23.08
|
Go to the documentation of this file.
67 if(
dst.total_size() > 0)
94 const int dst_width_x =
dst->dimension(0);
116 build_opts.
add_option(
"-DOPERATION=rsqrt_op");
131 build_opts.
add_option(
"-DOPERATION=natural_log_op");
134 build_opts.
add_option(
"-DOPERATION=round_op");
137 build_opts.
add_option(
"-DOPERATION=logical_not_op");
150 ICLKernel::configure_internal(win);
177 unsigned int idx = 0;
std::string to_string(T &&value)
Convert integer and float values to string.
constexpr int start() const
Return the start of the dimension.
constexpr unsigned int vector_size_byte_opencl
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 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.
@ QASYMM8
quantized, asymmetric fixed-point 8-bit number unsigned
ClElementWiseUnaryKernel()
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.
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.
#define ARM_COMPUTE_ERROR(msg)
Print the given message then throw an std::runtime_error.
ITensor * get_tensor(int id)
Get tensor of a given id from the pac.
@ RSQRT
Reverse square root.
#define ARM_COMPUTE_RETURN_ERROR_ON_MISMATCHING_DATA_TYPES(...)
#define ARM_COMPUTE_RETURN_ERROR_ON_DATA_TYPE_CHANNEL_NOT_IN(t, c,...)
void configure(const CLCompileContext &compile_context, const ITensorInfo *src, ITensorInfo *dst, const ElementWiseUnary &op)
Initialise the kernel's srcs, dst.
#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.
@ U8
unsigned 8-bit number
#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.
@ QASYMM8_SIGNED
quantized, asymmetric fixed-point 8-bit number signed
#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.
#define ARM_COMPUTE_UNUSED(...)
To avoid unused variables warnings.
Describe one of the image's dimensions with a start, end and step.
void set(size_t dimension, const Dimension &dim)
Set the values of a given dimension.
auto ceil_to_multiple(S value, T divisor) -> decltype(((value+divisor - 1)/divisor) *divisor)
Computes the smallest number larger or equal to value that is a multiple of divisor.
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.
Copyright (c) 2017-2023 Arm Limited.
static Status validate(const ITensorInfo *src, const ITensorInfo *dst, const ElementWiseUnary &op)
Static function to check if given info will lead to a valid configuration.
@ 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.
@ S32
signed 32-bit number
cl::NDRange lws_hint() const
Return the Local-Workgroup-Size hint.
#define ARM_COMPUTE_RETURN_ERROR_ON_NULLPTR(...)
bool is_data_type_quantized(DataType dt)
Check if a given data type is of quantized type.
Store the tensor's metadata.
@ F32
32-bit floating-point number
constexpr int end() const
Return the end of the dimension.
unsigned int num_elems_processed_per_iteration
constexpr const Dimension & x() const
Alias to access the first dimension of the window.
std::unordered_map< const ITensorInfo *, PaddingSize > get_padding_info(std::initializer_list< const ITensorInfo * > infos)
Stores padding information before configuring a kernel.
@ LOGICAL_NOT
Logical Not.
SimpleTensor< T > slice(const SimpleTensor< T > &src, Coordinates starts, Coordinates ends)
ElementWiseUnary
Available element wise unary operations.
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.