Welcome!
To use the personalized features of this site, please log in or register.
If you have forgotten your username or password, we can help.
|
 |
rMPI: Message Passing on Multicore Processors with On-Chip Interconnect
| |
|
rMPI: Message Passing on Multicore Processors with On-Chip Interconnect
James Psota1 and Anant Agarwal1
| (1) |
Massachusetts Institute of Technology, Cambridge, MA 02139, USA |
Abstract
With multicore processors becoming the standard architecture, programmers are faced with the challenge of developing applications
that capitalize on multicore’s advantages. This paper presents rMPI, which leverages the on-chip networks of multicore processors
to build a powerful abstraction with which many programmers are familiar: the MPI programming interface. To our knowledge,
rMPI is the first MPI implementation for multicore processors that have on-chip networks. This study uses the MIT Raw processor
as an experimentation and validation vehicle, although the findings presented are applicable to multicore processors with
on-chip networks in general. Likewise, this study uses the MPI API as a general interface which allows parallel tasks to communicate,
but the results shown in this paper are generally applicable to message passing communication. Overall, rMPI’s design constitutes
the marriage of message passing communication and on-chip networks, allowing programmers to employ a well-understood programming
model to a high performance multicore processor architecture.
This work assesses the applicability of the MPI API to multicore processors with on-chip interconnect, and carefully analyzes
overheads associated with common MPI operations. This paper contrasts MPI to lower-overhead network interface abstractions
that the on-chip networks provide. The evaluation also compares rMPI to hand-coded applications running directly on one of
the processor’s low-level on-chip networks, as well as to a commercial-quality MPI implementation running on a cluster of
Ethernet-connected workstations. Results show speedups of 4x to 15x for 16 processor cores relative to one core, depending
on the application, which equal or exceed performance scalability of the MPI cluster system. However, this paper ultimately
argues that while MPI offers reasonable performance on multicores when, for instance, legacy applications must be run, its
large overheads squander the multicore opportunity. Performance of multicores could be significantly improved by replacing
MPI with a lighter-weight communications API with a smaller memory footprint.
Fulltext Preview (Small, Large)
 References secured to subscribers.
|
|
|
|
|
|