A framework to accelerate FP32 deconvolution in Synet Framework. More...

Functions
SIMD_API void *	SimdSynetDeconvolution32fInit (size_t batch, const SimdConvolutionParameters *conv, SimdSynetCompatibilityType compatibility)
	Initializes an FP32 deconvolution context. More...

SIMD_API size_t	SimdSynetDeconvolution32fExternalBufferSize (const void *context)
	Gets the size of caller-provided temporary buffer for FP32 deconvolution. More...

SIMD_API size_t	SimdSynetDeconvolution32fInternalBufferSize (const void *context)
	Gets the size of internal storage used by an FP32 deconvolution context. More...

SIMD_API const char *	SimdSynetDeconvolution32fInfo (const void *context)
	Gets a short description of the selected FP32 deconvolution implementation. More...

SIMD_API void	SimdSynetDeconvolution32fSetParams (void context, const float weight, SimdBool internal, const float bias, const float *params)
	Sets weights, bias and activation parameters for FP32 deconvolution. More...

SIMD_API void	SimdSynetDeconvolution32fForward (void context, const float src, float buf, float dst)
	Performs forward propagation of FP32 deconvolution. More...

Detailed Description

A framework to accelerate FP32 deconvolution in Synet Framework.

Function Documentation

◆ SimdSynetDeconvolution32fInit()

void * SimdSynetDeconvolution32fInit	(	size_t	batch,
		const SimdConvolutionParameters *	conv,
		SimdSynetCompatibilityType	compatibility
	)

Initializes an FP32 deconvolution context.

The function validates deconvolution parameters and chooses a suitable implementation (GEMM-based or NHWC direct 2x2 when available). It supports FP32 source and destination tensors with matching NCHW format, or matching NHWC format when group is 1. The destination spatial size must match deconvolution parameters:

dstH = strideY*(srcH - 1) + dilationY*(kernelY - 1) + 1 - padY - padH
dstW = strideX*(srcW - 1) + dilationX*(kernelX - 1) + 1 - padX - padW

A created context stores tensor shape, format, deconvolution geometry, group count, activation type and compatibility flags. Weights, bias and activation parameters are attached later by SimdSynetDeconvolution32fSetParams.

Parameters

[in]	batch	- a batch size.
[in]	conv	- a pointer to deconvolution parameters. Source and destination tensor types must be FP32.
[in]	compatibility	- calculation compatibility flags.

Returns: a pointer to FP32 deconvolution context. On error it returns NULL. It must be released with using of function SimdRelease. This pointer is used in functions SimdSynetDeconvolution32fExternalBufferSize, SimdSynetDeconvolution32fInternalBufferSize, SimdSynetDeconvolution32fInfo, SimdSynetDeconvolution32fSetParams and SimdSynetDeconvolution32fForward.

◆ SimdSynetDeconvolution32fExternalBufferSize()

size_t SimdSynetDeconvolution32fExternalBufferSize ( const void * context )

Gets the size of caller-provided temporary buffer for FP32 deconvolution.

The returned value is a number of 32-bit float elements, not bytes. It depends on the implementation selected during initialization and can be used to allocate the buf argument of SimdSynetDeconvolution32fForward. Some implementations return 1 when they do not need external temporary storage.

Parameters

[in] context - a pointer to FP32 deconvolution context. It must be created by function SimdSynetDeconvolution32fInit and released by function SimdRelease.

Returns: a number of FP32 elements required for external temporary buffer.

◆ SimdSynetDeconvolution32fInternalBufferSize()

size_t SimdSynetDeconvolution32fInternalBufferSize ( const void * context )

Gets the size of internal storage used by an FP32 deconvolution context.

The returned value is a number of 32-bit float elements, not bytes. It reports internal storage tracked by the selected implementation, such as internal temporary buffers and implementation-specific reordered weights, bias or activation parameters already allocated by the context.

Parameters

[in] context - a pointer to FP32 deconvolution context. It must be created by function SimdSynetDeconvolution32fInit and released by function SimdRelease.

Returns: a number of FP32 elements used by internal buffers.

◆ SimdSynetDeconvolution32fInfo()

const char * SimdSynetDeconvolution32fInfo ( const void * context )

Gets a short description of the selected FP32 deconvolution implementation.

The returned string contains the implementation extension and algorithm name, for example a GEMM-based or NHWC direct 2x2 variant. The returned pointer is owned by the context and remains valid until the next call of this function for the same context or until the context is released.

Parameters

[in] context - a pointer to FP32 deconvolution context. It must be created by function SimdSynetDeconvolution32fInit and released by function SimdRelease.

Returns: a string with description of internal implementation of FP32 deconvolution algorithm.

◆ SimdSynetDeconvolution32fSetParams()

void SimdSynetDeconvolution32fSetParams	(	void *	context,
		const float *	weight,
		SimdBool *	internal,
		const float *	bias,
		const float *	params
	)

Sets weights, bias and activation parameters for FP32 deconvolution.

This function must be called before SimdSynetDeconvolution32fForward. The weight array contains FP32 deconvolution weights with kernelY*kernelX*srcC*dstC/group elements. Depending on the selected implementation, weights can be used directly or transformed and stored inside the context. If internal is not NULL, the selected implementation writes the weight storage mode to it: SimdTrue means that weights were transformed and stored internally, while SimdFalse means that the implementation may use the original weight array directly, so the caller must keep it valid for later forward calls. Bias and activation parameters can also be copied internally by some implementations; otherwise their pointers are stored in the context.

Parameters

[in,out]	context	- a pointer to FP32 deconvolution context. It must be created by function SimdSynetDeconvolution32fInit and released by function SimdRelease.
[in]	weight	- a pointer to FP32 deconvolution weights.
[out]	internal	- a pointer to a flag receiving weight ownership mode. Can be NULL.
[in]	bias	- a pointer to FP32 bias array with dstC elements. Can be NULL.
[in]	params	- a pointer to FP32 parameters of activation function (see SimdConvolutionActivationType). Can be NULL when activation does not require parameters.

◆ SimdSynetDeconvolution32fForward()

void SimdSynetDeconvolution32fForward	(	void *	context,
		const float *	src,
		float *	buf,
		float *	dst
	)

Performs forward propagation of FP32 deconvolution.

The function applies transposed convolution to each image in the batch, adds bias when it was set, and applies the activation specified in SimdConvolutionParameters:

dst[:] = 0;
for(sc = 0; sc < srcC/group; ++sc)
    for(sy = 0; sy < srcH; ++sy)
        for(sx = 0; sx < srcW; ++sx)
            for(ky = 0; ky < kernelY; ++ky)
                for(kx = 0; kx < kernelX; ++kx)
                    dst[outputOffset] += src[inputOffset] * weight[weightOffset];
dst[outputOffset] = Activate(dst[outputOffset] + bias[dc], activation, params);

The exact offsets depend on tensor format, padding, dilation, stride and group. The input and output tensors use the shape and format from the context created by SimdSynetDeconvolution32fInit.

Parameters

[in]	context	- a pointer to FP32 deconvolution context. It must be created by function SimdSynetDeconvolution32fInit and released by function SimdRelease.
[in]	src	- a pointer to FP32 input tensor.
[out]	buf	- a pointer to external temporary FP32 buffer. The required number of elements is determined by function SimdSynetDeconvolution32fExternalBufferSize. Can be NULL (it causes usage of internal buffer).
[out]	dst	- a pointer to FP32 output tensor.

Simd Library Documentation.

Functions

Detailed Description

Function Documentation

◆ SimdSynetDeconvolution32fInit()

◆ SimdSynetDeconvolution32fExternalBufferSize()

◆ SimdSynetDeconvolution32fInternalBufferSize()

◆ SimdSynetDeconvolution32fInfo()

◆ SimdSynetDeconvolution32fSetParams()

◆ SimdSynetDeconvolution32fForward()