To a first approximation, run the same job on both and compare. IBM has a synthetic benchmark, and you can use those numbers as long as you understand that your workload may not give the same ratios as IBM's.
-- Shmuel (Seymour J.) Metz http://mason.gmu.edu/~smetz3 ________________________________________ From: IBM Mainframe Discussion List <[email protected]> on behalf of Charles Mills <[email protected]> Sent: Friday, December 13, 2019 3:26 PM To: [email protected] Subject: How do I compare CPU times on two machines? I know this is a pretty basic question. I can research it but I am afraid that if I miss one detail I could be off by an order of magnitude. How do I compare CPU seconds on two different machines -- in this case a z196 model M49 and a z114 model M10? This is not like a huge purchase decision benchmark or anything like that. It's just a very simple Job X consumed m CPU seconds on the z196, and Job Y consumed n CPU seconds on the z114 -- how do I compare those two numbers? Thanks much, Charles ---------------------------------------------------------------------- For IBM-MAIN subscribe / signoff / archive access instructions, send email to [email protected] with the message: INFO IBM-MAIN ---------------------------------------------------------------------- For IBM-MAIN subscribe / signoff / archive access instructions, send email to [email protected] with the message: INFO IBM-MAIN
