24 #ifndef ARM_COMPUTE_CLGEMMMATRIXMULTIPLYKERNEL_H 25 #define ARM_COMPUTE_CLGEMMMATRIXMULTIPLYKERNEL_H void run(const Window &window, cl::CommandQueue &queue) override
Enqueue the OpenCL kernel to process the given window on the passed OpenCL command queue...
const Window & window() const
The maximum window the kernel can be executed on.
const ICLTensor * _input2
GEMM reshape information class.
Store the tensor's metadata.
Common interface for all the OpenCL kernels.
Activation Layer Information class.
CLGEMMMatrixMultiplyKernel()
Default constructor.
static Status validate(const ITensorInfo *input0, const ITensorInfo *input1, const ITensorInfo *input2, const ITensorInfo *output, float alpha, float beta, bool is_interleaved_transposed, const GEMMReshapeInfo &reshape_info, GPUTarget gpu_target, bool fp_mixed_precision=false, const ActivationLayerInfo &activation_info=ActivationLayerInfo())
Static function to check if given info will lead to a valid configuration of CLGEMMMatrixMultiplyKern...
Copyright (c) 2017-2021 Arm Limited.
bool _reinterpret_input_as_3d
void configure(const ICLTensor *input0, const ICLTensor *input1, const ICLTensor *input2, ICLTensor *output, float alpha, float beta=0.f, bool is_interleaved_transposed=true, const GEMMReshapeInfo &reshape_info=GEMMReshapeInfo(), bool fp_mixed_precision=false, const ActivationLayerInfo &activation_info=ActivationLayerInfo())
Initialise the kernel's input, output and alpha.
OpenCL kernel to multiply two input matrices "A" and "B" and add a martix "C" if provided.
const ICLTensor * _input1
CLGEMMMatrixMultiplyKernel & operator=(const CLGEMMMatrixMultiplyKernel &)=delete
Prevent instances of this class from being copied (As this class contains pointers) ...
const ICLTensor * _input0
Interface for OpenCL tensor.
GPUTarget
Available GPU Targets.
bool _reinterpret_output_as_3d
Describe a multidimensional execution window.