You need JavaScript to view this

SCWEB, Scientific Workstation Evaluation Benchmark

Miscellaneous:

Abstract

1 - Description of program or function: The SCWEB (Scientific Workstation Evaluation Benchmark) software includes 16 programs which are executed in a well-defined scenario to measure the following performance capabilities of a scientific workstation: implementation of FORTRAN77, processor speed, memory management, disk I/O, monitor (or display) output, scheduling of processing (multiprocessing), and scheduling of print tasks (spooling). 2 - Method of solution: The benchmark programs are: DK1, DK2, and DK3, which do Fourier series fitting based on spline techniques; JC1, which checks the FORTRAN function routines which produce numerical results; JD1 and JD2, which solve dense systems of linear equations in double- and single-precision, respectively; JD3 and JD4, which perform matrix multiplication in single- and double-precision, respectively; RB1, RB2, and RB3, which perform substantial amounts of I/O processing on files other than the input and output files; RR1, which does intense single-precision floating-point multiplication in a tight loop, RR2, which initializes a 512x512 integer matrix in a manner which skips around in the address space rather than initializing each consecutive memory cell in turn; RR3, which writes alternating text buffers to the output file; RR4, which evaluates the timer routines and demonstrates that they conform to the specification; and RR5,  More>>
Authors:
Raffenetti, R C [1] 
  1. Computing Services-Support Services Division, Argonne National Laboratory, 9700 South Cass Avenue, Argonne, Illinois 60439 (United States)
Publication Date:
Jun 16, 1988
Product Type:
Miscellaneous
Resource Relation:
Other Information: Country of input: International Atomic Energy Agency (IAEA); 1 ref.
Subject:
97 MATHEMATICAL METHODS AND COMPUTING; BENCHMARKS; COMPUTER PROGRAM DOCUMENTATION; EQUATIONS; EVALUATION; FORTRAN; MEMORY MANAGEMENT; PARALLEL PROCESSING; PERFORMANCE TESTING; S CODES; SPECIFICATIONS; WEBSITES; COMPUTER CODES; DATA PROCESSING; DOCUMENT TYPES; PROCESSING; PROGRAMMING; PROGRAMMING LANGUAGES; TESTING
OSTI ID:
21352476
Research Organizations:
Organisation for Economic Co-Operation and Development, Nuclear Energy Agency - OECD/NEA, Le Seine Saint-Germain, 12 boulevard des Iles, F-92130 Issy-les-Moulineaux (France)
Country of Origin:
NEA
Language:
English
Other Identifying Numbers:
TRN: XN10V1894086612
Availability:
Available on-line: http://www.nea.fr/abs/html/nesc9717.html
Submitting Site:
INIS
Size:
[html] pages
Announcement Date:
Nov 19, 2010

Miscellaneous:

Citation Formats

Raffenetti, R C. SCWEB, Scientific Workstation Evaluation Benchmark. NEA: N. p., 1988. Web.
Raffenetti, R C. SCWEB, Scientific Workstation Evaluation Benchmark. NEA.
Raffenetti, R C. 1988. "SCWEB, Scientific Workstation Evaluation Benchmark." NEA.
@misc{etde_21352476,
title = {SCWEB, Scientific Workstation Evaluation Benchmark}
author = {Raffenetti, R C}
abstractNote = {1 - Description of program or function: The SCWEB (Scientific Workstation Evaluation Benchmark) software includes 16 programs which are executed in a well-defined scenario to measure the following performance capabilities of a scientific workstation: implementation of FORTRAN77, processor speed, memory management, disk I/O, monitor (or display) output, scheduling of processing (multiprocessing), and scheduling of print tasks (spooling). 2 - Method of solution: The benchmark programs are: DK1, DK2, and DK3, which do Fourier series fitting based on spline techniques; JC1, which checks the FORTRAN function routines which produce numerical results; JD1 and JD2, which solve dense systems of linear equations in double- and single-precision, respectively; JD3 and JD4, which perform matrix multiplication in single- and double-precision, respectively; RB1, RB2, and RB3, which perform substantial amounts of I/O processing on files other than the input and output files; RR1, which does intense single-precision floating-point multiplication in a tight loop, RR2, which initializes a 512x512 integer matrix in a manner which skips around in the address space rather than initializing each consecutive memory cell in turn; RR3, which writes alternating text buffers to the output file; RR4, which evaluates the timer routines and demonstrates that they conform to the specification; and RR5, which determines whether the workstation is capable of executing a 4-megabyte program}
place = {NEA}
year = {1988}
month = {Jun}
}