eugene@pioneer.arpa (Eugene Miya N.) (11/03/87)
In article <18966@amdcad.AMD.COM> tim@amdcad.UUCP (Tim Olson) writes: >In article <3285@ames.arpa> eugene@pioneer.UUCP (Eugene Miya N.) writes: >| In article <3806@sol.ARPA> crowl@cs.rochester.edu (Lawrence Crowl) writes: >| >Of course, 780's are becoming scarce. We may have to pick another machine just >| >to keep the base machine readily available. Suggestions? >| >| Yes, the Cray X-MP. >| Arguments removed (but included an analogy to "Atomic clocks"). >Another problem: it is not a very common computer. Nearly everyone who >is doing some serious benchmarking at least has access to a VAX. >If it weren't for the memory restrictions and porting problems, I'd vote >for the IBM PC with specified compilers -- common as dirt (also *runs* >as slow as dirt, but that's a different matter ;-) Minor correction, readers who have net access have access to a VAX. There are several major benchmarking efforts inside IBM based and other organizations (some in Europe as well) who don't use or have VAX access. I won't argue their significance. My analogy to atomic clocks is very important. The NBS researches and keeps accurate time for a variety of reasons. You can say you will standardize (democratize) on the VAX or the IBM PC, but this would be akin to taking the little gift MacClock I have sitting on my desk and designating it THE "second," an example of "Gold plating" metrics [John Simpson, "Foundations of Metrology," J. NBS Research]. "Official time" is not such a measure. If we treated the Meter and the (Micron) so casually, I seriously doubt we would have microelectronics. That would be the least of the world's problems. Sure, you should have your VAXen and PCs, but standards are not defined simply by quantity. I would argue that to improve future computer architectures, we will have to take a view of refining time similar to improving linear measurement. I won't argue anymore about this issue, because frankly, I'm cynical since most people don't really care. P.S. the MacClock is running 20 minutes fast after 3 months. From the Rock of Ages Home for Retired Hackers: --eugene miya, NASA Ames Research Center, eugene@ames-aurora.ARPA "You trust the `reply' command with all those different mailers out there?" "Send mail, avoid follow-ups. If enough, I'll summarize." {hplabs,hao,ihnp4,decwrl,allegra,tektronix}!ames!aurora!eugene
aglew@ccvaxa.UUCP (11/06/87)
..> VAx-standard MIPS, and the need for a new architecture ..> for relative performance measures, Eugene suggesting ..> the Cray XMP. Sorry, I don't have access to a Cray - at least not for the type of multiuser workloads I like to run, hoping that they are reasonable characterizations. Can I borrow one of yours, Eugene? Seriously, use whatever relative performance measure you want, as long as you (1) state what machine, configuration, etc. it is, and (2) print the absolute numbers in the appendix to your performance report. Andy "Krazy" Glew. Gould CSD-Urbana. USEnet: ihnp4!uiucdcs!ccvaxa!aglew 1101 E. University, Urbana, IL 61801 ARPAnet: aglew@gswd-vms.arpa I always felt that disclaimers were silly and affected, but there are people who let themselves be affected by silly things, so: my opinions are my own, and not the opinions of my employer, or any other organisation with which I am affiliated. I indicate my employer only so that other people may account for any possible bias I may have towards my employer's products or systems.