Consiglio Nazionale delle Ricerche

Tipo di prodottoArticolo in rivista
TitoloLU factorization with maximum performances on FPS architectures 38/64 bit
Anno di pubblicazione1988
FormatoCartaceo
Autore/iA. Corana, C. Martini, S. Ridella, C. Rolando
Affiliazioni autoriICE-CNR, Genova; ICE-CNR, Genova; ICE-CNR, Genova; ICE-CNR, Genova;
Autori CNR e affiliazioni
  • CLAUDIO MARTINI
  • CLAUDIA ROLANDO
  • ANGELO CORANA
Lingua/e
  • inglese
AbstractA technique for dense linear system solution is presented which reaches the maximum performances on attached processors like FPS-120, 5000 and X64 using the Fortran language with calls to the vector routines. Starting from the Dongarra's LU factorization algorithm the key idea is to carry out a pseudo-transposition of the lower triangular matrix L (including the main diagonal) around the minor diagonal. The pseudo-transposition allows to carry out all the matrix vector operations involved in LU factorization with only stride 1 dot product operations which, using the TM Auxiliary Memory and the TMDOT routine, can be executed in the FPS processor obtaining the maximum speed. Since the algorithm uses only vector instructions it is fully portable on all the FPS 38/64 bit machines and in general on all the vector computers with a similar memory structure. Furthermore the algorithm can be easily translated into the new FORTRAN 8X, which will probably become the standard for future SIMD computers for numerical applications. The algorithm has been implemented on a FPS-100 yielding the asymptotic speed r?=8 MegaFLOPS (FPS-100 peak performances) and the half performances length N1/2 = 235. The N1/2 value could be lowered by using the APAL Assembly Language to code some critical parts, losing however the code portability.
Lingua abstractinglese
Altro abstract-
Lingua altro abstract-
Pagine da782
Pagine a788
Pagine totali-
RivistaLecture notes in computer science
Attiva dal 1973
Editore: Springer - Berlin
Paese di pubblicazione: Germania
Lingua: multilingue
ISSN: 0302-9743
Titolo chiave: Lecture notes in computer science
Titolo proprio: Lecture notes in computer science.
Titolo abbreviato: Lect. notes comput. sci.
Titoli alternativi:
  • Lecture notes in computer science. Lecture notes in artificial intelligence
  • Lecture notes in artificial intelligence
  • LNCS. Lecture notes in computer science (Print)
  • Lecture notes in computer science (Print)
  • Lecture notes in computer science. LNAI. Lecture notes in artificial intelligence
  • Lecture notes in computer science. Lecture notes in bioinformatics (Print)
  • Lecture notes in computer science. Journal subline
Numero volume della rivista297
Fascicolo della rivista-
DOI-
Verificato da refereeSì: Internazionale
Stato della pubblicazionePublished version
Indicizzazione (in banche dati controllate)-
Parole chiaveLU factorization; vector computers; FPS array processors; stride-1 dot product; performance evaluation
Link (URL, URI)http://link.springer.com/chapter/10.1007%2F3-540-18991-2_44
Titolo parallelo-
Data di accettazione-
Note/Altre informazioni-
Strutture CNR
  • IEIIT — IEIIT - Sede secondaria di Genova
Moduli CNR-
Progetti Europei-
Allegati
  • LU factorization with maximum performances on FPS architectures 38/64 bit