Re: BAKR Instruction

2018-05-28 Thread Ed Jaffe
On 5/28/2018 2:57 PM, Peter Relson wrote: -- You might find that use of BAKR by the caller poses an unnecessary dependency between the caller and the callee. Consider the alternative of calling via BASR, and the callee deciding whether to save/restore regs via BAKR/PR or via STMG(+STAM)/LMG(+LAM)

Re: BAKR Instruction

2018-05-28 Thread Dan Greiner
Mr. Relson's warnings on the performance of BAKR/PR warrant some additional comment. 1. A well-tuned subroutine call can limit the number of registers that are saved/restored. BAKR/PR saves/restores all 16 general-purpose registers, and it always saves all 64-bits of the register, even if the

Re: BAKR Instruction

2018-05-28 Thread Peter Relson
Some things to think about: -- Recovery routines and retry points are tied to specific linkage stack levels in the general case. Use of BAKR as a linkage can complicate that. -- BAKR/PR is slower than using a typical savearea linkage. -- You might find that use of BAKR by the caller poses an unne

Re: BAKR Instruction

2018-05-28 Thread Dan Greiner
In 2012, I did a presentation at SHARE in Atlanta on the details of the dual-address-space (DAS) and linkage-stack (LS) architecture which includes BAKR and PR. Most likely, this contains far more detail than any sane person would want to know, but it's easier to digest than the description in