MOPED: Orchestrating interprocess message data on CMPs

Future CMPs will combine many simple cores with deep cache hierarchies. With more cores, cache resources per core are fewer, and must be shared carefully to avoid poor utilization due to conflicts and pollution. Explicit motion of data in these architectures, such as message passing, can provide hints about program behavior that can be used to hide latency and improve cache behavior. However, to make these models attractive, synchronization overhead and data copying must also be offloaded from the processors. In this paper, we describe a Message Orchestration and Performance Enhancement Device (MOPED) that provides hardware mechanisms to support state-of-the-art message passing protocols such as MPI. MOPED extends the perprocessor cache controllers and coherence protocol to support message synchronization and management in hardware, to transfer message data efficiently without intermediate buffer copies, and to place useful data in caches in a timely manner. MOPED thus allows full ...

• Type: Journal
• Year: 2011
• Where: HPCA
• Authors: Junli Gu, Steven S. Lumetta, Rakesh Kumar, Yihe Sun
• Keywords: Coherence Protocol, Distributed And Parallel Computing, HPCA 2011, Mpi Execution, Parallel Benchmarks