Speeding up the systolic design in bidirectional linear arrays

References

• Kung , H.T. and Leiserson , C.E. April 1978 . Systolic arrays(for VLSI) , April , Pitsburg, PA : Carnegie Mellon University . Tech, Rep, CS-79-103
   Google Scholar
• Mead , C. and Conway , L. 1980 . Introduction to VLSI Systems , Addison-Wesley .
   Google Scholar
• Foster , M.J. and Kung , H.T. 1980 . The design of special-purpose VLSI chips . IEEE Computer , 13 January : 26 – 40 .
   Google Scholar
• Gentleman , W.M. and Kung , H.T. 1981 . Matrix triangularization by systolic arrays . Proc. SPIE Real-Time Signal Processing IV , 298 January : 19 – 26 .
   Google Scholar
• Kung , H.T. 1982 . Why systolic architectures . IEEE Computer , 15 January : 37 – 46 .
   Google Scholar
• Suros , R. and Montagne , E. 1987 . Optimizing systolic networks by fitting diagonals . Parallel Computing , 4 April : 167 – 174 .
   Google Scholar
• Gušev , M. and Evans , D.J. April 1992 . VLSI processor array IPS cells , April , Loughborough University of Technology . Tech. Rep, 699 PARC, Dept. of Computer Studies
   Google Scholar
• Kung , S.Y. 1988 . VLSI Array Processors , Englewood Clifs, N. J : Prentice-Hall .
   Google Scholar
• Kung , H.T. 1983 . “ Notes on VLSI computation ” . In Parallel Processing Systems , Edited by: Evans , D.J. 339 – 356 . Cambridge University Press .
   Google Scholar
• Robert , Y. 1985 . Block LU decomposition of a band matrix on a systolic array . Int. Journal Computer Math , 17 : 295 – 315 .
   Web of Science ®Google Scholar
• Megson , G.M. and Evans , D.J. . Soft-systolic pipelined matrix algorithms . Int. Conf, on Parallel Computing 85 . pp. 171 – 180 . North-Holiand : Elsevier Science Publishers B.V .
   Google Scholar
• Gušev , M. and Evans , D.J. January 1992 . Fast systolic design and double pipelines , January , Loughborough University of Technology . Tech. Rep. 665.PARC, Dept, of Computer Studies
   Google Scholar
• Evans , D.J. and Gušev , M. January 1992 . Double pipelines and fast systolic designs on linear arrays , January , Loughborough University of Technology . Tech. Rep. 667 PARC,Dept. of Computer Studies
   Google Scholar
• Evans , D.J. and Gušev , M. March 1992 . Double pipelines and fast Systolic Designs on linear , March , Loughborough University of Technology . Tech. Rep. 696 PARC, Dept. of Computer Studies
   Google Scholar
• Gušev , M. and Evans , D.J. October 1991 . “ Folding transformations for systolic processor arrays ” . In Dept. of Computer Studies , October , Loughborough University of Technology . Tech. Rep. 643 PARC
   Google Scholar
• Gušev , M. , Evans , D.J. and Tasič , J. 1992 . Fast linear systolic matrix vector multiplication . Int. Journal Computer Math , October to be published in
   Google Scholar
• Gušev , M. and Evans , D.J. April 1992 . The fastest matrix vector multiplication , April , Loughborough University of Technology . Tech. Rep, 703 PARC, Dept, of Computer Studies
   Google Scholar
• Annaratone , M. , Arnould , E. , Gross , T. , Kung , H.T. , Lam , M. , Menzilciogly , O. and Web , J.A. 1987 . The WARP computer: Architecture, implementation and performance . IEEE Trans. Computers , C-36 December : 1523 – 1538 .
   Google Scholar