A framework to accelerate Quantized addition in Synet Framework. More...

Functions
SIMD_API void *	SimdSynetQuantizedAddInit (const size_t aShape, size_t aCount, SimdTensorDataType aType, const float aScale, int32_t aZero, const size_t bShape, size_t bCount, SimdTensorDataType bType, const float bScale, int32_t bZero, SimdConvolutionActivationType actType, const float actParams, SimdTensorDataType dstType, const float dstScale, int32_t dstZero)
	Initilizes quantized addition algorithm. More...

SIMD_API void	SimdSynetQuantizedAddForward (void context, const uint8_t a, const uint8_t b, uint8_t dst)
	Performs forward propagation of quantized addition algorithm. More...

Detailed Description

A framework to accelerate Quantized addition in Synet Framework.

Function Documentation

void * SimdSynetQuantizedAddInit	(	const size_t *	aShape,
		size_t	aCount,
		SimdTensorDataType	aType,
		const float *	aScale,
		int32_t	aZero,
		const size_t *	bShape,
		size_t	bCount,
		SimdTensorDataType	bType,
		const float *	bScale,
		int32_t	bZero,
		SimdConvolutionActivationType	actType,
		const float *	actParams,
		SimdTensorDataType	dstType,
		const float *	dstScale,
		int32_t	dstZero
	)

Initilizes quantized addition algorithm.

Parameters

[in]	aShape	- a pointer to shape of input A tensor.
[in]	aCount	- a count of dimensions of input A tensor.
[in]	aType	- a type of input A tensor. Can be FP32 of UINT8.
[in]	aScale	- a quantization scale parameter of A tensor.
[in]	aZero	- a quantization zero parameter of A tensor.
[in]	bShape	- a pointer to shape of input B tensor.
[in]	bCount	- a count of dimensions of input B tensor.
[in]	bType	- a type of input B tensor. Can be FP32 of UINT8.
[in]	bScale	- a quantization scale parameter of B tensor.
[in]	bZero	- a quantization zero parameter of B tensor.
[in]	actType	- an activation function type (if it merged to quantized addition).
[in]	actParams	- a pointer to activation function parameters. Can be NULL.
[in]	dstType	- a type of output tensor. Can be FP32 of UINT8.
[in]	dstScale	- an output quantization scale.
[in]	dstZero	- an output quantization zero.

Returns: a pointer to quantized addition context. On error it returns NULL. It must be released with using of function SimdRelease. This pointer is used in function SimdSynetQuantizedAddForward.

void SimdSynetQuantizedAddForward	(	void *	context,
		const uint8_t *	a,
		const uint8_t *	b,
		uint8_t *	dst
	)

Performs forward propagation of quantized addition algorithm.

Parameters

[in]	context	- a pointer to quantized addition context. It must be created by function SimdSynetQuantizedAddInit and released by function SimdRelease.
[in]	a	- a pointer to input A tensor.
[in]	b	- a pointer to input B tensor.
[out]	dst	- a pointer to output tensor.