skip to main content
OSTI.GOV title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: COS: A Parallel Performance Model for Dynamic Variations in Processor Speed, Memory Speed, and Thread Concurrency

Authors:
; ;
Publication Date:
Research Org.:
Lawrence Livermore National Lab. (LLNL), Livermore, CA (United States)
Sponsoring Org.:
USDOE
OSTI Identifier:
1378502
Report Number(s):
LLNL-CONF-728263
DOE Contract Number:
AC52-07NA27344
Resource Type:
Conference
Resource Relation:
Conference: Presented at: International Symposium on High Performance Parallel and Distributed Computing, Washington, DC, United States, Jun 26 - Jun 30, 2017
Country of Publication:
United States
Language:
English
Subject:
97 MATHEMATICS, COMPUTING, AND INFORMATION SCIENCE

Citation Formats

Li, B, Leon, E A, and Cameron, K W. COS: A Parallel Performance Model for Dynamic Variations in Processor Speed, Memory Speed, and Thread Concurrency. United States: N. p., 2017. Web. doi:10.1145/3078597.3078601.
Li, B, Leon, E A, & Cameron, K W. COS: A Parallel Performance Model for Dynamic Variations in Processor Speed, Memory Speed, and Thread Concurrency. United States. doi:10.1145/3078597.3078601.
Li, B, Leon, E A, and Cameron, K W. Thu . "COS: A Parallel Performance Model for Dynamic Variations in Processor Speed, Memory Speed, and Thread Concurrency". United States. doi:10.1145/3078597.3078601. https://www.osti.gov/servlets/purl/1378502.
@article{osti_1378502,
title = {COS: A Parallel Performance Model for Dynamic Variations in Processor Speed, Memory Speed, and Thread Concurrency},
author = {Li, B and Leon, E A and Cameron, K W},
abstractNote = {},
doi = {10.1145/3078597.3078601},
journal = {},
number = ,
volume = ,
place = {United States},
year = {Thu Mar 30 00:00:00 EDT 2017},
month = {Thu Mar 30 00:00:00 EDT 2017}
}

Conference:
Other availability
Please see Document Availability for additional information on obtaining the full-text document. Library patrons may search WorldCat to identify libraries that hold this conference proceeding.

Save / Share:
  • In this study, results of an investigation into applying parallel computing on a shared memory multiprocessor computer to the dynamic process simulation of a distillation column with use of a sequential modular simulator are reported. Two DYFLO process simulation models of distillation columns were parallelized and ported to a BBN Butterfly Parallel Processor computer. Computations were performed with up to 14 concurrently operating processors. General performance aspects of simulation on parallel computers are discussed and speedup as a function of humber of concurrently operating processors is reported for the two distillation column simulations.
  • Dynamic memory allocation is a useful feature for the UM as it allows the pre-compilation of a large amount of the model code. Production runs of differing resolutions can then use this pre-compiled object code thus reducing their compilation time. Although sequentially free lists are effective for the UM on the KSR1, a shared free list for the memory allocator {open_quote}malloc{close_quote} can seriously degrade performance in parallel. Thread based free lists or the separate allocation of memory from a threads stack alleviates this problem.
  • In this thesis the author studies the interconnection networks and their switch architectures, the performance of different architectures, under the MIMD shared memory environment, using both simulation and analytical methods. The networks he studies are constructed with a basic building block, a switch element. Quite a few alternatives are proposed in designing the switch element. Naturally, different switch architectures given different performance. He studies the performance of different switches with both analytical methods and extensive simulations. He also proposes a multiple hand shaking signal switch architecture which gives the maximum performance. Various interconnection networks and interested issues related to themmore » are reviewed in the thesis. He proposes a new class of interconnection networks called F networks. In comparison to traditional multi-stage network, F networks provide faster communications among nodes within a cluster. Also extra routes available in the F network fault-tolerant. Based on simulations and analysis, Kruskal, Snir and Weiss established a formula for calculating network delays under moderate traffic. From his simulations the author surprisedly discovered that the Kruskal-Snir-Weiss formula holds only of the forward path delay of the networks, the return path delay is actually substantially less than the delay of the forward path. He completes the network performance formula by extending the Kruskal-Snir-Weiss formula to include the return path. He also analyzes the network performance under hot spot' traffic and obtains analytic results on the performance attained.« less