home *** CD-ROM | disk | FTP | other *** search
- Path: sparky!uunet!dtix!darwin.sura.net!mips!mash
- From: mash@mips.com (John Mashey)
- Newsgroups: comp.sys.sgi
- Subject: Re: R4000 compiler directive, is there one ???
- Message-ID: <l90m36INNs5c@spim.mips.com>
- Date: 18 Aug 92 01:54:46 GMT
- References: <oisl0q0@zuni.esd.sgi.com> <1992Aug16.210505.18316@megatek.uucp> <olujgk4@zuni.esd.sgi.com>
- Organization: MIPS Computer Systems, Inc.
- Lines: 27
- NNTP-Posting-Host: winchester.mips.com
-
- In article <olujgk4@zuni.esd.sgi.com> olson@anchor.esd.sgi.com (Dave Olson) writes:
- >| It's my understanding that MIPS specifically did NOT want to use
- >| code optimized specifically for the R4000 in the Specmark suite.
- >| To wit: I believe the code wasn't even compiled -mips2 (which
- >| is clearly supported), much less with -r4000.
-
- Well, actually we used both the last time we did the benchmarks,
- and put out the results on the ARCsystems...
-
- There is an ongoing argument about flags within SPEC, which is
- what you may have been thinking of.
-
- Personally, I'd love to see people provide both numbers:
- a) With a minimal set of options that you'd likely use across
- almost everything by default.
- b) All-out tuning.
- But, for the time being, b) is what everybody is doing; maybe there will
- get to be a good set of rules for a), but so far, there aren't.
- In particular, for SGI's customer base, I don't see any great problem
- with b), as at least some people will commit *vile acts* if needed
- to make things go faster :-) This was less so with MIPS' customer base,
- but there were some there who would do anything, too...
- --
- -john mashey DISCLAIMER: <generic disclaimer, I speak for me only, etc>
- UUCP: mash@mips.com [soon to be mash@sgi.com, but not quite moved yet].
- DDD: 408-524-7015, or 524-8253
- USPS: (soon) Silicon Graphics, 2011 N. Shoreline Blvd, Mountain View, CA 94043
-