57 ICPPKernel::configure(win);
108 const size_t vector_size = 16 / element_size;
112 const uint8_t *in_ptr = in.
ptr();
113 uint8_t *
const out_ptr = out.
ptr() + (
id.y() * vector_size) * element_size + (
id.x() / vector_size) * out_stride;
115 for(
size_t k = 0; k < vector_size; ++k)
118 if((
id.x() + k) >= in_width)
120 std::memset(out_ptr + k * element_size, 0, element_size);
124 std::memcpy(out_ptr + k * element_size, in_ptr + k * element_size, element_size);
133 return "CpuGemmTranspose1xWKernel";
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.
TensorShape compute_transpose1xW_with_element_size_shape(const ITensorInfo &b, int mult_transpose1xW_width=1)
Calculate the transposed 1xW width element shape.
virtual size_t dimension(size_t index) const =0
Return the size of the requested dimension.
#define ARM_COMPUTE_RETURN_ERROR_ON_MISMATCHING_QUANTIZATION_INFO(...)
bool empty() const
Checks if pack is empty.
virtual DataType data_type() const =0
Data type used for each element of the tensor.
#define ARM_COMPUTE_ERROR_ON(cond)
If the condition is true then an error message is printed and an exception thrown.
static Status validate(const ITensorInfo *src, const ITensorInfo *dst)
Static function to check if given info will lead to a valid configuration of CpuGemmTranspose1xWKerne...
Store the tensor's metadata.
#define ARM_COMPUTE_ERROR_THROW_ON(status)
Describe one of the image's dimensions with a start, end and step.
#define ARM_COMPUTE_RETURN_ERROR_ON(cond)
If the condition is true, an error is returned.
Interface for CPU tensor.
#define ARM_COMPUTE_RETURN_ERROR_ON_MISMATCHING_DIMENSIONS(...)
SimpleTensor< float > src
Copyright (c) 2017-2021 Arm Limited.
#define ARM_COMPUTE_RETURN_ERROR_ON_NULLPTR(...)
const ITensor * get_const_tensor(int id) const
Get constant tensor of a given id.
static constexpr size_t DimX
Alias for dimension 0 also known as X dimension.
#define ARM_COMPUTE_UNUSED(...)
To avoid unused variables warnings.
virtual const TensorShape & tensor_shape() const =0
Size for each dimension of the tensor.
Class to describe a number of elements in each dimension.
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...
virtual std::unique_ptr< T > clone() const =0
Provide a clone of the current object of class T.
virtual ITensorInfo * info() const =0
Interface to be implemented by the child class to return the tensor's metadata.
constexpr uint8_t * ptr() const
Return a pointer to the current pixel.
virtual size_t element_size() const =0
Element size in bytes calculated as data_size() * num_channels()
void configure(const ITensorInfo *src, ITensorInfo *dst)
Configure kernel for a given list of arguments.
#define ARM_COMPUTE_ERROR_ON_UNCONFIGURED_KERNEL(k)
static constexpr size_t DimY
Alias for dimension 1 also known as Y dimension.
ScaleKernelInfo info(interpolation_policy, default_border_mode, PixelValue(), sampling_policy, false)
ITensor * get_tensor(int id)
Get tensor of a given id from the pac.
Information about executing thread and CPU.
virtual size_t total_size() const =0
Returns the total size of the tensor in bytes.
#define ARM_COMPUTE_RETURN_ERROR_ON_MISMATCHING_DATA_TYPES(...)
void run_op(ITensorPack &tensors, const Window &window, const ThreadInfo &info) override
Execute the kernel on the passed window.
#define ARM_COMPUTE_ERROR_ON_NULLPTR(...)
void execute_window_loop(const Window &w, L &&lambda_function, Ts &&... iterators)
Iterate through the passed window, automatically adjusting the iterators and calling the lambda_funct...
const char * name() const override
Name of the kernel.
virtual const Strides & strides_in_bytes() const =0
The strides in bytes for accessing each dimension of the tensor.
Iterator updated by execute_window_loop for each window element.
Describe a multidimensional execution window.
#define ARM_COMPUTE_ERROR_ON_INVALID_SUBWINDOW(f, s)