You can use z/OS page reference pattern services to optimize large table storage access (limited to 31-bit addressing). You can use PFD instruction to give the processor a "heads up" signal that you will be accessing a storage are in the near future and it should be prefer chef into the cache. There are numerous techniques to optimize table node access. Updated instruction address interlock facilities allow asynchronous table updates with fewer instructions.
Jeffrey Celander > On Oct 7, 2015, at 3:18 PM, [email protected] wrote: > > The recent discussions about table techniques brings to mind an issue that > this august group can illuminate. > > I remember many years ago writing a search routine on the 360 just as an > exercise in using BXH/BXLE. I had already used it on 7094 and wondered > what it bought on a machine with more than one accumulator. I also wrote > a binary search routine to the same end. > > My experience of the last three decades has shown me that the format of > tables and the method to search them can have an amazing effect on program > performance. In one case, VTAM was crashed by a routine that "hooked" it > but managed its storage badly. In another an exit to a JES writer ground > to a halt when the size of a table it was building exceeded a certain > limit. > > So my questions are: > > In light of the extreme effect caching can have on performance, does it > make any sense to have any table, except a quite small one, be searched > using a binary search? > > Is there a rule of thumb on when tables should be split into "search > arguments" and "data" to speed up the search? > > Are there any other experienced based rules for tables on modern > mainframes? > > Thanks in advance for your comments > > Richard > > Efforts and courage are not enough without purpose and direction. - John > F. Kennedy > Fasten your seat belts, it's going to be a bumpy ride. - Bette Davis (as > character Margo Channing) _All About Eve_1950 > Furious activity is no substitute for understanding. - H. H. Williams > Our greatest danger in life is in permitting the urgent things to crowd > out the important. - Charles E. Hummel > Quidquid latine dictum sit, altum videtur. > > ----------------------------------------- The information contained in this > communication (including any attachments hereto) is confidential and is > intended solely for the personal and confidential use of the individual or > entity to whom it is addressed. The information may also constitute a legally > privileged confidential communication. If the reader of this message is not > the intended recipient or an agent responsible for delivering it to the > intended recipient, you are hereby notified that you have received this > communication in error and that any review, dissemination, copying, or > unauthorized use of this information, or the taking of any action in reliance > on the contents of this information is strictly prohibited. If you have > received this communication in error, please notify us immediately by e-mail, > and delete the original message. Thank you
