The following message is a courtesy copy of an article that has been posted to bit.listserv.ibm-main as well.
[email protected] (Don Williams) writes: > From a practical view point, I disagree. I believe that a usage note in the > POP > can imply a programming interface is likely to exist. Here’s why. re: http://www.garlic.com/~lynn/2009d.html#24 the compare&swap notes were somewhat that way. Charlie had invented compare&swap doing fine grain multiprocessing locking work on (virtual machine) cp67 work at the science center (compare&swap was chosen because CAS are charlie's initials) http://www.garlic.com/~lynn/subtopic.html#545tech trying to get compare&swp into 370 architecture had lot of push back from the architecture group ... in part because the favorite son operating system in POK said that test&set was more than adequate for multiprocessor support. the architecture group commented that in order to get compare&swap included in 370 architecture ... a non-multiprocessor specific use was required. Thus was born the compare&swap programming notes for multithreaded/multiprogramming use (still to be found) ... i.e. multithreaded applications ... running enabled for interrupts ... and requiring atomic operation (previously requiring kernel calls to approximate atomic operation). misc. past posts mentioning multiprocessing and/or compare&swap instruction http://www.garlic.com/~lynn/subtopic.html#smp for other topic drift ... another mnemonic from invention at the science center is GML (by "G", "M", and "L") which as since morphed into stuff like SGML, HTML, XML, etc http://www.garlic.com/~lynn/submain.html#sgml -- 40+yrs virtualization experience (since Jan68), online at home since Mar70 ---------------------------------------------------------------------- For IBM-MAIN subscribe / signoff / archive access instructions, send email to [email protected] with the message: GET IBM-MAIN INFO Search the archives at http://bama.ua.edu/archives/ibm-main.html
