Peter Boyle d1afebf71e Sizable improvement in multigrid for unsquared. ...

6000 matmuls CG unprec
2000 matmuls CG prec (4000 eo muls)
1050 matmuls PGCR on 16^3 x 32 x 8 m=.01

Substantial effort on timing and logging infrastructure

2015-07-24 01:31:13 +09:00

..

algorithms

Sizable improvement in multigrid for unsquared.

2015-07-24 01:31:13 +09:00

cartesian

Extra check that failed in quenched test

2015-06-16 14:04:56 +01:00

communicator

Experimental support for ARM

2015-06-09 15:46:21 +09:00

cshift

Reorganise of file naming

2015-06-03 12:47:05 +01:00

lattice

Sizable improvement in multigrid for unsquared.

2015-07-24 01:31:13 +09:00

Old

Cleaning up the recursion for traceIndex<n> after the changes the enable G++ to

2015-07-01 23:43:57 +01:00

parallelIO

Removed std::string calls from NerscIO map indexing

2015-06-07 17:06:25 +01:00

qcd

Sizable improvement in multigrid for unsquared.

2015-07-24 01:31:13 +09:00

simd

Debugged vector version of ProjectOnGroup

2015-07-06 02:24:58 +09:00

stencil

Experimental support for ARM

2015-06-09 15:46:21 +09:00

tensors

Sizable improvement in multigrid for unsquared.

2015-07-24 01:31:13 +09:00

.dirstamp

Addedd Ta functionality to the tensor types

2015-06-04 18:11:32 +09:00

Algorithms.h

Variable preconditioned GCR with restarting.

2015-06-21 10:58:46 +01:00

AlignedAllocator.h

pointer cast

2015-06-16 14:04:33 +01:00

Cartesian.h

Reorganise of file naming

2015-06-03 12:47:05 +01:00

Communicator.h

Reorganise of file naming

2015-06-03 12:47:05 +01:00

Cshift.h

Reorganise of file naming

2015-06-03 12:47:05 +01:00

Grid.h

Sizable improvement in multigrid for unsquared.

2015-07-24 01:31:13 +09:00

GridConfig.h

Skeleton of HMC/Integrators

2015-07-03 16:51:41 +09:00

GridConfig.h.in

Change the SIMD command correctly with precision = double vs. single and

2015-07-01 22:45:15 +01:00

GridInit.cc

Sizable improvement in multigrid for unsquared.

2015-07-24 01:31:13 +09:00

GridLog.cc

Sizable improvement in multigrid for unsquared.

2015-07-24 01:31:13 +09:00

GridLog.h

Sizable improvement in multigrid for unsquared.

2015-07-24 01:31:13 +09:00

GridTime.h

Sizable improvement in multigrid for unsquared.

2015-07-24 01:31:13 +09:00

Lattice.h

Reorganise of file naming

2015-06-03 12:47:05 +01:00

Make.inc

Sizable improvement in multigrid for unsquared.

2015-07-24 01:31:13 +09:00

Makefile.am

Reorganise of file naming

2015-06-03 12:47:05 +01:00

Simd.h

Change the SIMD command correctly with precision = double vs. single and

2015-07-01 22:45:15 +01:00

stamp-h1

Addedd Ta functionality to the tensor types

2015-06-04 18:11:32 +09:00

Stencil.h

Reorganise of file naming

2015-06-03 12:47:05 +01:00

Tensors.h

Cleaning up the recursion for traceIndex<n> after the changes the enable G++ to

2015-07-01 23:43:57 +01:00

Threads.h

Reorganise of file naming

2015-06-03 12:47:05 +01:00