Abstract | ||
---|---|---|
Prior studies have established the performance impact of coherence protocols optimized for specific patterns of shared-data accesses in Non-Uniform-Memory-Architecture (NUMA) systems. First, this work incorporates a directory-based protocol into the runtime system of X10 — a Partitioned-Global-Address-Space (PGAS) programming language — to manage read-mostly, producer-consumer, stencil, and migratory variables. This protocol complements the existing X10Protocol, which keeps a unique copy of a shared variable and relies on message transfers for all remote accesses. The X10Protocol is effective to manage accumulator, write-mostly and general read-write variables. Then, it introduces a new shared-variable access-pattern profiler that is used by a new coherence-policy manager to decide which protocol should be used for each shared variable. The profiler can be run in both offline and online modes. An evaluation on a 128-core distributed-memory machine reveals that coordination between these protocols does not degrade performance on any of the applications studied, and achieves speedup in the range of 15% to 40% over X10Protocol. The performance is also comparable to carefully hand-written versions of the applications. |
Year | DOI | Venue |
---|---|---|
2014 | 10.1109/HiPC.2014.7116889 | International Conference on High Performance Computing |
Field | DocType | ISSN |
Data structure,Computer science,Stencil,Parallel computing,Distributed memory,Data diffusion machine,Distributed shared memory,Partitioned global address space,Operating system,Distributed computing,Runtime system,Speedup | Conference | 1094-7256 |
ISBN | Citations | PageRank |
978-1-4799-5975-4 | 1 | 0.36 |
References | Authors | |
25 | 3 |
Name | Order | Citations | PageRank |
---|---|---|---|
Jeeva Paudel | 1 | 22 | 2.82 |
Olivier Tardieu | 2 | 462 | 32.13 |
José Nelson Amaral | 3 | 436 | 40.18 |