hrcak mascot   Srce   HID

Izvorni znanstveni članak
https://doi.org/10.2498/cit.2000.01.03

Performance Analysis, PVM and MPI Implementation of a DSCF Hartree Fock Program

Peter Zinterhof
Othmar Steinhauser
Siegfried Hoefinger

Puni tekst: engleski, pdf (224 KB) str. 19-30 preuzimanja: 500* citiraj
APA 6th Edition
Zinterhof, P., Steinhauser, O. i Hoefinger, S. (2000). Performance Analysis, PVM and MPI Implementation of a DSCF Hartree Fock Program. Journal of computing and information technology, 8 (1), 19-30. https://doi.org/10.2498/cit.2000.01.03
MLA 8th Edition
Zinterhof, Peter, et al. "Performance Analysis, PVM and MPI Implementation of a DSCF Hartree Fock Program." Journal of computing and information technology, vol. 8, br. 1, 2000, str. 19-30. https://doi.org/10.2498/cit.2000.01.03. Citirano 28.02.2021.
Chicago 17th Edition
Zinterhof, Peter, Othmar Steinhauser i Siegfried Hoefinger. "Performance Analysis, PVM and MPI Implementation of a DSCF Hartree Fock Program." Journal of computing and information technology 8, br. 1 (2000): 19-30. https://doi.org/10.2498/cit.2000.01.03
Harvard
Zinterhof, P., Steinhauser, O., i Hoefinger, S. (2000). 'Performance Analysis, PVM and MPI Implementation of a DSCF Hartree Fock Program', Journal of computing and information technology, 8(1), str. 19-30. https://doi.org/10.2498/cit.2000.01.03
Vancouver
Zinterhof P, Steinhauser O, Hoefinger S. Performance Analysis, PVM and MPI Implementation of a DSCF Hartree Fock Program. Journal of computing and information technology [Internet]. 2000 [pristupljeno 28.02.2021.];8(1):19-30. https://doi.org/10.2498/cit.2000.01.03
IEEE
P. Zinterhof, O. Steinhauser i S. Hoefinger, "Performance Analysis, PVM and MPI Implementation of a DSCF Hartree Fock Program", Journal of computing and information technology, vol.8, br. 1, str. 19-30, 2000. [Online]. https://doi.org/10.2498/cit.2000.01.03

Sažetak
A new Direct SCF-Hartree Fock program (DSCF) has been improved by the method of DIIS. (17), (18) General performance measurement tools, as provided on the SGIPower Challenge/R10000 (194 MHz) running IRIX 6.2, which are the shell-commands perfex -a a.out and ssrun -(pcsampl, ideal, usertime) a.out, have been used for profiling the code. The main cpu-time-consuming subroutine was detected and parallel versions for PVM 3.3 as well as MPI have been deduced. An additional module for the purpose of achieving load-balancewas introduced and obtained speed-up parameters are presented and compared.

Hrčak ID: 44849

URI
https://hrcak.srce.hr/44849

Posjeta: 710 *