24.02.1
|
Go to the documentation of this file.
56 if (
dst->total_size() > 0)
82 const unsigned int vec_size_x =
adjust_vec_size(max_cl_vector_width /
src->element_size(),
src->dimension(0));
83 const int vec_size_x_leftovers =
src->dimension(0) % vec_size_x;
94 IClKernel::configure_internal(win);
118 unsigned int idx = 0;
Class to describe a number of elements in each dimension.
std::string to_string(T &&value)
Convert integer and float values to string.
SimpleTensor< float > src
const StringSet & options() const
Gets the current options list set.
Window calculate_max_window(const ValidRegion &valid_region, const Steps &steps, bool skip_border, BorderSize border_size)
Status validate_arguments(const ITensorInfo *src, const ITensorInfo *weights, const ITensorInfo *dst, const PadStrideInfo &conv_info)
#define ARM_COMPUTE_ERROR_ON_UNCONFIGURED_KERNEL(k)
#define ARM_COMPUTE_RETURN_ERROR_ON_MISMATCHING_SHAPES(...)
Window collapse_if_possible(const Window &full_window, size_t first, size_t last, bool *has_collapsed=nullptr) const
Collapse the dimensions between first and last if possible.
void run_op(ITensorPack &tensors, const Window &window, cl::CommandQueue &queue) override
Enqueue the OpenCL kernel to process the given window on the passed OpenCL command queue.
ITensor * get_tensor(int id)
Get tensor of a given id from the pac.
#define ARM_COMPUTE_RETURN_ERROR_ON_MISMATCHING_DATA_TYPES(...)
#define ARM_COMPUTE_RETURN_ERROR_ON_DATA_TYPE_CHANNEL_NOT_IN(t, c,...)
Manages all the OpenCL kernels compilation and caching, provides accessors for the OpenCL Context.
#define ARM_COMPUTE_RETURN_ON_ERROR(status)
Checks if a status contains an error and returns it.
#define ARM_COMPUTE_ERROR_ON_NULLPTR(...)
#define ARM_COMPUTE_ERROR_ON(cond)
If the condition is true then an error message is printed and an exception thrown.
const ITensor * get_const_tensor(int id) const
Get constant tensor of a given id.
#define ARM_COMPUTE_ERROR_THROW_ON(status)
void add_option(std::string option)
Adds option to the existing build option list.
static Status validate(const ITensorInfo *src, const ITensorInfo *dst)
Static function to check if given info will lead to a valid configuration.
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...
#define ARM_COMPUTE_RETURN_ERROR_ON_F16_UNSUPPORTED(tensor)
cl::Kernel create_kernel(const CLCompileContext &ctx, const std::string &kernel_name, const std::set< std::string > &build_opts=std::set< std::string >())
Creates an opencl kernel using a compile context.
bool slide_window_slice_3D(Window &slice) const
Slide the passed 3D window slice.
Window first_slice_window_3D() const
First 3D slice of the window.
void configure(const ClCompileContext &compile_context, const ITensorInfo *src, ITensorInfo *dst)
Configure kernel for a given list of arguments.
const Window & window() const
The maximum window the kernel can be executed on.
std::string get_cl_type_from_data_type(const DataType &dt)
Translates a tensor data type to the appropriate OpenCL type.
void add_3D_tensor_argument(unsigned int &idx, const ICLTensor *tensor, const Window &window)
Add the passed 3D tensor's parameters to the object's kernel's arguments starting from the index idx.
Describe a multidimensional execution window.
@ ELEMENTWISE
Elementwise CL kernel type.
Copyright (c) 2017-2024 Arm Limited.
@ F16
16-bit floating-point number
unsigned int adjust_vec_size(unsigned int vec_size, size_t dim0)
Returns the adjusted vector size in case it is less than the input's first dimension,...
bool has_padding_changed(const std::unordered_map< const ITensorInfo *, PaddingSize > &padding_map)
Check if the previously stored padding info has changed after configuring a kernel.
static constexpr size_t DimZ
Alias for dimension 2 also known as Z dimension.
cl::NDRange lws_hint() const
Return the Local-Workgroup-Size hint.
#define ARM_COMPUTE_RETURN_ERROR_ON_NULLPTR(...)
Store the tensor's metadata.
@ F32
32-bit floating-point number
#define ARM_COMPUTE_ERROR_ON_MISMATCHING_WINDOWS(f, w)
std::unordered_map< const ITensorInfo *, PaddingSize > get_padding_info(std::initializer_list< const ITensorInfo * > infos)
Stores padding information before configuring a kernel.
SimpleTensor< T > slice(const SimpleTensor< T > &src, Coordinates starts, Coordinates ends)
void enqueue(cl::CommandQueue &queue, ICLKernel &kernel, const Window &window, const cl::NDRange &lws_hint=CLKernelLibrary::get().default_ndrange(), bool use_dummy_work_items=false)
Add the kernel to the command queue with the given window.