ThreadArray

Functions
void	Pscf::ThreadArray::init ()
	Initialize static variables in Pscf::ThreadArray namespace.
void	Pscf::ThreadArray::setThreadsPerBlock ()
	Set the number of threads per block to a default value.
void	Pscf::ThreadArray::setThreadsPerBlock (int nThreadsPerBlock)
	Set the number of threads per block to a specified value.
void	Pscf::ThreadArray::setThreadsLogical (int nThreadsLogical)
	Given total number of threads, set 1D execution configuration.
void	Pscf::ThreadArray::setThreadsLogical (int nThreadsLogical, int &nBlocks)
	Given total number of threads, set 1D execution configuration.
void	Pscf::ThreadArray::setThreadsLogical (int nThreadsLogical, int &nBlocks, int &nThreads)
	Given total number of threads, set 1D execution configuration.
void	Pscf::ThreadArray::checkExecutionConfig ()
	Check the execution configuration (threads and block counts).
int	Pscf::ThreadArray::nBlocks ()
	Get the current number of blocks for execution.
int	Pscf::ThreadArray::nThreads ()
	Get the number of threads per block for execution.
int	Pscf::ThreadArray::nThreadsLogical ()
	Return previously requested total number of threads.
int	Pscf::ThreadArray::warpSize ()
	Get the warp size.
bool	Pscf::ThreadArray::hasUnusedThreads ()
	Indicates whether there will be unused threads.

Detailed Description

Management of GPU resources and setting of execution configurations.

Function Documentation

init()

void Pscf::ThreadArray::init

(

)

Initialize static variables in Pscf::ThreadArray namespace.

Definition at line 40 of file ThreadArray.cu.

References Util::Log::file(), Pscf::ThreadArray::setThreadsPerBlock(), and UTIL_THROW.

Referenced by Pscf::ThreadArray::setThreadsLogical(), and Pscf::Rpg::System< D >::System().

setThreadsPerBlock() [1/2]

void Pscf::ThreadArray::setThreadsPerBlock

(

)

Set the number of threads per block to a default value.

Query the hardware to determine a reasonable number.

Definition at line 58 of file ThreadArray.cu.

References Pscf::ThreadArray::setThreadsPerBlock().

Referenced by Pscf::Rpg::WaveList< D >::computeMinimumImages(), Pscf::ThreadArray::init(), Pscf::Prdc::Cuda::Reduce::innerProduct(), Pscf::Prdc::Cuda::Reduce::max(), Pscf::Prdc::Cuda::Reduce::maxAbs(), Pscf::Prdc::Cuda::Reduce::min(), Pscf::Prdc::Cuda::Reduce::minAbs(), Pscf::Rpg::System< D >::setOptions(), Pscf::ThreadArray::setThreadsPerBlock(), and Pscf::Prdc::Cuda::Reduce::sum().

setThreadsPerBlock() [2/2]

void Pscf::ThreadArray::setThreadsPerBlock

(

int

nThreadsPerBlock

)

Set the number of threads per block to a specified value.

Parameters

nThreadsPerBlock

the number of threads per block (input)

Definition at line 79 of file ThreadArray.cu.

References Pscf::ThreadArray::checkExecutionConfig().

setThreadsLogical() [1/3]

void Pscf::ThreadArray::setThreadsLogical

(

int

nThreadsLogical

)

Given total number of threads, set 1D execution configuration.

Calculates the number of blocks and threads per block, and stores the results in static variables along with the total number of threads requested.

Parameters

nThreadsLogical

total number of required threads (input)

Definition at line 87 of file ThreadArray.cu.

References Pscf::ThreadArray::init(), Pscf::ThreadArray::nThreadsLogical(), and UTIL_ASSERT.

Referenced by Pscf::Rpg::addEqMulVVc(), Pscf::Prdc::Cuda::VecOp::addEqS(), Pscf::Prdc::Cuda::VecOp::addEqS(), Pscf::Prdc::Cuda::VecOp::addEqS(), Pscf::Prdc::Cuda::VecOp::addEqV(), Pscf::Prdc::Cuda::VecOp::addEqV(), Pscf::Prdc::Cuda::VecOp::addEqV(), Pscf::Prdc::Cuda::VecOp::addEqVc(), Pscf::Prdc::Cuda::VecOp::addVcVc(), Pscf::Prdc::Cuda::VecOp::addVcVcVc(), Pscf::Prdc::Cuda::VecOp::addVMany(), Pscf::Prdc::Cuda::VecOp::addVMany(), Pscf::Prdc::Cuda::VecOp::addVS(), Pscf::Prdc::Cuda::VecOp::addVS(), Pscf::Prdc::Cuda::VecOp::addVS(), Pscf::Prdc::Cuda::VecOp::addVS(), Pscf::Prdc::Cuda::VecOp::addVV(), Pscf::Prdc::Cuda::VecOp::addVV(), Pscf::Prdc::Cuda::VecOp::addVV(), Pscf::Prdc::Cuda::VecOp::addVV(), Pscf::Rpg::VecOpFts::computeDField(), Pscf::Rpg::WaveList< D >::computedKSq(), Pscf::Rpg::VecOpFts::computeForceBias(), Pscf::Rpg::WaveList< D >::computeKSq(), Pscf::Rpg::WaveList< D >::computeMinimumImages(), Pscf::Prdc::Cuda::VecOp::divEqS(), Pscf::Prdc::Cuda::VecOp::divEqS(), Pscf::Prdc::Cuda::VecOp::divEqV(), Pscf::Prdc::Cuda::VecOp::divEqV(), Pscf::Prdc::Cuda::VecOp::divEqVc(), Pscf::Prdc::Cuda::VecOp::divVS(), Pscf::Prdc::Cuda::VecOp::divVS(), Pscf::Prdc::Cuda::VecOp::divVV(), Pscf::Prdc::Cuda::VecOp::divVV(), Pscf::Prdc::Cuda::VecOp::eqS(), Pscf::Prdc::Cuda::VecOp::eqS(), Pscf::Prdc::Cuda::VecOp::eqV(), Pscf::Prdc::Cuda::VecOp::eqV(), Pscf::Prdc::Cuda::VecOp::eqVPair(), Pscf::Prdc::Cuda::VecOp::expV(), Pscf::Prdc::Cuda::VecOp::expV(), Pscf::Prdc::Cuda::VecOp::expVc(), Pscf::Rpg::VecOpFts::fourierMove(), Pscf::Prdc::Cuda::Reduce::innerProduct(), Pscf::Prdc::Cuda::Reduce::max(), Pscf::Prdc::Cuda::Reduce::maxAbs(), Pscf::Rpg::VecOpFts::mcftsScale(), Pscf::Prdc::Cuda::Reduce::min(), Pscf::Prdc::Cuda::Reduce::minAbs(), Pscf::Prdc::Cuda::VecOp::mulEqS(), Pscf::Prdc::Cuda::VecOp::mulEqS(), Pscf::Prdc::Cuda::VecOp::mulEqS(), Pscf::Prdc::Cuda::VecOp::mulEqV(), Pscf::Prdc::Cuda::VecOp::mulEqV(), Pscf::Prdc::Cuda::VecOp::mulEqV(), Pscf::Prdc::Cuda::VecOp::mulEqVPair(), Pscf::Prdc::Cuda::VecOp::mulVMany(), Pscf::Prdc::Cuda::VecOp::mulVMany(), Pscf::Prdc::Cuda::VecOp::mulVS(), Pscf::Prdc::Cuda::VecOp::mulVS(), Pscf::Prdc::Cuda::VecOp::mulVS(), Pscf::Prdc::Cuda::VecOp::mulVS(), Pscf::Prdc::Cuda::VecOp::mulVV(), Pscf::Prdc::Cuda::VecOp::mulVV(), Pscf::Prdc::Cuda::VecOp::mulVV(), Pscf::Prdc::Cuda::VecOp::mulVV(), Pscf::Prdc::Cuda::VecOp::mulVVPair(), Pscf::Rpg::realMulVConjVV(), Pscf::Rpg::richardsonEx(), Pscf::ThreadArray::setThreadsLogical(), Pscf::ThreadArray::setThreadsLogical(), Pscf::Prdc::Cuda::VecOp::sqNormV(), Pscf::Prdc::Cuda::VecOp::sqSqNormV(), Pscf::Prdc::Cuda::VecOp::subEqS(), Pscf::Prdc::Cuda::VecOp::subEqS(), Pscf::Prdc::Cuda::VecOp::subEqS(), Pscf::Prdc::Cuda::VecOp::subEqV(), Pscf::Prdc::Cuda::VecOp::subEqV(), Pscf::Prdc::Cuda::VecOp::subEqV(), Pscf::Prdc::Cuda::VecOp::subVS(), Pscf::Prdc::Cuda::VecOp::subVS(), Pscf::Prdc::Cuda::VecOp::subVS(), Pscf::Prdc::Cuda::VecOp::subVS(), Pscf::Prdc::Cuda::VecOp::subVV(), Pscf::Prdc::Cuda::VecOp::subVV(), Pscf::Prdc::Cuda::VecOp::subVV(), Pscf::Prdc::Cuda::VecOp::subVV(), Pscf::Prdc::Cuda::VecOp::subVVS(), and Pscf::Prdc::Cuda::Reduce::sum().

setThreadsLogical() [2/3]

void Pscf::ThreadArray::setThreadsLogical	(	int	nThreadsLogical,
		int &	nBlocks )

Given total number of threads, set 1D execution configuration.

Calculates the number of blocks and threads per block, and stores the results in static variables along with the total number of threads requested.

Sets the parameter nBlocks equal to the calculated number of blocks.

Parameters

nThreadsLogical	total number of required threads (input)
nBlocks	updated number of blocks (output)

Definition at line 115 of file ThreadArray.cu.

References Pscf::ThreadArray::nBlocks(), Pscf::ThreadArray::nThreadsLogical(), and Pscf::ThreadArray::setThreadsLogical().

setThreadsLogical() [3/3]

void Pscf::ThreadArray::setThreadsLogical	(	int	nThreadsLogical,
		int &	nBlocks,
		int &	nThreads )

Given total number of threads, set 1D execution configuration.

Calculates the number of blocks and threads per block, and stores the results in static variables along with the total number of threads requested.

Sets the parameter nBlocks equal to the calculated number of blocks, and nThreads to the calculated number of threads per block.

Parameters

nThreadsLogical	total number of required threads (input)
nBlocks	updated number of blocks (output)
nThreads	updated number threads per block (output)

Definition at line 123 of file ThreadArray.cu.

References Pscf::ThreadArray::nBlocks(), Pscf::ThreadArray::nThreads(), Pscf::ThreadArray::nThreadsLogical(), and Pscf::ThreadArray::setThreadsLogical().

checkExecutionConfig()

void Pscf::ThreadArray::checkExecutionConfig

(

)

Check the execution configuration (threads and block counts).

Check for validity and optimality, based on hardware warp size and streaming multiprocessor constraints.

Definition at line 131 of file ThreadArray.cu.

References UTIL_THROW.

Referenced by Pscf::ThreadArray::setThreadsPerBlock().

nBlocks()

int Pscf::ThreadArray::nBlocks

(

)

Get the current number of blocks for execution.

Definition at line 178 of file ThreadArray.cu.

Referenced by Pscf::ThreadArray::setThreadsLogical(), and Pscf::ThreadArray::setThreadsLogical().

nThreads()

int Pscf::ThreadArray::nThreads

(

)

Get the number of threads per block for execution.

Definition at line 181 of file ThreadArray.cu.

Referenced by Pscf::ThreadArray::setThreadsLogical().

nThreadsLogical()

int Pscf::ThreadArray::nThreadsLogical

(

)

Return previously requested total number of threads.

Definition at line 184 of file ThreadArray.cu.

Referenced by Pscf::ThreadArray::setThreadsLogical(), Pscf::ThreadArray::setThreadsLogical(), and Pscf::ThreadArray::setThreadsLogical().

warpSize()

int Pscf::ThreadArray::warpSize

(

)

Get the warp size.

Definition at line 187 of file ThreadArray.cu.

Referenced by Pscf::Prdc::Cuda::Reduce::innerProduct(), Pscf::Prdc::Cuda::Reduce::max(), Pscf::Prdc::Cuda::Reduce::maxAbs(), Pscf::Prdc::Cuda::Reduce::min(), Pscf::Prdc::Cuda::Reduce::minAbs(), and Pscf::Prdc::Cuda::Reduce::sum().

hasUnusedThreads()

bool Pscf::ThreadArray::hasUnusedThreads

(

)

Indicates whether there will be unused threads.

Returns true iff nThreads*nBlocks != nThreadsLogical.

Definition at line 190 of file ThreadArray.cu.