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.
derived relationship. Have Text/Binary/Xml versions of
Reader & Writer.
Any new Reader/Writer class inheriting the interface can give object serialisation
to any desired format now.
new file: lib/serialisation/BaseIO.h
modified: lib/serialisation/BinaryIO.h
modified: lib/serialisation/Serialisation.h
modified: lib/serialisation/TextIO.h
modified: lib/serialisation/XmlIO.h
The test uses the Xml, Binary and Text formats as well as cout << Object.
Azusa is working hard on the rectangle term and we'll hopefully start reproducing plaquettes
from RBC-UKQCD parameters soon !
My new laptop is pretty warm and is starting to groan ;)
