43 : _input(nullptr), _output(nullptr)
65 std::set<std::string> build_opts;
67 build_opts.emplace((
"#define " + dt_name));
73 build_opts.emplace(
"#define GEMM_INTERLEAVE4x4");
78 constexpr
unsigned int num_elems_processed_per_iteration_y = 4;
79 const unsigned int num_elems_written_per_iteration = num_elems_processed_per_iteration_x * num_elems_processed_per_iteration_y;
83 AccessWindowRectangle input_access(input->
info(), 0, 0, num_elems_processed_per_iteration_x, num_elems_processed_per_iteration_y);
90 IGCKernel::configure(win);
118 unsigned int idx = 0;
122 _kernel.update_shader_params();
Window first_slice_window_2D() const
First 2D slice of the window.
void scale(size_t dimension, float scale_value)
Scale the values of a given dimension by the given scale_value.
Window calculate_max_window(const ValidRegion &valid_region, const Steps &steps, bool skip_border, BorderSize border_size)
const Window & window() const
The maximum window the kernel can be executed on.
void enqueue(IGCKernel &kernel, const Window &window, const gles::NDRange &lws=gles::NDRange(1U, 1U, 1U))
Add the kernel to the command queue with the given window.
virtual size_t dimension(size_t index) const =0
Return the size of the requested dimension.
std::string to_string(T &&value)
Convert integer and float values to string.
virtual DataType data_type() const =0
Data type used for each element of the tensor.
1 channel, 1 F32 per channel
Interface for GLES Compute tensor.
bool slide_window_slice_2D(Window &slice) const
Slide the passed 2D window slice.
Copyright (c) 2017-2021 Arm Limited.
virtual void set_valid_region(const ValidRegion &valid_region)=0
Set the valid region of the tensor.
1 channel, 1 F16 per channel
Implementation of a rectangular access pattern.
static constexpr size_t DimX
Alias for dimension 0 also known as X dimension.
bool update_window_and_padding(Window &win, Ts &&... patterns)
Update window and padding size for each of the access patterns.
virtual const TensorShape & tensor_shape() const =0
Size for each dimension of the tensor.
#define ARM_COMPUTE_ERROR_ON_MISMATCHING_DATA_TYPES(...)
Manages all the GLES kernels compilation and caching, provides accessors for the GLES Context...
Class to describe a number of elements in each dimension.
bool auto_init_if_empty(ITensorInfo &info, const TensorShape &shape, int num_channels, DataType data_type, QuantizationInfo quantization_info=QuantizationInfo())
Auto initialize the tensor info (shape, number of channels and data type) if the current assignment i...
virtual ITensorInfo * info() const =0
Interface to be implemented by the child class to return the tensor's metadata.
size_t data_size_from_type(DataType data_type)
The size in bytes of the data type.
void add_2D_tensor_argument(unsigned int &idx, const IGCTensor *tensor, const unsigned int binding_point, const Window &window)
Add the passed 2D tensor's parameters to the object's kernel's arguments starting from the index idx...
GCGEMMInterleave4x4Kernel()
Default constructor.
#define ARM_COMPUTE_ERROR_ON_UNCONFIGURED_KERNEL(k)
#define ARM_COMPUTE_ERROR_ON_DATA_TYPE_CHANNEL_NOT_IN(t, c,...)
void run(const Window &window) override
Enqueue the OpenGL ES shader to process the given window.
static constexpr size_t DimY
Alias for dimension 1 also known as Y dimension.
Wrapper to configure the Khronos EGL and OpenGL ES C header.
static GCKernelLibrary & get()
Get the static instance of GCKernelLibrary.
#define ARM_COMPUTE_ERROR_ON_MISMATCHING_DIMENSIONS(...)
GCKernel create_kernel(const std::string &shader_name, const StringSet &build_options_set={}) const
Creates a kernel from the kernel library.
#define ARM_COMPUTE_ERROR_ON_NULLPTR(...)
Container for valid region of a window.
void configure(const IGCTensor *input, IGCTensor *output)
Initialise the kernel's input and output.
Describe a multidimensional execution window.
TensorShape & set(size_t dimension, size_t value, bool apply_dim_correction=true, bool increase_dim_unit=true)
Accessor to set the value of one of the dimensions.
#define ARM_COMPUTE_ERROR_ON_INVALID_SUBWINDOW(f, s)