yes, it was built for the java JVMs that use blocking techniques on non-z platforms but there is no reason we can't use it
Best Regards, Larry Larry Lawler C.T.O. [email protected] Unicom Systems Intl, Inc. 15535 San Fernando Mission Blvd. Suite 310, Unicom Plaza Mission Hills, CA 91345 Office: (949)-873-2225 VoIP x3883 **************************************************************************** **************************************************************** This message (including any attachments) contains confidential information that is PRIVILEGED, CONFIDENTIAL and/or ATTORNEY WORK PRODUCT and is intended only for the individual(s) named herein. If you are not the intended recipient, you are hereby notified that any dissemination, distribution or copying of this email is strictly prohibited. If you have received this message in error, please notify the UNICOM Systems, Inc. Postmaster ([email protected]) of the error immediately, do not read or use the email and any attachments in any manner, destroy all copies, and delete it from your system if the communication was sent via email. UNICOM Systems, Inc. (818) 838-0606 Fax: (818) 838-0776 **************************************************************************** ***************************************************************** -----Original Message----- From: IBM Mainframe Assembler List [mailto:[email protected]] On Behalf Of Chuck Arney Sent: Tuesday, September 18, 2012 8:02 PM To: [email protected] Subject: Re: Model 2827 New Instructions It seems to be an extended PLO instruction. Chuck Arney Arney Computer Systems -----Original Message----- From: IBM Mainframe Assembler List [mailto:[email protected]] On Behalf Of McKown, John Sent: Tuesday, September 18, 2012 1:21 PM To: [email protected] Subject: Re: Model 2827 New Instructions I just read up on the Transaction Execution. I now need two things: 1. Aspirin; 2. a nap. I get the general concept, but the restrictions are immense. I guess it is good for a *very* short routine which does not update very much storage. The conditions under which it can abort are a multitude. I wonder exactly what it was that made IBM decide to implement it, as opposed to doing a CPU "spin loop". I guess it is the only way to guarantee that another CPU simply cannot observe an "in flight" set of updates by *any* other code on *any* other CPU.
