Synch multigrid rewrite to repository and

broad unicode elimination effort
This commit is contained in:
Peter Boyle committed 2026-09-29 12:36:34 -04:00
1 parent 865c338dd2
commit 3bd5e8883f
73 files changed
+1018 -3219

No files matched your search

+38 -38
View File
@@ -190,8 +190,8 @@ public:
}
};
// Lüscher deflated guesser (arXiv:0706.2298 Sec A.3) for a non-Hermitian solve.
// C_{st} = <psi[s] | LinOp | psi[t]>; guess = sum_s c_s psi[s] where c = C^{-1} psi† src.
// Luscher deflated guesser (arXiv:0706.2298 Sec A.3) for a non-Hermitian solve.
// C_{st} = <psi[s] | LinOp | psi[t]>; guess = sum_s c_s psi[s] where c = C^{-1} psi^dag src.
template<class Field>
class LuscherGuesser : public LinearFunction<Field> {
const std::vector<Field> &psi;
@@ -344,7 +344,7 @@ void runMG(
TrivialPrecon<LatticeFermionD> simple_fine;
//////////////////////////////////////////////////////////////////////
// Level 0→1: coarsen PVdagM, build LinOpCoarse
// Level 0->1: coarsen PVdagM, build LinOpCoarse
//////////////////////////////////////////////////////////////////////
LittleDiracOperator LittleDiracOpPV(geom, FGrid, Coarse5d);
LittleDiracOpPV.CoarsenOperator(PVdagM, AggregatesPD);
@@ -368,7 +368,7 @@ void runMG(
//////////////////////////////////////////////////////////////////////
// psi_coarse: coarse projections of pre-GS fine null vectors.
// These are the Level 1 near-null vectors, promoted from Level 0.
// Used as the aggregation basis for Level 1→2 coarsening.
// Used as the aggregation basis for Level 1->2 coarsening.
//////////////////////////////////////////////////////////////////////
std::vector<CoarseVector> psi_coarse(nbasis, Coarse5d);
for (int k = 0; k < nbasis; k++)
@@ -398,22 +398,22 @@ void runMG(
RealD normC = C.norm();
RealD normCmCdag = (C - C.adjoint()).norm();
std::cout << GridLogMessage << "Coarse null matrix ||C|| = " << normC << std::endl;
std::cout << GridLogMessage << "Coarse null matrix ||C - C†||/||C|| = " << normCmCdag/normC << std::endl;
std::cout << GridLogMessage << "Coarse null matrix ||C - C^dag||/||C|| = " << normCmCdag/normC << std::endl;
std::cout << GridLogMessage << "Galerkin check ||C||/||W|| = " << normC/normW << std::endl;
}
//////////////////////////////////////////////////////////////////////
// Level 1→2: set up aggregation using psi_coarse as subspace.
// Level 1->2: set up aggregation using psi_coarse as subspace.
// Block factor 2,2,3,2 (removes odd local sublattice in z given MPI
// geometry 3×6×4×4 where z-local at Level 1 is 6).
// geometry 3x6x4x4 where z-local at Level 1 is 6).
// psi_coarse are assigned directly; CoarsenOperator performs
// block-GS orthogonalisation before building LinOpCoarseCoarse.
//////////////////////////////////////////////////////////////////////
// innerProduct(CoarseSiteObj, CoarseSiteObj) returns iScalar<vTComplex>, so CComplex
// for the L1→L2 level must be iScalar<vTComplex>, not vTComplex.
// for the L1->L2 level must be iScalar<vTComplex>, not vTComplex.
typedef typename CoarseVector::vector_object CoarseSiteObj;
typedef iScalar<vTComplex> vTTComplex;
typedef GeneralCoarsenedMatrix<CoarseSiteObj,vTTComplex,NB> LittleDiracOperatorL2;
typedef DeprecatedGeneralCoarsenedMatrix<CoarseSiteObj,vTTComplex,NB> LittleDiracOperatorL2;
typedef typename LittleDiracOperatorL2::CoarseVector CoarseCoarseVector;
typedef Aggregation<CoarseSiteObj,vTTComplex,NB> SubspaceL2;
typedef MGPreconditioner<CoarseSiteObj,vTTComplex,NB> L1to2MG;
@@ -431,12 +431,12 @@ void runMG(
TrivialPrecon<CoarseCoarseVector> simpleCC;
//////////////////////////////////////////////////////////////////////
// Lüscher deflation guesser for L3PGCR.
// Luscher deflation guesser for L3PGCR.
// Step 1: project psi_coarse[k] (promoted fine null vectors) to
// CoarseCoarseVector space — these cover the zero-momentum
// CoarseCoarseVector space -- these cover the zero-momentum
// component of the near-null space of LinOpCC.
// Step 2: breed Nextra additional null vectors directly on LinOpCC
// using GCR with random sources — these pick up near-null
// using GCR with random sources -- these pick up near-null
// modes at all spatial frequencies not spanned by step 1.
// Step 3: build C_{st} = <psi_cc[s]|LinOpCC|psi_cc[t]> over the
// full augmented basis and invert directly via Eigen LU.
@@ -478,13 +478,13 @@ void runMG(
RealD normCcc = Ccc.norm();
RealD normCccmCdag = (Ccc - Ccc.adjoint()).norm();
std::cout << GridLogMessage << "Coarse-coarse deflation matrix ||Ccc|| = " << normCcc << std::endl;
std::cout << GridLogMessage << "Coarse-coarse deflation matrix ||Ccc-Ccc†||/||Ccc|| = " << normCccmCdag/normCcc << std::endl;
std::cout << GridLogMessage << "Coarse-coarse deflation matrix ||Ccc-Ccc^dag||/||Ccc|| = " << normCccmCdag/normCcc << std::endl;
}
Eigen::MatrixXcd Ccc_inv = Ccc.inverse();
LuscherGuesser<CoarseCoarseVector> CCDeflGuesser(psi_cc, Ccc_inv);
//////////////////////////////////////////////////////////////////////
// Level 2→3: coarsen LinOpCC using the RAW promoted psi_cc as aggregation
// Level 2->3: coarsen LinOpCC using the RAW promoted psi_cc as aggregation
// to build the Level 4 (coarse-coarse-coarse) operator.
// psi_cc[0..nbasis-1] are the coarse-coarse near-null vectors, projected
// from the RAW psi_coarse (themselves projected from the RAW fine null
@@ -493,11 +493,11 @@ void runMG(
// so assign COPIES of psi_cc and keep psi_cc itself raw.
//
// Tensor depth deepens once more: innerProduct(CoarseCoarseSiteObj,...) returns
// iScalar<vTTComplex>, so CComplex for the L2→L3 level is iScalar<iScalar<vTComplex>>.
// iScalar<vTTComplex>, so CComplex for the L2->L3 level is iScalar<iScalar<vTComplex>>.
//////////////////////////////////////////////////////////////////////
typedef typename CoarseCoarseVector::vector_object CoarseCoarseSiteObj;
typedef iScalar<vTTComplex> vTTTComplex;
typedef GeneralCoarsenedMatrix<CoarseCoarseSiteObj,vTTTComplex,NB> LittleDiracOperatorL3;
typedef DeprecatedGeneralCoarsenedMatrix<CoarseCoarseSiteObj,vTTTComplex,NB> LittleDiracOperatorL3;
typedef typename LittleDiracOperatorL3::CoarseVector CoarseCoarseCoarseVector;
typedef Aggregation<CoarseCoarseSiteObj,vTTTComplex,NB> SubspaceL3;
typedef MGPreconditioner<CoarseCoarseSiteObj,vTTTComplex,NB> L2to3MG;
@@ -514,7 +514,7 @@ void runMG(
TrivialPrecon<CoarseCoarseCoarseVector> simpleCCC;
//////////////////////////////////////////////////////////////////////
// Level 3→4: coarsen LinOpCCC to build the Level 5 operator, using a
// Level 3->4: coarsen LinOpCCC to build the Level 5 operator, using a
// TRUNCATED basis of only the first NB5 (< nbasis) raw promoted null vectors.
// psi_ccc[k] = raw psi_cc projected through the (block-GS'd) L3 aggregation
// -- the pre-block-GS chain continued one level deeper. We keep only the
@@ -526,7 +526,7 @@ void runMG(
// NB: a positive result is conservative (sigma-ordering can only help); a
// negative one is inconclusive until the sigma-ordered NB5 is tried.
//
// Tensor depth deepens once more: CComplex for the L3→L4 level is
// Tensor depth deepens once more: CComplex for the L3->L4 level is
// iScalar<vTTTComplex>. NB5 (the coarse dimension) is independent of the
// depth -- it just makes the coarsest site vector NB5-dimensional.
//////////////////////////////////////////////////////////////////////
@@ -542,10 +542,10 @@ void runMG(
// Optional sigma-ordering of psi_ccc (SVD_REORDER set): replace the crude
// first-NB5 slice with the NB5 genuinely-most-null directions of span(psi_ccc)
// under LinOpCCC. For a NON-NORMAL operator the nullness measure is the
// singular value of A restricted to the span -- eig of Q†A†AQ -- NOT the
// numerical range Q†AQ (which non-normality contaminates). Robust route:
// singular value of A restricted to the span -- eig of Q^dag A^dag AQ -- NOT the
// numerical range Q^dag AQ (which non-normality contaminates). Robust route:
// whiten by the Gram (drop near-dependent directions), Hermitian-eig the
// whitened A†A, rotate. The printed singular spectrum IS the SVD study: where
// whitened A^dag A, rotate. The printed singular spectrum IS the SVD study: where
// it falls off tells you the natural NB5, and the same numbers illuminate why
// the earlier singular-subspace deflation re-entered. Safe here because we
// ORDER vectors that then feed a Galerkin projection, not REMOVE a subspace.
@@ -603,7 +603,7 @@ void runMG(
typedef typename CoarseCoarseCoarseVector::vector_object CoarseCoarseCoarseSiteObj;
typedef iScalar<vTTTComplex> vTTTTComplex;
typedef GeneralCoarsenedMatrix<CoarseCoarseCoarseSiteObj,vTTTTComplex,NB5> LittleDiracOperatorL4;
typedef DeprecatedGeneralCoarsenedMatrix<CoarseCoarseCoarseSiteObj,vTTTTComplex,NB5> LittleDiracOperatorL4;
typedef typename LittleDiracOperatorL4::CoarseVector CoarseCoarseCoarseCoarseVector;
typedef Aggregation<CoarseCoarseCoarseSiteObj,vTTTTComplex,NB5> SubspaceL4;
typedef MGPreconditioner<CoarseCoarseCoarseSiteObj,vTTTTComplex,NB5> L3to4MG;
@@ -635,7 +635,7 @@ void runMG(
L5PGCR.Name("CCCCouter");
//////////////////////////////////////////////////////////////////////
// Level 3→4 V-cycle: depth-2 SHIFTED smoother on LinOpCCC + Level 5 bottom.
// Level 3->4 V-cycle: depth-2 SHIFTED smoother on LinOpCCC + Level 5 bottom.
// Level 4 is no longer the bottom -- it is smoothed shallowly and recursed to
// Level 5, mirroring how Level 3 recurses to Level 4.
//////////////////////////////////////////////////////////////////////
@@ -660,14 +660,14 @@ void runMG(
simpleCCCC); // trivial guesser at the bottom
//////////////////////////////////////////////////////////////////////
// Level 4 (coarse-coarse-coarse) solve: GCR preconditioned by the L3→L4 V-cycle.
// Level 4 (coarse-coarse-coarse) solve: GCR preconditioned by the L3->L4 V-cycle.
//////////////////////////////////////////////////////////////////////
PrecGeneralisedConjugateResidualNonHermitian<CoarseCoarseCoarseVector> L4MGsolver(1.0e-1,200,LinOpCCC,L3to4Precon,16,16);
L4MGsolver.Level(4);
L4MGsolver.Name("CCCouter");
//////////////////////////////////////////////////////////////////////
// Level 2→3 V-cycle: depth-2 SHIFTED smoother on LinOpCC + Level 4 solve.
// Level 2->3 V-cycle: depth-2 SHIFTED smoother on LinOpCC + Level 4 solve.
// The shift slides the coarse-coarse field of values off the origin so a
// 2-step smoother has something to bite on a non-normal operator (IRS idea).
//////////////////////////////////////////////////////////////////////
@@ -688,11 +688,11 @@ void runMG(
simpleCC, // no pre-smoother
CoarseCoarseSmootherGCR, // post-smoother: depth-2 shifted GCR
LinOpCCC,
L4MGsolver, // coarse solve is now the L3→L4 V-cycle
L4MGsolver, // coarse solve is now the L3->L4 V-cycle
simpleCCC); // trivial guesser
//////////////////////////////////////////////////////////////////////
// Level 3 (coarse-coarse) solve: GCR preconditioned by the L2→L3 V-cycle.
// Level 3 (coarse-coarse) solve: GCR preconditioned by the L2->L3 V-cycle.
// Replaces the plain L3PGCR of the 3-level build -- the coarse-coarse level
// is now smoothed shallowly and recursed rather than solved deeply.
//////////////////////////////////////////////////////////////////////
@@ -701,7 +701,7 @@ void runMG(
L3MGsolver.Name("CCouter");
//////////////////////////////////////////////////////////////////////
// Coarse-level GCR smoother for Level 1→2 V-cycle.
// Coarse-level GCR smoother for Level 1->2 V-cycle.
// Mirrors fine-grid SmootherGCR: shifted operator + fixed step count.
// coarse_smoother_shift and coarse_smoother_nstep are the tuning knobs.
//////////////////////////////////////////////////////////////////////
@@ -717,15 +717,15 @@ void runMG(
CoarseSmootherGCR.Name("Csmoother");
//////////////////////////////////////////////////////////////////////
// Level 1→2 V-cycle preconditioner.
// Level 1->2 V-cycle preconditioner.
//////////////////////////////////////////////////////////////////////
L1to2MG L1to2Precon(AggregatesL2,
LinOpCoarse,
simpleC, // no pre-smoother (matches fine-grid setup)
CoarseSmootherGCR, // post-smoother: depth-2 shifted GCR
LinOpCC,
L3MGsolver, // coarse-coarse solve is now the L2→L3 V-cycle
CCDeflGuesser); // Lüscher guesser: psi_cc C^{-1} psi_cc†
L3MGsolver, // coarse-coarse solve is now the L2->L3 V-cycle
CCDeflGuesser); // Luscher guesser: psi_cc C^{-1} psi_cc^dag
//////////////////////////////////////////////////////////////////////
// Standalone Level 1 two-level solve test.
@@ -760,7 +760,7 @@ void runMG(
f_src = one;
// Pre-smoother: none (TrivialPrecon); post-smoother: shifted PGCR.
// Coarse solver: L2MGsolver (PGCR preconditioned by Level 1→2 V-cycle).
// Coarse solver: L2MGsolver (PGCR preconditioned by Level 1->2 V-cycle).
TwoLevelMG ThreeLevelPrecon(AggregatesPD,
PVdagM,
simple_fine,
@@ -804,7 +804,7 @@ int main (int argc, char ** argv)
GridCartesian * FGrid = SpaceTimeGrid::makeFiveDimGrid(Ls,UGrid);
GridRedBlackCartesian * FrbGrid = SpaceTimeGrid::makeFiveDimRedBlackGrid(Ls,UGrid);
// Level 1 coarse grid: block 2^4 from fine (48×48×48×96 → 24×24×24×48, Ls=1)
// Level 1 coarse grid: block 2^4 from fine (48x48x48x96 -> 24x24x24x48, Ls=1)
Coordinate clatt = lat_size;
for (int d = 0; d < 4; d++) clatt[d] /= 2;
std::cout << GridLogMessage << "Level 1 coarse lattice: " << clatt << std::endl;
@@ -812,13 +812,13 @@ int main (int argc, char ** argv)
GridCartesian *Coarse4d = SpaceTimeGrid::makeFourDimGrid(clatt, GridDefaultSimd(Nd,vComplex::Nsimd()),GridDefaultMpi());
GridCartesian *Coarse5d = SpaceTimeGrid::makeFiveDimGrid(1,Coarse4d);
// Level 2 coarse-coarse grid: block 2,2,3,3 from Level 1 (24×24×24×48 → 12×12×8×16, Ls=1).
// Level 2 coarse-coarse grid: block 2,2,3,3 from Level 1 (24x24x24x48 -> 12x12x8x16, Ls=1).
// MPI geometry 3.6.4.4 (288 ranks): fine local {16,8,12,24}.
// Level 1 local {8,4,6,12}; Level 2 local {4,2,2,4}.
// z blocked by 3: z-Level1-local=6; 6/3=2 (even), 6/2=3 (odd) → must use 3.
// z blocked by 3: z-Level1-local=6; 6/3=2 (even), 6/2=3 (odd) -> must use 3.
// t blocked by 3: t-Level1-local=12; 12/3=4 divisible by Nsimd=4 (gen-simd-width=64).
// t-block=2 gives t2-local=6, 6 mod 4 ≠ 0, fails Grid SIMD assertion. ✓
// With {4,2,2,4}: Nsimd=4 goes into x or t (both =4). ✓
// t-block=2 gives t2-local=6, 6 mod 4 != 0, fails Grid SIMD assertion.
// With {4,2,2,4}: Nsimd=4 goes into x or t (both =4).
Coordinate clatt2 = clatt;
clatt2[0] /= 2;
clatt2[1] /= 2;
@@ -880,7 +880,7 @@ int main (int argc, char ** argv)
typedef PVdagMLinearOperator<MobiusFermionD,LatticeFermionD> PVdagM_t;
typedef ShiftedPVdagMLinearOperator<MobiusFermionD,LatticeFermionD> ShiftedPVdagM_t;
typedef GeneralCoarsenedMatrix<vSpinColourVector,vTComplex,nbasis> LittleDiracOperator;
typedef DeprecatedGeneralCoarsenedMatrix<vSpinColourVector,vTComplex,nbasis> LittleDiracOperator;
typedef LittleDiracOperator::CoarseVector CoarseVector;
typedef Aggregation<vSpinColourVector,vTComplex,nbasis> Subspace;
typedef MGPreconditioner<vSpinColourVector,vTComplex,nbasis> TwoLevelMG;