Sheesh. The z/OS 2.4 page still links to the -11 version of PoOp (I don't understand what "PoPs" is supposed be abbreviating).
I agree that a Redbook of commentary from the architects would be a best-seller. Probably everything they know is a trade secret though. btw, I think I found a bug, which likely has been there a long time. On page 7-8, Programming Notes #2, there's a list of instructions that can modify the high-half of registers (the ones that aren't tagged with G or GF). LOAD LOGICAL IMMEDIATE is qualified (LLIHF, LLIHH, LLIHL only). But *all* LLI* instructions always modify all 64 bits (i.e. the ones not mentioned always clear the high half to 0). That's a surprise to some people, but it shouldn't be to the PoOp authors. Anyway, did I miss some subtlety there? sas
