21.02
|
Basic function to execute NEGEMMLowpQuantizeDownInt32ToInt8ScaleByFixedPoint on Neon. More...
#include <NEGEMMLowpOutputStage.h>
Public Member Functions | |
NEGEMMLowpQuantizeDownInt32ToInt8ScaleByFixedPoint ()=default | |
Constructor. More... | |
NEGEMMLowpQuantizeDownInt32ToInt8ScaleByFixedPoint (const NEGEMMLowpQuantizeDownInt32ToInt8ScaleByFixedPoint &)=delete | |
Prevent instances of this class from being copied (As this class contains pointers) More... | |
NEGEMMLowpQuantizeDownInt32ToInt8ScaleByFixedPoint & | operator= (const NEGEMMLowpQuantizeDownInt32ToInt8ScaleByFixedPoint &)=delete |
Prevent instances of this class from being copied (As this class contains pointers) More... | |
NEGEMMLowpQuantizeDownInt32ToInt8ScaleByFixedPoint (NEGEMMLowpQuantizeDownInt32ToInt8ScaleByFixedPoint &&)=delete | |
Prevent instances of this class from being moved (As this class contains non movable objects) More... | |
NEGEMMLowpQuantizeDownInt32ToInt8ScaleByFixedPoint & | operator= (NEGEMMLowpQuantizeDownInt32ToInt8ScaleByFixedPoint &&)=delete |
Prevent instances of this class from being moved (As this class contains non movable objects) More... | |
~NEGEMMLowpQuantizeDownInt32ToInt8ScaleByFixedPoint () | |
Default destructor. More... | |
void | configure (const ITensor *input, const ITensor *bias, ITensor *output, int result_fixedpoint_multiplier, int result_shift, int result_offset_after_shift, int min=std::numeric_limits< int32_t >::lowest(), int max=std::numeric_limits< int32_t >::max()) |
Initialise the kernel's inputs, output. More... | |
Public Member Functions inherited from INESimpleFunctionNoBorder | |
INESimpleFunctionNoBorder (IRuntimeContext *ctx=nullptr) | |
Constructor. More... | |
INESimpleFunctionNoBorder (const INESimpleFunctionNoBorder &)=delete | |
Prevent instances of this class from being copied (As this class contains pointers) More... | |
INESimpleFunctionNoBorder (INESimpleFunctionNoBorder &&)=default | |
Default move constructor. More... | |
INESimpleFunctionNoBorder & | operator= (const INESimpleFunctionNoBorder &)=delete |
Prevent instances of this class from being copied (As this class contains pointers) More... | |
INESimpleFunctionNoBorder & | operator= (INESimpleFunctionNoBorder &&)=default |
Default move assignment operator. More... | |
~INESimpleFunctionNoBorder () | |
Default destructor. More... | |
void | run () override final |
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 *bias, const ITensorInfo *output, int min=std::numeric_limits< int32_t >::lowest(), int max=std::numeric_limits< int32_t >::max()) |
Static function to check if given info will lead to a valid configuration of NEGEMMLowpQuantizeDownInt32ToInt8ScaleByFixedPoint. More... | |
Basic function to execute NEGEMMLowpQuantizeDownInt32ToInt8ScaleByFixedPoint on Neon.
NEGEMMLowpQuantizeDownInt32ToInt8ScaleByFixedPoint depends on 3 parameters:
result_fixedpoint_multiplier, result_shift, result_offset_after_shift
The final result is:
(FixedPointMul(input[i][k], result_fixedpoint_multiplier) >> result_shift) + result_offset_after_shift
where FixedPointMul(x, y) is the nearest integer to the following mathematical expression, evaluated without overflow or intermediate rounding:
(x * y) / 2^31
For more information: https://github.com/google/gemmlowp/blob/master/public/output_stages.h#L68
In case the bias tensor is provided, the final result is:
((FixedPointMul(input[i][k] + bias[k], result_fixedpoint_multiplier)) >> result_shift) + result_offset_after_shift
This function calls the following Neon kernels:
Definition at line 143 of file NEGEMMLowpOutputStage.h.
Constructor.
|
delete |
Prevent instances of this class from being copied (As this class contains pointers)
|
delete |
Prevent instances of this class from being moved (As this class contains non movable objects)
|
default |
Default destructor.
Referenced by NEGEMMLowpQuantizeDownInt32ToUint8ScaleByFixedPoint::validate().
void configure | ( | const ITensor * | input, |
const ITensor * | bias, | ||
ITensor * | output, | ||
int | result_fixedpoint_multiplier, | ||
int | result_shift, | ||
int | result_offset_after_shift, | ||
int | min = std::numeric_limits<int32_t>::lowest() , |
||
int | max = std::numeric_limits<int32_t>::max() |
||
) |
Initialise the kernel's inputs, output.
[in] | input | Input tensor. Data type supported: S32 |
[in] | bias | Biases tensor. Only shared biases supported and it can be a nullptr if the biases addition is not required. Biases are 1D tensor with dimensions [OFM]. Data type supported: Same as input . |
[out] | output | Output tensor. Data type supported: Data type supported: QASYMM8_SIGNED |
[in] | result_fixedpoint_multiplier | Fixed point value to be multiplied to each element of the input matrix when once the result_offset has been add |
[in] | result_shift | Number of bits to shift right the result after the fixed point multiplication |
[in] | result_offset_after_shift | Offset to be applied to result before converting it back to QASYMM8_SIGNED |
[in] | min | (Optional) Min value used to saturate down the output result before converting back to QASYMM8_SIGNED. Defaults to the minimum possible 32-bit signed integer. |
[in] | max | (Optional) Max value used to saturate up the output result before converting back to QASYMM8_SIGNED, Along with min , this value can be used to implement "rectified linear unit" activation functions. Defaults to the maximum possible 32-bit signed integer. |
Definition at line 52 of file NEGEMMLowpOutputStage.cpp.
|
delete |
Prevent instances of this class from being copied (As this class contains pointers)
|
delete |
Prevent instances of this class from being moved (As this class contains non movable objects)
|
static |
Static function to check if given info will lead to a valid configuration of NEGEMMLowpQuantizeDownInt32ToInt8ScaleByFixedPoint.
[in] | input | Input tensor. It is the output of NEGEMMLowpMatrixMultiplyCore function. Data type supported: S32 |
[in] | bias | Biases tensor. Only shared biases supported and it can be a nullptr if the addition of biases is not required. Biases are 1D tensor with dimensions [OFM]. Data type supported: Same as input . |
[in] | output | Output tensor. Data type supported: Data type supported: QASYMM8_SIGNED |
[in] | min | (Optional) Min value used to saturate down the output result before converting back to QASYMM8_SIGNED. Defaults to the minimum possible 32-bit signed integer. |
[in] | max | (Optional) Max value used to saturate up the output result before converting back to QASYMM8_SIGNED, Along with min , this value can be used to implement "rectified linear unit" activation functions. Defaults to the maximum possible 32-bit signed integer. |
Definition at line 60 of file NEGEMMLowpOutputStage.cpp.
References NEGEMMLowpQuantizeDownInt32ToInt8ScaleByFixedPointKernel::validate(), and NEGEMMLowpQuantizeDownInt32ToInt16ScaleByFixedPoint::~NEGEMMLowpQuantizeDownInt32ToInt16ScaleByFixedPoint().
Referenced by arm_compute::test::validation::DATA_TEST_CASE().