[Info-vax] Question about Alphaservers ES40 performances

[Keith Cayemberg]

On Tuesday, April 3, 2012 11:03:10 AM UTC+2, Mspec wrote:

> Do you know what the performances of AlphaServers ES40 6/500, 6/667 and 6/833 in the VUPs measurements, both Int and Float? 
> 
> Please, help me and clarify these numbers for me!


There have been many attempts to compare performance between systems with different processors, cache hierarchies, bus architectures, I/O subsystems, etc. Deciding on their relevance to your situation has always been the difficult task of each one of us as our own "accidental performance analyst".

I can only provide you with several historic sources pulled out of the depths of deprecated cyberspace.

Please take note that the URLs are long and are likely to wrap to the next line.

http://web.archive.org/web/20041209055735/http://www.decsy.ru/products/alpha/compare.htm

http://web.archive.org/web/20060306102157/http://sites.inka.de/pcde/dbp/

http://web.archive.org/web/20081011161713/http://swox.com/gmp/gmpbench.html

http://web.archive.org/web/20041025111103/http://www.openvms.nl/besloten/ov1002.htm

http://web.archive.org/web/20080830020742/http://www.hardy.demon.co.uk/paul/programs/vms_cpus.html

http://web.archive.org/web/20090205143143/http://fmslib.com/mkt/platforms.html

http://web.archive.org/web/19991128065854/http://anacin.nsc.vcu.edu/~jim/mvax/mvax_faq.html

http://web.archive.org/web/19990922021732/http://anacin.nsc.vcu.edu/~jim/mvax/vax-perf.html

http://www.algonet.se/~tucker/VaxCPUtable.txt

http://web.archive.org/web/20050324201324/http://www.xanthosmicrosystems.com/~joachim/vaxmips.html

http://web.archive.org/web/20060222035800/http://www.pyramiddec.com/vup.htm

http://web.archive.org/web/20031021032539/http://bridge.anglia.ac.uk/~systimk/History/Vaxes.txt

http://web.archive.org/web/20050507190848/http://www.vajhoej.dk/arne/vms/vms_hw.htmlx

http://h18002.www1.hp.com/alphaserver/performance/perf_tps.html

http://h18002.www1.hp.com/alphaserver/a-chart2.html#es40

http://h18002.www1.hp.com/cpq-alphaserver/performance/perf_by_perf_dec.html

http://www.kunhardt-computer.de/kunden/kch/achart.htm

http://www.kunhardt-computer.de/kunden/kch/dchart.htm

http://www.kunhardt-computer.de/kunden/kch/vaxchart.htm

http://web.archive.org/web/20041021041005/http://www.c3.lanl.gov/par_arch/pubs/LAUR-02-4850.pdf

http://www.cs.virginia.edu/stream/


As often proselytized over the years, the best benchmark is the one you build with your own real life productive workload.

Cheers!


Keith Cayemberg