38 constexpr
unsigned int vector_size_byte_opencl = 16;
69 : _start(0), _end(1), _step(1), _output(nullptr)
108 kernel_name +=
"_quantized";
112 ICLKernel::configure_internal(win);
133 unsigned int idx = 0;
Window calculate_max_window(const ValidRegion &valid_region, const Steps &steps, bool skip_border, BorderSize border_size)
#define ARM_COMPUTE_RETURN_ERROR_ON_F16_UNSUPPORTED(tensor)
const Window & window() const
The maximum window the kernel can be executed on.
static Status validate(const ITensorInfo *output, float start, float end, float step)
Static function to check if given info will lead to a valid configuration of CLRangeKernel.
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.
const StringSet & options() const
Gets the current options list set.
cl::NDRange lws_hint() const
Return the Local-Workgroup-Size hint.
1 channel, 1 U8 per channel
#define ARM_COMPUTE_RETURN_ON_ERROR(status)
Checks if a status contains an error and returns it.
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
#define ARM_COMPUTE_ERROR_ON(cond)
If the condition is true then an error message is printed and an exception thrown.
static CLKernelLibrary & get()
Access the KernelLibrary singleton.
Store the tensor's metadata.
#define ARM_COMPUTE_ERROR_THROW_ON(status)
1 channel, 1 U16 per channel
std::string lower_string(const std::string &val)
Lower a given string.
Copyright (c) 2017-2021 Arm Limited.
1 channel, 1 F16 per channel
#define ARM_COMPUTE_RETURN_ERROR_ON_NULLPTR(...)
1 channel, 1 S32 per channel
void add_option(std::string option)
Adds option to the existing build option list.
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.
const std::string & string_from_data_type(DataType dt)
Convert a data type identity into a string.
1 channel, 1 U32 per channel
std::string float_to_string_with_full_precision(float val)
Create a string with the float in full precision.
bool check_value_range(T val, DataType dt, QuantizationInfo qinfo=QuantizationInfo())
Returns true if the value can be represented by the given data type.
quantized, asymmetric fixed-point 8-bit number unsigned
Class to describe a number of elements in each dimension.
UniformQuantizationInfo uniform() const
Return per layer quantization info.
std::string get_cl_type_from_data_type(const DataType &dt)
Translates a tensor data type to the appropriate OpenCL type.
CLRangeKernel()
Default constructor.
virtual ITensorInfo * info() const =0
Interface to be implemented by the child class to return the tensor's metadata.
virtual size_t element_size() const =0
Element size in bytes calculated as data_size() * num_channels()
void end(TokenStream &in, bool &valid)
virtual QuantizationInfo quantization_info() const =0
Get the quantization settings (scale and offset) of the tensor.
size_t num_of_elements_in_range(const float start, const float end, const float step)
Returns the number of elements required to go from start to end with the wanted step.
#define ARM_COMPUTE_ERROR_ON_UNCONFIGURED_KERNEL(k)
1 channel, 1 S16 per channel
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.
void configure(ICLTensor *output, float start, float end, float step)
Initialize the kernel's output tensor, start, end and step of the sequence.
bool is_data_type_quantized_asymmetric(DataType dt)
Check if a given data type is of asymmetric quantized type.
Interface for OpenCL tensor.
const QuantizationInfo qinfo
#define ARM_COMPUTE_RETURN_ERROR_ON_DATA_TYPE_CHANNEL_NOT_IN(t, c,...)
std::unordered_map< const ITensorInfo *, PaddingSize > get_padding_info(std::initializer_list< const ITensorInfo *> infos)
Stores padding information before configuring a kernel.
Status validate_arguments(const ITensorInfo *input, const ITensorInfo *bias, const ITensorInfo *output, const GEMMLowpOutputStageInfo *output_stage)
unsigned int num_elems_processed_per_iteration
#define ARM_COMPUTE_RETURN_ERROR_ON_MSG(cond, msg)
If the condition is true, an error is returned.
#define ARM_COMPUTE_ERROR_ON_NULLPTR(...)
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, getting rounded down to its closest valid vector size.
void add_1D_tensor_argument(unsigned int &idx, const ICLTensor *tensor, const Window &window)
Add the passed 1D tensor's parameters to the object's kernel's arguments starting from the index idx...
Describe a multidimensional execution window.
#define ARM_COMPUTE_ERROR_ON_INVALID_SUBWINDOW(f, s)
void run(const Window &window, cl::CommandQueue &queue) override
Enqueue the OpenCL kernel to process the given window on the passed OpenCL command queue...