mirror of
https://github.com/paboyle/Grid.git
synced 2024-11-10 07:55:35 +00:00
133 lines
5.2 KiB
Plaintext
133 lines
5.2 KiB
Plaintext
* FIXME audit
|
|
* Remove vload/store etc..
|
|
* Replace vset with a call to merge.
|
|
* Replace vset with a call to merge.
|
|
|
|
* Conditional execution Subset, where etc...
|
|
* Coordinate information, integers etc...
|
|
* Integer type padding/union to vector.
|
|
* LatticeCoordinate[mu]
|
|
|
|
* Optimise the extract/merge SIMD routines
|
|
|
|
* Broadcast, reduction tests.
|
|
|
|
* QDP++ regression suite and comparative benchmark
|
|
|
|
* NERSC Lattice loading, plaquette test
|
|
|
|
* Conformable test in Cshift routines.
|
|
|
|
* Gamma/Dirac structures
|
|
* Fourspin, two spin project
|
|
|
|
* Stencil operator support
|
|
|
|
* Check for missing functionality
|
|
|
|
* I/O support
|
|
- MPI IO?
|
|
- BinaryWriter, TextWriter etc...
|
|
- protocol buffers?
|
|
-
|
|
// Cartesian grid inheritance
|
|
// Grid::GridBase
|
|
// |
|
|
// __________|___________
|
|
// | |
|
|
// Grid::GridCartesian Grid::GridCartesianRedBlack
|
|
//
|
|
// TODO: document the following as an API guaranteed public interface
|
|
|
|
/*
|
|
* Rough map of functionality against QDP++ Layout
|
|
*
|
|
* Param | Grid | QDP++
|
|
* -----------------------------------------
|
|
* | |
|
|
* void | oSites, iSites, lSites | sitesOnNode
|
|
* void | gSites | vol
|
|
* | |
|
|
* gcoor | oIndex, iIndex | linearSiteIndex // no virtual node in QDP
|
|
* lcoor | |
|
|
*
|
|
* void | CheckerBoarded | - // No checkerboarded in QDP
|
|
* void | FullDimensions | lattSize
|
|
* void | GlobalDimensions | lattSize // No checkerboarded in QDP
|
|
* void | LocalDimensions | subgridLattSize
|
|
* void | VirtualLocalDimensions | subgridLattSize // no virtual node in QDP
|
|
* | |
|
|
* int x 3 | oiSiteRankToGlobal | siteCoords
|
|
* | ProcessorCoorLocalCoorToGlobalCoor |
|
|
* | |
|
|
* vector<int> | GlobalCoorToRankIndex | nodeNumber(coord)
|
|
* vector<int> | GlobalCoorToProcessorCoorLocalCoor| nodeCoord(coord)
|
|
* | |
|
|
* void | Processors | logicalSize // returns cart array shape
|
|
* void | ThisRank | nodeNumber(); // returns this node rank
|
|
* void | ThisProcessorCoor | // returns this node coor
|
|
* void | isBoss(void) | primaryNode();
|
|
* | |
|
|
* | RankFromProcessorCoor | getLogicalCoorFrom(node)
|
|
* | ProcessorCoorFromRank | getNodeNumberFrom(logical_coord)
|
|
*/
|
|
// Work out whether to permute
|
|
// ABCDEFGH -> AE BF CG DH permute wrap num
|
|
//
|
|
// Shift 0 AE BF CG DH 0 0 0 0 ABCDEFGH 0 0
|
|
// Shift 1 BF CG DH AE 0 0 0 1 BCDEFGHA 0 1
|
|
// Shift 2 CG DH AE BF 0 0 1 1 CDEFGHAB 0 2
|
|
// Shift 3 DH AE BF CG 0 1 1 1 DEFGHABC 0 3
|
|
// Shift 4 AE BF CG DH 1 1 1 1 EFGHABCD 1 0
|
|
// Shift 5 BF CG DH AE 1 1 1 0 FGHACBDE 1 1
|
|
// Shift 6 CG DH AE BF 1 1 0 0 GHABCDEF 1 2
|
|
// Shift 7 DH AE BF CG 1 0 0 0 HABCDEFG 1 3
|
|
|
|
// Suppose 4way simd in one dim.
|
|
// ABCDEFGH -> AECG BFDH permute wrap num
|
|
|
|
// Shift 0 AECG BFDH 0,00 0,00 ABCDEFGH 0 0
|
|
// Shift 1 BFDH CGEA 0,00 1,01 BCDEFGHA 0 1
|
|
// Shift 2 CGEA DHFB 1,01 1,01 CDEFGHAB 1 0
|
|
// Shift 3 DHFB EAGC 1,01 1,11 DEFGHABC 1 1
|
|
// Shift 4 EAGC FBHD 1,11 1,11 EFGHABCD 2 0
|
|
// Shift 5 FBHD GCAE 1,11 1,10 FGHABCDE 2 1
|
|
// Shift 6 GCAE HDBF 1,10 1,10 GHABCDEF 3 0
|
|
// Shift 7 HDBF AECG 1,10 0,00 HABCDEFG 3 1
|
|
|
|
// Generalisation to 8 way simd, 16 way simd required.
|
|
//
|
|
// Need log2 Nway masks. consisting of
|
|
// 1 bit 256 bit granule
|
|
// 2 bit 128 bit granule
|
|
// 4 bits 64 bit granule
|
|
// 8 bits 32 bit granules
|
|
//
|
|
// 15 bits....
|
|
// TODO
|
|
//
|
|
// Base class to share common code between vRealF, VComplexF etc...
|
|
//
|
|
// lattice Broad cast assignment
|
|
//
|
|
// where() support
|
|
// implement with masks, and/or? Type of the mask & boolean support?
|
|
//
|
|
// Unary functions
|
|
// cos,sin, tan, acos, asin, cosh, acosh, tanh, sinh, // Scalar<vReal> only arg
|
|
// exp, log, sqrt, fabs
|
|
//
|
|
// transposeColor, transposeSpin,
|
|
// adjColor, adjSpin,
|
|
// traceColor, traceSpin.
|
|
// peekColor, peekSpin + pokeColor PokeSpin
|
|
//
|
|
// copyMask.
|
|
//
|
|
// localMaxAbs
|
|
//
|
|
// norm2,
|
|
// sumMulti equivalent.
|
|
// Fourier transform equivalent.
|
|
//
|