Class CudaRandDevice

Wrapper for a CUrand generator handle in device mode

Inheritance

System.Object

CudaRandDevice

Implements

System.IDisposable

Inherited Members

System.Object.Equals(System.Object)

System.Object.Equals(System.Object, System.Object)

System.Object.GetHashCode()

System.Object.GetType()

System.Object.MemberwiseClone()

System.Object.ReferenceEquals(System.Object, System.Object)

System.Object.ToString()

Namespace: ManagedCuda.CudaRand

Assembly: CudaRand.dll

Syntax

public class CudaRandDevice : IDisposable

Constructors

| Improve this Doc View Source

CudaRandDevice(GeneratorType)

Creates a new random number generator of type Type

Declaration

public CudaRandDevice(GeneratorType Type)

Parameters

Type	Name	Description
GeneratorType	Type	Generator type

Properties

| Improve this Doc View Source

Generator

Returns the wrapped curand generator handle

Declaration

public CurandGenerator Generator { get; }

Property Value

Type	Description
CurandGenerator

Methods

| Improve this Doc View Source

Dispose()

Dispose

Declaration

public void Dispose()

| Improve this Doc View Source

Dispose(Boolean)

For IDisposable

Declaration

protected virtual void Dispose(bool fDisposing)

Parameters

Type	Name	Description
System.Boolean	fDisposing

| Improve this Doc View Source

Finalize()

For dispose

Declaration

protected void Finalize()

| Improve this Doc View Source

Generate(CudaDeviceVariable<UInt32>)

Use generator to generate num 32-bit results into the device memory at output. The device memory must have been previously allocated and be large enough to hold all the results. Launches are done with the stream set using SetStream(CUstream), or the null stream if no stream has been set.

Results are 32-bit values with every bit random.

Declaration

public void Generate(CudaDeviceVariable<uint> output)

Parameters

Type	Name	Description
CudaDeviceVariable<System.UInt32>	output	CudaDeviceVariable

| Improve this Doc View Source

Generate(CudaDeviceVariable<UInt64>)

Use generator to generate num 64-bit results into the device memory at output. The device memory must have been previously allocated and be large enough to hold all the results. Launches are done with the stream set using SetStream(CUstream), or the null stream if no stream has been set.

Results are 64-bit values with every bit random.

Declaration

public void Generate(CudaDeviceVariable<ulong> output)

Parameters

Type	Name	Description
CudaDeviceVariable<System.UInt64>	output	CudaDeviceVariable

| Improve this Doc View Source

Generate32(CUdeviceptr, SizeT)

Results are 32-bit values with every bit random.

Declaration

public void Generate32(CUdeviceptr output, SizeT size)

Parameters

Type	Name	Description
CUdeviceptr	output	DevicePtr of type uint*
SizeT	size	Number of random elements to create

| Improve this Doc View Source

Generate64(CUdeviceptr, SizeT)

Results are 64-bit values with every bit random.

Declaration

public void Generate64(CUdeviceptr output, SizeT size)

Parameters

Type	Name	Description
CUdeviceptr	output	DevicePtr of type ulong*
SizeT	size	Number of random elements to create

| Improve this Doc View Source

GenerateLogNormal(CudaDeviceVariable<Double>, Double, Double)

Use generator to generate num double results into the device memory at outputPtr. The device memory must have been previously allocated and be large enough to hold all the results. Launches are done with the stream set using curandSetStream(), or the null stream if no stream has been set.

Results are 64-bit floating point values with log-normal distribution based on an associated normal distribution with mean mean and standard deviation stddev.

Normally distributed results are generated from pseudorandom generators with a Box-Muller transform, and so require num to be even. Quasirandom generators use an inverse cumulative distribution function to preserve dimensionality. The normally distributed results are transformed into log-normal distribution.

There may be slight numerical differences between results generated on the GPU with generators created with ::curandCreateGenerator() and results calculated on the CPU with generators created with ::curandCreateGeneratorHost(). These differences arise because of differences in results for transcendental functions. In addition, future versions of CURAND may use newer versions of the CUDA math library, so different versions of CURAND may give slightly different numerical values.

Declaration

public void GenerateLogNormal(CudaDeviceVariable<double> output, double mean, double stddev)

Parameters

Type	Name	Description
CudaDeviceVariable<System.Double>	output	CudaDeviceVariable
System.Double	mean
System.Double	stddev

| Improve this Doc View Source

GenerateLogNormal(CudaDeviceVariable<Single>, Single, Single)

Use generator to generate num float results into the device memory at outputPtr. The device memory must have been previously allocated and be large enough to hold all the results. Launches are done with the stream set using ::curandSetStream(), or the null stream if no stream has been set.

Results are 32-bit floating point values with log-normal distribution based on an associated normal distribution with mean mean and standard deviation stddev.

The normally distributed results are transformed into log-normal distribution.

Declaration

public void GenerateLogNormal(CudaDeviceVariable<float> output, float mean, float stddev)

Parameters

Type	Name	Description
CudaDeviceVariable<System.Single>	output	CudaDeviceVariable
System.Single	mean
System.Single	stddev

| Improve this Doc View Source

GenerateLogNormal32(CUdeviceptr, SizeT, Single, Single)

Results are 32-bit floating point values with log-normal distribution based on an associated normal distribution with mean mean and standard deviation stddev.

The normally distributed results are transformed into log-normal distribution.

Declaration

public void GenerateLogNormal32(CUdeviceptr output, SizeT size, float mean, float stddev)

Parameters

Type	Name	Description
CUdeviceptr	output	DevicePtr of type float*
SizeT	size	Number of random elements to create
System.Single	mean
System.Single	stddev

| Improve this Doc View Source

GenerateLogNormal64(CUdeviceptr, SizeT, Single, Single)

Results are 64-bit floating point values with log-normal distribution based on an associated normal distribution with mean mean and standard deviation stddev.

Declaration

public void GenerateLogNormal64(CUdeviceptr output, SizeT size, float mean, float stddev)

Parameters

Type	Name	Description
CUdeviceptr	output	DevicePtr of type double*
SizeT	size	Number of random elements to create
System.Single	mean
System.Single	stddev

| Improve this Doc View Source

GenerateNormal(CudaDeviceVariable<Double>, Double, Double)

Results are 64-bit floating point values with mean mean and standard deviation stddev.

There may be slight numerical differences between results generated on the GPU with generators created with curandCreateGenerator() and results calculated on the CPU with generators created with curandCreateGeneratorHost(). These differences arise because of differences in results for transcendental functions. In addition, future versions of CURAND may use newer versions of the CUDA math library, so different versions of CURAND may give slightly different numerical values.

Declaration

public void GenerateNormal(CudaDeviceVariable<double> output, double mean, double stddev)

Parameters

Type	Name	Description
CudaDeviceVariable<System.Double>	output	CudaDeviceVariable
System.Double	mean
System.Double	stddev

| Improve this Doc View Source

GenerateNormal(CudaDeviceVariable<Single>, Single, Single)

Use generator to generate num float results into the device memory at outputPtr. The device memory must have been previously allocated and be large enough to hold all the results. Launches are done with the stream set using curandSetStream(), or the null stream if no stream has been set.

Results are 32-bit floating point values with mean mean and standard deviation stddev.

Declaration

public void GenerateNormal(CudaDeviceVariable<float> output, float mean, float stddev)

Parameters

Type	Name	Description
CudaDeviceVariable<System.Single>	output	CudaDeviceVariable
System.Single	mean
System.Single	stddev

| Improve this Doc View Source

GenerateNormal32(CUdeviceptr, SizeT, Single, Single)

Use generator to generate num float results into the device memory at outputPtr. The device memory must have been previously allocated and be large enough to hold all the results. Launches are done with the stream set using curandSetStream(), or the null stream if no stream has been set.

Results are 32-bit floating point values with mean mean and standard deviation stddev.

Declaration

public void GenerateNormal32(CUdeviceptr output, SizeT size, float mean, float stddev)

Parameters

Type	Name	Description
CUdeviceptr	output	DevicePtr of type float*
SizeT	size	Number of random elements to create
System.Single	mean
System.Single	stddev

| Improve this Doc View Source

GenerateNormal64(CUdeviceptr, SizeT, Single, Single)

Results are 64-bit floating point values with mean mean and standard deviation stddev.

Declaration

public void GenerateNormal64(CUdeviceptr output, SizeT size, float mean, float stddev)

Parameters

Type	Name	Description
CUdeviceptr	output	DevicePtr of type double*
SizeT	size	Number of random elements to create
System.Single	mean
System.Single	stddev

| Improve this Doc View Source

GenerateSeeds()

Generate the starting state of the generator. This function is automatically called by generation functions such as Generate(CudaDeviceVariable) and GenerateUniform(CudaDeviceVariable). It can be called manually for performance testing reasons to separate timings for starting state generation and random number generation.

Declaration

public void GenerateSeeds()

| Improve this Doc View Source

GenerateUniform(CudaDeviceVariable<Double>)

Results are 64-bit double precision floating point values between 0.0 and 1.0, excluding 0.0 and including 1.0.

Declaration

public void GenerateUniform(CudaDeviceVariable<double> output)

Parameters

Type	Name	Description
CudaDeviceVariable<System.Double>	output	CudaDeviceVariable

| Improve this Doc View Source

GenerateUniform(CudaDeviceVariable<Single>)

Use generator to generate num float results into the device memory at outputPtr. The device memory must have been previously allocated and be large enough to hold all the results. Launches are done with the stream set using SetStream(), or the null stream if no stream has been set.

Results are 32-bit floating point values between 0.0f and 1.0f, excluding 0.0f and including 1.0f.

Declaration

public void GenerateUniform(CudaDeviceVariable<float> output)

Parameters

Type	Name	Description
CudaDeviceVariable<System.Single>	output	CudaDeviceVariable

| Improve this Doc View Source

GenerateUniform32(CUdeviceptr, SizeT)

Use generator to generate num float results into the device memory at outputPtr. The device memory must have been previously allocated and be large enough to hold all the results. Launches are done with the stream set using SetStream(), or the null stream if no stream has been set.

Results are 32-bit floating point values between 0.0f and 1.0f, excluding 0.0f and including 1.0f.

Declaration

public void GenerateUniform32(CUdeviceptr output, SizeT size)

Parameters

Type	Name	Description
CUdeviceptr	output	DevicePtr of type float*
SizeT	size	Number of random elements to create

| Improve this Doc View Source

GenerateUniform64(CUdeviceptr, SizeT)

Results are 64-bit double precision floating point values between 0.0 and 1.0, excluding 0.0 and including 1.0.

Declaration

public void GenerateUniform64(CUdeviceptr output, SizeT size)

Parameters

Type	Name	Description
CUdeviceptr	output	DevicePtr of type double*
SizeT	size	Number of random elements to create

| Improve this Doc View Source

GetDirectionVectors32(DirectionVectorSet)

Get an array of direction vectors that can be used for quasirandom number generation.

The array contains vectors for many dimensions. Each dimension has 32 vectors. Each individual vector is an unsigned int.

Legal values for set are: - JoeKuo6_32 (20,000 dimensions) - ScrambledJoeKuo6_32 (20,000 dimensions)

Declaration

public static DirectionVectors32[] GetDirectionVectors32(DirectionVectorSet set)

Parameters

Type	Name	Description
DirectionVectorSet	set

Returns

Type	Description
DirectionVectors32[]

| Improve this Doc View Source

GetDirectionVectors64(DirectionVectorSet)

Get an array of direction vectors that can be used for quasirandom number generation.

The array contains vectors for many dimensions. Each dimension has 64 vectors. Each individual vector is an unsigned long long.

Legal values for set are: - JoeKuo6_64 (20,000 dimensions) - ScrambledJoeKuo6_64 (20,000 dimensions)

Declaration

public static DirectionVectors64[] GetDirectionVectors64(DirectionVectorSet set)

Parameters

Type	Name	Description
DirectionVectorSet	set

Returns

Type	Description
DirectionVectors64[]

| Improve this Doc View Source

GetScrambleConstants32()

Get scramble constants that can be used for quasirandom number generation.

The array contains constants for many dimensions. Each dimension has a single uint constant.

Declaration

public static uint[] GetScrambleConstants32()

Returns

Type	Description
System.UInt32[]

| Improve this Doc View Source

GetScrambleConstants64()

Get scramble constants that can be used for quasirandom number generation.

The array contains constants for many dimensions. Each dimension has a single ulong constant.

Declaration

public static ulong[] GetScrambleConstants64()

Returns

Type	Description
System.UInt64[]

| Improve this Doc View Source

GetVersion()

Returns the version number of the dynamically linked CURAND library.

Declaration

public static Version GetVersion()

Returns

Type	Description
System.Version

| Improve this Doc View Source

SetGeneratorOrdering(Ordering)

Set the ordering of results of the pseudo or quasirandom number generator.

Legal values of order for pseudorandom generators are:

- PseudoDefault

- PseudoBest

- PseudoSeeded

Legal values of order for quasirandom generators are:

- QuasiDefault

Declaration

public void SetGeneratorOrdering(Ordering order)

Parameters

Type	Name	Description
Ordering	order

| Improve this Doc View Source

SetOffset(UInt64)

Set the absolute offset of the pseudo or quasirandom number generator.

All values of offset are valid. The offset position is absolute, not relative to the current position in the sequence.

Declaration

public void SetOffset(ulong offset)

Parameters

Type	Name	Description
System.UInt64	offset	All values of offset are valid.

| Improve this Doc View Source

SetPseudoRandomGeneratorSeed(UInt64)

Set the seed value of the pseudorandom number generator.

All values of seed are valid. Different seeds will produce different sequences. Different seeds will often not be statistically correlated with each other, but some pairs of seed values may generate sequences which are statistically correlated.

Declaration

public void SetPseudoRandomGeneratorSeed(ulong seed)

Parameters

Type	Name	Description
System.UInt64	seed	All values of seed are valid.

| Improve this Doc View Source

SetQuasiRandomGeneratorDimensions(UInt32)

Set the number of dimensions to be generated by the quasirandom number generator.

Legal values for dimensions are 1 to 20000.

Declaration

public void SetQuasiRandomGeneratorDimensions(uint dimensions)

Parameters

Type	Name	Description
System.UInt32	dimensions	Legal values for dimensions are 1 to 20000.

| Improve this Doc View Source

SetStream(CUstream)

Set the current stream for CURAND kernel launches. All library functions will use this stream until set again.

Declaration

public void SetStream(CUstream stream)

Parameters

Type	Name	Description
CUstream	stream

Implements

System.IDisposable