24.02.1
|
Go to the documentation of this file.
71 unsigned int batch_offset,
79 _batch_offset = batch_offset;
111 ICLKernel::configure_internal(win);
114 _config_id =
"concatenate_";
131 unsigned int batch_offset,
149 const int offset_to_first_elements_in_bytes = _batch_offset *
dst->info()->strides_in_bytes()[3];
152 _kernel.setArg<cl_int>(idx, offset_to_first_elements_in_bytes);
156 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)
void configure(const CLCompileContext &compile_context, ITensorInfo *src, unsigned int batch_offset, ITensorInfo *dst)
Initialise the kernel's source and destination.
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(...)
static constexpr size_t DimX
Alias for dimension 0 also known as X dimension.
ClBatchConcatenateKernel()
ITensor * get_tensor(int id)
Get tensor of a given id from the pac.
std::string upper_string(const std::string &val)
Raise a given string to upper case.
static Status validate(const ITensorInfo *src, unsigned int batch_offset, const ITensorInfo *dst)
Static function to check if given info will lead to a valid configuration.
#define ARM_COMPUTE_RETURN_ERROR_ON_MISMATCHING_DATA_TYPES(...)
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.
#define ARM_COMPUTE_RETURN_ERROR_ON(cond)
If the condition is true, an error is returned.
#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.
#define ARM_COMPUTE_ERROR_ON_INVALID_SUBWINDOW(f, s)
std::string float_to_string_with_full_precision(float val)
Create a string with the float in full precision.
bool slide_window_slice_3D(Window &slice) const
Slide the passed 3D window slice.
Describe one of the image's dimensions with a start, end and step.
static constexpr size_t DimY
Alias for dimension 1 also known as Y dimension.
Window first_slice_window_3D() const
First 3D slice of the window.
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.
constexpr static unsigned int num_arguments_per_3D_tensor()
Returns the number of arguments enqueued per 3D tensor object.
Copyright (c) 2017-2024 Arm Limited.
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.
bool is_data_type_quantized_asymmetric(DataType dt)
Check if a given data type is of asymmetric quantized type.
#define ARM_COMPUTE_RETURN_ERROR_ON_NULLPTR(...)
Store the tensor's metadata.
void run_op(ITensorPack &tensors, const Window &window, ::cl::CommandQueue &queue) override
@ UNKNOWN
Unknown data type.
unsigned int num_elems_processed_per_iteration
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.