pme_gpu_timings.h File Reference

#include <cstddef>

Include dependency graph for pme_gpu_timings.h:

This graph shows which files directly or indirectly include this file:

Description

Defines PME GPU timing functions.

Author

Aleksei Iupinov a.yup.nosp@m.inov.nosp@m.@gmai.nosp@m.l.co.nosp@m.m

Functions
enum PmeStage int void	pme_gpu_start_timing (const PmeGpu *pmeGpu, PmeStage pmeStageId)
	Starts timing the certain PME GPU stage during a single computation (if timings are enabled). More...
void	pme_gpu_stop_timing (const PmeGpu *pmeGpu, PmeStage pmeStageId)
	Stops timing the certain PME GPU stage during a single computation (if timings are enabled). More...
bool	pme_gpu_timings_enabled (const PmeGpu *pmeGpu)
	Tells if CUDA-based performance tracking is enabled for PME. More...
void	pme_gpu_update_timings (const PmeGpu *pmeGpu)
	Finalizes all the active PME GPU stage timings for the current computation. Should be called at the end of every computation. More...
void	pme_gpu_reinit_timings (const PmeGpu *pmeGpu)
	Updates the internal list of active PME GPU stages (if timings are enabled). More...
void	pme_gpu_reset_timings (const PmeGpu *pmeGpu)
	Resets the PME GPU timings. To be called at the reset MD step. More...
void	pme_gpu_get_timings (const PmeGpu *pmeGpu, gmx_wallclock_gpu_pme_t *timings)
	Copies the PME GPU timings to the gmx_wallclock_gpu_t structure (for log output). To be called at the run end. More...

Function Documentation

void pme_gpu_get_timings	(	const PmeGpu *	pmeGpu,
		gmx_wallclock_gpu_pme_t *	timings
	)

Copies the PME GPU timings to the gmx_wallclock_gpu_t structure (for log output). To be called at the run end.

Parameters

[in]	pmeGpu	The PME GPU structure.
[in]	timings	The gmx_wallclock_gpu_pme_t structure.

void pme_gpu_reinit_timings

(

const PmeGpu *

pmeGpu

)

Updates the internal list of active PME GPU stages (if timings are enabled).

Parameters

[in]

pmeGpu

The PME GPU data structure.

void pme_gpu_reset_timings

(

const PmeGpu *

pmeGpu

)

Resets the PME GPU timings. To be called at the reset MD step.

Parameters

[in]

pmeGpu

The PME GPU structure.

enum PmeStage int void pme_gpu_start_timing ( const PmeGpu *  pmeGpu, PmeStage  pmeStageId  )

strong

Starts timing the certain PME GPU stage during a single computation (if timings are enabled).

Parameters

[in]	pmeGpu	The PME GPU data structure.
[in]	pmeStageId	The PME GPU stage gtPME_ index from the enum in src/gromacs/timing/gpu_timing.h

void pme_gpu_stop_timing	(	const PmeGpu *	pmeGpu,
		PmeStage	pmeStageId
	)

Stops timing the certain PME GPU stage during a single computation (if timings are enabled).

Parameters

[in]	pmeGpu	The PME GPU data structure.
[in]	pmeStageId	The PME GPU stage gtPME_ index from the enum in src/gromacs/timing/gpu_timing.h

bool pme_gpu_timings_enabled

(

const PmeGpu *

pmeGpu

)

Tells if CUDA-based performance tracking is enabled for PME.

Parameters

[in]

pmeGpu

The PME GPU data structure.

Returns

True if timings are enabled, false otherwise.

void pme_gpu_update_timings

(

const PmeGpu *

pmeGpu

)

Finalizes all the active PME GPU stage timings for the current computation. Should be called at the end of every computation.

Parameters

[in]

pmeGpu

The PME GPU structure.