On Mon, 11 Apr 2016 09:16:30 -0700, Ed Jaffe wrote: >On 4/8/2016 12:50 PM, Jesse 1 Robinson wrote: >> The real question is how closely this program resembles a real life >> application program here. Doing only one I/O is pretty extreme, but the >> ratio of pure computation to I/O may be high enough to show improvement >> overall. I'm now waiting for availability of application programmers to >> pursue this further. > >In POK just now, Sophia Lopez claimed clients (on z13?) are seeing >15-25% improvement using ABO. Of course, full recompile should see >considerably more... > Does ABO have its best-case improvement on certain worst-case input, such as where it can reduce operator strength, move redundant code outside loops, or remove otiose statements? (What are best-case candidates?)
(It might be hardly productive to optimize code that should never have been written in the first place.) -- gil ---------------------------------------------------------------------- For IBM-MAIN subscribe / signoff / archive access instructions, send email to [email protected] with the message: INFO IBM-MAIN
