... I don't have measurements for the latter - and the former is in the public domain. ...
1. Everything after 16 was 'straight-lined', which is wrong since incremental MIPS are not linear. That used to be documented on the LSPR Site; I don't know if it is still. Plot the numbers; you'll see. 2. A new workload was added to the z/990 mix that was never calibrated on the z/900. So, how can you consider its measurements to 'speak for themselves'? 3. A workload was dropped from the z/990 mix. Same question. In what I laughably call my mind (and in the opinion of a few others) this is incomplete analysis. I do not trust any figure over 16 CP's. Given the above, how could anybody? (PS: I'm not giving away any IBM secrets. The above three statements are 'in the public domain'. You just have to read the documentation. I performed my analysis without access to any internal documentation, after I left IBM.) -teD In God we Trust! All others bring data! -- W. Edwards Deming ---------------------------------------------------------------------- For IBM-MAIN subscribe / signoff / archive access instructions, send email to [EMAIL PROTECTED] with the message: GET IBM-MAIN INFO Search the archives at http://bama.ua.edu/archives/ibm-main.html
