aboutsummaryrefslogtreecommitdiff
path: root/arm_compute/core/CL/kernels/CLDepthwiseConvolutionLayerNativeKernel.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/CLDepthwiseConvolutionLayerNativeKernel.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/CLDepthwiseConvolutionLayerNativeKernel.h')
-rw-r--r--arm_compute/core/CL/kernels/CLDepthwiseConvolutionLayerNativeKernel.h22
1 files changed, 22 insertions, 0 deletions
diff --git a/arm_compute/core/CL/kernels/CLDepthwiseConvolutionLayerNativeKernel.h b/arm_compute/core/CL/kernels/CLDepthwiseConvolutionLayerNativeKernel.h
index 7e19ed6285..db26b4a06f 100644
--- a/arm_compute/core/CL/kernels/CLDepthwiseConvolutionLayerNativeKernel.h
+++ b/arm_compute/core/CL/kernels/CLDepthwiseConvolutionLayerNativeKernel.h
@@ -68,6 +68,28 @@ public:
void configure(const ICLTensor *input, const ICLTensor *weights, const ICLTensor *biases, ICLTensor *output, const DWCWeightsKernelInfo &dwc_weights_info,
const DWCKernelInfo &dwc_info, const PadStrideInfo &conv_info, unsigned int depth_multiplier = 1, const Size2D &dilation = Size2D(1U, 1U),
const ICLTensor *output_multipliers = nullptr, const ICLTensor *output_shifts = nullptr);
+ /** Initialize the function's source, destination and parameters
+ *
+ * @param[in] compile_context The compile context to be used.
+ * @param[in] input Source tensor. Data type supported: QASYMM8/QASYMM8_SIGNED/FP32/FP16. Data layout supported: NHWC
+ * @param[in] weights Weights tensor. A 3D tensor with dimensions [IFM, N, M].
+ * Data type supported: Same as @p input or QASYMM8/QASYMM8_SIGNED/QSYMM8_PER_CHANNEL when @p 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/QASYMM8_SIGNED.
+ * @param[out] output Destination tensor. Data type supported: Same as @p input.
+ * @param[in] dwc_weights_info Depthwise convolution layer weights info to retrieve the number of output elements processed by each thread
+ * @param[in] dwc_info Depthwise convolution layer info
+ * @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] 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
+ */
+ void configure(CLCompileContext &compile_context, const ICLTensor *input, const ICLTensor *weights, const ICLTensor *biases, ICLTensor *output, const DWCWeightsKernelInfo &dwc_weights_info,
+ const DWCKernelInfo &dwc_info, const PadStrideInfo &conv_info, unsigned int depth_multiplier = 1, const Size2D &dilation = Size2D(1U, 1U),
+ const ICLTensor *output_multipliers = nullptr, const ICLTensor *output_shifts = nullptr);
/** Static function to check if given info will lead to a valid configuration of @ref CLDepthwiseConvolutionLayerNativeKernel
*
* @param[in] input Source tensor info. Data type supported: QASYMM8/QASYMM8_SIGNED/FP32/FP16. Data layout supported: NHWC