gpuregiontimer.h File Reference

#include <string>
#include "gromacs/utility/gmxassert.h"

Include dependency graph for gpuregiontimer.h:

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

Description

Defines the GPU region timer implementation/wrapper classes. The implementations live in gpuregiontimer.cuh for CUDA and gpuregiontimer_ocl.h for OpenCL.

Author

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

Classes
struct	GpuTraits< GpuFramework >
	GPU build-path traits such as types. More...
class	GpuRegionTimerImpl< framework >
	This is a GPU region timing implementation interface. It should provide methods for measuring the last timespan. Copying/assignment is disabled since the underlying timing events are owned by this. More...
class	GpuRegionTimerWrapper< framework >
	This is a GPU region timing wrapper class. It allows for host-side tracking of the accumulated execution timespans in GPU code (measuring kernel or transfers duration). It also partially tracks the correctness of the timer state transitions, as far as current implementation allows (see TODO in getLastRangeTime() for a disabled check). Internally it uses GpuRegionTimerImpl for measuring regions. More...

Enumerations
enum	GpuFramework { CUDA, OpenCL }
	Enumeration of possible GPU build-paths. More...

Variables
static const bool	c_debugTimerState = true
	Debug GPU timers in debug builds only.

Enumeration Type Documentation

enum GpuFramework

strong

Enumeration of possible GPU build-paths.

Todo:

Move somewhere general?