Title
Reaching bandwidth saturation using transparent injection parallelization
Abstract
AbstractAlthough logically available, applications may not exploit enough instantaneous communication concurrency to maximize network utilization on HPC systems. This is exacerbated in hybrid programming models that combine single program multiple data with OpenMP or CUDA. We present the design of a źmulti-threadedź runtime able to transparently increase the instantaneous network concurrency and to provide near saturation bandwidth, independent of the application configuration and dynamic behavior. The runtime offloads communication requests from application level tasks to multiple communication servers. The servers use system specific performance models to attain network saturation. Our techniques alleviate the need for spatial and temporal application level message concurrency optimizations. Experimental results show improved message throughput and bandwidth by as much as 150% for 4 KB messages on InfiniBand and by as much as 120% for 4 KB messages on Cray Aries. For more complex operations such as all-to-all collectives, we observe as much as 30% speedup. This translates into 23% speedup on 12,288 cores for a NAS FT implemented using FFTW. We observe as much as 76% speedup on 1500 cores for an already optimized UPC+OpenMP geometric multigrid application using hybrid parallelism. For the geometric multigrid GPU implementation, we observe as much as 44% speedup on 512 GPUs.
Year
DOI
Venue
2017
10.1177/1094342016672720
Periodicals
Keywords
Field
DocType
Communication concurrency, multi-threaded runtime, one sided communication, parallel injection, UPC
Saturation (chemistry),InfiniBand,CUDA,Computer science,Concurrency,Server,Parallel computing,Exploit,Bandwidth (signal processing),Throughput
Journal
Volume
Issue
ISSN
31
5
1094-3420
Citations 
PageRank 
References 
1
0.38
19
Authors
4
Name
Order
Citations
PageRank
Nicholas Chaimov1263.55
Khaled Z. Ibrahim2282.47
Samuel Williams3707.37
Costin Iancu452934.78