Grid: Grid/threads/Accelerator.h File Reference

Grid 0.7.0

#include <string.h>

Go to the source code of this file.

Macros
#define	accelerator
#define	accelerator_inline
#define	accelerator_for(iterator, num, nsimd, ...)
#define	accelerator_forNB(iterator, num, nsimd, ...)
#define	accelerator_barrier(dummy)
#define	accelerator_for2d(iter1, num1, iter2, num2, nsimd, ...)

Typedefs
typedef int	acceleratorEvent_t

Functions
	NAMESPACE_BEGIN (Grid)
uint32_t	acceleratorThreads (void)
void	acceleratorThreads (uint32_t)
void	acceleratorInit (void)
void	acceleratorPin (void *ptr, unsigned long bytes)
void	acceleratorMem (void)
accelerator_inline int	acceleratorSIMTlane (int Nsimd)
void	acceleratorCopyToDevice (void from, void to, size_t bytes)
void	acceleratorCopyFromDevice (void from, void to, size_t bytes)
acceleratorEvent_t	acceleratorCopyToDeviceAsynch (void from, void to, size_t bytes)
acceleratorEvent_t	acceleratorCopyFromDeviceAsynch (void from, void to, size_t bytes)
void	acceleratorEventWait (acceleratorEvent_t ev)
int	acceleratorEventIsComplete (acceleratorEvent_t ev)
acceleratorEvent_t	acceleratorCopyDeviceToDeviceAsynch (void from, void to, size_t bytes)
void	acceleratorCopySynchronise (void)
int	acceleratorIsCommunicable (void *ptr)
void	acceleratorMemSet (void *base, int value, size_t bytes)
void *	acceleratorAllocShared (size_t bytes)
void *	acceleratorAllocDevice (size_t bytes)
void	acceleratorFreeShared (void *ptr)
void	acceleratorFreeDevice (void *ptr)
void *	acceleratorAllocCpu (size_t bytes)
void	acceleratorFreeCpu (void *ptr)
void	acceleratorFenceComputeStream (void)
accelerator_inline void	acceleratorSynchronise (void)
accelerator_inline void	acceleratorSynchroniseAll (void)
accelerator_inline void	acceleratorFence (void)
void	acceleratorCopyDeviceToDevice (void from, void to, size_t bytes)
template<class T>
void	acceleratorPut (T &dev, const T &host)
template<class T>
T	acceleratorGet (T &dev)
	NAMESPACE_END (Grid)

Macro Definition Documentation

◆ accelerator

#define accelerator

Definition at line 607 of file Accelerator.h.

Referenced by WilsonKernels< Impl >::DhopDirTm(), DivIntFunctor< scalar >::DivIntFunctor(), Gamma::Gamma(), GparityFlavour::GparityFlavour(), Grid_half::Grid_half(), Grid_half::Grid_half(), Grid_simd< float, SIMD_Ftype >::Grid_simd(), Grid_simd2< complex< double >, vComplexD >::Grid_simd2(), iMatrix< CComplex, nbasis >::iMatrix(), iScalar< vInteger >::iScalar(), iVector< CComplex, nbasis >::iVector(), ModIntFunctor< scalar >::ModIntFunctor(), AbsRealFunctor< scalar >::operator()(), AcosRealFunctor< scalar >::operator()(), AndAndFunctor< scalar >::operator()(), AndFunctor< scalar >::operator()(), AsinRealFunctor< scalar >::operator()(), CosRealFunctor< scalar >::operator()(), DivIntFunctor< scalar >::operator()(), ExpFunctor< scalar >::operator()(), ImagFunctor< scalar >::operator()(), LogRealFunctor< scalar >::operator()(), ModIntFunctor< scalar >::operator()(), NotFunctor< scalar >::operator()(), OrFunctor< scalar >::operator()(), OrOrFunctor< scalar >::operator()(), PowRealFunctor< scalar >::operator()(), RealFunctor< scalar >::operator()(), RSqrtRealFunctor< scalar >::operator()(), seq< lobj, robj >::operator()(), sge< lobj, robj >::operator()(), sgt< lobj, robj >::operator()(), SinRealFunctor< scalar >::operator()(), sle< lobj, robj >::operator()(), slt< lobj, robj >::operator()(), sne< lobj, robj >::operator()(), SqrtRealFunctor< scalar >::operator()(), veq< lobj, robj >::operator()(), vge< lobj, robj >::operator()(), vgt< lobj, robj >::operator()(), vle< lobj, robj >::operator()(), vlt< lobj, robj >::operator()(), vne< lobj, robj >::operator()(), Grid::operator*(), Grid::operator*(), Grid::operator+(), Grid::operator+(), Grid::operator-(), Grid::operator-(), Grid::operator/(), Grid::operator/(), PowRealFunctor< scalar >::PowRealFunctor(), and WilsonProjector::Proj().

◆ accelerator_inline

#define accelerator_inline

Definition at line 608 of file Accelerator.h.

Referenced by abs(), abs(), acceleratorFence(), acceleratorSIMTlane(), acceleratorSynchronise(), acceleratorSynchroniseAll(), AcceleratorVector< int, STENCIL_MAX >::AcceleratorVector(), AcceleratorVector< int, STENCIL_MAX >::AcceleratorVector(), AcceleratorVector< int, STENCIL_MAX >::AcceleratorVector(), accumRecon5m(), accumRecon5m(), accumRecon5m(), accumRecon5m(), accumRecon5p(), accumRecon5p(), accumRecon5p(), accumRecon5p(), accumReconTm(), accumReconTm(), accumReconTm(), accumReconTm(), accumReconTp(), accumReconTp(), accumReconTp(), accumReconTp(), accumReconXm(), accumReconXm(), accumReconXm(), accumReconXm(), accumReconXp(), accumReconXp(), accumReconXp(), accumReconXp(), accumReconYm(), accumReconYm(), accumReconYm(), accumReconYm(), accumReconYp(), accumReconYp(), accumReconYp(), accumReconYp(), accumReconZm(), accumReconZm(), accumReconZm(), accumReconZm(), accumReconZp(), accumReconZp(), accumReconZp(), accumReconZp(), acos(), acos(), add(), add(), add(), add(), add(), add(), add(), add(), add(), add(), Grid_simd2< complex< double >, vComplexD >::add, Grid_simd2< complex< double >, vComplexD >::add, Grid_simd2< complex< double >, vComplexD >::add, Grid_simd< float, SIMD_Ftype >::add, Grid_simd< float, SIMD_Ftype >::add, Grid_simd< float, SIMD_Ftype >::add, adj(), adj(), adj(), adj(), adj(), adj(), adj(), adj(), adj(), LatticeAccelerator< vobj >::Advise(), LatticeAccelerator< vobj >::Advise(), asin(), asin(), AcceleratorVector< int, STENCIL_MAX >::begin(), AcceleratorVector< int, STENCIL_MAX >::begin(), LatticeView< typename T::vector_object >::begin(), bgq_l1p_optimisation(), binary(), LatticeAccelerator< vobj >::Checkerboard(), LatticeAccelerator< vobj >::Checkerboard(), AcceleratorVector< int, STENCIL_MAX >::clear(), CartesianStencilAccelerator< vobj, cobj, Parameters >::CommBuf(), SimpleCompressorGather< vobj, FaceGatherSimple >::CommDatumSize(), WilsonCompressorTemplate< HCS, HS, S, WilsonProjector >< SiteHalfCommSpinor, SiteHalfSpinor, SiteSpinor >::CommDatumSize(), Comparison(), Comparison(), Comparison(), SimpleCompressorGather< vobj, FaceGatherSimple >::Compress(), WilsonCompressorTemplate< HCS, HS, S, WilsonProjector >< SiteHalfCommSpinor, SiteHalfSpinor, SiteSpinor >::Compress(), SimpleCompressorGather< vobj, FaceGatherSimple >::CompressExchange(), WilsonCompressorTemplate< HCS, HS, S, WilsonProjector >< SiteHalfCommSpinor, SiteHalfSpinor, SiteSpinor >::CompressExchange(), LatticeAccelerator< vobj >::Conformable(), conformable(), conjugate(), conjugate(), conjugate(), conjugate(), conjugate(), conjugate(), conjugate(), conjugate(), conjugate(), Grid_simd2< Scalar_type, Vector_type >::conv_t_union::conv_t_union(), convertType(), convertType(), convertType(), convertType(), convertType(), convertType(), convertType(), convertType(), convertType(), convertType(), convertType(), Grid::Lexicographic::CoorFromIndex(), cos(), cos(), SimpleCompressorGather< vobj, FaceGatherSimple >::Decompress(), WilsonCompressorTemplate< HCS, HS, S, WilsonProjector >< SiteHalfCommSpinor, SiteHalfSpinor, SiteSpinor >::Decompress(), SimpleCompressorGather< vobj, FaceGatherSimple >::DecompressionStep(), WilsonCompressorTemplate< HCS, HS, S, WilsonProjector >< SiteHalfCommSpinor, SiteHalfSpinor, SiteSpinor >::DecompressionStep(), Determinant(), Determinant(), Determinant(), Determinant(), Determinant(), Determinant(), DhopDirMacro(), WilsonKernels< Impl >::DhopDirTm(), WilsonKernels< Impl >::DhopDirTp(), WilsonKernels< Impl >::DhopDirXm(), WilsonKernels< Impl >::DhopDirXp(), WilsonKernels< Impl >::DhopDirYm(), WilsonKernels< Impl >::DhopDirYp(), WilsonKernels< Impl >::DhopDirZm(), WilsonKernels< Impl >::DhopDirZp(), ImprovedStaggeredFermion< StaggeredImplF >::DhopSiteGenericInt(), div(), div(), div(), Grid::Optimization::PrecisionChange::DtoH(), Grid::Optimization::PrecisionChange::DtoH(), PrecisionChange::DtoH(), Grid::Optimization::PrecisionChange::DtoS(), Grid::Optimization::PrecisionChange::DtoS(), PrecisionChange::DtoS(), AcceleratorVector< int, STENCIL_MAX >::end(), AcceleratorVector< int, STENCIL_MAX >::end(), LatticeView< typename T::vector_object >::end(), SimpleCompressorGather< vobj, FaceGatherSimple >::Exchange(), WilsonCompressorTemplate< HCS, HS, S, WilsonProjector >< SiteHalfCommSpinor, SiteHalfSpinor, SiteSpinor >::Exchange(), Grid_simd2< complex< double >, vComplexD >::exchange, Grid_simd< float, SIMD_Ftype >::exchange, iMatrix< CComplex, nbasis >::exchange, iScalar< vInteger >::exchange, iVector< CComplex, nbasis >::exchange, Exchange::Exchange0(), Grid::Optimization::Exchange::Exchange0(), Grid_simd2< complex< double >, vComplexD >::exchange0, Grid_simd< float, SIMD_Ftype >::exchange0, Exchange::Exchange1(), Grid::Optimization::Exchange::Exchange1(), Grid_simd2< complex< double >, vComplexD >::exchange1, Grid_simd< float, SIMD_Ftype >::exchange1, Exchange::Exchange2(), Grid::Optimization::Exchange::Exchange2(), Grid_simd2< complex< double >, vComplexD >::exchange2, Grid_simd< float, SIMD_Ftype >::exchange2, Exchange::Exchange3(), Grid::Optimization::Exchange::Exchange3(), Grid_simd2< complex< double >, vComplexD >::exchange3, Grid_simd< float, SIMD_Ftype >::exchange3, Grid_simd2< complex< double >, vComplexD >::exchange4, Exchange::ExchangeN(), Grid::Optimization::Exchange::ExchangeN(), Grid::Optimization::Exchange::ExchangeN(), Grid::Optimization::Exchange::ExchangeN(), exchangeSIMT(), exp(), exp(), Exponentiate(), Exponentiate(), Exponentiate(), Grid::float2half(), WilsonKernels< ImplD >::GenericDhopSiteDagExt(), CartesianStencilAccelerator< vobj, cobj, Parameters >::GetEntry(), GeneralLocalStencilView::GetEntry(), CartesianStencilAccelerator< vobj, cobj, Parameters >::GetInfo(), getlane(), getlane(), getlane(), Grid_simd2< complex< double >, vComplexD >::getlane(), Grid_simd< float, SIMD_Ftype >::getlane(), CartesianStencilAccelerator< vobj, cobj, Parameters >::GetPFInfo(), Gpermute(), Grid::GpuComplex< Half2 >::GpuComplex(), Grid::GpuComplex< Half2 >::GpuComplex(), Grid::GpuComplex< Half2 >::GpuComplex(), Grid_simd< float, SIMD_Ftype >::Grid_simd(), Grid_simd< float, SIMD_Ftype >::Grid_simd(), Grid_simd< float, SIMD_Ftype >::Grid_simd(), Grid_simd< float, SIMD_Ftype >::Grid_simd(), Grid_simd2< complex< double >, vComplexD >::Grid_simd2(), Grid_simd2< complex< double >, vComplexD >::Grid_simd2(), Grid_simd2< complex< double >, vComplexD >::Grid_simd2(), GridFromExpression(), Grid::half2float(), Grid::Optimization::PrecisionChange::HtoD(), Grid::Optimization::PrecisionChange::HtoD(), PrecisionChange::HtoD(), Grid::Optimization::PrecisionChange::HtoS(), Grid::Optimization::PrecisionChange::HtoS(), PrecisionChange::HtoS(), CartesianStencilAccelerator< vobj, cobj, Parameters >::iCoorFromIindex(), Grid::GpuComplex< Half2 >::imag(), imag(), imag(), imag(), imag(), imag(), imag(), imag(), iMatrix< CComplex, nbasis >::iMatrix(), iMatrix< CComplex, nbasis >::iMatrix(), Grid::Lexicographic::IndexFromCoor(), Grid::Lexicographic::IndexFromCoor(), indexRank(), TensorIndexRecursion< Level >::indexRank(), TensorIndexRecursion< Level >::indexRank(), TensorIndexRecursion< Level >::indexRank(), TensorIndexRecursion< 0 >::indexRank(), TensorIndexRecursion< 0 >::indexRank(), TensorIndexRecursion< 0 >::indexRank(), CompactWilsonCloverHelpers< Impl >::INHERIT_COMPACT_CLOVER_TYPES(), innerProduct(), innerProduct(), innerProduct(), innerProduct(), innerProduct(), innerProduct(), innerProductD(), innerProductD(), innerProductD(), innerProductD(), innerProductD(), innerProductD(), innerProductD(), innerProductD(), innerProductD2(), innerProductD2(), innerProductD2(), innerProductD2(), innerProductD2(), innerProductD2(), innerProductD2(), innerProductD2(), iScalar< vInteger >::iScalar(), iScalar< vInteger >::iScalar(), isMatrix(), TensorIndexRecursion< Level >::isMatrix(), TensorIndexRecursion< Level >::isMatrix(), TensorIndexRecursion< Level >::isMatrix(), TensorIndexRecursion< 0 >::isMatrix(), TensorIndexRecursion< 0 >::isMatrix(), TensorIndexRecursion< 0 >::isMatrix(), isScalar(), TensorIndexRecursion< Level >::isScalar(), TensorIndexRecursion< Level >::isScalar(), TensorIndexRecursion< Level >::isScalar(), TensorIndexRecursion< 0 >::isScalar(), TensorIndexRecursion< 0 >::isScalar(), TensorIndexRecursion< 0 >::isScalar(), isVector(), TensorIndexRecursion< Level >::isVector(), TensorIndexRecursion< Level >::isVector(), TensorIndexRecursion< Level >::isVector(), TensorIndexRecursion< 0 >::isVector(), TensorIndexRecursion< 0 >::isVector(), TensorIndexRecursion< 0 >::isVector(), iVector< CComplex, nbasis >::iVector(), LatticeAccelerator< vobj >::LatticeAccelerator(), lmultFlavourIdentity(), lmultFlavourMinusIdentity(), lmultFlavourMinusProjMinus(), lmultFlavourMinusProjPlus(), lmultFlavourMinusSigmaX(), lmultFlavourMinusSigmaY(), lmultFlavourMinusSigmaZ(), lmultFlavourProjMinus(), lmultFlavourProjPlus(), lmultFlavourSigmaX(), lmultFlavourSigmaY(), lmultFlavourSigmaZ(), lmultGammaT(), lmultGammaTGamma5(), lmultGammaX(), lmultGammaXGamma5(), lmultGammaY(), lmultGammaYGamma5(), lmultGammaZ(), lmultGammaZGamma5(), lmultIdentity(), lmultMinusGamma5(), lmultMinusGammaT(), lmultMinusGammaTGamma5(), lmultMinusGammaX(), lmultMinusGammaXGamma5(), lmultMinusGammaY(), lmultMinusGammaYGamma5(), lmultMinusGammaZ(), lmultMinusGammaZGamma5(), lmultMinusIdentity(), lmultMinusSigmaXT(), lmultMinusSigmaXY(), lmultMinusSigmaXZ(), lmultMinusSigmaYT(), lmultMinusSigmaYZ(), lmultMinusSigmaZT(), lmultSigmaXT(), lmultSigmaXY(), lmultSigmaXZ(), lmultSigmaYT(), lmultSigmaYZ(), lmultSigmaZT(), DomainWallVec5dImpl< vComplex, FundamentalRepresentation, CoeffReal >::loadLinkElement(), GparityWilsonImpl< vComplex, FundamentalRepresentation, CoeffReal >::loadLinkElement(), StaggeredImpl< vComplex, FundamentalRepresentation >::loadLinkElement(), StaggeredVec5dImpl< vComplex, FundamentalRepresentation >::loadLinkElement(), WilsonImpl< vComplex, FundamentalRepresentation, CoeffReal >::loadLinkElement(), log(), log(), Grid::Optimization::Mult::mac(), Grid::Optimization::Mult::mac(), Grid_simd2< complex< double >, vComplexD >::mac, Grid_simd2< complex< double >, vComplexD >::mac, Grid_simd2< complex< double >, vComplexD >::mac, Grid_simd< float, SIMD_Ftype >::mac, Grid_simd< float, SIMD_Ftype >::mac, Grid_simd< float, SIMD_Ftype >::mac, mac(), mac(), mac(), mac(), mac(), mac(), mac(), mac(), mac(), mac(), mac(), mac(), mod(), mod(), mod(), Grid_simd2< complex< double >, vComplexD >::mult, Grid_simd2< complex< double >, vComplexD >::mult, Grid_simd2< complex< double >, vComplexD >::mult, Grid_simd< float, SIMD_Ftype >::mult, Grid_simd< float, SIMD_Ftype >::mult, Grid_simd< float, SIMD_Ftype >::mult, mult(), mult(), mult(), mult(), mult(), mult(), mult(), mult(), mult(), mult(), mult(), mult(), WilsonCloverHelpers< Impl >::multClover(), multFlavourIdentity(), multFlavourMinusIdentity(), multFlavourMinusProjMinus(), multFlavourMinusProjPlus(), multFlavourMinusSigmaX(), multFlavourMinusSigmaY(), multFlavourMinusSigmaZ(), multFlavourProjMinus(), multFlavourProjPlus(), multFlavourSigmaX(), multFlavourSigmaY(), multFlavourSigmaZ(), multGamma5(), multGammaT(), multGammaTGamma5(), multGammaX(), multGammaXGamma5(), multGammaY(), multGammaYGamma5(), multGammaZ(), multGammaZGamma5(), multIdentity(), DomainWallVec5dImpl< vComplex, FundamentalRepresentation, CoeffReal >::multLink(), GparityWilsonImpl< vComplex, FundamentalRepresentation, CoeffReal >::multLink(), GparityWilsonImpl< vComplex, FundamentalRepresentation, CoeffReal >::multLink(), StaggeredImpl< vComplex, FundamentalRepresentation >::multLink(), StaggeredVec5dImpl< vComplex, FundamentalRepresentation >::multLink(), WilsonImpl< vComplex, FundamentalRepresentation, CoeffReal >::multLink(), WilsonImpl< vComplex, FundamentalRepresentation, CoeffReal >::multLink(), StaggeredImpl< vComplex, FundamentalRepresentation >::multLinkAdd(), StaggeredVec5dImpl< vComplex, FundamentalRepresentation >::multLinkAdd(), multMinusGamma5(), multMinusGammaT(), multMinusGammaTGamma5(), multMinusGammaX(), multMinusGammaXGamma5(), multMinusGammaY(), multMinusGammaYGamma5(), multMinusGammaZ(), multMinusGammaZGamma5(), multMinusIdentity(), multMinusSigmaXT(), multMinusSigmaXY(), multMinusSigmaXZ(), multMinusSigmaYT(), multMinusSigmaYZ(), multMinusSigmaZT(), multSigmaXT(), multSigmaXY(), multSigmaXZ(), multSigmaYT(), multSigmaYZ(), multSigmaZT(), NAMESPACE_BEGIN(), norm2(), Not(), Not(), Grid_simd2< complex< double >, vComplexD >::Nsimd(), Grid_simd< float, SIMD_Ftype >::Nsimd(), iMatrix< CComplex, nbasis >::Nsimd(), iScalar< vInteger >::Nsimd(), iVector< CComplex, nbasis >::Nsimd(), operator&(), operator&&(), Conj::operator()(), Div::operator()(), Grid::Optimization::Conj::operator()(), Grid::Optimization::Conj::operator()(), Grid::Optimization::Div::operator()(), Grid::Optimization::Div::operator()(), Grid::Optimization::Div::operator()(), Grid::Optimization::Div::operator()(), Grid::Optimization::Div::operator()(), Grid::Optimization::MaddRealPart::operator()(), Grid::Optimization::MaddRealPart::operator()(), Grid::Optimization::Mult::operator()(), Grid::Optimization::Mult::operator()(), Grid::Optimization::Mult::operator()(), Grid::Optimization::MultComplex::operator()(), Grid::Optimization::MultComplex::operator()(), Grid::Optimization::MultRealPart::operator()(), Grid::Optimization::MultRealPart::operator()(), Grid::Optimization::Reduce< S, T >::operator()(), Grid::Optimization::Sub::operator()(), Grid::Optimization::Sub::operator()(), Grid::Optimization::Sub::operator()(), Grid::Optimization::Sub::operator()(), Grid::Optimization::Sub::operator()(), Grid::Optimization::Sum::operator()(), Grid::Optimization::Sum::operator()(), Grid::Optimization::Sum::operator()(), Grid::Optimization::Sum::operator()(), Grid::Optimization::Sum::operator()(), Grid::Optimization::TimesI::operator()(), Grid::Optimization::TimesI::operator()(), Grid::Optimization::TimesMinusI::operator()(), Grid::Optimization::TimesMinusI::operator()(), Grid::Optimization::Vset::operator()(), Grid::Optimization::Vset::operator()(), Grid::Optimization::Vset::operator()(), Grid::Optimization::Vset::operator()(), Grid::Optimization::Vset::operator()(), Grid::Optimization::Vsplat::operator()(), Grid::Optimization::Vsplat::operator()(), Grid::Optimization::Vsplat::operator()(), Grid::Optimization::Vsplat::operator()(), Grid::Optimization::Vsplat::operator()(), Grid::Optimization::Vstore::operator()(), Grid::Optimization::Vstore::operator()(), Grid::Optimization::Vstream::operator()(), Grid::Optimization::Vstream::operator()(), iMatrix< CComplex, nbasis >::operator()(), iMatrix< CComplex, nbasis >::operator()(), iScalar< vInteger >::operator()(), iScalar< vInteger >::operator()(), iVector< CComplex, nbasis >::operator()(), iVector< CComplex, nbasis >::operator()(), LatticeView< typename T::vector_object >::operator()(), MaddRealPart::operator()(), Mult::operator()(), MultComplex::operator()(), MultRealPart::operator()(), Reduce< Out_type, In_type >::operator()(), Reduce< Out_type, In_type >::operator()(), Reduce< Out_type, In_type >::operator()(), Reduce< Out_type, In_type >::operator()(), SimpleCompressorGather< vobj, FaceGatherSimple >::operator()(), Sub::operator()(), Sum::operator()(), TimesI::operator()(), TimesMinusI::operator()(), Vset::operator()(), Vset::operator()(), Vsplat::operator()(), Vsplat::operator()(), Vstore::operator()(), Vstream::operator()(), Grid::GpuComplex< Half2 >::operator*, Grid_simd2< complex< double >, vComplexD >::operator*, Grid_simd2< complex< double >, vComplexD >::operator*, Grid_simd< float, SIMD_Ftype >::operator*, Grid_simd< float, SIMD_Ftype >::operator*, operator*(), operator*(), operator*(), operator*(), operator*(), operator*(), operator*(), operator*(), operator*(), operator*(), operator*(), operator*(), operator*(), operator*(), operator*(), operator*(), operator*(), operator*(), operator*(), operator*(), operator*(), operator*(), operator*(), operator*(), operator*(), operator*(), operator*(), operator*(), operator*(), operator*(), operator*(), operator*(), operator*(), operator*(), operator*(), operator*(), operator*(), operator*(), operator*(), operator*(), operator*(), operator*(), operator*(), operator*(), operator*(), operator*(), Grid::GpuComplex< Half2 >::operator*=(), Grid_simd2< complex< double >, vComplexD >::operator*=(), Grid_simd< float, SIMD_Ftype >::operator*=(), iMatrix< CComplex, nbasis >::operator*=(), iScalar< vInteger >::operator*=(), iVector< CComplex, nbasis >::operator*=(), Grid::GpuComplex< Half2 >::operator+, operator+(), operator+(), operator+(), operator+(), operator+(), operator+(), operator+(), operator+(), operator+(), operator+(), operator+(), operator+(), operator+(), operator+(), operator+(), operator+(), operator+(), operator+(), operator+(), Grid::GpuComplex< Half2 >::operator+=(), Grid_simd2< complex< double >, vComplexD >::operator+=(), Grid_simd< float, SIMD_Ftype >::operator+=(), iMatrix< CComplex, nbasis >::operator+=(), iScalar< vInteger >::operator+=(), iVector< CComplex, nbasis >::operator+=(), Grid::GpuComplex< Half2 >::operator-, Grid_simd2< complex< double >, vComplexD >::operator-, Grid_simd< float, SIMD_Ftype >::operator-, iMatrix< CComplex, nbasis >::operator-, iScalar< vInteger >::operator-, iVector< CComplex, nbasis >::operator-, operator-(), operator-(), operator-(), operator-(), operator-(), operator-(), operator-(), operator-(), operator-(), operator-(), operator-(), operator-(), operator-(), operator-(), operator-(), operator-(), operator-(), operator-(), Grid::GpuComplex< Half2 >::operator-=(), Grid_simd2< complex< double >, vComplexD >::operator-=(), Grid_simd< float, SIMD_Ftype >::operator-=(), iMatrix< CComplex, nbasis >::operator-=(), iScalar< vInteger >::operator-=(), iVector< CComplex, nbasis >::operator-=(), Grid_simd2< complex< double >, vComplexD >::operator/, Grid_simd2< complex< double >, vComplexD >::operator/, Grid_simd< float, SIMD_Ftype >::operator/, Grid_simd< float, SIMD_Ftype >::operator/, operator/(), operator/(), Grid::GpuComplex< Half2 >::operator=(), Grid_simd2< complex< double >, vComplexD >::operator=(), Grid_simd2< complex< double >, vComplexD >::operator=(), Grid_simd2< complex< double >, vComplexD >::operator=(), Grid_simd< float, SIMD_Ftype >::operator=(), Grid_simd< float, SIMD_Ftype >::operator=(), Grid_simd< float, SIMD_Ftype >::operator=(), iMatrix< CComplex, nbasis >::operator=(), iMatrix< CComplex, nbasis >::operator=(), iMatrix< CComplex, nbasis >::operator=(), iScalar< vInteger >::operator=(), iScalar< vInteger >::operator=(), iScalar< vInteger >::operator=(), iVector< CComplex, nbasis >::operator=(), iVector< CComplex, nbasis >::operator=(), iVector< CComplex, nbasis >::operator=(), operator==(), operator==(), operator==(), AcceleratorVector< int, STENCIL_MAX >::operator[](), AcceleratorVector< int, STENCIL_MAX >::operator[](), LatticeView< typename T::vector_object >::operator[](), operator|(), operator||(), LatticeAccelerator< vobj >::oSites(), outerProduct(), outerProduct(), outerProduct(), outerProduct(), peekIndex(), peekIndex(), TensorIndexRecursion< Level >::peekIndex(), TensorIndexRecursion< Level >::peekIndex(), TensorIndexRecursion< Level >::peekIndex(), TensorIndexRecursion< Level >::peekIndex(), TensorIndexRecursion< Level >::peekIndex(), TensorIndexRecursion< Level >::peekIndex(), Grid_simd2< complex< double >, vComplexD >::permute, Grid_simd< float, SIMD_Ftype >::permute, iMatrix< CComplex, nbasis >::permute, iScalar< vInteger >::permute, iVector< CComplex, nbasis >::permute, permute(), permute(), permute(), permute(), Grid::Optimization::Permute::Permute0(), Grid_simd2< complex< double >, vComplexD >::permute0, Grid_simd< float, SIMD_Ftype >::permute0, Grid::Optimization::Permute::Permute1(), Grid_simd2< complex< double >, vComplexD >::permute1, Grid_simd< float, SIMD_Ftype >::permute1, Grid::Optimization::Permute::Permute2(), Grid_simd2< complex< double >, vComplexD >::permute2, Grid_simd< float, SIMD_Ftype >::permute2, Grid::Optimization::Permute::Permute3(), Grid_simd2< complex< double >, vComplexD >::permute3, Grid_simd< float, SIMD_Ftype >::permute3, Grid_simd2< complex< double >, vComplexD >::permute4, Grid::Optimization::Permute::PermuteN(), Grid::Optimization::Permute::PermuteN(), Grid::Optimization::Permute::PermuteN(), pow(), pow(), pow(), pow(), precisionChange(), precisionChange(), precisionChange(), precisionChange(), precisionChange(), precisionChange(), precisionChange(), precisionChange(), precisionChange(), precisionChange(), precisionChange(), precisionChange(), precisionChange(), precisionChange(), precisionChange(), precisionChange(), precisionChange(), precisionChange(), precisionChange(), precisionChange(), predicatedWhere(), iMatrix< CComplex, nbasis >::prefetch, iScalar< vInteger >::prefetch, iVector< CComplex, nbasis >::prefetch, Grid::prefetch_HINT_T0(), prefetch_HINT_T0(), LatticeMatrix< ncolour, group_name >::ProjectOnGeneralGroup(), LatticeMatrix< ncolour, group_name >::ProjectOnGeneralGroup(), LatticeMatrix< ncolour, group_name >::ProjectOnGeneralGroup(), ProjectOnGeneralGroup(), ProjectOnGeneralGroup(), ProjectOnGeneralGroup(), ProjectOnGeneralGroup(), ProjectOnGeneralGroup(), ProjectOnGeneralGroup(), ProjectOnGroup(), ProjectOnGroup(), ProjectOnGroup(), ProjectOnSpGroup(), ProjectOnSpGroup(), ProjectOnSpGroup(), projImag(), projImag(), projReal(), projReal(), AcceleratorVector< int, STENCIL_MAX >::push_back(), Grid_simd2< complex< double >, vComplexD >::putlane(), Grid_simd< float, SIMD_Ftype >::putlane(), putlane(), putlane(), putlane(), rbroadcast(), rbroadcast(), Grid::GpuComplex< Half2 >::real(), real(), real(), real(), real(), real(), real(), real(), real(), real(), real_madd(), real_madd(), Grid::GpuComplex< Half2 >::real_mult, real_mult(), real_mult(), RedBlackCheckerBoardFromOindex(), Grid_simd2< complex< double >, vComplexD >::Reduce, Grid_simd< float, SIMD_Ftype >::Reduce, Reduce(), Reduce(), Reduce(), Reduce(), Reduce(), AcceleratorVector< int, STENCIL_MAX >::resize(), AcceleratorVector< int, STENCIL_MAX >::resize(), rmultFlavourIdentity(), rmultFlavourMinusIdentity(), rmultFlavourMinusProjMinus(), rmultFlavourMinusProjPlus(), rmultFlavourMinusSigmaX(), rmultFlavourMinusSigmaY(), rmultFlavourMinusSigmaZ(), rmultFlavourProjMinus(), rmultFlavourProjPlus(), rmultFlavourSigmaX(), rmultFlavourSigmaY(), rmultFlavourSigmaZ(), rmultGamma5(), rmultGammaT(), rmultGammaTGamma5(), rmultGammaX(), rmultGammaXGamma5(), rmultGammaY(), rmultGammaYGamma5(), rmultGammaZ(), rmultGammaZGamma5(), rmultIdentity(), rmultMinusGamma5(), rmultMinusGammaT(), rmultMinusGammaTGamma5(), rmultMinusGammaX(), rmultMinusGammaXGamma5(), rmultMinusGammaY(), rmultMinusGammaYGamma5(), rmultMinusGammaZ(), rmultMinusGammaZGamma5(), rmultMinusIdentity(), rmultMinusSigmaXT(), rmultMinusSigmaXY(), rmultMinusSigmaXZ(), rmultMinusSigmaYT(), rmultMinusSigmaYZ(), rmultMinusSigmaZT(), rmultSigmaXT(), rmultSigmaXY(), rmultSigmaXZ(), rmultSigmaYT(), rmultSigmaYZ(), rmultSigmaZT(), Grid::Optimization::Rotate::rotate(), Grid::Optimization::Rotate::rotate(), Grid::Optimization::Rotate::rotate(), Grid::Optimization::Rotate::rotate(), Grid::Optimization::Rotate::rotate(), Grid::Optimization::Rotate::rotate(), Grid::Optimization::Rotate::rotate(), iMatrix< CComplex, nbasis >::rotate, iScalar< vInteger >::rotate, iVector< CComplex, nbasis >::rotate, rotate(), rotate(), Rotate::rotate(), Grid::Optimization::Rotate::rotate_template(), Grid::Optimization::Rotate::rotate_template(), Grid::Optimization::Rotate::rotate_template(), rsplat(), rsplat(), sfw_float_to_half(), sfw_half_to_float(), Grid_simd2< complex< double >, vComplexD >::SimdApply, Grid_simd< float, SIMD_Ftype >::SimdApply, Grid_simd2< complex< double >, vComplexD >::SimdApplyBinop, Grid_simd< float, SIMD_Ftype >::SimdApplyBinop, sin(), sin(), AcceleratorVector< int, STENCIL_MAX >::size(), LatticeView< typename T::vector_object >::size(), spProj5m(), spProj5m(), spProj5m(), spProj5m(), spProj5m(), spProj5m(), spProj5m(), spProj5m(), spProj5m(), spProj5p(), spProj5p(), spProj5p(), spProj5p(), spProj5p(), spProj5p(), spProj5p(), spProj5p(), spProj5p(), spProjTm(), spProjTm(), spProjTm(), spProjTm(), spProjTp(), spProjTp(), spProjTp(), spProjTp(), spProjXm(), spProjXm(), spProjXm(), spProjXm(), spProjXp(), spProjXp(), spProjXp(), spProjXp(), spProjYm(), spProjYm(), spProjYm(), spProjYm(), spProjYp(), spProjYp(), spProjYp(), spProjYp(), spProjZm(), spProjZm(), spProjZm(), spProjZm(), spProjZp(), spProjZp(), spProjZp(), spProjZp(), spRecon5m(), spRecon5m(), spRecon5m(), spRecon5m(), spRecon5p(), spRecon5p(), spRecon5p(), spRecon5p(), spReconTm(), spReconTm(), spReconTm(), spReconTm(), spReconTp(), spReconTp(), spReconTp(), spReconTp(), spReconXm(), spReconXm(), spReconXm(), spReconXm(), spReconXp(), spReconXp(), spReconXp(), spReconXp(), spReconYm(), spReconYm(), spReconYm(), spReconYm(), spReconYp(), spReconYp(), spReconYp(), spReconYp(), spReconZm(), spReconZm(), spReconZm(), spReconZm(), spReconZp(), spReconZp(), spReconZp(), spReconZp(), SpTa(), SpTa(), SpTa(), sqrt(), sqrt(), stencilIndex(), Grid::Optimization::PrecisionChange::StoD(), Grid::Optimization::PrecisionChange::StoD(), PrecisionChange::StoD(), Grid::Optimization::PrecisionChange::StoH(), Grid::Optimization::PrecisionChange::StoH(), PrecisionChange::StoH(), LatticeMatrix< ncolour, group_name >::su2SubGroupIndex(), su2SubGroupIndex(), su2SubGroupIndex(), Grid_simd2< complex< double >, vComplexD >::sub, Grid_simd2< complex< double >, vComplexD >::sub, Grid_simd2< complex< double >, vComplexD >::sub, Grid_simd< float, SIMD_Ftype >::sub, Grid_simd< float, SIMD_Ftype >::sub, Grid_simd< float, SIMD_Ftype >::sub, sub(), sub(), sub(), sub(), sub(), sub(), sub(), sub(), sub(), sub(), Ta(), Ta(), Ta(), TensorRemove(), TensorRemove(), TensorRemove(), Grid::timesI(), Grid::timesI(), timesI(), timesI(), timesI(), timesI(), timesI(), timesI(), timesI(), timesI(), timesI(), timesI(), timesI(), timesI(), timesI(), timesI(), Grid::timesMinusI(), Grid::timesMinusI(), timesMinusI(), timesMinusI(), timesMinusI(), timesMinusI(), timesMinusI(), timesMinusI(), timesMinusI(), timesMinusI(), timesMinusI(), timesMinusI(), timesMinusI(), timesMinusI(), timesMinusI(), timesMinusI(), toComplex(), toComplex(), toComplex(), toComplex(), toComplex(), toComplex(), toReal(), toReal(), toReal(), toReal(), toReal(), toReal(), toReal(), toReal(), trace(), trace(), trace(), trace(), trace(), trace(), trace(), trace(), trace(), TensorIndexRecursion< Level >::traceIndex(), TensorIndexRecursion< Level >::traceIndex(), TensorIndexRecursion< Level >::traceIndex(), traceIndex(), traceProduct(), traceProduct(), traceProduct(), transpose(), transpose(), transpose(), transpose(), transposeIndex(), CompactWilsonCloverHelpers< Impl >::triangle_elem(), CompactWilsonCloverHelpers< Impl >::triangle_index(), trinary(), Grid::Optimization::Rotate::tRotate(), Rotate::tRotate(), unary(), Grid::v_prefetch0(), v_prefetch0(), iMatrix< CComplex, nbasis >::vbroadcast, iScalar< vInteger >::vbroadcast, iVector< CComplex, nbasis >::vbroadcast, vbroadcast(), vbroadcast(), vcomplex_i(), vcomplex_i(), vfalse(), vfalse(), visign(), visign(), vone(), vone(), Grid_simd2< complex< double >, vComplexD >::vprefetch, Grid_simd< float, SIMD_Ftype >::vprefetch, vrsign(), vrsign(), Grid_simd2< complex< double >, vComplexD >::vset, Grid_simd< float, SIMD_Ftype >::vset, vsplat(), vsplat(), vsplat(), vsplat(), vsplat(), vsplat(), Grid_simd2< complex< double >, vComplexD >::vstore, Grid_simd< float, SIMD_Ftype >::vstore, iMatrix< CComplex, nbasis >::vstream, iScalar< vInteger >::vstream, iVector< CComplex, nbasis >::vstream, vstream(), vstream(), vstream(), vstream(), vstream(), vstream(), vstream(), vtrue(), vtrue(), vzero(), vzero(), iMatrix< CComplex, nbasis >::zeroit, iScalar< vInteger >::zeroit, iVector< CComplex, nbasis >::zeroit, zeroit(), zeroit(), zeroit(), zeroit(), zeroit(), zeroit(), zeroit(), and zeroit().

◆ accelerator_for

#define accelerator_for	(		iterator,
			num,
			nsimd,
			... )

Definition at line 609 of file Accelerator.h.

Referenced by acceleratorPickCheckerboard(), acceleratorSetCheckerboard(), add(), add(), add(), GaugeImplTypes< vComplex, Nc >::AddLink(), adj(), ag5xpbg5y_ssp(), ag5xpby_ssp(), CompactWilsonCloverHelpers< Impl >::ApplyBoundaryMask(), MomentumFilterApplyPhase< MomentaField >::applyFilter(), A2Autils< FImpl >::AslashField(), axpbg5y_ssp(), axpby(), axpby_norm_fast(), axpby_ssp(), axpby_ssp_pminus(), axpby_ssp_pplus(), axpibg5x(), axpy(), BaryonUtils< FImpl >::BaryonGamma3pt(), basisRotate(), basisRotateJ(), batchBlockProject(), MultiGeneralCoarsenedMatrix< Fobj, CComplex, nbasis >::BLAStoGrid(), blockInnerProduct(), blockInnerProductD(), blockProject(), blockProjectFast(), blockSum(), blockZAXPY(), CoarsenedMatrix< Fobj, CComplex, nbasis >::CoarsenOperator(), GeneralCoarsenedMatrix< Fobj, CComplex, nbasis >::CoarsenOperator(), MultiGeneralCoarsenedMatrix< Fobj, CComplex, nbasis >::CoarsenOperator(), conjugate(), BaryonUtils< FImpl >::ContractBaryons(), BaryonUtils< FImpl >::ContractBaryonsMatrix(), CompactWilsonCloverHelpers< Impl >::ConvertLayout(), CompactWilsonCloverHelpers< Impl >::ConvertLayout(), convertType(), Copy_plane(), Copy_plane_permute(), Aggregation< Fobj, CComplex, nbasis >::CreateSubspaceChebyshev(), WilsonKernels< Impl >::DhopDirAll(), CoarsenedMatrix< Fobj, CComplex, nbasis >::DhopInternal(), div(), CoarsenedMatrix< Fobj, CComplex, nbasis >::DselfInternal(), expMat(), MultiRHSBlockProject< Field >::ExportCoarseGridVectors(), MultiRHSBlockProject< Field >::ExportFineGridVectors(), ExtractSliceFast(), WilsonCloverHelpers< Impl >::fillCloverXT(), WilsonCloverHelpers< Impl >::fillCloverXY(), WilsonCloverHelpers< Impl >::fillCloverXZ(), WilsonCloverHelpers< Impl >::fillCloverYT(), WilsonCloverHelpers< Impl >::fillCloverYZ(), WilsonCloverHelpers< Impl >::fillCloverZT(), G5C(), G5R5(), Gather_plane_extract(), Gather_plane_simple(), GatherSlice(), MultiGeneralCoarsenedMatrix< Fobj, CComplex, nbasis >::GridtoBLAS(), CompactExpCloverHelpers< Impl >::IdentityTimesC(), ExpCloverHelpers< Impl >::IdentityTimesC(), imag(), MultiRHSBlockProject< Field >::ImportCoarseGridVectors(), MultiRHSBlockProject< Field >::ImportFineGridVectors(), MultiRHSBlockCGLinalg< Field >::InnerProductMatrix(), innerProductNorm(), GparityWilsonImpl< vComplex, FundamentalRepresentation, CoeffReal >::InsertForce5D(), WilsonImpl< vComplex, FundamentalRepresentation, CoeffReal >::InsertForce5D(), InsertSliceFast(), LatticeMatrix< ncolour, group_name >::LieAlgebraProject(), localCopyRegion(), localInnerProduct(), localInnerProductD(), localNorm2(), CoarsenedMatrix< Fobj, CComplex, nbasis >::M(), CayleyFermion5D< Impl >::M5D(), DomainWallEOFAFermion< Impl >::M5D(), MobiusEOFAFermion< Impl >::M5D(), DomainWallEOFAFermion< Impl >::M5Ddag(), MobiusEOFAFermion< Impl >::M5Ddag(), mac(), mac(), mac(), CoarsenedMatrix< Fobj, CComplex, nbasis >::MdagNonHermitian(), CoarsenedMatrix< Fobj, CComplex, nbasis >::MdirCalc(), A2Autils< FImpl >::MesonField(), mod(), CompactWilsonCloverHelpers< Impl >::MooeeKernel_gpu(), GeneralCoarsenedMatrix< Fobj, CComplex, nbasis >::Mult(), mult(), mult(), mult(), WilsonCloverHelpers< Impl >::multCloverField(), WilsonImpl< vComplex, FundamentalRepresentation, CoeffReal >::multLinkField(), BiCGSTAB< Field >::operator()(), ConjugateGradient< Field >::operator()(), Lattice< CoarseSiteVector >::operator=(), Lattice< CoarseSiteVector >::operator=(), Lattice< CoarseSiteVector >::operator=(), Lattice< CoarseSiteVector >::operator=(), Lattice< CoarseSiteVector >::operator=(), Lattice< CoarseSiteVector >::operator=(), outerProduct(), PeekIndex(), PeekIndex(), PokeIndex(), PokeIndex(), pow(), precisionChange(), precisionChangeFast(), rankInnerProduct(), real(), WilsonLoops< PeriodicGimplR >::RectStaplePaddedAll(), Scatter_plane_merge(), Scatter_plane_simple(), ScatterSlice(), BaryonUtils< FImpl >::SigmaToNucleonEye(), BaryonUtils< FImpl >::SigmaToNucleonNonEye(), sliceSumReduction_large(), Smear_HISQ< Gimpl >::smear(), WilsonLoops< PeriodicGimplR >::Staple(), WilsonLoops< PeriodicGimplR >::StaplePaddedAll(), su2Extract(), su2Insert(), sub(), sub(), sub(), sumD_gpu_large(), toComplex(), toReal(), TraceIndex(), traceProduct(), traceProduct(), TransposeIndex(), GaugeImplTypes< vComplex, Nc >::update_field(), and BaryonUtils< FImpl >::XiToSigmaEye().

◆ accelerator_forNB

#define accelerator_forNB	(		iterator,
			num,
			nsimd,
			... )

Definition at line 610 of file Accelerator.h.

Referenced by CartesianStencil< SiteSpinor, SiteSpinor, ImplParams >::CommsCopy(), CartesianStencil< SiteSpinor, SiteSpinor, ImplParams >::CompressPacket(), FaceGatherSimple::DecompressFace(), CartesianStencil< SiteSpinor, SiteSpinor, ImplParams >::DecompressPacket(), FaceGatherSimple::Gather_plane_exchange(), FaceGatherSimple::Gather_plane_simple(), and FaceGatherSimple::MergeFace().

◆ accelerator_barrier

#define accelerator_barrier ( dummy )

Definition at line 611 of file Accelerator.h.

Referenced by CartesianStencil< SiteSpinor, SiteSpinor, ImplParams >::CommunicateBegin(), CartesianStencil< SiteSpinor, SiteSpinor, ImplParams >::HaloExchange(), CartesianStencil< SiteSpinor, SiteSpinor, ImplParams >::HaloGather(), WilsonStencil< SiteSpinor, SiteHalfSpinor, ImplParams >::HaloGatherOpt(), sumD_gpu_small(), and GridBLAS::synchronise().

◆ accelerator_for2d

#define accelerator_for2d	(		iter1,
			num1,
			iter2,
			num2,
			nsimd,
			... )

Definition at line 612 of file Accelerator.h.

Typedef Documentation

◆ acceleratorEvent_t

typedef int acceleratorEvent_t

Definition at line 595 of file Accelerator.h.

Function Documentation

◆ NAMESPACE_BEGIN()

NAMESPACE_BEGIN ( Grid )

References accelerator_inline, and acceleratorAbortOnGpuError.

◆ acceleratorThreads() [1/2]

uint32_t acceleratorThreads ( void )

Definition at line 7 of file Accelerator.cc.

References accelerator_threads.

Referenced by GridParseLayout().

◆ acceleratorThreads() [2/2]

void acceleratorThreads ( uint32_t t )

Definition at line 8 of file Accelerator.cc.

References accelerator_threads.

◆ acceleratorInit()

void acceleratorInit ( void )

Definition at line 287 of file Accelerator.cc.

Referenced by Grid_init().

◆ acceleratorPin()

void acceleratorPin	(	void *	ptr,
		unsigned long	bytes )

inline

Definition at line 561 of file Accelerator.h.

◆ acceleratorMem()

void acceleratorMem ( void )

inline

Definition at line 597 of file Accelerator.h.

◆ acceleratorSIMTlane()

accelerator_inline int acceleratorSIMTlane ( int Nsimd )

Definition at line 614 of file Accelerator.h.

References accelerator_inline.

Referenced by WilsonCompressorTemplate< HCS, HS, S, WilsonProjector >< SiteHalfCommSpinor, SiteHalfSpinor, SiteSpinor >::CompressExchange(), CartesianStencil< SiteSpinor, SiteSpinor, ImplParams >::CompressPacket(), CartesianStencil< SiteSpinor, SiteSpinor, ImplParams >::DecompressPacket(), WilsonKernels< Impl >::DhopDirK(), StaggeredKernels< Impl >::DhopImproved(), StaggeredKernels< Impl >::DhopNaive(), StaggeredKernels< Impl >::DhopSiteGenericExt(), StaggeredKernels< Impl >::DhopSiteGenericInt(), StaggeredKernels< Impl >::DhopSiteHand(), StaggeredKernels< Impl >::DhopSiteHandExt(), StaggeredKernels< Impl >::DhopSiteHandInt(), eval(), exchangeSIMT(), MultiRHSBlockProject< Field >::ExportCoarseGridVectors(), MultiRHSBlockProject< Field >::ExportFineGridVectors(), GatherSlice(), WilsonKernels< Impl >::GenericDhopSite(), WilsonKernels< Impl >::GenericDhopSiteDag(), WilsonKernels< Impl >::GenericDhopSiteDagExt(), WilsonKernels< Impl >::GenericDhopSiteDagInt(), WilsonKernels< Impl >::GenericDhopSiteExt(), WilsonKernels< Impl >::GenericDhopSiteInt(), WilsonKernels< Impl >::HandDhopSite(), WilsonKernels< Impl >::HandDhopSiteDag(), WilsonKernels< Impl >::HandDhopSiteDagExt(), WilsonKernels< Impl >::HandDhopSiteDagInt(), WilsonKernels< Impl >::HandDhopSiteExt(), WilsonKernels< Impl >::HandDhopSiteInt(), MultiRHSBlockProject< Field >::ImportCoarseGridVectors(), MultiRHSBlockProject< Field >::ImportFineGridVectors(), GparityWilsonImpl< vComplex, FundamentalRepresentation, CoeffReal >::multLink(), and ScatterSlice().

◆ acceleratorCopyToDevice()

void acceleratorCopyToDevice	(	void *	from,
		void *	to,
		size_t	bytes )

inline

Definition at line 616 of file Accelerator.h.

References thread_bcopy().

Referenced by acceleratorCopyToDeviceAsynch(), acceleratorPut(), basisRotate(), CartesianStencil< SiteSpinor, SiteSpinor, ImplParams >::BuildSurfaceList(), CartesianStencil< SiteSpinor, SiteSpinor, ImplParams >::CartesianStencil(), Cshift_comms(), Cshift_comms_simd(), MultiRHSDeflation< Field >::DeflateSources(), PaddedCell::Face_exchange(), CoarsenedMatrix< Fobj, CComplex, nbasis >::fillFactor(), CartesianStencil< SiteSpinor, SiteSpinor, ImplParams >::Gather(), CartesianStencil< SiteSpinor, SiteSpinor, ImplParams >::GatherSimd(), GridBLAS::gemmBatched(), GridBLAS::gemmBatched(), GridBLAS::gemmBatched(), GridBLAS::gemmBatched(), MultiRHSBlockCGLinalg< Field >::InnerProductMatrix(), CayleyFermion5D< Impl >::M5D(), DomainWallEOFAFermion< Impl >::M5D(), MobiusEOFAFermion< Impl >::M5D(), DomainWallEOFAFermion< Impl >::M5Ddag(), MobiusEOFAFermion< Impl >::M5Ddag(), MapCshiftCopy(), MultiRHSBlockCGLinalg< Field >::MulMatrix(), GeneralCoarsenedMatrix< Fobj, CComplex, nbasis >::Mult(), WilsonLoops< PeriodicGimplR >::RectStaplePaddedAll(), SharedMemory::SharedMemoryTest(), and WilsonLoops< PeriodicGimplR >::StaplePaddedAll().

◆ acceleratorCopyFromDevice()

void acceleratorCopyFromDevice	(	void *	from,
		void *	to,
		size_t	bytes )

inline

Definition at line 617 of file Accelerator.h.

References thread_bcopy().

Referenced by acceleratorCopyFromDeviceAsynch(), acceleratorGet(), MultiRHSBlockProject< Field >::blasNorm2(), Cshift_comms(), Cshift_comms_simd(), MultiRHSDeflation< Field >::DeflateSources(), PaddedCell::Face_exchange(), GridBLAS::gemmBatched(), MultiRHSBlockCGLinalg< Field >::InnerProductMatrix(), SharedMemory::SharedMemoryTest(), and sumD_gpu_small().

◆ acceleratorCopyToDeviceAsynch()

acceleratorEvent_t acceleratorCopyToDeviceAsynch	(	void *	from,
		void *	to,
		size_t	bytes )

inline

Definition at line 618 of file Accelerator.h.

References acceleratorCopyToDevice().

◆ acceleratorCopyFromDeviceAsynch()

acceleratorEvent_t acceleratorCopyFromDeviceAsynch	(	void *	from,
		void *	to,
		size_t	bytes )

inline

Definition at line 619 of file Accelerator.h.

References acceleratorCopyFromDevice().

◆ acceleratorEventWait()

void acceleratorEventWait ( acceleratorEvent_t ev )

inline

Definition at line 620 of file Accelerator.h.

Referenced by acceleratorEventIsComplete().

◆ acceleratorEventIsComplete()

int acceleratorEventIsComplete ( acceleratorEvent_t ev )

inline

Definition at line 621 of file Accelerator.h.

References acceleratorEventWait().

◆ acceleratorCopyDeviceToDeviceAsynch()

acceleratorEvent_t acceleratorCopyDeviceToDeviceAsynch	(	void *	from,
		void *	to,
		size_t	bytes )

inline

Definition at line 622 of file Accelerator.h.

References thread_bcopy().

Referenced by acceleratorCopyDeviceToDevice(), and CartesianCommunicator::StencilSendToRecvFromBegin().

◆ acceleratorCopySynchronise()

void acceleratorCopySynchronise ( void )

inline

Definition at line 624 of file Accelerator.h.

Referenced by acceleratorCopyDeviceToDevice(), CartesianStencil< SiteSpinor, SiteSpinor, ImplParams >::CommunicateBegin(), and CartesianCommunicator::StencilSendToRecvFromComplete().

◆ acceleratorIsCommunicable()

int acceleratorIsCommunicable ( void * ptr )

inline

Definition at line 626 of file Accelerator.h.

Referenced by CartesianCommunicator::SendToRecvFrom().

◆ acceleratorMemSet()

void acceleratorMemSet	(	void *	base,
		int	value,
		size_t	bytes )

inline

Definition at line 627 of file Accelerator.h.

References base.

Referenced by GridBLAS::benchmark(), CartesianStencil< SiteSpinor, SiteSpinor, ImplParams >::GatherSimd(), MultiRHSBlockProject< Field >::ImportFineGridVectors(), and GlobalSharedMemory::SharedMemoryZero().

◆ acceleratorAllocShared()

void * acceleratorAllocShared ( size_t bytes )

inline

Definition at line 636 of file Accelerator.h.

References GRID_ALLOC_ALIGN.

Referenced by MemoryManager::CpuAllocate(), and MemoryManager::SharedAllocate().

◆ acceleratorAllocDevice()

void * acceleratorAllocDevice ( size_t bytes )

inline

Definition at line 637 of file Accelerator.h.

References GRID_ALLOC_ALIGN.

Referenced by MemoryManager::AcceleratorAllocate(), WilsonLoops< PeriodicGimplR >::RectStaplePaddedAll(), and WilsonLoops< PeriodicGimplR >::StaplePaddedAll().

◆ acceleratorFreeShared()

void acceleratorFreeShared ( void * ptr )

inline

Definition at line 638 of file Accelerator.h.

Referenced by MemoryManager::CpuFree(), and MemoryManager::SharedFree().

◆ acceleratorFreeDevice()

void acceleratorFreeDevice ( void * ptr )

inline

Definition at line 639 of file Accelerator.h.

Referenced by MemoryManager::AcceleratorFree(), and precisionChangeWorkspace::~precisionChangeWorkspace().

◆ acceleratorAllocCpu()

void * acceleratorAllocCpu ( size_t bytes )

inline

Definition at line 648 of file Accelerator.h.

References GRID_ALLOC_ALIGN.

◆ acceleratorFreeCpu()

void acceleratorFreeCpu ( void * ptr )

inline

Definition at line 649 of file Accelerator.h.

◆ acceleratorFenceComputeStream()

void acceleratorFenceComputeStream ( void )

inline

Definition at line 660 of file Accelerator.h.

Referenced by CartesianStencil< SiteSpinor, SiteSpinor, ImplParams >::CommsCopy(), CartesianStencil< SiteSpinor, SiteSpinor, ImplParams >::CommsMerge(), WilsonKernels< Impl >::DhopDagKernel(), and WilsonKernels< Impl >::DhopKernel().

◆ acceleratorSynchronise()

accelerator_inline void acceleratorSynchronise ( void )

Definition at line 666 of file Accelerator.h.

References accelerator_inline.

Referenced by CoarsenedMatrix< Fobj, CComplex, nbasis >::DselfInternal(), CoarsenedMatrix< Fobj, CComplex, nbasis >::M(), CoarsenedMatrix< Fobj, CComplex, nbasis >::MdagNonHermitian(), CoarsenedMatrix< Fobj, CComplex, nbasis >::MdirCalc(), and reduceBlock().

◆ acceleratorSynchroniseAll()

accelerator_inline void acceleratorSynchroniseAll ( void )

Definition at line 675 of file Accelerator.h.

References accelerator_inline.

Referenced by reduceBlock(), and reduceKernel().

◆ acceleratorFence()

accelerator_inline void acceleratorFence ( void )

Definition at line 690 of file Accelerator.h.

References accelerator_inline.

Referenced by reduceKernel().

◆ acceleratorCopyDeviceToDevice()

void acceleratorCopyDeviceToDevice	(	void *	from,
		void *	to,
		size_t	bytes )

inline

Definition at line 706 of file Accelerator.h.

References acceleratorCopyDeviceToDeviceAsynch(), and acceleratorCopySynchronise().

Referenced by MultiRHSDeflation< Field >::DeflateSources(), MultiRHSDeflation< Field >::ImportEigenVector(), MultiRHSBlockCGLinalg< Field >::InnerProductMatrix(), and MultiRHSBlockCGLinalg< Field >::MulMatrix().

◆ acceleratorPut()

template<class T>

void acceleratorPut	(	T &	dev,
		const T &	host )

Definition at line 712 of file Accelerator.h.

References acceleratorCopyToDevice().

Referenced by BaryonUtils< FImpl >::BaryonGamma3pt(), basisRotate(), basisRotateJ(), GridBLAS::benchmark(), MultiRHSBlockProject< Field >::blockProject(), MultiRHSBlockProject< Field >::blockPromote(), MultiRHSDeflation< Field >::DeflateSources(), CoarsenedMatrix< Fobj, CComplex, nbasis >::DhopInternal(), GeneralLocalStencil::GeneralLocalStencil(), MultiRHSBlockCGLinalg< Field >::InnerProductMatrix(), CoarsenedMatrix< Fobj, CComplex, nbasis >::M(), CoarsenedMatrix< Fobj, CComplex, nbasis >::MdagNonHermitian(), CoarsenedMatrix< Fobj, CComplex, nbasis >::MdirCalc(), MultiRHSBlockCGLinalg< Field >::MulMatrix(), MultiGeneralCoarsenedMatrix< Fobj, CComplex, nbasis >::MultiGeneralCoarsenedMatrix(), Lattice< CoarseSiteVector >::operator=(), BaryonUtils< FImpl >::SigmaToNucleonEye(), BaryonUtils< FImpl >::SigmaToNucleonNonEye(), and BaryonUtils< FImpl >::XiToSigmaEye().

◆ acceleratorGet()

template<class T>

T acceleratorGet ( T & dev )

Definition at line 716 of file Accelerator.h.

References acceleratorCopyFromDevice().

◆ NAMESPACE_END()

NAMESPACE_END ( Grid )

Grid
threads
Accelerator.h
Generated by 1.16.1