source tensor. DataType supported: QASYMM8/F16/F32.
+ * @param[in] weights Weights tensor. A 3D tensor with dimensions [3, 3, IFM].
+ * Data type supported: Same as @p input, QASYMM8/QSYMM8_PER_CHANNEL when input is QASYMM8.
+ * @param[in] biases Biases tensor. A 1D tensor with dimensions [IFM]. Must be nullptr if not needed.
+ * Data type supported: Same as @p input, S32 when input is QASYMM8.
+ * @param[out] output Destination tensor. Data type supported: Same as @p input.
+ * @param[in] conv_info Padding and stride information to use for the convolution.
+ * @param[in] depth_multiplier (Optional) Multiplier to apply to the input's depth in order to retrieve the output's depth. Defaults to 1.
+ * @param[in] act_info (Optional) Activation layer information in case of a fused activation. Only RELU, BOUNDED_RELU and LU_BOUNDED_RELU are supported for QASYMM8.
+ * @param[in] dilation (Optional) Dilation, in elements, across x and y. Defaults to (1, 1).
+ * @param[in] output_multipliers (Optional) Output multipliers tensor for quantized computations. In case of per-channel quantization,
+ * the number of multipliers must be equal to the number of filters (IFM). Supported data types: S32
+ * @param[in] output_shifts (Optional) Output shifts tensor for quantized computations. In case of per-channel quantization,
+ * the number of multipliers must be equal to the number of filters (IFM). Supported data types: S32
+ */
+ virtual void configure(CLCompileContext &compile_context, const ICLTensor *input, const ICLTensor *weights, const ICLTensor *biases, ICLTensor *output, const PadStrideInfo &conv_info,
+ unsigned int depth_multiplier = 1, ActivationLayerInfo act_info = ActivationLayerInfo(), const Size2D &dilation = Size2D(1U, 1U),
+ const ICLTensor *output_multipliers = nullptr, const ICLTensor *output_shifts = nullptr) = 0;
protected:
BorderSize _border_size;