Well, SLR, SR and XR have less of a I-cache hit then the others. What about, e.g., SGR, SLGR, XFR?
-- Shmuel (Seymour J.) Metz http://mason.gmu.edu/~smetz3 ________________________________________ From: IBM Mainframe Discussion List [IBM-MAIN@LISTSERV.UA.EDU] on behalf of Attila Fogarasi [fogar...@gmail.com] Sent: Monday, August 7, 2023 8:19 PM To: IBM-MAIN@LISTSERV.UA.EDU Subject: Re: What's the fastest way to clear a register? Was: Trucks and Politics Starting with zEC12 the 4 common ways to clear a register are identical speed: LHI/LGHI, XR, SR, SLR. On earlier models it varied due to differences in pipeline implementation and going way back, to limitations in microcode. For current machines there is a lot of capability for implementing optimization context, so it isn't so much single instructions being optimized but the outcome of a sequence. Clearing a register is recognized as a trivial special case (IBM has the patent). On Tue, Aug 8, 2023 at 10:03 AM Tom Brennan <t...@tombrennansoftware.com> wrote: > So what's the fastest way to clear a register? > > Maybe that will get things back to mainframes, and I even know what a > mainframe is. > > On 8/7/2023 4:42 PM, Bill Johnson wrote: > > America should never allow trucks as large as we do. Should also not > permit doubles and even triples and all trucks should have a lower speed > limit. But we all know lives aren’t nearly as important as profits for > trucking companies. America also had an opportunity to limit the size of > regular vehicles and fossil fuels usage but failed miserably because > Americans are self centered, piggish, and environmental denialists. > > > > > > Sent from Yahoo Mail for iPhone > > > > > > On Monday, August 7, 2023, 7:32 PM, Bob Bridges <robhbrid...@gmail.com> > wrote: > > > > This is off-topic, and I'll happily take it up with both Bill and Shmuel > offline if requested. But I may as well point out that "fewer deaths" may > not be as simple as they're assuming. It seems likely to me as well that > if we had smaller trucks going slower, fewer people would die in accidents > caused by bigger trucks going faster. But how many people would die > because of smaller trucks going slower? You gotta compare deaths to > deaths, not simply deaths to nothing. > > > > Why would people die from smaller trucks going slower? Well, a good > deal less cargo would be transported as a result, and I surmise (but it's > only surmise) that there'd be a lot more pressure on drivers, as a result, > to produce more. Some of that pressure would translate to tired drivers. > And all of it would translate to more expensive transportation, meaning > that poorer people would have increased difficulty affording the goods that > are cheaper now. > > > > Don't assume I'm saying that it's better as we do things now. I'm not; > I'm just saying that "this cause of death would be reduced" is no help > unless you can estimate how many deaths would also increase. And if anyone > thinks there'd be NO deaths owing to more expensive goods, I'll just shut > up. > > > > --- > > Bob Bridges, robhbrid...@gmail.com, cell 336 382-7313 > > > > /* A good scare is worth more than good advice. -Horace (65 BC – 8 BC) > */ > > > > -----Original Message----- > > From: IBM Mainframe Discussion List <IBM-MAIN@LISTSERV.UA.EDU> On > Behalf Of Bill Johnson > > Sent: Monday, August 7, 2023 18:45 > > > > For Americans here who’ve never been to Europe, trucks in Europe are > much smaller than US trucks, are required to have governors to limit their > speed, and are restricted to the right lane. The result is far fewer > traffic deaths involving trucks. > > > > In addition, Europeans almost never drive pickups and their automobiles > are much smaller. > > > > Their rates of deaths and serious injury are far less than America. > > > > So for you pro life people, perhaps some road restrictions would keep > more people alive. > > > > ---------------------------------------------------------------------- > > For IBM-MAIN subscribe / signoff / archive access instructions, > > send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN > > > > > > > > > > ---------------------------------------------------------------------- > > For IBM-MAIN subscribe / signoff / archive access instructions, > > send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN > > > > > > ---------------------------------------------------------------------- > For IBM-MAIN subscribe / signoff / archive access instructions, > send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN > ---------------------------------------------------------------------- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN ---------------------------------------------------------------------- For IBM-MAIN subscribe / signoff / archive access instructions, send email to lists...@listserv.ua.edu with the message: INFO IBM-MAIN
