portelli/Grid
1
0
Fork 0
mirror of https://github.com/paboyle/Grid.git synced 2024-11-10 07:55:35 +00:00
Code Releases Activity
1,475 Commits 86 Branches 14 Tags 74 MiB
C++ 92.7%
C 3.6%
M4 1.7%
Shell 0.9%
Mathematica 0.8%
Other 0.2%
ab45f029f4
Go to file
Antonin Portelli ab45f029f4 ignore Config.h.in
2015-12-08 13:52:44 +00:00
benchmarks Bigger ncall as timing loops got small on cori 2015-11-07 00:04:40 -08:00
docs Small modification to the configure files 2015-06-04 14:17:58 +09:00
gcc-bug-report Sizable improvement in multigrid for unsquared. 2015-07-24 01:31:13 +09:00
lib XmlIO: minor code cleaning 2015-12-07 18:30:00 +00:00
m4 fix of AX_GCC_X86_AVX_XGETBV macro 2015-07-17 11:15:57 +09:00
scripts precision set 2015-11-29 00:30:44 +00:00
tests Warn fix clang 2015-11-29 11:19:12 +00:00
.gitignore ignore Config.h.in 2015-12-08 13:52:44 +00:00
AUTHORS Update AUTHORS 2015-03-07 07:00:39 +00:00
ChangeLog Updating build system 2015-03-04 04:53:40 +00:00
configure.ac EXEC INFO check 2015-11-06 10:31:05 +00:00
COPYING Extra files 2015-03-04 12:03:07 +00:00
LICENSE Initial commit 2015-03-04 02:30:11 +00:00
Makefile.am Reorganise of file naming 2015-06-03 12:47:05 +01:00
NEWS Updating build system 2015-03-04 04:53:40 +00:00
README Added check of mpfr and gmp at configure time 2015-05-19 13:54:55 +09:00
README.md Check at configure time if CPU supports the requested SIMD optimization 2015-05-27 18:30:11 +09:00
TODO Reintroducing the hand unrolled loops 2015-09-08 17:45:30 +01:00

README.md

Grid

Data parallel C++ mathematical object library

This library provides data parallel C++ container classes with internal memory layout that is transformed to map efficiently to SIMD architectures. CSHIFT facilities are provided, similar to HPF and cmfortran, and user control is given over the mapping of array indices to both MPI tasks and SIMD processing elements.

  • Identically shaped arrays then be processed with perfect data parallelisation.
  • Such identically shapped arrays are called conformable arrays.

The transformation is based on the observation that Cartesian array processing involves identical processing to be performed on different regions of the Cartesian array.

The library will both geometrically decompose into MPI tasks and across SIMD lanes. Local vector loops are parallelised with OpenMP pragmas.

Data parallel array operations can then be specified with a SINGLE data parallel paradigm, but optimally use MPI, OpenMP and SIMD parallelism under the hood. This is a significant simplification for most programmers.

The layout transformations are parametrised by the SIMD vector length. This adapts according to the architecture. Presently SSE4 (128 bit) AVX, AVX2 (256 bit) and IMCI and AVX512 (512 bit) targets are supported.

These are presented as

vRealF, vRealD, vComplexF, vComplexD

internal vector data types. These may be useful in themselves for other programmers. The corresponding scalar types are named

RealF, RealD, ComplexF, ComplexD

MPI, OpenMP, and SIMD parallelism are present in the library.

You can give `configure' initial values for configuration parameters by setting variables in the command line or in the environment. Here are examples:

 ./configure CXX=clang++ CXXFLAGS="-std=c++11 -O3 -msse4" --enable-simd=SSE4

 ./configure CXX=clang++ CXXFLAGS="-std=c++11 -O3 -mavx" --enable-simd=AVX1

 ./configure CXX=clang++ CXXFLAGS="-std=c++11 -O3 -mavx2" --enable-simd=AVX2

 ./configure CXX=icpc CXXFLAGS="-std=c++11 -O3 -mmic" --enable-simd=AVX512 --host=none

For developers: Use reconfigure_script in the scripts/ directory to create the autotools environment