aboutsummaryrefslogtreecommitdiff
path: root/arm_compute/core/CL/kernels/CLDepthwiseConvolutionLayer3x3NHWCKernel.h
diff options
context:
space:
mode:
authorgiuros01 <giuseppe.rossini@arm.com>2019-01-07 17:47:19 +0000
committerGiuseppe Rossini <giuseppe.rossini@arm.com>2019-01-30 16:22:47 +0000
commit6d109965f3641056bb8164dc8450a7327e76e939 (patch)
tree45e40a75e7f2d80e403a33087284f08b2b2a0b6b /arm_compute/core/CL/kernels/CLDepthwiseConvolutionLayer3x3NHWCKernel.h
parentedc21e44313edea693700a6bdfa353edcfbe25be (diff)
downloadComputeLibrary-6d109965f3641056bb8164dc8450a7327e76e939.tar.gz
COMPMID-1691: Optimize CLDepthwiseConvolutionKernel (QASYMM8/NHWC) for 3x3 kernels (stride=1 and stride=2)
Change-Id: I7d0d2dc350feeb40d253d17f9ffd5051a8fb42ef Reviewed-on: https://review.mlplatform.org/511 Reviewed-by: Gian Marco Iodice <gianmarco.iodice@arm.com> Tested-by: Arm Jenkins <bsgcomp@arm.com>
Diffstat (limited to 'arm_compute/core/CL/kernels/CLDepthwiseConvolutionLayer3x3NHWCKernel.h')
-rw-r--r--arm_compute/core/CL/kernels/CLDepthwiseConvolutionLayer3x3NHWCKernel.h11
1 files changed, 6 insertions, 5 deletions
diff --git a/arm_compute/core/CL/kernels/CLDepthwiseConvolutionLayer3x3NHWCKernel.h b/arm_compute/core/CL/kernels/CLDepthwiseConvolutionLayer3x3NHWCKernel.h
index 85fbaaee37..2fc9780a2f 100644
--- a/arm_compute/core/CL/kernels/CLDepthwiseConvolutionLayer3x3NHWCKernel.h
+++ b/arm_compute/core/CL/kernels/CLDepthwiseConvolutionLayer3x3NHWCKernel.h
@@ -1,5 +1,5 @@
/*
- * Copyright (c) 2018 ARM Limited.
+ * Copyright (c) 2018-2019 ARM Limited.
*
* SPDX-License-Identifier: MIT
*
@@ -53,11 +53,11 @@ public:
ActivationLayerInfo act_info) override;
/** Static function to check if given info will lead to a valid configuration of @ref CLDepthwiseConvolutionLayer3x3NHWCKernel
*
- * @param[in] input Source tensor. DataType supported: QASYMM8.
- * @param[in] weights Weights tensor. A 3D tensor with dimensions [IFM, 3, 3]. Data type supported: Same as @p input.
- * @param[in] biases (Optional) Biases tensor. A 1D tensor with dimensions [IFM]. Must be nullptr if not needed.
+ * @param[in] input Source tensor info. DataType supported: QASYMM8.
+ * @param[in] weights Weights tensor info. A 3D tensor with dimensions [IFM, 3, 3]. Data type supported: Same as @p input.
+ * @param[in] biases (Optional) Biases tensor info. A 1D tensor with dimensions [IFM]. Must be nullptr if not needed.
* Data type supported: Same as @p input.
- * @param[in] output Destination tensor. Data type supported: Same as @p input.
+ * @param[in] output Destination tensor info. 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.
@@ -67,6 +67,7 @@ public:
static Status validate(const ITensorInfo *input, const ITensorInfo *weights, const ITensorInfo *biases, const ITensorInfo *output, const PadStrideInfo &conv_info, unsigned int depth_multiplier,
ActivationLayerInfo act_info = ActivationLayerInfo());
+ // Inherited methods overridden:
void run(const Window &window, cl::CommandQueue &queue) override;
BorderSize border_size() const override;