cuda Namespace Reference

Contains utility function for the host related to GPUs. More...

Classes
class	_Block

Functions
cudaDeviceProp *	getGPUDeviceInfo (unsigned int device)
	send device information to the gpu More...
template<typename T >
T *	copyArrayToDevice (const T *in, unsigned int numElems)
template<typename T >
T *	copyValueToDevice (const T *in)
template<typename T >
T *	alloc1DCudaArray (unsigned int sz1)
template<typename T >
T **	alloc2DCudaArray (unsigned int sz1, unsigned int sz2)
	allocates a 2D cuda array on the device. More...
template<typename T >
T **	alloc2DCudaArray (T **&hostPtr, unsigned int sz1, unsigned int sz2)
	allocates a 2D cuda array on the device. More...
template<typename T >
T **	alloc2DCudaArray (const T **in, unsigned int sz1, unsigned int sz2)
	allocates a 2D cuda array on the device and copy data. More...
template<typename T >
void	copyArrayToDeviceAsync (const T *in, T *__deviceptr, unsigned int numElems, const cudaStream_t stream)
template<typename T >
void	copy2DCudaArrayToDeviceAsync (const T **in, T **__devicePtr, unsigned int sz1, unsigned int sz2, const cudaStream_t stream)
	allocates a 2D cuda array on the device and copy data. More...
template<typename T >
void	copyArrayToHostAsync (T *host_ptr, const T *__deviceptr, unsigned int numElems, const cudaStream_t stream)
template<typename T >
void	dealloc2DCudaArray (T **&__array2D, unsigned int sz1)
	deallocates the 2D cuda array. More...
void	computeDendroBlockToGPUMap (const ot::Block *blkList, unsigned int numBlocks, unsigned int *&blockMap, dim3 &gridDim)
template<typename T >
void	copyArrayToHost (T *host_ptr, const T *__device_ptr, unsigned int numElems)
template<typename T >
void	copy2DArrayToHost (T **host_ptr, const T **__device_ptr, unsigned int sz1, unsigned int sz2)

Detailed Description

Contains utility function for the host related to GPUs.

Author

Milinda Fernando School of Computing, University of Utah

Function Documentation

alloc1DCudaArray()

template<typename T >

T * cuda::alloc1DCudaArray

(

unsigned int

sz1

)

allocates 1D array

Parameters

[in]

sz1

Returns

the pointer to the device allocation

alloc2DCudaArray() [1/3]

template<typename T >

T ** cuda::alloc2DCudaArray	(	unsigned int	sz1,
		unsigned int	sz2
	)

allocates a 2D cuda array on the device.

Parameters

[in]	sz1	dim 1 size
[in]	sz2	dim 2 size

Returns

the double pointer to the 2D array.

alloc2DCudaArray() [2/3]

template<typename T >

T ** cuda::alloc2DCudaArray	(	T **&	hostPtr,
		unsigned int	sz1,
		unsigned int	sz2
	)

allocates a 2D cuda array on the device.

Parameters

[out]	hostPtr	2D pointer accesible from the host.
[in]	sz1	dim 1 size
[in]	sz2	dim 2 size

Returns

the double pointer to the 2D array (device pointer).

alloc2DCudaArray() [3/3]

template<typename T >

T ** cuda::alloc2DCudaArray	(	const T **	in,
		unsigned int	sz1,
		unsigned int	sz2
	)

allocates a 2D cuda array on the device and copy data.

Parameters

[in]	sz1	dim 1 size
[in]	sz2	dim 2 size

Returns

the double pointer to the 2D array.

copy2DArrayToHost()

template<typename T >

void cuda::copy2DArrayToHost	(	T **	host_ptr,
		const T **	__device_ptr,
		unsigned int	sz1,
		unsigned int	sz2
	)

copy 2D array from device to memory

Parameters

[in]	__device_ptr	: 2D pointer to the device
[in]	sz1	: size1
[in]	sz2	: size2
[out]	host_ptr	host ptr

copy2DCudaArrayToDeviceAsync()

template<typename T >

void cuda::copy2DCudaArrayToDeviceAsync	(	const T **	in,
		T **	__devicePtr,
		unsigned int	sz1,
		unsigned int	sz2,
		const cudaStream_t	stream
	)

allocates a 2D cuda array on the device and copy data.

Parameters

[in]	sz1	dim 1 size
[in]	sz2	dim 2 size

Returns

the double pointer to the 2D array.

copyArrayToDevice()

template<typename T >

T * cuda::copyArrayToDevice	(	const T *	in,
		unsigned int	numElems
	)

send mesh blocks to the gpu

Parameters

[in]	in	: input array
[in]	out	device pointer where the data is copied to.

copyArrayToDeviceAsync()

template<typename T >

void cuda::copyArrayToDeviceAsync	(	const T *	in,
		T *	__deviceptr,
		unsigned int	numElems,
		const cudaStream_t	stream
	)

send mesh blocks to the gpu (async)

Parameters

[in]	in	: input array
[in]	out	device pointer where the data is copied to.

copyArrayToHost()

template<typename T >

void cuda::copyArrayToHost	(	T *	host_ptr,
		const T *	__device_ptr,
		unsigned int	numElems
	)

copy array from device to memory

Parameters

[in]	__device_ptr	: device pointer
[in]	numElems	: number of elements
[out]	host_ptr	host ptr

copyValueToDevice()

template<typename T >

T * cuda::copyValueToDevice ( const T *  in )

inline

copy value to device

Parameters

[in]	in	: input value
[in]	out	device pointer where the data is copied to.

dealloc2DCudaArray()

template<typename T >

void cuda::dealloc2DCudaArray	(	T **&	__array2D,
		unsigned int	sz1
	)

deallocates the 2D cuda array.

Parameters

[in]

sz1

dim 1 size

getGPUDeviceInfo()

cudaDeviceProp * cuda::getGPUDeviceInfo

(

unsigned int

device

)

send device information to the gpu

Parameters

[in]

device

: gpu device ID

Returns

cudaDeviceProp allocated on the device