Abstract
This article presents various data redistribution methods for block-partitioned linear algebra algorithms operating on dense matrices that are distributed in a block-cyclic fashion. Because the algorithmic partitioning unit and the distribution blocking factor are most often chosen to be equal, severe alignment restrictions are induced on the operands, and optimal values with respect to performance are architecture dependent. The techniques presented in this paper redistribute data `on the fly,' so that the user's data distribution blocking factor becomes independent from the architecture dependent algorithmic partitioning. These techniques are applied to the matrix-matrix multiplication operation. A performance analysis along with experimental results shows that alignment restrictions can then be removed and that high performance can be maintained across platforms independently from the user's data distribution blocking factor.
| Original language | English |
|---|---|
| Pages (from-to) | 1201-1216 |
| Number of pages | 16 |
| Journal | IEEE Transactions on Parallel and Distributed Systems |
| Volume | 10 |
| Issue number | 12 |
| DOIs | |
| State | Published - 1999 |
| Externally published | Yes |
Funding
The authors acknowledge using the Intel Paragon XP/S 5 computer, located in the Oak Ridge National Laboratory Center for Computational Sciences (CCS), funded by the Department of Energy's Mathematical, Information, and Computational Sciences (MICS) Division of the Office of Computational and Technology Research. This work also was supported by the U.S. Defense Advanced Research Projects Agency under contract DAAH04-95-1-0077, administered by the Army Research Office. This research was conducted, as well, by using the resources of the Cornell Theory Center, which receives major funding from the U.S. National Science Foundation (NSF) and New York State, with additional support from the Advanced Research Projects Agency (ARPA), the National Center for Research Resources at the National Institutes of Health (NIH), IBM Corporation, and other members of the center's Corporate Partnership Program.
| Funders | Funder number |
|---|---|
| Office of Computational and Technology Research | |
| U.S. National Science Foundation | |
| National Science Foundation | |
| National Institutes of Health | |
| U.S. Department of Energy | |
| National Center for Research Resources | |
| Army Research Office | |
| Defense Advanced Research Projects Agency | DAAH04-95-1-0077 |
| International Business Machines Corporation | |
| Oak Ridge National Laboratory | |
| Advanced Research Projects Agency |