On Wed 2008-06-25 16:35, Roy Stogner wrote: > If the PETSc people went to all the trouble of adding asynchronous > communication to their assembly code, were they smart enough to start > that communication as soon as possible? Because there is one bit of > computation that could definitely be started before the start of the > assembly has been communicated: the rest of the assembly.
Maybe I don't understand, but it is not normally necessary to start communicating for assembly until all entries have been computed. Flushing the stash early will just require some entries to be communicated more than once. For what it's worth, overlapping communication with computation rarely makes a big difference on modern hardware. The CPU is used for packing and unpacking. It can be used to hide a bit of network latency, but I wouldn't worry about it. This recently came up on the PETSc mailing list and Barry said he generally doesn't recommend bothering to overlap communication with computation. Jed
pgpoQieMwrwF8.pgp
Description: PGP signature
------------------------------------------------------------------------- Check out the new SourceForge.net Marketplace. It's the best place to buy or sell services for just about anything Open Source. http://sourceforge.net/services/buy/index.php
_______________________________________________ Libmesh-devel mailing list [email protected] https://lists.sourceforge.net/lists/listinfo/libmesh-devel
