Phil Smith wrote: 
>Mmm...I'm pretty sure a single instruction is still atomic. I'm sure Peter 
>Relson or one of the other IBMers will chime in, but it there has to be some 
>sort of interlock at some level. And I've debugged plenty of concurrency 
>problems, never seen a mixture from a single instruction!

>...phsiii

I have seen cases where NI and OI instructions were caught by a multi-CP issue. 
 The byte being ANDed or ORed by one CP was modified between the fetch of the 
old byte and the store for the result by another store from a different CP.  
There is no atomicity in a single instruction unless POPs says so, such as with 
CS or CDS.   


G. Tom Russell   
“Stay calm. Be brave. Wait for the signs” — Jasper FriendlyBear
“… and remember to leave good news alone.” — Gracie HeavyHand 

Reply via email to