kuszewsk@euler.biology.yale.edu (John Kuszewski) (05/23/91)
Hi! Does anyone know if anyone is working on bringing a VLIW machine to market? Multiflow had a great technology. Aslo, can anyone give me some solid background references on VLIW architecture (esp. the memory architecture)? All the arch. books I've seen make no mention of VLIW. Thanks. --- John Kuszewski kuszewsk@euler.biology.yale.edu
wadswort@babss.UUCP (John H. Wadsworth) (05/24/91)
In article <1991May23.144817.23820@cs.yale.edu> kuszewsk@euler.biology.yale.edu writes: >Hi! > >Does anyone know if anyone is working on bringing a VLIW machine to market? >Multiflow had a great technology. Aslo, can anyone give me some solid >background references on VLIW architecture (esp. the memory architecture)? >Allthe arch. books I've seen make no mention of VLIW. > Several firms bought rights to the compiler and I expect they will be offering some variation within the next few years. For a good book on vliw see the "Bulldog" compiler book put out by Yale Press. The Multiflow founders were all from Yale and some assisted with the book. You could also stop by and I'll give you a technical reference book. BTW, Multiflow is still alive and the machines are still available as well as technology deals. Call or write me if you're interested. Bell Atlantic Business Systems Services John H. Wadsworth {uunet,yale}!babss!wadswort (203)488-5377
benseb@grumpy.sdsc.edu (Booker Bense) (05/24/91)
In article <1349@b1.babss.UUCP> wadswort@babss.UUCP (John H. Wadsworth) writes: >In article <1991May23.144817.23820@cs.yale.edu> kuszewsk@euler.biology.yale.edu writes: >>Hi! >> >>Does anyone know if anyone is working on bringing a VLIW machine to market? >>Multiflow had a great technology. Aslo, can anyone give me some solid >>background references on VLIW architecture (esp. the memory architecture)? >>Allthe arch. books I've seen make no mention of VLIW. >> > [ stuff deleted ] - I believe Alliant considers their FX8000 machines to be VLIW ( Very Long Instruction Word for the lurkers out there ). Too bad Alliant doesn't have VLTBC (Very Long Time Between Crashes) %-)!!! - Booker C. Bense prefered: benseb@grumpy.sdsc.edu "I think it's GOOD that everyone NeXT Mail: benseb@next.sdsc.edu becomes food " - Hobbes
colwell@pdx023.pdx023 (Robert Colwell) (05/24/91)
In article <1991May23.144817.23820@cs.yale.edu> kuszewsk@euler.biology.yale.edu (John Kuszewski) writes:
Does anyone know if anyone is working on bringing a VLIW machine to market?
Multiflow had a great technology. Aslo, can anyone give me some solid
background references on VLIW architecture (esp. the memory architecture)? All
the arch. books I've seen make no mention of VLIW.
John,
1) no comment on anyone bringing a VLIW to market (Alliant's isn't)
2) thanks for the MFCI plug, it was a great technology and it deserved
more user time than it got
3) we wrote two arch papers while there, the first in IEEE Transactions
on Computers, Aug. 1988, the second in 1990's Supercomputing Conf.,
and Chandra Joshi wrote a paper on the memory system arch that will
appear in this year's Parallel Processing Conf. in Chicago.
4) Actually the newer arch books. like Patterson/Hennessy do have a
section on VLIWs.
Bob Colwell colwell@ichips.intel.com 503-696-4550
Intel Corp. JF1-19
5200 NE Elam Young Parkway
Hillsboro, Oregon 97124