Quantized merged convolution framework

A framework to accelerate Quantized merged convolution in Synet Framework. More...

Functions
SIMD_API void *	SimdSynetQuantizedMergedConvolutionInit (size_t batch, const SimdConvolutionParameters *convs, size_t count, SimdBool add)
	Initilizes Quantized merged convolution algorithm. More...
SIMD_API size_t	SimdSynetQuantizedMergedConvolutionExternalBufferSize (const void *context)
	Gets size of external temporary buffer required for Quantized merged convolution algorithm. More...
SIMD_API size_t	SimdSynetQuantizedMergedConvolutionInternalBufferSize (const void *context)
	Gets size of internal buffer used inside Quantized merged convolution algorithm. More...
SIMD_API const char *	SimdSynetQuantizedMergedConvolutionInfo (const void *context)
	Gets description of internal implementation of Quantized merged convolution algorithm. More...
SIMD_API void	SimdSynetQuantizedMergedConvolutionSetParams (void *context, const float *ioScale, const uint8_t *ioZero, const int8_t *const *weight, const float *const *weightScale, const int32_t *const *bias)
	Sets weights, biases, input/output parameters required for Quantized merged convolution algorithm. More...
SIMD_API void	SimdSynetQuantizedMergedConvolutionForward (void *context, const uint8_t *src, uint8_t *buf, uint8_t *dst)
	Performs forward propagation of Quantized merged convolution algorithm. More...

Detailed Description

A framework to accelerate Quantized merged convolution in Synet Framework.

Function Documentation

SimdSynetQuantizedMergedConvolutionInit()

void * SimdSynetQuantizedMergedConvolutionInit	(	size_t	batch,
		const SimdConvolutionParameters *	convs,
		size_t	count,
		SimdBool	add
	)

Initilizes Quantized merged convolution algorithm.

Parameters

[in]	batch	- a batch size.
[in]	convs	- an array with convolutions parameters.
[in]	count	- a number of merged convolutions.
[in]	add	- a flag that signilizes if we need to add source to output value.

Returns

a pointer to Quantized merged convolution context. On error it returns NULL. It must be released with using of function SimdRelease. This pointer is used in functions SimdSynetQuantizedMergedConvolutionExternalBufferSize, SimdSynetQuantizedMergedConvolutionInternalBufferSize, SimdSynetQuantizedMergedConvolutionInfo, SimdSynetQuantizedMergedConvolutionSetParams and SimdSynetQuantizedMergedConvolutionForward.

SimdSynetQuantizedMergedConvolutionExternalBufferSize()

size_t SimdSynetQuantizedMergedConvolutionExternalBufferSize

(

const void *

context

)

Gets size of external temporary buffer required for Quantized merged convolution algorithm.

Parameters

[in]

context

- a pointer to Quantized merged convolution context. It must be created by function SimdSynetQuantizedMergedConvolutionInit and released by function SimdRelease.

Returns

size of external temporary buffer required for Quantized merged convolution algorithm.

SimdSynetQuantizedMergedConvolutionInternalBufferSize()

size_t SimdSynetQuantizedMergedConvolutionInternalBufferSize

(

const void *

context

)

Gets size of internal buffer used inside Quantized merged convolution algorithm.

Parameters

[in]

context

- a pointer to Quantized merged convolution context. It must be created by function SimdSynetQuantizedMergedConvolutionInit and released by function SimdRelease.

Returns

size of internal buffer used inside Quantized merged convolution algorithm.

SimdSynetQuantizedMergedConvolutionInfo()

const char * SimdSynetQuantizedMergedConvolutionInfo

(

const void *

context

)

Gets description of internal implementation of Quantized merged convolution algorithm.

Parameters

[in]

context

- a pointer to Quantized merged convolution context. It must be created by function SimdSynetQuantizedMergedConvolutionInit and released by function SimdRelease.

Returns

string with description of internal implementation of Quantized merged convolution algorithm.

SimdSynetQuantizedMergedConvolutionSetParams()

void SimdSynetQuantizedMergedConvolutionSetParams	(	void *	context,
		const float *	ioScale,
		const uint8_t *	ioZero,
		const int8_t *const *	weight,
		const float *const *	weightScale,
		const int32_t *const *	bias
	)

Sets weights, biases, input/output parameters required for Quantized merged convolution algorithm.

Parameters

[in,out]	context	- a pointer to Quantized merged convolution context. It must be created by function SimdSynetQuantizedMergedConvolutionInit and released by function SimdRelease.
[in]	ioScale	- a pointer to 32-bit float point input/output tensors scales.
[in]	ioZero	- a pointer to 8-bit unsigned integer input/output tensors zeros.
[in]	weight	- a pointer to 8-bit integer convolution weights.
[in]	weightScale	- a pointer to 32-bit float point weight scales.
[in]	bias	- a pointer to 32-bit integer biases.

SimdSynetQuantizedMergedConvolutionForward()

void SimdSynetQuantizedMergedConvolutionForward	(	void *	context,
		const uint8_t *	src,
		uint8_t *	buf,
		uint8_t *	dst
	)

Performs forward propagation of Quantized merged convolution algorithm.

Parameters

[in]	context	- a pointer to Quantized merged convolution context. It must be created by function SimdSynetQuantizedMergedConvolutionInit and released by function SimdRelease.
[in]	src	- a pointer to input tensor.
[out]	buf	- a pointer to external temporary buffer. The size of the external temporary buffer is determined by function SimdSynetQuantizedMergedConvolutionExternalBufferSize. Can be NULL (it causes usage of internal buffer).
[out]	dst	- a pointer to output tensor.