TissueForge::cuda::BondConfig Struct Reference

CUDA runtime control interface for Tissue Forge bonds. More...

#include <tfBondConfig.h>

Static Public Member Functions
static bool	onDevice ()
	Check whether the bonds are currently on a device.
static int	getDevice ()
	Get the id of the device designated for running bonds.
static HRESULT	setDevice (int deviceId=0)
	Set the id of the device for running bonds.
static HRESULT	toDevice ()
	Send bonds to device. If bonds are already on device, then the call is ignored.
static HRESULT	fromDevice ()
	Pull engine from device. If engine is not on a device, then the call is ignored.
static HRESULT	setBlocks (unsigned int numBlocks)
	Set the number of blocks of the CUDA configuration for a CUDA device.
static HRESULT	setThreads (unsigned int numThreads)
	Set the number of threads of the CUDA configuration for a CUDA device.
static HRESULT	refreshBond (BondHandle *bh)
	Update a bond on a CUDA device.
static HRESULT	refreshBonds (std::vector< BondHandle * > bonds)
	Update bonds on a CUDA device.
static HRESULT	refresh ()
	Update all bonds on a CUDA device.

Detailed Description

CUDA runtime control interface for Tissue Forge bonds.

This object provides control for configuring bond calculations on CUDA devices.

At any time during a simulation, supported bond calculations can be sent to a particular CUDA device, or brought back to the CPU when deployed on a CUDA device. CUDA dynamic parallelism can also be specified before deploying bond calculations to a CUDA device. Future Tissue Forge versions will support deployment on multiple devices.

Member Function Documentation

fromDevice()

static HRESULT TissueForge::cuda::BondConfig::fromDevice ( )

static

Pull engine from device. If engine is not on a device, then the call is ignored.

Returns

HRESULT

getDevice()

static int TissueForge::cuda::BondConfig::getDevice ( )

static

Get the id of the device designated for running bonds.

Returns

int

onDevice()

static bool TissueForge::cuda::BondConfig::onDevice ( )

static

Check whether the bonds are currently on a device.

Returns

true

false

refresh()

static HRESULT TissueForge::cuda::BondConfig::refresh ( )

static

Update all bonds on a CUDA device.

Useful for notifying the device that bonds have changed.

If engine is not on a device, then the call is ignored.

Returns

HRESULT

refreshBond()

static HRESULT TissueForge::cuda::BondConfig::refreshBond ( BondHandle * bh )

static

Update a bond on a CUDA device.

Useful for notifying the device that a bond has changed.

If engine is not on a device, then the call is ignored.

Parameters

bh	bond to update

Returns

HRESULT

refreshBonds()

static HRESULT TissueForge::cuda::BondConfig::refreshBonds ( std::vector< BondHandle * > bonds )

static

Update bonds on a CUDA device.

Useful for notifying the device that bonds have changed.

If engine is not on a device, then the call is ignored.

Parameters

bonds

bonds to update

Returns

HRESULT

setBlocks()

static HRESULT TissueForge::cuda::BondConfig::setBlocks ( unsigned int numBlocks )

static

Set the number of blocks of the CUDA configuration for a CUDA device.

Throws an error if called when the bonds are already deployed to a CUDA device.

Parameters

numBlocks

number of blocks

Returns

HRESULT

setDevice()

static HRESULT TissueForge::cuda::BondConfig::setDevice ( int deviceId = 0 )

static

Set the id of the device for running bonds.

Can be safely called while bonds are currently on a device.

Parameters

deviceId

Returns

HRESULT

setThreads()

static HRESULT TissueForge::cuda::BondConfig::setThreads ( unsigned int numThreads )

static

Set the number of threads of the CUDA configuration for a CUDA device.

Throws an error if called when bonds are already deployed to a CUDA device.

Parameters

numThreads

number of threads

Returns

HRESULT

toDevice()

static HRESULT TissueForge::cuda::BondConfig::toDevice ( )

static

Send bonds to device. If bonds are already on device, then the call is ignored.

Returns

HRESULT

---

The documentation for this struct was generated from the following file:

• source/cuda/tfBondConfig.h