24.02.1
|
Go to the documentation of this file.
24 #ifndef ARM_COMPUTE_CPU_GEMM_MATRIX_MULTIPLY_KERNEL_H
25 #define ARM_COMPUTE_CPU_GEMM_MATRIX_MULTIPLY_KERNEL_H
45 using GemmMatrixMulKernelPtr = std::add_pointer<void(
92 const char *
name()
const override;
108 GemmMatrixMulKernelPtr _func{
nullptr};
void run_op(ITensorPack &tensors, const Window &window, const ThreadInfo &info) override
Execute the kernel on the passed window.
decltype(strategy::transforms) typedef type
Kernel to multiply two input matrices "A" and "B".
GEMM reshape information class.
static Status validate(const ITensorInfo *lhs, const ITensorInfo *rhs, const ITensorInfo *dst, float alpha, bool is_interleaved, const GEMMReshapeInfo &reshape_info)
Static function to check if given info will lead to a valid configuration of CpuGemmMatrixMultiplyKer...
Interface for CPU tensor.
static const std::vector< GemmMatrixMulKernel > & get_available_kernels()
const DataTypeISASelectorPtr is_selected
std::add_pointer< bool(const DataTypeISASelectorData &data)>::type DataTypeISASelectorPtr
void configure(const ITensorInfo *lhs, const ITensorInfo *rhs, ITensorInfo *dst, float alpha, bool is_interleaved, const GEMMReshapeInfo &reshape_info=GEMMReshapeInfo())
Initialise the kernel's input and output.
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.
const char * name() const override
Name of the kernel.
Store the tensor's metadata.
ScaleKernelInfo info(interpolation_policy, default_border_mode, PixelValue(), sampling_policy, false)
ARM_COMPUTE_DISALLOW_COPY_ALLOW_MOVE(CpuGemmMatrixMultiplyKernel)
CpuGemmMatrixMultiplyKernel()=default
GemmMatrixMulKernelPtr ukernel