================================================================== -----Original Message----- From: "Binyamin Dissen" <[EMAIL PROTECTED]> Sent: 6/29/2006 1:40 PM To: "[email protected]" <[email protected]> Subject: Re: Using different storage key's
On Thu, 29 Jun 2006 14:24:17 -0500 Doug Henry <[EMAIL PROTECTED]> wrote: /snip/ :>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]> ================================================================== It has to do with addressability. MVCP, MVCS require virtual storage references to different spaces. MVCSK, MVCDK can also refer to different spaces using access registers. These instructions *could* be implemented in silicon instead of millicode, but millicode is far easier and cheaper. Millicode must set addressability to the "source domain space", fetch the domain data, then set addressability to the "target domain space", store the data. /J ---------------------------------------------------------------------- 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
