53 const std::string
kernel_name = std::string(
"integral_horizontal");
58 const unsigned int num_elems_accessed_per_iteration =
ceil_to_multiple(num_elems_processed_per_iteration, 16);
69 ICLKernel::configure_internal(win);
102 const std::string
kernel_name = std::string(
"integral_vertical");
106 constexpr
unsigned int num_elems_processed_per_iteration_x = 8;
111 AccessWindowRectangle in_out_access(in_out->
info(), 0, 0, num_elems_processed_per_iteration_x, num_elems_processed_per_iteration_y);
117 ICLKernel::configure_internal(win);
140 unsigned int idx = 0;
142 _kernel.setArg<cl_uint>(idx++, height);
Window first_slice_window_2D() const
First 2D slice of the window.
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.
cl::NDRange lws_hint() const
Return the Local-Workgroup-Size hint.
1 channel, 1 U8 per channel
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.
static CLKernelLibrary & get()
Access the KernelLibrary singleton.
std::string lower_string(const std::string &val)
Lower a given string.
bool slide_window_slice_2D(Window &slice) const
Slide the passed 2D window slice.
Copyright (c) 2017-2021 Arm Limited.
virtual ValidRegion valid_region() const =0
Valid region of the tensor.
Implementation of a rectangular access pattern.
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.
bool update_window_and_padding(Window &win, Ts &&... patterns)
Update window and padding size for each of the access patterns.
1 channel, 1 U32 per channel
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.
Class to describe a number of elements in each dimension.
void run(const Window &window, cl::CommandQueue &queue) override
Enqueue the OpenCL kernel to process the given window on the passed OpenCL command queue...
Implementation of a row access pattern.
virtual ITensorInfo * info() const =0
Interface to be implemented by the child class to return the tensor's metadata.
void configure(const ICLTensor *input, ICLTensor *output)
Initialise the kernel's input and output.
#define ARM_COMPUTE_ERROR_ON_UNCONFIGURED_KERNEL(k)
#define ARM_COMPUTE_ERROR_ON_DATA_TYPE_CHANNEL_NOT_IN(t, c,...)
static constexpr size_t DimY
Alias for dimension 1 also known as Y dimension.
void add_2D_tensor_argument(unsigned int &idx, const ICLTensor *tensor, const Window &window)
Add the passed 2D tensor's parameters to the object's kernel's arguments starting from the index idx...
Interface for OpenCL tensor.
Manages all the OpenCL kernels compilation and caching, provides accessors for the OpenCL Context...
Wrapper to configure the Khronos OpenCL C++ header.
unsigned int num_elems_processed_per_iteration
CLIntegralImageVertKernel()
Default constructor.
void configure(ICLTensor *in_out)
Initialise the kernel's input and output.
Describe a multidimensional execution window.
#define ARM_COMPUTE_ERROR_ON_INVALID_SUBWINDOW(f, s)
SimpleTensor< T > slice(const SimpleTensor< T > &src, Coordinates starts, Coordinates ends)