portelli/Grid
1
0
Fork 0
mirror of https://github.com/paboyle/Grid.git synced 2025-06-11 11:56:56 +01:00
Code Releases Activity

Binary IO file for generic Grid array parallel I/O.

Browse Source 
Number of IO MPI tasks can be varied by selecting which
dimensions use parallel IO and which dimensions use Serial send to boss
I/O.

Thus can neck down from, say 1024 nodes = 4x4x8x8 to {1,8,32,64,128,256,1024} nodes
doing the I/O.

Interpolates nicely between ALL nodes write their data, a single boss per time-plane
in processor space [old UKQCD fortran code did this], and a single node doing all I/O.

Not sure I have the transfer sizes big enough and am not overly convinced fstream
is guaranteed to not give buffer inconsistencies unless I set streambuf size to zero.

Practically it has worked on 8 tasks, 2x1x2x2 writing /cloning NERSC configurations
on my MacOS + OpenMPI and Clang environment.

It is VERY easy to switch to pwrite at a later date, and also easy to send x-strips around from
each node in order to gather bigger chunks at the syscall level.

That would push us up to the circa 8x 18*4*8 == 4KB size write chunk, and by taking, say, x/y non
parallel we get to 16MB contiguous chunks written in multi 4KB transactions
per IOnode in 64^3 lattices for configuration I/O.

I suspect this is fine for system performance.
This commit is contained in:
Peter Boyle
2015-08-26 13:40:29 +01:00
parent 612957f057
commit dc814f30da
14 changed files with 840 additions and 410 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
tests/Test_GaugeAction.cc
View File

@ -50,7 +50,7 @@ int main (int argc, char ** argv)
NerscField header;
std::string file("./ckpoint_lat.4000");
readNerscConfiguration(Umu,header,file);
NerscIO::readConfiguration(Umu,header,file);
for(int mu=0;mu<Nd;mu++){
U[mu] = PeekIndex<LorentzIndex>(Umu,mu);

2
tests/Test_cayley_ldop_cr.cc
View File

@ -42,7 +42,7 @@ int main (int argc, char ** argv)
NerscField header;
std::string file("./ckpoint_lat.400");
readNerscConfiguration(Umu,header,file);
NerscIO::readConfiguration(Umu,header,file);
// SU3::ColdConfiguration(RNG4,Umu);
// SU3::TepidConfiguration(RNG4,Umu);

2
tests/Test_dwf_hdcr.cc
View File

@ -388,7 +388,7 @@ int main (int argc, char ** argv)
NerscField header;
std::string file("./ckpoint_lat.4000");
readNerscConfiguration(Umu,header,file);
NerscIO::readConfiguration(Umu,header,file);
// SU3::ColdConfiguration(RNG4,Umu);
// SU3::TepidConfiguration(RNG4,Umu);

9
tests/Test_nersc_io.cc
View File

@ -28,7 +28,7 @@ int main (int argc, char ** argv)
NerscField header;
std::string file("./ckpoint_lat.4000");
readNerscConfiguration(Umu,header,file);
NerscIO::readConfiguration(Umu,header,file);
for(int mu=0;mu<Nd;mu++){
U[mu] = PeekIndex<LorentzIndex>(Umu,mu);
@ -89,6 +89,13 @@ int main (int argc, char ** argv)
TComplex TcP = sum(cPlaq);
Complex ll= TensorRemove(TcP);
std::cout<<GridLogMessage << "coarsened plaquettes sum to " <<ll*PlaqScale<<std::endl;
std::string clone2x3("./ckpoint_clone2x3.4000");
std::string clone3x3("./ckpoint_clone3x3.4000");
int precision32 = 0;
NerscIO::writeConfiguration(Umu,clone3x3,0,precision32);
NerscIO::writeConfiguration(Umu,clone2x3,1,precision32);
Grid_finalize();
}