fused_exterior_ndeg_tm_dslash_cuda_gen Namespace Reference

Functions
def	complexify (a)
	complex numbers ######################################################################## More...
def	complexToStr (c)
def	gplus (g1, g2)
def	gminus (g1, g2)
def	projectorToStr (p)
def	indent (code)
	code generation ######################################################################## More...
def	block (code)
def	sign (x)
def	nthFloat4 (n)
def	nthFloat2 (n)
def	in_re (s, c)
def	in_im (s, c)
def	g_re (d, m, n)
def	g_im (d, m, n)
def	out1_re (s, c)
def	out1_im (s, c)
def	out2_re (s, c)
def	out2_im (s, c)
def	h1_re (h, c)
def	h1_im (h, c)
def	h2_re (h, c)
def	h2_im (h, c)
def	a_re (b, s, c)
def	a_im (b, s, c)
def	tmp_re (s, c)
def	tmp_im (s, c)
def	acc_re (s, c)
def	acc_im (s, c)
def	acc1_re (s, c)
def	acc1_im (s, c)
def	acc2_re (s, c)
def	acc2_im (s, c)
def	def_input_spinor ()
def	def_gauge ()
def	def_output_spinor ()
def	prolog ()
def	gen (dir, pack_only=False)
def	twisted ()
def	xpay ()
def	epilog ()
def	generate_dslash ()
	temporal More...
def	generate_dslash_kernels (arch)

Variables
def	id
	projector matrices ######################################################################## More...
def	gamma1
def	gamma2
def	gamma3
def	gamma4
def	igamma5
list	projectors
int	i = 3*s+c
	start here More...
string	a1 = ""
string	a2 = ""
bool	dslash = False
bool	dagger = False
bool	twist = False
int	sharedFloatsPerFlavor = 0
bool	sharedDslash = False
int	arch = 200

Function Documentation

a_im()

def fused_exterior_ndeg_tm_dslash_cuda_gen.a_im	(		b,
			s,
			c
	)

Definition at line 131 of file fused_exterior_ndeg_tm_dslash_cuda_gen.py.

a_re()

def fused_exterior_ndeg_tm_dslash_cuda_gen.a_re	(		b,
			s,
			c
	)

Definition at line 130 of file fused_exterior_ndeg_tm_dslash_cuda_gen.py.

acc1_im()

def fused_exterior_ndeg_tm_dslash_cuda_gen.acc1_im	(		s,
			c
	)

Definition at line 139 of file fused_exterior_ndeg_tm_dslash_cuda_gen.py.

acc1_re()

def fused_exterior_ndeg_tm_dslash_cuda_gen.acc1_re	(		s,
			c
	)

Definition at line 138 of file fused_exterior_ndeg_tm_dslash_cuda_gen.py.

acc2_im()

def fused_exterior_ndeg_tm_dslash_cuda_gen.acc2_im	(		s,
			c
	)

Definition at line 141 of file fused_exterior_ndeg_tm_dslash_cuda_gen.py.

acc2_re()

def fused_exterior_ndeg_tm_dslash_cuda_gen.acc2_re	(		s,
			c
	)

Definition at line 140 of file fused_exterior_ndeg_tm_dslash_cuda_gen.py.

acc_im()

def fused_exterior_ndeg_tm_dslash_cuda_gen.acc_im	(		s,
			c
	)

Definition at line 137 of file fused_exterior_ndeg_tm_dslash_cuda_gen.py.

acc_re()

def fused_exterior_ndeg_tm_dslash_cuda_gen.acc_re	(		s,
			c
	)

Definition at line 136 of file fused_exterior_ndeg_tm_dslash_cuda_gen.py.

block()

def fused_exterior_ndeg_tm_dslash_cuda_gen.block

(

code

)

Definition at line 102 of file fused_exterior_ndeg_tm_dslash_cuda_gen.py.

References indent().

Referenced by epilog(), gen(), and twisted().

Here is the call graph for this function:

Here is the caller graph for this function:

complexify()

def fused_exterior_ndeg_tm_dslash_cuda_gen.complexify

(

a

)

complex numbers ########################################################################

Definition at line 6 of file fused_exterior_ndeg_tm_dslash_cuda_gen.py.

complexToStr()

def fused_exterior_ndeg_tm_dslash_cuda_gen.complexToStr

(

c

)

Definition at line 9 of file fused_exterior_ndeg_tm_dslash_cuda_gen.py.

References int.

Referenced by projectorToStr().

Here is the caller graph for this function:

def_gauge()

def fused_exterior_ndeg_tm_dslash_cuda_gen.def_gauge

(

)

Definition at line 173 of file fused_exterior_ndeg_tm_dslash_cuda_gen.py.

References g_im(), g_re(), nthFloat2(), and nthFloat4().

Referenced by prolog().

Here is the call graph for this function:

Here is the caller graph for this function:

def_input_spinor()

def fused_exterior_ndeg_tm_dslash_cuda_gen.def_input_spinor

(

)

Definition at line 144 of file fused_exterior_ndeg_tm_dslash_cuda_gen.py.

References in_im(), in_re(), nthFloat2(), and nthFloat4().

Referenced by prolog().

Here is the call graph for this function:

Here is the caller graph for this function:

def_output_spinor()

def fused_exterior_ndeg_tm_dslash_cuda_gen.def_output_spinor

(

)

Definition at line 206 of file fused_exterior_ndeg_tm_dslash_cuda_gen.py.

References out1_im(), out1_re(), out2_im(), and out2_re().

Referenced by prolog().

Here is the call graph for this function:

Here is the caller graph for this function:

epilog()

def fused_exterior_ndeg_tm_dslash_cuda_gen.epilog

(

)

Definition at line 990 of file fused_exterior_ndeg_tm_dslash_cuda_gen.py.

References block(), g_im(), g_re(), in_im(), in_re(), out1_im(), out1_re(), twisted(), and xpay().

Referenced by generate_dslash().

Here is the call graph for this function:

Here is the caller graph for this function:

g_im()

def fused_exterior_ndeg_tm_dslash_cuda_gen.g_im	(		d,
			m,
			n
	)

Definition at line 121 of file fused_exterior_ndeg_tm_dslash_cuda_gen.py.

Referenced by def_gauge(), epilog(), and gen().

Here is the caller graph for this function:

g_re()

def fused_exterior_ndeg_tm_dslash_cuda_gen.g_re	(		d,
			m,
			n
	)

Definition at line 120 of file fused_exterior_ndeg_tm_dslash_cuda_gen.py.

Referenced by def_gauge(), epilog(), and gen().

Here is the caller graph for this function:

gen()

def fused_exterior_ndeg_tm_dslash_cuda_gen.gen	(		dir,
			pack_only = False
	)

Definition at line 403 of file fused_exterior_ndeg_tm_dslash_cuda_gen.py.

References block(), g_im(), g_re(), h1_im(), h1_re(), h2_im(), h2_re(), in_im(), in_re(), indent(), out1_im(), out1_re(), out2_im(), out2_re(), projectorToStr(), and sign().

Here is the call graph for this function:

generate_dslash()

def fused_exterior_ndeg_tm_dslash_cuda_gen.generate_dslash

(

)

temporal

Definition at line 1037 of file fused_exterior_ndeg_tm_dslash_cuda_gen.py.

References epilog(), and prolog().

Referenced by generate_dslash_kernels().

Here is the call graph for this function:

Here is the caller graph for this function:

generate_dslash_kernels()

def fused_exterior_ndeg_tm_dslash_cuda_gen.generate_dslash_kernels

(

arch

)

Definition at line 1043 of file fused_exterior_ndeg_tm_dslash_cuda_gen.py.

References generate_dslash().

Here is the call graph for this function:

gminus()

def fused_exterior_ndeg_tm_dslash_cuda_gen.gminus	(		g1,
			g2
	)

Definition at line 78 of file fused_exterior_ndeg_tm_dslash_cuda_gen.py.

gplus()

def fused_exterior_ndeg_tm_dslash_cuda_gen.gplus	(		g1,
			g2
	)

Definition at line 75 of file fused_exterior_ndeg_tm_dslash_cuda_gen.py.

h1_im()

def fused_exterior_ndeg_tm_dslash_cuda_gen.h1_im	(		h,
			c
	)

Definition at line 127 of file fused_exterior_ndeg_tm_dslash_cuda_gen.py.

Referenced by gen().

Here is the caller graph for this function:

h1_re()

def fused_exterior_ndeg_tm_dslash_cuda_gen.h1_re	(		h,
			c
	)

Definition at line 126 of file fused_exterior_ndeg_tm_dslash_cuda_gen.py.

Referenced by gen().

Here is the caller graph for this function:

h2_im()

def fused_exterior_ndeg_tm_dslash_cuda_gen.h2_im	(		h,
			c
	)

Definition at line 129 of file fused_exterior_ndeg_tm_dslash_cuda_gen.py.

Referenced by gen().

Here is the caller graph for this function:

h2_re()

def fused_exterior_ndeg_tm_dslash_cuda_gen.h2_re	(		h,
			c
	)

Definition at line 128 of file fused_exterior_ndeg_tm_dslash_cuda_gen.py.

Referenced by gen().

Here is the caller graph for this function:

in_im()

def fused_exterior_ndeg_tm_dslash_cuda_gen.in_im	(		s,
			c
	)

Definition at line 119 of file fused_exterior_ndeg_tm_dslash_cuda_gen.py.

Referenced by def_input_spinor(), epilog(), gen(), and prolog().

Here is the caller graph for this function:

in_re()

def fused_exterior_ndeg_tm_dslash_cuda_gen.in_re	(		s,
			c
	)

Definition at line 118 of file fused_exterior_ndeg_tm_dslash_cuda_gen.py.

Referenced by def_input_spinor(), epilog(), gen(), and prolog().

Here is the caller graph for this function:

indent()

def fused_exterior_ndeg_tm_dslash_cuda_gen.indent

(

code

)

code generation ########################################################################

Definition at line 98 of file fused_exterior_ndeg_tm_dslash_cuda_gen.py.

Referenced by block(), gen(), and prolog().

Here is the caller graph for this function:

nthFloat2()

def fused_exterior_ndeg_tm_dslash_cuda_gen.nthFloat2

(

n

)

Definition at line 114 of file fused_exterior_ndeg_tm_dslash_cuda_gen.py.

Referenced by def_gauge(), and def_input_spinor().

Here is the caller graph for this function:

nthFloat4()

def fused_exterior_ndeg_tm_dslash_cuda_gen.nthFloat4

(

n

)

Definition at line 111 of file fused_exterior_ndeg_tm_dslash_cuda_gen.py.

Referenced by def_gauge(), and def_input_spinor().

Here is the caller graph for this function:

out1_im()

def fused_exterior_ndeg_tm_dslash_cuda_gen.out1_im	(		s,
			c
	)

Definition at line 123 of file fused_exterior_ndeg_tm_dslash_cuda_gen.py.

Referenced by def_output_spinor(), epilog(), gen(), prolog(), twisted(), and xpay().

Here is the caller graph for this function:

out1_re()

def fused_exterior_ndeg_tm_dslash_cuda_gen.out1_re	(		s,
			c
	)

Definition at line 122 of file fused_exterior_ndeg_tm_dslash_cuda_gen.py.

Referenced by def_output_spinor(), epilog(), gen(), prolog(), twisted(), and xpay().

Here is the caller graph for this function:

out2_im()

def fused_exterior_ndeg_tm_dslash_cuda_gen.out2_im	(		s,
			c
	)

Definition at line 125 of file fused_exterior_ndeg_tm_dslash_cuda_gen.py.

Referenced by def_output_spinor(), gen(), prolog(), twisted(), and xpay().

Here is the caller graph for this function:

out2_re()

def fused_exterior_ndeg_tm_dslash_cuda_gen.out2_re	(		s,
			c
	)

Definition at line 124 of file fused_exterior_ndeg_tm_dslash_cuda_gen.py.

Referenced by def_output_spinor(), gen(), prolog(), twisted(), and xpay().

Here is the caller graph for this function:

projectorToStr()

def fused_exterior_ndeg_tm_dslash_cuda_gen.projectorToStr

(

p

)

Definition at line 81 of file fused_exterior_ndeg_tm_dslash_cuda_gen.py.

References complexToStr().

Referenced by gen().

Here is the call graph for this function:

Here is the caller graph for this function:

prolog()

def fused_exterior_ndeg_tm_dslash_cuda_gen.prolog

(

)

Definition at line 238 of file fused_exterior_ndeg_tm_dslash_cuda_gen.py.

References def_gauge(), def_input_spinor(), def_output_spinor(), in_im(), in_re(), indent(), out1_im(), out1_re(), out2_im(), and out2_re().

Referenced by generate_dslash().

Here is the call graph for this function:

Here is the caller graph for this function:

sign()

def fused_exterior_ndeg_tm_dslash_cuda_gen.sign

(

x

)

Definition at line 105 of file fused_exterior_ndeg_tm_dslash_cuda_gen.py.

Referenced by gen().

Here is the caller graph for this function:

tmp_im()

def fused_exterior_ndeg_tm_dslash_cuda_gen.tmp_im	(		s,
			c
	)

Definition at line 134 of file fused_exterior_ndeg_tm_dslash_cuda_gen.py.

tmp_re()

def fused_exterior_ndeg_tm_dslash_cuda_gen.tmp_re	(		s,
			c
	)

Definition at line 133 of file fused_exterior_ndeg_tm_dslash_cuda_gen.py.

twisted()

def fused_exterior_ndeg_tm_dslash_cuda_gen.twisted

(

)

Definition at line 714 of file fused_exterior_ndeg_tm_dslash_cuda_gen.py.

References block(), out1_im(), out1_re(), out2_im(), and out2_re().

Referenced by epilog().

Here is the call graph for this function:

Here is the caller graph for this function:

xpay()

def fused_exterior_ndeg_tm_dslash_cuda_gen.xpay

(

)

Definition at line 781 of file fused_exterior_ndeg_tm_dslash_cuda_gen.py.

References out1_im(), out1_re(), out2_im(), and out2_re().

Referenced by epilog().

Here is the call graph for this function:

Here is the caller graph for this function:

Variable Documentation

a1

string fused_exterior_ndeg_tm_dslash_cuda_gen.a1 = ""

Definition at line 909 of file fused_exterior_ndeg_tm_dslash_cuda_gen.py.

Referenced by quda::blas.axpyBzpcx(), quda::blas.caxpy_recurse(), quda::blas.caxpyBxpz(), quda::blas.caxpyz_recurse(), GaugeAlgTest.comparePlaquette(), quda.GaugeFixHit_NoAtomicAdd(), and GaugeAlgTest.SetUp().

a2

string fused_exterior_ndeg_tm_dslash_cuda_gen.a2 = ""

Definition at line 910 of file fused_exterior_ndeg_tm_dslash_cuda_gen.py.

Referenced by benchmark(), GaugeAlgTest.comparePlaquette(), quda.GaugeFixHit_NoAtomicAdd(), and test().

arch

int fused_exterior_ndeg_tm_dslash_cuda_gen.arch = 200

Definition at line 1102 of file fused_exterior_ndeg_tm_dslash_cuda_gen.py.

dagger

bool fused_exterior_ndeg_tm_dslash_cuda_gen.dagger = False

Definition at line 1093 of file fused_exterior_ndeg_tm_dslash_cuda_gen.py.

dslash

bool fused_exterior_ndeg_tm_dslash_cuda_gen.dslash = False

Definition at line 1092 of file fused_exterior_ndeg_tm_dslash_cuda_gen.py.

gamma1

def fused_exterior_ndeg_tm_dslash_cuda_gen.gamma1

Initial value:

=  complexify([
    0,  0, 0, 1j,
    0,  0, 1j, 0,
    0, -1j, 0, 0,
    -1j,  0, 0, 0
])

Definition at line 39 of file fused_exterior_ndeg_tm_dslash_cuda_gen.py.

gamma2

def fused_exterior_ndeg_tm_dslash_cuda_gen.gamma2

Initial value:

=  complexify([
    0, 0, 0, 1,
    0, 0, -1,  0,
    0, -1, 0,  0,
    1, 0, 0,  0
])

Definition at line 46 of file fused_exterior_ndeg_tm_dslash_cuda_gen.py.

gamma3

def fused_exterior_ndeg_tm_dslash_cuda_gen.gamma3

Initial value:

=  complexify([
    0, 0, 1j,  0,
    0, 0, 0, -1j,
    -1j, 0, 0,  0,
    0, 1j, 0,  0
])

Definition at line 53 of file fused_exterior_ndeg_tm_dslash_cuda_gen.py.

gamma4

def fused_exterior_ndeg_tm_dslash_cuda_gen.gamma4

Initial value:

=  complexify([
    1, 0, 0, 0,
    0, 1, 0, 0,
    0, 0, -1, 0,
    0, 0, 0, -1
])

Definition at line 60 of file fused_exterior_ndeg_tm_dslash_cuda_gen.py.

i

int fused_exterior_ndeg_tm_dslash_cuda_gen.i = 3*s+c

start here

Definition at line 816 of file fused_exterior_ndeg_tm_dslash_cuda_gen.py.

Referenced by accumGivensRotation(), add_3f_force_to_mom(), add_force_to_momentum(), LoadStore< Real >.addMatrixToField(), adjoint_su3_matrix(), advance_coords(), quda::cpuColorSpinorField.allocateGhostBuffer(), quda.appendMatrixToArray(), quda::BiCGstabLUpdate.apply(), quda.applyB(), applyGaugeFieldScaling(), applyGaugeFieldScaling_long(), quda.applyT(), quda.applyThirdTerm(), applyTwist(), quda.asin(), quda.atan(), aX(), ax(), axmy(), quda::blas.axpby(), axpby(), aXpY(), axpy(), quda.axpy(), quda::linalg::Cholesky< Mat, T, N, fast >.backward(), quda::cublas.BatchInvertMatrix(), bdSVD(), benchmark(), quda::BiCGstabL.BiCGstabL(), blasKernel(), block_idx(), quda::gauge::BQCDOrder< Float, length >.BQCDOrder(), quda.calculateY(), quda::CalculateYArg< Float, coarseGauge, fineGauge, fineSpinor, fineSpinorTmp, fineClover >.CalculateYArg(), quda::CalculateYhatArg< Flloat, Gauge, n >.CalculateYhatArg(), quda.CalculateYhatCPU(), quda.CalculateYhatGPU(), quda::blas.caxpby(), quda::blas.caxpbypcz(), quda::blas.caxpy_recurse(), quda::blas.caxpyz_recurse(), quda::blas.cDotProduct(), quda::blas.cDotProductCopy(), check_displacement(), quda::LatticeField.checkField(), checkGauge(), quda.checkNan(), quda::Matrix< T, N >.checksum(), quda.checkUnitary(), quda.checkUnitaryPrint(), quda::linalg::Cholesky< Mat, T, N, fast >.Cholesky(), cloverReference(), quda.CoarseOp(), quda::ColorSpinor< Float, Nc, Ns >.ColorSpinor(), quda::ColorSpinor< Float, Nc, 4 >.ColorSpinor(), quda::ColorSpinor< Float, Nc, 2 >.ColorSpinor(), comm_create_topology(), comm_declare_receive_displaced(), comm_declare_send_displaced(), comm_declare_strided_receive_displaced(), comm_declare_strided_receive_relative_(), comm_declare_strided_send_displaced(), comm_declare_strided_send_relative_(), comm_dim_partitioned_reset(), comm_gather_gpuid(), comm_gather_hostname(), comm_init(), comm_partitioned(), comm_rank_displaced(), compare_mom(), compareFloats(), compareLink(), quda.compareSpinor(), compute_gauge_force_quda_(), compute_path_product(), quda.computeBeta(), quda.computeCloverForce(), computeCloverForceQuda(), quda.computeCloverSigmaOprod(), quda.computeCoarseClover(), quda.computeCoeffs(), computeHISQForceQuda(), computeLinkOrderedOuterProduct(), computeLongLinkCPU(), quda::MPCG.computeMatrixPowers(), quda::MPBiCGstab.computeMatrixPowers(), computeStaggeredForceQuda(), computeSVD(), quda.computeYhat(), conj(), quda.conj(), construct_fat_long_gauge_field(), constructCloverField(), constructGaugeField(), constructSpinorField(), constructUnitaryGaugeField(), constructUnitGaugeField(), quda::MultiShiftSolver.convergence(), coordsFromIndex(), quda::cpuColorSpinorField.copy(), quda.copyArrayToLink(), quda.copyColumn(), quda.copyGauge(), quda.copyGaugeEx(), quda.copyGaugeKernel(), quda.copyGaugeMG(), quda.copyGhost(), quda.copyGhostKernel(), quda::blas::copy_ns.copyKernel(), quda.copyLinkToArray(), covdevReference(), quda::cpuGaugeField.cpuGaugeField(), quda::cpuColorSpinorField.create(), quda::LatticeField.createComms(), quda::cudaColorSpinorField.createComms(), quda.createDslashEvents(), createGaugeForcePaths(), quda::Transfer.createGeoMap(), quda::GaugeField.createGhostZone(), quda::ColorSpinorField.createGhostZone(), createHwCPU(), createMomCPU(), createNoisyLinkCPU(), createSiteLinkCPU(), quda::gauge.ct_sqrt(), quda::cudaGaugeField.cudaGaugeField(), quda::linalg::Cholesky< Mat, T, N, fast >.D(), quda::cpuColorSpinorField.destroy(), quda::LatticeField.destroyComms(), quda.destroyDslashEvents(), quda::Dirac.Dirac(), display_link(), display_link_internal(), display_spinor(), display_test_info(), do_color_matrix_hisq_force_reference(), do_halfwilson_hisq_force_reference(), quda.domainWallDslashCuda(), quda::DslashCoarsePolicyTune.DslashCoarsePolicyTune(), dslashCUDA(), DslashCuda.DslashCuda(), anonymous_namespace{dslash_policy.cuh}::DslashPolicyTune.DslashPolicyTune(), dslashReference(), dslashReference_4d_sgpu(), dslashReference_5th(), dslashReference_5th_inv(), dslashTest(), dw_setDims(), end(), endQuda(), quda.ErrorSU3(), quda::GaugeField.exchange(), quda::ColorSpinorField.exchange(), quda.exchangeExtendedGhost(), quda::cudaColorSpinorField.exchangeGhost(), quda::cpuColorSpinorField.exchangeGhost(), quda.extractGhost(), quda.extractGhostKernel(), fetch_double(), fetch_double2(), fetch_double2_old(), quda::GMResDR.FlexArnoldiProcedure(), quda::colorspinor::FloatNOrder< Float, Ns, Nc, N, huge_alloc >.FloatNOrder(), quda::gauge::FloatNOrder< Float, length, N, reconLenParam, stag_phase, huge_alloc >.FloatNOrder(), flushChronoQuda(), quda::linalg::Cholesky< Mat, T, N, fast >.forward(), forward_shifted_outer_prod(), freeFields(), quda::cpuColorSpinorField.freeGhostBuffer(), fullLatticeIndex(), fullLatticeIndex_4d(), fullLatticeIndex_5d(), fullLatticeIndex_5d_4dpc(), quda::Gamma< ValueType, basis, dir >.Gamma(), quda::ColorSpinor< Float, Nc, 4 >.gamma(), gauge_force_reference_dir(), gauge_force_test(), quda.GaugeFixHit_NoAtomicAdd(), gaugeLink(), gaugeLink_mgpu(), gaugeLink_sgpu(), quda::GCR.GCR(), quda::MG.generateNullVectors(), quda.GenericPackGhost(), get_coords(), quda::gauge::Reconstruct< 13, Float >.getPhase(), quda::gauge::Reconstruct< 9, Float >.getPhase(), anonymous_namespace{dslash_policy.cuh}.getStreamIndex(), gf_neighborIndexFullLattice(), quda::ColorSpinorField.Ghost(), quda::ColorSpinorField.GhostNorm(), quda::ColorSpinorField.GhostNormOffset(), quda::ColorSpinorField.GhostOffset(), quda::Eig_Solver.GrandSchm_test(), quda::blas.hDotProduct(), quda::blas.hDotProduct_Anorm(), quda::blas.HeavyQuarkResidualNorm(), hisq_force_test(), hisqStaplesForceCPU(), quda::HMatrix< T, N >.HMatrix(), if(), quda::ColorSpinor< Float, Nc, 4 >.igamma(), quda.improvedStaggeredDslashCuda(), quda::Deflation.increment(), index(), quda::Matrix< T, N >.index(), quda::HMatrix< T, N >.index(), quda::clover.indexFloatN(), quda::colorspinor.indexFloatN(), quda::gauge.indexFloatN(), initComms(), initCommsGridQuda(), initFields(), quda::DiracCoarse.initializeCoarse(), initQudaDevice(), initQudaMemory(), insertNoise(), inside_subset(), quda::linalg::Cholesky< Mat, T, N, fast >.invert(), invert_multishift_quda_(), invert_test(), invertMultiShiftQuda(), invertMultiSrcQuda(), invertQuda(), anonymous_namespace{dslash_policy.cuh}.issueGather(), anonymous_namespace{dslash_policy.cuh}.issuePack(), anonymous_namespace{dslash_policy.cuh}.issueRecv(), quda.isUnitary(), quda.kernel_random(), l2(), quda::LatticeFieldParam.LatticeFieldParam(), quda::colorspinor::FieldOrderCB< Float, nSpin, nColor, nVec, order >.LatticeIndex(), quda::ColorSpinorField.LatticeIndex(), quda.launch_kernel_random(), quda::gauge::LegacyOrder< Float, length >.LegacyOrder(), lex_rank_from_coords(), lex_rank_from_coords_t(), lex_rank_from_coords_x(), link_sanity_check(), link_sanity_check_internal_12(), link_sanity_check_internal_8(), quda.linkIndexM1(), quda.linkIndexP1(), quda.linkIndexShift(), quda.linkNormalIndexP1(), llfat_add_su3_matrix(), llfat_compute_gen_staple_field(), llfat_cpu(), llfat_mult_su3_an(), llfat_mult_su3_na(), llfat_mult_su3_nn(), llfat_scalar_mult_add_su3_matrix(), llfat_scalar_mult_su3_matrix(), llfat_test(), SpinorTexture< RegType, StoreType, N, tex_id >.load(), quda::clover::FloatNOrder< Float, length, N, huge_alloc >.load(), quda::colorspinor::FloatNOrder< Float, Ns, Nc, N, huge_alloc >.load(), quda::clover::QDPOrder< Float, length >.load(), quda::clover::QDPJITOrder< Float, length >.load(), quda::clover::BQCDOrder< Float, length >.load(), quda::gauge::FloatNOrder< Float, length, N, reconLenParam, stag_phase, huge_alloc >.load(), quda::gauge::QDPOrder< Float, length >.load(), quda::gauge::QDPJITOrder< Float, length >.load(), quda::gauge::MILCOrder< Float, length >.load(), quda::gauge::MILCSiteOrder< Float, length >.load(), quda::gauge::CPSOrder< Float, length >.load(), quda::gauge::BQCDOrder< Float, length >.load(), quda::gauge::TIFROrder< Float, length >.load(), quda::gauge::TIFRPaddedOrder< Float, length >.load(), loadCloverQuda(), loadGaugeQuda(), SpinorTexture< RegType, StoreType, N, tex_id >.loadGhost(), quda::colorspinor::FloatNOrder< Float, Ns, Nc, N, huge_alloc >.loadGhost(), quda::gauge::FloatNOrder< Float, length, N, reconLenParam, stag_phase, huge_alloc >.loadGhost(), quda::gauge::LegacyOrder< Float, length >.loadGhost(), quda::gauge::FloatNOrder< Float, length, N, reconLenParam, stag_phase, huge_alloc >.loadGhostEx(), quda::gauge::LegacyOrder< Float, length >.loadGhostEx(), quda.loadLinkVariableFromArray(), quda.loadMatrixFromArray(), LoadStore< Real >.loadMatrixFromField(), quda::Deflation.loadVectors(), quda::MG.loadVectors(), main(), quda.makeAntiHerm(), quda.massRescale(), quda::Matrix< T, N >.Matrix(), matrix_mult_an(), matrix_mult_na(), matrix_mult_nn(), quda.maxGauge(), quda.MDWFDslashCuda(), quda::MG.MG(), quda::MGParam.MGParam(), mult_adj_su3_mat_vec(), mult_su3_an(), mult_su3_mat_vec(), mult_su3_na(), mult_su3_nn(), MultiBlasArg< NXZ, SpinorX, SpinorY, SpinorZ, SpinorW, Functor >.MultiBlasArg(), multiblasCuda(), multiblasKernel(), quda::multigrid_solver.multigrid_solver(), multiplySpinorByDiracProjector(), multiplySpinorByDiracProjector5(), quda.multiplyVUV(), quda::blas.multiReduce_recurse(), MultiReduceArg< NXZ, ReduceType, SpinorX, SpinorY, SpinorZ, SpinorW, Reducer >.MultiReduceArg(), multiReduceCuda(), multiReduceKernel(), multiReduceLaunch(), mXpY(), quda.ndegTwistedMassDslashCuda(), ndegTwistGamma5(), negx(), neighborIndex(), neighborIndex_4d(), neighborIndex_5d(), neighborIndex_mg(), neighborIndexFullLattice(), neighborIndexFullLattice_mg(), new_load_half(), new_save_half(), newCopyToFloat(), newCopyToHalf(), node_index(), node_number(), quda::blas.norm(), norm2(), normalize(), quda::colorspinor::FieldOrderCB< Float, nSpin, nColor, nVec, order >.OffsetIndex(), quda::ColorSpinorField.OffsetIndex(), old_load_half(), old_save_half(), oldCopyToFloat(), oldCopyToHalf(), quda::RitzMat.operator()(), quda::Matrix< T, N >.operator()(), quda::blas::multicaxpy_< NXZ, Float2, FloatN >.operator()(), quda::Deflation.operator()(), quda::reduce_vector< T >.operator()(), quda::HMatrix< T, N >.operator()(), quda::blas::CdotCopy< NXZ, ReduceType, Float2, FloatN >.operator()(), Identity< N, T >.operator()(), anonymous_namespace{dslash_policy.cuh}::DslashBasic.operator()(), quda::blas::multicaxpyz_< NXZ, Float2, FloatN >.operator()(), quda::CG.operator()(), quda::MPCG.operator()(), anonymous_namespace{dslash_policy.cuh}::DslashPthreads.operator()(), quda::MPBiCGstab.operator()(), quda::BiCGstabL.operator()(), anonymous_namespace{dslash_policy.cuh}::DslashFusedExterior.operator()(), quda::GCR.operator()(), quda::XSD.operator()(), quda::blas::multi_axpyBzpcx_< NXZ, Float2, FloatN >.operator()(), anonymous_namespace{dslash_policy.cuh}::DslashGDR.operator()(), quda::MultiShiftCG.operator()(), anonymous_namespace{dslash_policy.cuh}::DslashFusedGDR.operator()(), quda::MinResExt.operator()(), anonymous_namespace{dslash_policy.cuh}::DslashGDRRecv.operator()(), quda::DslashCoarseLaunch.operator()(), anonymous_namespace{dslash_policy.cuh}::DslashFusedGDRRecv.operator()(), anonymous_namespace{dslash_policy.cuh}::DslashZeroCopyPack.operator()(), anonymous_namespace{dslash_policy.cuh}::DslashFusedZeroCopyPack.operator()(), anonymous_namespace{dslash_policy.cuh}::DslashZeroCopyPackGDRRecv.operator()(), anonymous_namespace{dslash_policy.cuh}::DslashFusedZeroCopyPackGDRRecv.operator()(), anonymous_namespace{dslash_policy.cuh}::DslashZeroCopy.operator()(), anonymous_namespace{dslash_policy.cuh}::DslashFusedZeroCopy.operator()(), operator*(), quda.operator*(), quda.operator+(), quda::ColorSpinor< Float, Nc, Ns >.operator+=(), quda::vector_type< scalar, n >.operator+=(), quda.operator+=(), Matrix< N, T >.operator+=(), quda::ColorSpinor< Float, Nc, 4 >.operator+=(), quda::ColorSpinor< Float, Nc, 2 >.operator+=(), quda.operator-(), quda.operator-=(), Matrix< N, T >.operator-=(), quda.operator<<(), operator<<(), quda::ColorSpinor< Float, Nc, Ns >.operator=(), quda::Matrix< T, N >.operator=(), quda::Dirac.operator=(), quda::ColorSpinor< Float, Nc, 4 >.operator=(), quda::HMatrix< T, N >.operator=(), quda::ColorSpinor< Float, Nc, 2 >.operator=(), quda::vector_type< scalar, n >.operator[](), quda::Array< T, N >.operator[](), quda.orthoDir(), quda::BiCGstabL.orthoDir(), orthogonalize(), quda.outerProd(), quda.outerProdSpinTrace(), quda::gauge::Reconstruct< reconLenParam, Float >.Pack(), quda::gauge::Reconstruct< 19, Float >.Pack(), quda::gauge::Reconstruct< 12, Float >.Pack(), quda::gauge::Reconstruct< 11, Float >.Pack(), quda::gauge::Reconstruct< 8, Float >.Pack(), quda::gauge::Reconstruct< 9, Float >.Pack(), quda::PackGhostArg< Field >.PackGhostArg(), performAPEnStep(), performOvrImpSTOUTnStep(), performSTOUTnStep(), performWuppertalnStep(), MultiBlasCuda< NXZ, FloatN, M, SpinorX, SpinorY, SpinorZ, SpinorW, Functor >.postTune(), MultiReduceCuda< NXZ, doubleN, ReduceType, FloatN, M, SpinorX, SpinorY, SpinorZ, SpinorW, Reducer >.postTune(), MultiBlasCuda< NXZ, FloatN, M, SpinorX, SpinorY, SpinorZ, SpinorW, Functor >.preTune(), MultiReduceCuda< NXZ, doubleN, ReduceType, FloatN, M, SpinorX, SpinorY, SpinorZ, SpinorW, Reducer >.preTune(), quda.print(), quda::DiracParam.print(), quda::TimeProfile.Print(), quda::HMatrix< T, N >.print(), print_m(), print_su3_matrix(), quda.print_trace(), quda::TimeProfile.PrintGlobal(), printLinkElement(), printQudaGaugeParam(), printQudaInvertParam(), printQudaMultigridParam(), quda::cudaColorSpinorField.PrintVector(), process_command_line_option(), quda::ColorSpinor< Float, Nc, 4 >.project(), quda::gauge::QDPJITOrder< Float, length >.QDPJITOrder(), quda::gauge::QDPOrder< Float, length >.QDPOrder(), quda::ColorSpinor< Float, Nc, 2 >.reconstruct(), quda::blas.reDotProduct(), quda::Deflation.reduce(), quda.reduce2d(), reduceKernel(), quda.reduceRow(), quda::EigCGArgs.RestartLanczos(), quda::IncEigCG.RestartVT(), quda::GMResDR.RestartVZH(), quda::RNG.RNG(), quda::clover::FloatNOrder< Float, length, N, huge_alloc >.save(), quda::colorspinor::FloatNOrder< Float, Ns, Nc, N, huge_alloc >.save(), Spinor< RegType, StoreType, N, write, tex_id >.save(), quda::clover::QDPOrder< Float, length >.save(), quda::clover::QDPJITOrder< Float, length >.save(), quda::gauge::FloatNOrder< Float, length, N, reconLenParam, stag_phase, huge_alloc >.save(), quda::gauge::QDPOrder< Float, length >.save(), quda::gauge::QDPJITOrder< Float, length >.save(), quda::gauge::MILCOrder< Float, length >.save(), quda::gauge::MILCSiteOrder< Float, length >.save(), quda::gauge::CPSOrder< Float, length >.save(), quda::gauge::BQCDOrder< Float, length >.save(), quda::gauge::TIFROrder< Float, length >.save(), quda::gauge::TIFRPaddedOrder< Float, length >.save(), quda::colorspinor::FloatNOrder< Float, Ns, Nc, N, huge_alloc >.saveGhost(), quda::gauge::FloatNOrder< Float, length, N, reconLenParam, stag_phase, huge_alloc >.saveGhost(), quda::gauge::LegacyOrder< Float, length >.saveGhost(), quda::gauge::FloatNOrder< Float, length, N, reconLenParam, stag_phase, huge_alloc >.saveGhostEx(), quda::gauge::LegacyOrder< Float, length >.saveGhostEx(), quda::Deflation.saveVectors(), quda::MG.saveVectors(), scalar_mult_add_su3_matrix(), scalar_mult_add_su3_vector(), scalar_mult_sub_su3_matrix(), scale_su3_matrix(), set_identity(), set_identity_matrix(), setDims(), quda.setDiracParam(), quda.setDiracPreParam(), quda.setDiracSloppyParam(), setFusedParam(), quda.setIdentity(), setInvertParam(), setMultigridParam(), setup_hyper_prime(), setup_layout(), setup_qmp_fixed(), setup_qmp_grid(), quda.setZero(), quda::ShiftColorSpinorFieldArg< Output, Input >.ShiftColorSpinorFieldArg(), shifted_outer_prod(), quda::ColorSpinor< Float, Nc, 4 >.sigma(), site_link_sanity_check(), site_link_sanity_check_internal_12(), quda.solve(), quda::Solver.solve(), quda::CG.solve(), quda::SolverParam.SolverParam(), quda::colorspinor::SpaceColorSpinorOrder< Float, Ns, Nc >.SpaceColorSpinorOrder(), quda::colorspinor::SpaceSpinorColorOrder< Float, Ns, Nc >.SpaceSpinorColorOrder(), spinorNeighbor(), spinorNeighbor_5d(), quda::HMatrix< T, N >.square(), quda.staggeredDslashCuda(), store_norm(), LoadStore< Real >.storeMatrixToField(), su3_adjoint(), su3_projector(), su3Construct8(), su3Reconstruct8(), SU3test(), sub(), sum(), quda::LatticeField.SurfaceCB(), test(), quda::blas::TileSizeTune< ReducerDiagonal, writeDiagonal, ReducerOffDiagonal, writeOffDiagonal >.TileSizeTune(), total_staple_io_flops(), transpose(), quda.tuneLaunch(), quda.twistedCloverDslashCuda(), twistGamma5(), quda.u32toa(), quda.u64toa(), u_shift_hw(), u_shift_mat(), unitarize_link_test(), quda::gauge::Reconstruct< reconLenParam, Float >.Unpack(), quda::gauge::Reconstruct< 19, Float >.Unpack(), quda::gauge::Reconstruct< 12, Float >.Unpack(), quda::gauge::Reconstruct< 11, Float >.Unpack(), quda::gauge::Reconstruct< 13, Float >.Unpack(), quda::gauge::Reconstruct< 9, Float >.Unpack(), update_mom(), quda.updateAp(), quda::SolverParam.updateInvertParam(), quda::BiCGstabL.updateR(), quda.updateSolution(), quda::BiCGstabL.updateUend(), quda::BiCGstabL.updateXRend(), vcompare_M(), vcreate_M(), vdestroy_M(), quda::vector_type< scalar, n >.vector_type(), quda::Deflation.verify(), quda::MG.verify(), vfill_m(), vget_M(), vput_M(), vset_M(), quda.writeLinkVariableToArray(), quda.writeMatrixToArray(), x4_from_full_index(), xpay(), quda::XSD.XSD(), quda.zero(), quda::cpuColorSpinorField.zero(), quda::BiCGstabL.~BiCGstabL(), quda::cpuGaugeField.~cpuGaugeField(), quda::cudaGaugeField.~cudaGaugeField(), quda::GCR.~GCR(), quda::MG.~MG(), and quda::multigrid_solver.~multigrid_solver().

id

def fused_exterior_ndeg_tm_dslash_cuda_gen.id

Initial value:

=  complexify([
    1, 0, 0, 0,
    0, 1, 0, 0,
    0, 0, 1, 0,
    0, 0, 0, 1
])

projector matrices ########################################################################

Definition at line 32 of file fused_exterior_ndeg_tm_dslash_cuda_gen.py.

igamma5

def fused_exterior_ndeg_tm_dslash_cuda_gen.igamma5

Initial value:

=  complexify([
    0, 0, 1j, 0,
    0, 0, 0, 1j,
    1j, 0, 0, 0,
    0, 1j, 0, 0
])

Definition at line 67 of file fused_exterior_ndeg_tm_dslash_cuda_gen.py.

projectors

list fused_exterior_ndeg_tm_dslash_cuda_gen.projectors

Initial value:

=  [
    gminus(id,gamma1), gplus(id,gamma1),
    gminus(id,gamma2), gplus(id,gamma2),
    gminus(id,gamma3), gplus(id,gamma3),
    gminus(id,gamma4), gplus(id,gamma4),
]

Definition at line 89 of file fused_exterior_ndeg_tm_dslash_cuda_gen.py.

sharedDslash

bool fused_exterior_ndeg_tm_dslash_cuda_gen.sharedDslash = False

Definition at line 1096 of file fused_exterior_ndeg_tm_dslash_cuda_gen.py.

sharedFloatsPerFlavor

int fused_exterior_ndeg_tm_dslash_cuda_gen.sharedFloatsPerFlavor = 0

Definition at line 1095 of file fused_exterior_ndeg_tm_dslash_cuda_gen.py.

twist

bool fused_exterior_ndeg_tm_dslash_cuda_gen.twist = False

Definition at line 1094 of file fused_exterior_ndeg_tm_dslash_cuda_gen.py.