gwu@clyde.ATT.COM (George Wu) (03/31/88)
I recently read a short blurb somewhere about Sandia achieving some
astonishing speedups in parallel processing. As the article was a non-technical
magazine, they didn't go into detail.
Could someone expound upon this, please? At the very least, I'd like to
know what tasks they were attempting. A quick summary of what methods were
used to acheive their results would be nice, too. I mean, did they used some
amazing new architecture? Or a fantastic optimzing compiler? Maybe completely
new algorithms? (I suspect it's more like a combination of all of these. At
the very least, I believe the article stated they did use their own hardware.)
As a minimum, a reference to a more informative article would be appreciated.
Thanks much in advance.
--
George J Wu
UUCP: {ihnp4,ulysses,cbosgd,allegra}!clyde!gwu
ARPA: gwu%clyde.att.com@rutgers.edu or gwu@faraday.ece.cmu.edulindsay@K.GP.CS.CMU.EDU (Donald Lindsay) (04/02/88)
In article <24119@clyde.ATT.COM> gwu@clyde.ATT.COM (George Wu) writes: >I recently read a short blurb somewhere about Sandia achieving some >astonishing speedups in parallel processing. As the article was a >non-technical magazine, they didn't go into detail. >Could someone expound upon this, please? They did it on a parallel machine, so the subject has been discussed on comp.parallel (formerly comp.hypercube). Rather than discuss it here, I recommend you read back news on that newsgroup, and then consider joining the newsgroup. -- Don lindsay@k.gp.cs.cmu.edu CMU Computer Science