Characterization of the Paging Activity of NAS Benchmark Programs on the Intel Paragon
نویسندگان
چکیده
In this work, a two prong dynamic paging activity data analysis is considered. The rrskyline analysis" studies how similar/dissimilar is the paging activity oj different node programs in SPMD execution mode. This analysis is done by determining the rate at which different events Deem", by isolating the peaks of activity from the background, and by correlating the time of occurrence and the amplitude of these peaks. The second type oJ analysis is the "cumulative profile," used La determine the total load due to paging activity on the communication and the riG sub-system. Finally, we "eport the 1·esult oj analysis of the paging activities oj a representative class oj applications, the NAS parallel benchmark progmms. 'Work supported in part by NSF llndcr grants CCR-9119388 and BIR-9301210, by a grant from Intel Corporation and by CNPq Brazil.
منابع مشابه
On Gang Scheduling and Demand Paging
Uniprocessor system schedulers hide the high latency of a page fault, by performing a context switch from the process or thread experiencing the fault to another process ready to run. Gang scheduling attempts to schedule all the processes in a process group at the same time. Processes in a process group do not experience page faults at precisely the same time, and process group context switchin...
متن کاملData Sieving and Collective I/O in ROMIO
The I/O access patterns of parallel programs often consist of accesses to a large number of small, noncontiguous pieces of data. If an application’s I/O needs are met by making many small, distinct I/O requests, however, the I/O performance degrades drastically. To avoid this problem, MPI-IO allows users to access a noncontiguous data set with a single I/O function call. This feature provides M...
متن کاملThe NAS Parallel Benchmarks 2.1 Results
We present performance results for version 2.1 of the NAS Parallel Benchmarks (NPB) on the following architectures: • IBM SP2/66 MHz • SGI Power Challenge Array/90 MHz • Cray Research T3D • Intel Paragon "MILl, Inc. This work is supported through NASA Contract NAS 2-14303. tNASA Ames Research Center, Moffett Field, CA, 94035-1000. tSterling Software, Palo Alto, CA. This work is supported throug...
متن کاملEnhancing Applications Performance on Intel Paragon through Dynamic Memory Allocation
The Paragon operating system (OS) supports virtual memory (VM). The OS manages virtual memory by performing two services. Firstly, paging-in service pages the executable code from the service node to the compute nodes. This includes the paging-in of empty data corresponding to statically allocated arrays. Secondly, pagingout service is performed by paging the unused part of the OSF server to th...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2007