gamiddleton@watmath.waterloo.edu (Guy Middleton) (01/18/89)
I'm sure this has been asked before, but I can't find where. I would like to know all the different names Tahoe systems are sold under (manufacturer and model name), and how each of these differs (if at all) from the CCI system. Thanks. -Guy Middleton, University of Waterloo gamiddleton@watmath.waterloo.edu
dick@hcx1.SSD.HARRIS.COM (01/24/89)
The ones I know of are: CCI Power 6/32 Unisys 7000 series ICL CLAN 6 and 7 ICL DRS500 These are manufactured by CCI and shipped with CCI's standard O.S. Harris HCX 2000 series (formerly HCX-5, HCX-9) Harris NH 7000 These are manufactured by Harris in Fort Lauderdale, Fl. and run Harris's CX/UX (System V / BSD dual universe). Benchmarks have measured CX/UX as having 30 to 50% better system throughput than CCI's System V. The 2000 series combines the CCI CPU board set with a VME bus and new controllers which make a much faster I/O subsystem. The NH7000 is a compatible CPU designed with ECL logic which increases the CPU power to 18 mips. Harris also supports a compatible Real-Time Unix (CX/RT) and a B1 secure Unix (CX/SX). Hope this doesn't sound too much like an advertisement. ------------------------------------------------------------------------------- |Dick Reynolds UUCP: dick@ssd.harris.com | |Harris Computer Systems {uunet|mit-eddie|cbosgd}!hcx1!dick | |2101 W. Cypress Creek Rd. | |Fort Lauderdale, Fl, 33309 Phone: +1 305 973 5330 | -------------------------------------------------------------------------------
mash@mips.COM (John Mashey) (01/26/89)
In article <127500004@hcx1> dick@hcx1.SSD.HARRIS.COM writes: > These are manufactured by CCI and shipped with CCI's standard O.S. > >Harris HCX 2000 series (formerly HCX-5, HCX-9) >Harris NH 7000 > These are manufactured by Harris in Fort Lauderdale, Fl. and run >Harris's CX/UX (System V / BSD dual universe). Benchmarks have >measured CX/UX as having 30 to 50% better system throughput than CCI's >System V. The 2000 series combines the CCI CPU board set with a >VME bus and new controllers which make a much faster I/O subsystem. >The NH7000 is a compatible CPU designed with ECL logic which increases >the CPU power to 18 mips. > > Harris also supports a compatible Real-Time Unix (CX/RT) and a B1 >secure Unix (CX/SX). > >Hope this doesn't sound too much like an advertisement. Any chance you could post some benchmark numbers for these? -- -john mashey DISCLAIMER: <generic disclaimer, I speak for me only, etc> UUCP: {ames,decwrl,prls,pyramid}!mips!mash OR mash@mips.com DDD: 408-991-0253 or 408-720-1700, x253 USPS: MIPS Computer Systems, 930 E. Arques, Sunnyvale, CA 94086
dick@hcx1.SSD.HARRIS.COM (01/28/89)
The numbers I am quoting are for AIM and Neal Nelson benchmarks which
are the property of AIM Technologies and Neal Nelson Associates
respectively. These results are available from AIM and NN. We
have also seen good results from internal benchmarks but I don't
wish to be accused of doctoring benchmarks to show us in the best
light.
In a nutshell, the improvements are obtained from:
1) Faster VME I/O bus with intelligent disk controller (with scatter/
gather).
2) A super optimizing compiler based on our proprietary "CCG"
technology.
3) Kernel rewrite which:
- replaced the scheduler with a lower overhead scheduler designed
to improve interactive response
- replaced the VM subsystem with one similar to AT&T System V
- improved numerous system routines to speed up all critical system
calls. csg@pyramid.pyramid.com (Carl S. Gutekunst) (01/31/89)
In article <127500005@hcx1> dick@hcx1.SSD.HARRIS.COM writes: > The numbers I am quoting are for AIM and Neal Nelson benchmarks which >are the property of AIM Technologies and Neal Nelson Associates >respectively. These results are available from AIM and NN. Please note that the Neal Nelson benchmark is meaningless when comparing machines with different architectures, or when comparing different com- pilers within the same architecture. It is weighted against machines using optimizing compilers (including strength reduction, loop unrolling, and common subexpression elimination), register allocators, branch pre- diction, and many other modern compiler and architectural enhancements. AIM, on the other hand, has proved itself to be quite meaningful, as syn- thetic benchmarks go. Anyone who is at all serious about benchmarking should get a copy of John Mashey's "MIPS Performance Brief," and the MIPS benchmark suite. (Last I knew, MIPS was giving the suite away for $200, on 9-track mag tape.) I'd like to see every systems vendor agree to run this under John's super- vision, and publish the results. Would settle a lot of bar bets. :-) Of course, I suspect John has more important things to do with his time. :-) <csg>