On Thu, 29 Jun 2006 14:24:17 -0500 Doug Henry <[EMAIL PROTECTED]> wrote:
:>On Thu, 29 Jun 2006 21:21:39 +0300, Binyamin Dissen :><[EMAIL PROTECTED]> wrote: :>>:>On Thu, 29 Jun 2006 09:32:50 -0400, Craddock, Chris :><[EMAIL PROTECTED]> :>>:>wrote: :>>:>>On z machines there is only one move instruction in hardware (MVC) and :>>:>>all of the other variants are implemented in milicode. So for a given :>>:>>amount of data and a particular set of environmental state (alignment, :>>:>>key etc) they are all going to take just as long as they need to and it :>>:>>will always be longer than MVC. :>>:>Really? Is that documented anywhere public? I'm a little surprised to :>>:>hear that MVCL, MVN, MVN, MVO and others are implemented in millicode. :>See Bob Rogers Share Session 2836 from Seattle titled "Even More of what :>you do when you're a CPU" :>It says in part "MVCL (for other than page size moves), MVCLE, MVCP,MVCS, :>MVCSK and MVCDK are microcoded subroutines that use MVC." :>"Started with CMOS G4,the processors used a vertical code which is very :>similar to the target architecture (S/390, zArchitecture)... Because of :>these similarities to normal code, this type of code is called Millicode." I wonder why MVCP or MVCS should require millicode. Is it because the length and key are in registers? -- Binyamin Dissen <[EMAIL PROTECTED]> http://www.dissensoftware.com Director, Dissen Software, Bar & Grill - Israel Should you use the mailblocks package and expect a response from me, you should preauthorize the dissensoftware.com domain. I very rarely bother responding to challenge/response systems, especially those from irresponsible companies. ---------------------------------------------------------------------- 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
