CLPixelWiseMultiplication Class Reference

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

#include <CLPixelWiseMultiplication.h>

Collaboration diagram for CLPixelWiseMultiplication:

Public Member Functions
	CLPixelWiseMultiplication ()
	Default Constructor. More...
	~CLPixelWiseMultiplication ()
	Default Destructor. More...
	CLPixelWiseMultiplication (const CLPixelWiseMultiplication &)=delete
	Prevent instances of this class from being copied (As this class contains pointers) More...
	CLPixelWiseMultiplication (CLPixelWiseMultiplication &&)
	Default move constructor. More...
CLPixelWiseMultiplication &	operator= (const CLPixelWiseMultiplication &)=delete
	Prevent instances of this class from being copied (As this class contains pointers) More...
CLPixelWiseMultiplication &	operator= (CLPixelWiseMultiplication &&)
	Default move assignment operator. More...
void	configure (ICLTensor *input1, ICLTensor *input2, ICLTensor *output, float scale, ConvertPolicy overflow_policy, RoundingPolicy rounding_policy, const ActivationLayerInfo &act_info=ActivationLayerInfo())
	Initialise the kernel's inputs, output and convertion policy. More...
void	configure (const CLCompileContext &compile_context, ICLTensor *input1, ICLTensor *input2, ICLTensor *output, float scale, ConvertPolicy overflow_policy, RoundingPolicy rounding_policy, const ActivationLayerInfo &act_info=ActivationLayerInfo())
	Initialise the kernel's inputs, output and convertion policy. 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 *input1, const ITensorInfo *input2, const ITensorInfo *output, float scale, ConvertPolicy overflow_policy, RoundingPolicy rounding_policy, const ActivationLayerInfo &act_info=ActivationLayerInfo())
	Static function to check if given info will lead to a valid configuration of CLPixelWiseMultiplication. More...

Detailed Description

Basic function to run opencl::ClMul.

Definition at line 40 of file CLPixelWiseMultiplication.h.

Constructor & Destructor Documentation

CLPixelWiseMultiplication() [1/3]

CLPixelWiseMultiplication

(

)

Default Constructor.

Definition at line 43 of file CLPixelWiseMultiplication.cpp.

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

~CLPixelWiseMultiplication()

~CLPixelWiseMultiplication ( )

default

Default Destructor.

CLPixelWiseMultiplication() [2/3]

CLPixelWiseMultiplication ( const CLPixelWiseMultiplication &  )

delete

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

CLPixelWiseMultiplication() [3/3]

CLPixelWiseMultiplication ( CLPixelWiseMultiplication &&  )

default

Default move constructor.

Member Function Documentation

configure() [1/2]

void configure	(	const CLCompileContext &	compile_context,
		ICLTensor *	input1,
		ICLTensor *	input2,
		ICLTensor *	output,
		float	scale,
		ConvertPolicy	overflow_policy,
		RoundingPolicy	rounding_policy,
		const ActivationLayerInfo &	act_info = ActivationLayerInfo()
	)

Initialise the kernel's inputs, output and convertion policy.

Parameters

[in]	compile_context	The compile context to be used.
[in,out]	input1	An input tensor. Data types supported: U8/QASYMM8/QASYMM8_SIGNED/S16/QSYMM16/F16/F32/S32 The input tensor is [in, out] because its TensorInfo might be modified inside the kernel in case of broadcasting of dimension 0.
[in,out]	input2	An input tensor. Data types supported: U8/QASYMM8/QASYMM8_SIGNED/S16/QSYMM16/F16/F32/S32 The input tensor is [in, out] because its TensorInfo might be modified inside the kernel in case of broadcasting of dimension 0.
[out]	output	The output tensor. Data types supported: U8/QASYMM8/QASYMM8_SIGNED/S16/QSYMM16/F16/F32/S32
[in]	scale	Scale to apply after multiplication. Scale must be positive and its value must be either 1/255 or 1/2^n where n is between 0 and 15.
[in]	overflow_policy	Overflow policy. Supported overflow policies: Wrap, Saturate
[in]	rounding_policy	Rounding policy. Supported rounding modes: to zero, to nearest even.
[in]	act_info	(Optional) Activation layer information in case of a fused activation.

Definition at line 57 of file CLPixelWiseMultiplication.cpp.

{
    _impl->src_0 = input1;
    _impl->src_1 = input2;
    _impl->dst   = output;
    _impl->op    = std::make_unique<opencl::ClMul>();
    _impl->op->configure(compile_context, input1->info(), input2->info(), output->info(), scale, overflow_policy, rounding_policy, act_info);
}

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

configure() [2/2]

void configure	(	ICLTensor *	input1,
		ICLTensor *	input2,
		ICLTensor *	output,
		float	scale,
		ConvertPolicy	overflow_policy,
		RoundingPolicy	rounding_policy,
		const ActivationLayerInfo &	act_info = ActivationLayerInfo()
	)

Initialise the kernel's inputs, output and convertion policy.

Valid data layouts:

• All

Valid data type configurations:

src0	src1	dst
QASYMM8	QASYMM8	QASYMM8
QASYMM8_SIGNED	QASYMM8_SIGNED	QASYMM8_SIGNED
QSYMM16	QSYMM16	QASYMM16
QSYMM16	QSYMM16	S32
U8	U8	U8
U8	U8	S16
U8	S16	S16
S16	U8	S16
S16	S16	S16
F16	F16	F16
F32	F32	F32
S32	S32	S32

Parameters

[in,out]	input1	An input tensor. Data types supported: U8/QASYMM8/QASYMM8_SIGNED/S16/QSYMM16/F16/F32/S32 The input tensor is [in, out] because its TensorInfo might be modified inside the kernel in case of broadcasting of dimension 0.
[in,out]	input2	An input tensor. Data types supported: U8/QASYMM8/QASYMM8_SIGNED/S16/QSYMM16/F16/F32/S32 The input tensor is [in, out] because its TensorInfo might be modified inside the kernel in case of broadcasting of dimension 0.
[out]	output	The output tensor. Data types supported: U8/QASYMM8/QASYMM8_SIGNED/S16/QSYMM16/F16/F32/S32
[in]	scale	Scale to apply after multiplication. Scale must be positive and its value must be either 1/255 or 1/2^n where n is between 0 and 15.
[in]	overflow_policy	Overflow policy. Supported overflow policies: Wrap, Saturate
[in]	rounding_policy	Rounding policy. Supported rounding modes: to zero, to nearest even.
[in]	act_info	(Optional) Activation layer information in case of a fused activation.

Definition at line 51 of file CLPixelWiseMultiplication.cpp.

{
    configure(CLKernelLibrary::get().get_compile_context(), input1, input2, output, scale, overflow_policy, rounding_policy, act_info);
}

References arm_compute::test::validation::act_info, CLKernelLibrary::get(), and arm_compute::test::validation::scale.

Referenced by CLLSTMLayerQuantized::configure(), CLLSTMLayer::configure(), and CLQLSTMLayer::configure().

operator=() [1/2]

CLPixelWiseMultiplication & operator= ( CLPixelWiseMultiplication &&  )

default

Default move assignment operator.

operator=() [2/2]

CLPixelWiseMultiplication& operator= ( const CLPixelWiseMultiplication &  )

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 73 of file CLPixelWiseMultiplication.cpp.

{
    ITensorPack pack;
    pack.add_tensor(TensorType::ACL_SRC_0, _impl->src_0);
    pack.add_tensor(TensorType::ACL_SRC_1, _impl->src_1);
    pack.add_tensor(TensorType::ACL_DST, _impl->dst);
 
    _impl->op->run(pack);
}

References arm_compute::ACL_DST, arm_compute::ACL_SRC_0, arm_compute::ACL_SRC_1, ITensorPack::add_tensor(), and arm_compute::test::validation::pack.

Referenced by CLLSTMLayerQuantized::run(), CLLSTMLayer::run(), and CLQLSTMLayer::run().

validate()

Status validate ( const ITensorInfo *  input1, const ITensorInfo *  input2, const ITensorInfo *  output, float  scale, ConvertPolicy  overflow_policy, RoundingPolicy  rounding_policy, const ActivationLayerInfo &  act_info = ActivationLayerInfo()  )

static

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

Parameters

[in]	input1	An input tensor info. Data types supported: U8/QASYMM8/QASYMM8_SIGNED/S16/QSYMM16/F16/F32.
[in]	input2	An input tensor info. Data types supported: U8/QASYMM8/QASYMM8_SIGNED/S16/QSYMM16/F16/F32.
[in]	output	The output tensor info. Data types supported: U8/QASYMM8/QASYMM8_SIGNED/S16/QSYMM16/F16/F32.
[in]	scale	Scale to apply after multiplication. Scale must be positive and its value must be either 1/255 or 1/2^n where n is between 0 and 15.
[in]	overflow_policy	Overflow policy. Supported overflow policies: Wrap, Saturate
[in]	rounding_policy	Rounding policy. Supported rounding modes: to zero, to nearest even.
[in]	act_info	(Optional) Activation layer information in case of a fused activation.

Returns

a status

Definition at line 67 of file CLPixelWiseMultiplication.cpp.

{
    return opencl::ClMul::validate(input1, input2, output, scale, overflow_policy, rounding_policy, act_info);
}

References arm_compute::test::validation::act_info, arm_compute::test::validation::scale, and ClMul::validate().

Referenced by CLLSTMLayerQuantized::validate(), CLLSTMLayer::validate(), and CLQLSTMLayer::validate().

---

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

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