24.02.1
|
Go to the documentation of this file.
24 #ifndef ARM_COMPUTE_CPU_DIRECT_CONV2D_OUTPUT_STAGE_KERNEL_H
25 #define ARM_COMPUTE_CPU_DIRECT_CONV2D_OUTPUT_STAGE_KERNEL_H
78 const char *
name()
const override;
85 int result_fixedpoint_multiplier,
87 int result_offset_after_shift);
89 OutputStageKernel *_func{
nullptr};
90 int _result_fixedpoint_multiplier{0};
92 int _result_offset_after_shift{0};
SimpleTensor< float > src
const char * name() const override
Name of the kernel.
ARM_COMPUTE_DISALLOW_COPY_ALLOW_MOVE(CpuDirectConv2dOutputStageKernel)
void configure(ITensorInfo *src, const ITensorInfo *bias=nullptr, ITensorInfo *dst=nullptr, const DirectConvolutionLayerOutputStageKernelInfo &info=DirectConvolutionLayerOutputStageKernelInfo())
Set the accumulate buffer and the biases of the kernel.
Descriptor used by the direct convolution layer output stage kernels.
Interface for CPU tensor.
Kernel to accumulate the biases, if provided, or downscale in case of quantized input.
void run_op(ITensorPack &tensors, const Window &window, const ThreadInfo &info) override
Execute the kernel on the passed window.
static Status validate(const ITensorInfo *src, const ITensorInfo *bias=nullptr, const ITensorInfo *dst=nullptr, const DirectConvolutionLayerOutputStageKernelInfo &info=DirectConvolutionLayerOutputStageKernelInfo())
Static function to check if given info will lead to a valid configuration.
const Window & window() const
The maximum window the kernel can be executed on.
Information about executing thread and CPU.
Describe a multidimensional execution window.
Copyright (c) 2017-2024 Arm Limited.
Store the tensor's metadata.
ScaleKernelInfo info(interpolation_policy, default_border_mode, PixelValue(), sampling_policy, false)
CpuDirectConv2dOutputStageKernel()=default