I asked because the pretty slide show linked to by the original post I replied to used that number (1500) on the 13th and last slide with no indication of scale factor or context.
After 48 yrs in IT I have an appreciation for the issues raised by the replies, both explicit and implicit. I was wondering from the practical point of view. Where is the cross-over point where one considers z10 vs squatty box? on power? on space? on software licences? admin bodies? is the issue to complicated without doing a full tca/tco? This was on my mind because I have the misfortune to have inherited support of a mainframe application connected to a squatty box using custom code and a token ring conenction to the mainframe. every time it burps i get indigestion. replacing it means using smtp to replace telephony -- swapping one poisonous snake for another breed. As an aside, what is a good abbreviation for mainframe than m_f? I would like to reserve that for M$, Office and InfoPath at the moment. IBM Mainframe Discussion List <[email protected]> wrote on 10/20/2009 02:54:30 PM: > > -----Original Message----- > > [mailto:[email protected]] On Behalf Of Hal Merritt > > Interesting. I'd think the number could be less than one. > > [mailto:[email protected]] On Behalf Of Chase, John > > > -----Original Message----- > > > From: IBM Mainframe Discussion List On Behalf Of Kirk Talman > > > How many Mainframe engines = 1500 x86 boxes? > > "It depends". Could be as few as one. > > In this case, I would bet it depends on what those x86 servers are > doing. If they are a Beowulf supercomputer cluster, then the z10 is > NOT going to beat it. But if they are Web servers? Or even > application servers? > > Speaking of such. The z10 is said, by IBM, to be the "fastest" > (clock time) CISC processor. So, does that mean that a single IFL > processor could outperform any single x86 (Xeon?) single threaded > processor around for something which is CPU intensive, such as > numeric computation? To be "fair", let us assume that this > computation is being done in Java by using the identical .class > file. I know that isn't "fair" since the JVMs are not identical. But > it is about as fair as I can think of. Or perhaps the same C code > compiled and run on Linux using the same version of GCC. > John McKown ----------------------------------------- The information contained in this communication (including any attachments hereto) is confidential and is intended solely for the personal and confidential use of the individual or entity to whom it is addressed. If the reader of this message is not the intended recipient or an agent responsible for delivering it to the intended recipient, you are hereby notified that you have received this communication in error and that any review, dissemination, copying, or unauthorized use of this information, or the taking of any action in reliance on the contents of this information is strictly prohibited. If you have received this communication in error, please notify us immediately by e-mail, and delete the original message. Thank you ---------------------------------------------------------------------- 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
