Lightweight remote procedure call
ACM Transactions on Computer Systems (TOCS)
Munin: distributed shared memory based on type-specific memory coherence
PPOPP '90 Proceedings of the second ACM SIGPLAN symposium on Principles & practice of parallel programming
Tolerating latency through software-controlled data prefetching
Tolerating latency through software-controlled data prefetching
Data Forwarding in Scalable Shared-Memory Multiprocessors
IEEE Transactions on Parallel and Distributed Systems
Multi-protocol active messages on a cluster of SMP's
SC '97 Proceedings of the 1997 ACM/IEEE conference on Supercomputing
Design and evaluation of multiprotocol communication on a cluster of smp's
Design and evaluation of multiprotocol communication on a cluster of smp's
Multifacet's general execution-driven multiprocessor simulator (GEMS) toolset
ACM SIGARCH Computer Architecture News - Special issue: dasCMP'05
Data Transfers between Processes in an SMP System: Performance Study and Application to MPI
ICPP '06 Proceedings of the 2006 International Conference on Parallel Processing
Comparing memory systems for chip multiprocessors
Proceedings of the 34th annual international symposium on Computer architecture
Hi-index | 0.00 |
Moving data between cores on hardware coherent architectures suffers from memory latency and causes cache misses and coherence traffic, which are obstacles to achieving high performance. In this paper, we evaluate the potential for hardware optimization of message data transfer on chip multiprocessors with a combination of NAS parallel MPI benchmarks, Intel IMB MPI benchmarks, and a few microbenchmarks on a full-system simulator based on Simics and FeS2. We show that while passive hardware driven by cores can reduce cache traffic, it provides limited performance gains. We propose a data movement manager (DMM) that uses the on-chip coherence protocols to implement zero-copy message passing between separate address spaces and to remove synchronization and copy overheads from the processors. We also discuss methods for managing data placement in caches to reduce latency. We show that such a design shows substantial promise for both cache traffic reduction and performance improvements.