CLScale Class Reference

Basic function to run opencl::ClScale. More...

#include <CLScale.h>

Collaboration diagram for CLScale:

Public Member Functions
	CLScale ()
	Default Constructor. More...
	~CLScale ()
	Default Destructor. More...
	CLScale (const CLScale &)=delete
	Prevent instances of this class from being copied (As this class contains pointers) More...
	CLScale (CLScale &&)=default
	Default move constructor. More...
CLScale &	operator= (const CLScale &)=delete
	Prevent instances of this class from being copied (As this class contains pointers) More...
CLScale &	operator= (CLScale &&)=default
	Default move assignment operator. More...
void	configure (ICLTensor *input, ICLTensor *output, const ScaleKernelInfo &info)
	Initialize the function's source, destination, interpolation type and border_mode. More...
void	configure (const CLCompileContext &compile_context, ICLTensor *input, ICLTensor *output, const ScaleKernelInfo &info)
	Initialize the function's source, destination, interpolation type and border_mode. More...
void	run () override
	Run the kernels contained in the function. More...
Public Member Functions inherited from IFunction
virtual	~IFunction ()=default
	Destructor. More...
virtual void	prepare ()
	Prepare the function for executing. More...

Static Public Member Functions
static Status	validate (const ITensorInfo *input, const ITensorInfo *output, const ScaleKernelInfo &info)
	Static function to check if given info will lead to a valid configuration of CLScale. More...

Detailed Description

Basic function to run opencl::ClScale.

Definition at line 40 of file CLScale.h.

Constructor & Destructor Documentation

CLScale() [1/3]

CLScale

(

)

Default Constructor.

Definition at line 41 of file CLScale.cpp.

    : _impl(std::make_unique<Impl>())
{
}

~CLScale()

~CLScale ( )

default

Default Destructor.

CLScale() [2/3]

CLScale ( const CLScale &  )

delete

Prevent instances of this class from being copied (As this class contains pointers)

CLScale() [3/3]

CLScale ( CLScale &&  )

default

Default move constructor.

Member Function Documentation

configure() [1/2]

void configure	(	const CLCompileContext &	compile_context,
		ICLTensor *	input,
		ICLTensor *	output,
		const ScaleKernelInfo &	info
	)

Initialize the function's source, destination, interpolation type and border_mode.

Parameters

[in]	compile_context	The compile context to be used.
[in,out]	input	Source tensor. Data types supported: U8/QASYMM8/QASYMM8_SIGNED/S16/F16/F32. (Written to only for border_mode != UNDEFINED)
[out]	output	Destination tensor. Data types supported: Same as input All but the lowest two dimensions must be the same size as in the input tensor, i.e. scaling is only performed within the XY-plane.
[in]	info	ScaleKernelInfo descriptor to be used to configure

Definition at line 52 of file CLScale.cpp.

{
    _impl->src = input;
    _impl->dst = output;
 
    _impl->op = std::make_unique<opencl::ClScale>();
    _impl->op->configure(compile_context, input->info(), output->info(), info);
}

References ITensor::info(), arm_compute::test::validation::info, and arm_compute::test::validation::input.

configure() [2/2]

void configure	(	ICLTensor *	input,
		ICLTensor *	output,
		const ScaleKernelInfo &	info
	)

Initialize the function's source, destination, interpolation type and border_mode.

Valid data layouts:

• NHWC
• NCHW

Valid data type configurations:

src	dst
QASYMM8	QASYMM8
QASYMM8_SIGNED	QASYMM8_SIGNED
F16	F16
F32	F32
U8	U8
S16	S16

Parameters

[in,out]	input	Source tensor. Data types supported: U8/QASYMM8/QASYMM8_SIGNED/S16/F16/F32. (Written to only for border_mode != UNDEFINED)
[out]	output	Destination tensor. Data types supported: Same as input All but the lowest two dimensions must be the same size as in the input tensor, i.e. scaling is only performed within the XY-plane.
[in]	info	ScaleKernelInfo descriptor to be used to configure

Definition at line 47 of file CLScale.cpp.

{
    configure(CLKernelLibrary::get().get_compile_context(), input, output, info);
}

References CLKernelLibrary::get(), arm_compute::test::validation::info, and arm_compute::test::validation::input.

operator=() [1/2]

CLScale& operator= ( CLScale &&  )

default

Default move assignment operator.

operator=() [2/2]

CLScale& operator= ( const CLScale &  )

delete

Prevent instances of this class from being copied (As this class contains pointers)

run()

void run ( )

overridevirtual

Run the kernels contained in the function.

For CPU kernels:

• Multi-threading is used for the kernels which are parallelisable.
• By default std::thread::hardware_concurrency() threads are used.

Note

CPPScheduler::set_num_threads() can be used to manually set the number of threads

For OpenCL kernels:

• All the kernels are enqueued on the queue associated with CLScheduler.
• The queue is then flushed.

Note

The function will not block until the kernels are executed. It is the user's responsibility to wait.

Will call prepare() on first run if hasn't been done

Implements IFunction.

Definition at line 66 of file CLScale.cpp.

{
    ITensorPack pack;
    pack.add_tensor(TensorType::ACL_SRC, _impl->src);
    pack.add_tensor(TensorType::ACL_DST, _impl->dst);
    _impl->op->run(pack);
}

References arm_compute::ACL_DST, arm_compute::ACL_SRC, ITensorPack::add_tensor(), and arm_compute::test::validation::pack.

validate()

Status validate ( const ITensorInfo *  input, const ITensorInfo *  output, const ScaleKernelInfo &  info  )

static

Static function to check if given info will lead to a valid configuration of CLScale.

Parameters

[in]	input	Source tensor info. Data types supported: U8/QASYMM8/QASYMM8_SIGNED/S16/F16/F32.
[in]	output	Output tensor info. Data type supported: Same as input All but the lowest two dimensions must be the same size as in the input tensor, i.e. scaling is only performed within the XY-plane.
[in]	info	ScaleKernelInfo descriptor to be used to validate

Returns

a status

Definition at line 61 of file CLScale.cpp.

{
    return opencl::ClScale::validate(input, output, info);
}

References arm_compute::test::validation::info, arm_compute::test::validation::input, and ClScale::validate().

Referenced by arm_compute::test::validation::TEST_CASE().

---

The documentation for this class was generated from the following files:

• arm_compute/runtime/CL/functions/CLScale.h
• src/runtime/CL/functions/CLScale.cpp