If you read the POP, MVCLE moves an implementation determined number of bytes for each execution until the specified number of bytes have been moved. You are supposed to branch back to the instruction on CC3. This is in lieu of making the instruction interruptable like MVCL is. It also gives you the option of polling for events during a very long move before branch back to the MVCLE.
Regards, Bill <[EMAIL PROTECTED]> wrote in message news:<[EMAIL PROTECTED]>... > Why is it that when I try to use an example of MVCLE that I found it > only does 4096 bytes at a time. Compare that to the fact that the > MVCL moves far more than that before it stops. I read POP and it > seems to indicate that MVCLE will move up to whatever 31bits of data > represents(exobytes?) in 24bit or 31bit mode. I did get MVCLE to move > everything, but I had to do a BO *-4 to get it to branch back to the > MVCLE until everything had been moved. That seems inefficient, at > least conceptually speaking. No need to cover the millicode concept, > I am aware the MVCL, etc. are in millicode, so maybe it isn't as > efficient as I would hope it might be. > ---------------------------------------------------------------------- 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
