Description

Main data structure for CUDA nonbonded force calculations.

Main data structure for SYCL nonbonded force calculations.

Main data structure for OpenCL nonbonded force calculations.

Public Attributes
const DeviceContext *	deviceContext_
	GPU device context. More...

bool	bUseTwoStreams = false
	true if doing both local/non-local NB work on GPU

bool	bNonLocalStreamDoneMarked = false
	true indicates that the nonlocal_done event was marked

NBAtomDataGpu *	atdat = nullptr
	atom data

int *	atomIndices = nullptr
	array of atom indices

int	atomIndicesSize = 0
	size of atom indices

int	atomIndicesSize_alloc = 0
	size of atom indices allocated in device buffer

int *	cxy_na = nullptr
	x buf ops num of atoms

int	ncxy_na = 0
	number of elements in cxy_na

int	ncxy_na_alloc = 0
	number of elements allocated allocated in device buffer

int *	cxy_ind = nullptr
	x buf ops cell index mapping

int	ncxy_ind = 0
	number of elements in cxy_ind

int	ncxy_ind_alloc = 0
	number of elements allocated allocated in device buffer

NBParamGpu *	nbparam = nullptr
	parameters required for the non-bonded calc.

gmx::EnumerationArray < Nbnxm::InteractionLocality, std::unique_ptr < Nbnxm::GpuPairlist > >	plist = { { nullptr } }
	pair-list data structures (local and non-local)

NBStagingData	nbst
	staging area where fshift/energies get downloaded More...

gmx::EnumerationArray < Nbnxm::InteractionLocality, const DeviceStream * >	deviceStreams
	local and non-local GPU streams More...

gmx::EnumerationArray < Nbnxm::InteractionLocality, bool >	haveWork = { { false } }
	True if there is work for the current domain in the respective locality. More...

bool	bDoTime = false
	True if event-based timing is enabled. More...

Nbnxm::GpuTimers *	timers = nullptr
	CUDA event-based timers. More...

gmx_wallclock_gpu_nbnxn_t *	timings = nullptr
	Timing data. TODO: deprecate this and query timers for accumulated data instead. More...

struct gmx_device_runtime_data_t *	dev_rundata = nullptr
	OpenCL runtime data (context, kernels) More...

cl_kernel	kernel_pruneonly [ePruneNR] = { nullptr }
	prune kernels, ePruneKind defined the kernel kinds

bool	bPrefetchLjParam = false
	true if prefetching fg i-atom LJ parameters should be used in the kernels More...

DeviceBuffer< int >	atomIndices
	array of atom indices

DeviceBuffer< int >	cxy_na
	x buf ops num of atoms

DeviceBuffer< int >	cxy_ind
	x buf ops cell index mapping

gmx::EnumerationArray < Nbnxm::InteractionLocality, bool >	didPairlistH2D = { { false } }
	true when a pair-list transfer has been done at this step

gmx::EnumerationArray < Nbnxm::InteractionLocality, bool >	didPrune = { { false } }
	true when we we did pruning on this step

gmx::EnumerationArray < Nbnxm::InteractionLocality, bool >	didRollingPrune = { { false } }
	true when we did rolling pruning (at the previous step)


GpuEventSynchronizer	nonlocal_done
	Event triggered when the non-local non-bonded kernel is done (and the local transfer can proceed) More...

GpuEventSynchronizer	misc_ops_and_local_H2D_done
	Event triggered when the tasks issued in the local stream that need to precede the non-local force or buffer operation calculations are done (e.g. f buffer 0-ing, local x/q H2D, buffer op initialization in local stream that is required also by nonlocal stream )


cl_kernel	kernel_noener_noprune_ptr [Nbnxm::c_numElecTypes][Nbnxm::c_numVdwTypes] = { { nullptr } }

cl_kernel	kernel_ener_noprune_ptr [Nbnxm::c_numElecTypes][Nbnxm::c_numVdwTypes] = { { nullptr } }

cl_kernel	kernel_noener_prune_ptr [Nbnxm::c_numElecTypes][Nbnxm::c_numVdwTypes] = { { nullptr } }

cl_kernel	kernel_ener_prune_ptr [Nbnxm::c_numElecTypes][Nbnxm::c_numVdwTypes] = { { nullptr } }


cl_kernel	kernel_memset_f = nullptr

cl_kernel	kernel_memset_f2 = nullptr

cl_kernel	kernel_memset_f3 = nullptr

Member Data Documentation

bool NbnxmGpu::bDoTime = false

True if event-based timing is enabled.

True if event-based timing is enabled. Always false for SYCL.

bool NbnxmGpu::bPrefetchLjParam = false

true if prefetching fg i-atom LJ parameters should be used in the kernels

auxiliary kernels implementing memset-like functions

struct gmx_device_runtime_data_t* NbnxmGpu::dev_rundata = nullptr

OpenCL runtime data (context, kernels)

Pointers to non-bonded kernel functions organized similar with nb_kfunc_xxx arrays in nbnxn_ocl.cpp

const DeviceContext * NbnxmGpu::deviceContext_

GPU device context.

Todo:: Make it constant reference, once NbnxmGpu is a proper class.

Todo:: Make it constant reference, once NbnxmGpu is a proper class.

gmx::EnumerationArray< Nbnxm::InteractionLocality, const DeviceStream * > NbnxmGpu::deviceStreams

local and non-local GPU streams

local and non-local GPU queues

gmx::EnumerationArray< Nbnxm::InteractionLocality, bool > NbnxmGpu::haveWork = { { false } }

True if there is work for the current domain in the respective locality.

True if there has been local/nonlocal GPU work, either bonded or nonbonded, scheduled.

This includes local/nonlocal GPU work, either bonded or nonbonded, scheduled to be executed in the current domain. As long as bonded work is not split up into local/nonlocal, if there is bonded GPU work, both flags will be true.

NBStagingData NbnxmGpu::nbst

staging area where fshift/energies get downloaded

staging area where fshift/energies get downloaded. Will be removed in SYCL.

GpuEventSynchronizer NbnxmGpu::nonlocal_done

Event triggered when the non-local non-bonded kernel is done (and the local transfer can proceed)

Events used for synchronization.

Event triggered when the non-local non-bonded kernel is done (and the local transfer can proceed)

Nbnxm::GpuTimers * NbnxmGpu::timers = nullptr

CUDA event-based timers.

Dummy timers.

OpenCL event-based timers.

gmx_wallclock_gpu_nbnxn_t * NbnxmGpu::timings = nullptr

Timing data. TODO: deprecate this and query timers for accumulated data instead.

Dummy timing data.

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

src/gromacs/nbnxm/cuda/nbnxm_cuda_types.h
src/gromacs/nbnxm/opencl/nbnxm_ocl_types.h
src/gromacs/nbnxm/sycl/nbnxm_sycl_types.h

Description

Public Attributes

Member Data Documentation