This stage filters the projections in the parallel beam sinogram with a precomputed filter function. More...

#include <Filter.h>

Collaboration diagram for risa::cuda::Filter:

Public Types
using	input_type = glados::Image< glados::cuda::DeviceMemoryManager< float, glados::cuda::async_copy_policy >>
	The input data type that needs to fit the output type of the previous stage. More...

using	output_type = glados::Image< glados::cuda::DeviceMemoryManager< float, glados::cuda::async_copy_policy >>
	The output data type that needs to fit the input type of the following stage. More...

Public Member Functions
	Filter (const std::string &configFile)
	Initializes everything, that needs to be done only once. More...

	~Filter ()
	Destroys everything that is not destroyed automatically. More...

auto	process (input_type &&sinogram) -> void
	Pushes the filtered parallel beam sinogram to the processor-threads. More...

auto	wait () -> output_type
	Takes one image from the output queue results_ and transfers it to the neighbored stage. More...

Private Member Functions
auto	processor (const int deviceID) -> void
	main data processing routine executed in its own thread for each CUDA device, that performs the data processing of this stage More...

auto	initCuFFT (const int deviceID) -> void
	initializes the cuFFT and creates the forward and inverse plans once for each deviceID More...

auto	readConfig (const std::string &configFile) -> bool
	Read configuration values from configuration file. More...

auto	designFilter () -> void

Private Attributes
std::map< int, glados::Queue< input_type > >	sinograms_
	one separate input queue for each available CUDA device More...

glados::Queue< output_type >	results_
	the output queue in which the processed sinograms are stored More...

std::map< int, std::thread >	processorThreads_
	stores the processor()-threads More...

int	numberOfProjections_
	the number of projections in the parallel beam sinogramm over 180 degrees More...

int	numberOfDetectors_
	the number of detectors in the parallel beam sinogramm over 180 degrees More...

int	numberOfPixels_
	the number of pixels in the reconstruction grid in one dimension More...

detail::FilterType	filterType_
	the filter type that shall be used; standarf filter type is the ramp filter. More...

float	cutoffFraction_
	the fraction at which the filter function is cropped and set to zero. More...

int	numberOfDevices_
	the number of available CUDA devices in the system More...

int	blockSize2D_
	the block size of the filter kernel More...

std::map< int, cufftHandle >	plansFwd_
	the forward plans for the cuFFT forward transformation; for each device one; More...

std::map< int, cufftHandle >	plansInv_
	the inverse plans for the cuFFT inverse tranformation; for each device one; More...

std::map< int, cudaStream_t >	streams_
	stores the cudaStreams that are created once More...

std::vector< float >	filter_
	stores the values of the filter function More...

Detailed Description

This stage filters the projections in the parallel beam sinogram with a precomputed filter function.

Definition at line 57 of file Filter.h.

Member Typedef Documentation

using risa::cuda::Filter::input_type = glados::Image<glados::cuda::DeviceMemoryManager<float, glados::cuda::async_copy_policy>>

The input data type that needs to fit the output type of the previous stage.

Definition at line 60 of file Filter.h.

using risa::cuda::Filter::output_type = glados::Image<glados::cuda::DeviceMemoryManager<float, glados::cuda::async_copy_policy>>

The output data type that needs to fit the input type of the following stage.

Definition at line 62 of file Filter.h.

Constructor & Destructor Documentation

risa::cuda::Filter::Filter ( const std::string & configFile )

Initializes everything, that needs to be done only once.

Runs as many processor-thread as CUDA devices are available in the system.

Parameters

[in] configFile path to configuration file

Definition at line 44 of file Filter.cu.

risa::cuda::Filter::~Filter ( )

Destroys everything that is not destroyed automatically.

Destroys the cudaStreams.

Definition at line 67 of file Filter.cu.

Member Function Documentation

auto risa::cuda::Filter::designFilter ( ) -> void

private

Definition at line 169 of file Filter.cu.

auto risa::cuda::Filter::initCuFFT ( const int deviceID ) -> void

private

initializes the cuFFT and creates the forward and inverse plans once for each deviceID

Parameters

[in] deviceID the ID of the device that shall be initialized for cuFFT

Definition at line 145 of file Filter.cu.

auto risa::cuda::Filter::process ( input_type && sinogram ) -> void

Pushes the filtered parallel beam sinogram to the processor-threads.

Parameters

[in] inp input data that arrived from previous stage

Definition at line 77 of file Filter.cu.

auto risa::cuda::Filter::processor ( const int deviceID ) -> void

private

main data processing routine executed in its own thread for each CUDA device, that performs the data processing of this stage

This method takes one sinogram from the queue. It calls the desired filter CUDA kernel in its own stream. After the computation of the filtered projections the filtered parallel sinogram is pushed into the output queue

Parameters

[in] deviceID specifies on which CUDA device to execute the device functions

Definition at line 102 of file Filter.cu.

auto risa::cuda::Filter::readConfig ( const std::string & configFile ) -> bool

private

Read configuration values from configuration file.

CUDA Kernel that weights all the projections with the filter function.

All values needed for setting up the class are read from the config file in this function. If an invalid filter function is requested, the ramp filter is used.

Parameters

[in] configFile path to config file

Return values

true	configuration options were read successfully
false	configuration options could not be read successfullyThis function computes the requested filter function once on the host

Definition at line 193 of file Filter.cu.

auto risa::cuda::Filter::wait ( ) -> output_type

Takes one image from the output queue results_ and transfers it to the neighbored stage.

Returns: the oldest reconstructed image in the output queue results_

Definition at line 98 of file Filter.cu.

Member Data Documentation

int risa::cuda::Filter::blockSize2D_

private

the block size of the filter kernel

Definition at line 109 of file Filter.h.

float risa::cuda::Filter::cutoffFraction_

private

the fraction at which the filter function is cropped and set to zero.

Definition at line 104 of file Filter.h.

std::vector<float> risa::cuda::Filter::filter_

private

stores the values of the filter function

Definition at line 116 of file Filter.h.

detail::FilterType risa::cuda::Filter::filterType_

private

the filter type that shall be used; standarf filter type is the ramp filter.

Definition at line 103 of file Filter.h.

int risa::cuda::Filter::numberOfDetectors_

private

the number of detectors in the parallel beam sinogramm over 180 degrees

Definition at line 100 of file Filter.h.

int risa::cuda::Filter::numberOfDevices_

private

the number of available CUDA devices in the system

Definition at line 106 of file Filter.h.

int risa::cuda::Filter::numberOfPixels_

private

the number of pixels in the reconstruction grid in one dimension

Definition at line 101 of file Filter.h.

int risa::cuda::Filter::numberOfProjections_

private

the number of projections in the parallel beam sinogramm over 180 degrees

Definition at line 99 of file Filter.h.

std::map<int, cufftHandle> risa::cuda::Filter::plansFwd_

private

the forward plans for the cuFFT forward transformation; for each device one;

Definition at line 111 of file Filter.h.

std::map<int, cufftHandle> risa::cuda::Filter::plansInv_

private

the inverse plans for the cuFFT inverse tranformation; for each device one;

Definition at line 112 of file Filter.h.

std::map<int, std::thread> risa::cuda::Filter::processorThreads_

private

stores the processor()-threads

Definition at line 97 of file Filter.h.

glados::Queue<output_type> risa::cuda::Filter::results_

private

the output queue in which the processed sinograms are stored

Definition at line 95 of file Filter.h.

std::map<int, glados::Queue<input_type> > risa::cuda::Filter::sinograms_

private

one separate input queue for each available CUDA device

Definition at line 94 of file Filter.h.

std::map<int, cudaStream_t> risa::cuda::Filter::streams_

private

stores the cudaStreams that are created once

Definition at line 114 of file Filter.h.

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

/home/frust45/RISA/RISA/risaLib/include/risa/Filter/Filter.h
/home/frust45/RISA/RISA/risaLib/src/Filter/Filter.cu

Public Types

Public Member Functions

Private Member Functions

Private Attributes

Detailed Description

Member Typedef Documentation

Constructor & Destructor Documentation

Member Function Documentation

Member Data Documentation