home *** CD-ROM | disk | FTP | other *** search
- Newsgroups: comp.parallel
- Path: sparky!uunet!zaphod.mps.ohio-state.edu!howland.reston.ans.net!paladin.american.edu!gatech!hubcap!fpst
- From: dsmith@chaos.cs.brandeis.edu (Donald A. Smith)
- Subject: Performance of MP1 vs MP2
- Message-ID: <1993Jan5.124428.5602@hubcap.clemson.edu>
- Apparently-To: comp-parallel@uunet.uu.net
- Sender: news@news.cs.brandeis.edu (USENET News System)
- Organization: Brandeis University
- Date: Mon, 4 Jan 1993 23:29:08 GMT
- Approved: parallel@hubcap.clemson.edu
- Lines: 13
-
- Can anyone send me information about the relative performance of the
- MasPar MP2 as compared to the MP1?
-
- I have been using MPL on the MP1 and I like the language (more than,
- say, TMC's C* or starlisp). It is well documented and reliable, and
- it has a seamless interface between sequential and parallel control
- structures. Things work the way you expect them to. Some minuses:
- the lack of virtual processing and the need to execute MPL programs on
- the slow intermediate processor, the ACU, instead of the faster front
- end. Can anyone send me their observations about the MP1 or MP2?
-
- Don Smith (dsmith@chaos.cs.brandeis.edu)
-
-