Bill Planer wrote: > 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.
The hardware/millicode could also decide to move more (much more) data if it knows that there are no outstanding interrupts pending, or based on load management considerations. In other words, the implementation determined number of bytes is allowed to vary dynamically. Whether it actually does on any given model is another matter. Tony H. ---------------------------------------------------------------------- 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
