> -----Original Message----- > From: IBM Mainframe Discussion List [mailto:[email protected]] On > Behalf Of Edward Jaffe > Sent: Saturday, August 08, 2009 1:03 PM > To: [email protected] > Subject: Re: z10 and overlapping/destructive moves > > Farley, Peter x23353 wrote: > > As you can see, there isn't much here to explain a spike except the > > MVI/MVC combination. The EVALUATE/WHEN that follows is comparing a > > 3-byte field to two literals (a less-than-this or greater-than-that > > construct). > > An MVC of 120 is not free. It will take much longer than CLC for three > bytes and other similar "trivial" instructions that operate on small > operands. If the routine is called a lot, it *should* spike on the report. > > The question is whether the MVI/MVC method of clearing a 120 byte field > can be improved upon. I think that's unlikely. As others have pointed > out, the smartest compilers in the world use this technique and my > understanding is that the hardware is optimized for it. > > You can speed things up if you change the algorithm not to require > blanking of the field at all. The fastest instructions are the ones you > don't execute.
Agreed. I need to step back and look at the larger algorithm picture instead of focusing on the minutiae of statement spikes. Thanks for the advice and insight. Peter This message and any attachments are intended only for the use of the addressee and may contain information that is privileged and confidential. If the reader of the message is not the intended recipient or an authorized representative of the intended recipient, you are hereby notified that any dissemination of this communication is strictly prohibited. If you have received this communication in error, please notify us immediately by e-mail and delete the message and any attachments from your system. ---------------------------------------------------------------------- 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
