Absolutely true for repeated STCKEs. However,
"Two executions of STORE CLOCK or STORE
CLOCK EXTENDED, possibly on different CPUs in
the same configuration, always store different values
of the clock if the clock is running."
says that the 64-bit time returned by repeated STCKs are also guaranteed to be
unique.
Bob
Victor Gil wrote:
Bob,
From the POP quote you've posted earlie:
"the value in bit positions 64-103 of the clock (bit positions 72-111 of the
storage operand) is always nonzero"
This is because, a single "machine" [identified by TOD Programmable Register,
bits 112-127] may have multiple CPUs - so the bits 64-103 are to make sure
concurrent subtasks running on *different* CPUs within the same "machine"
won't see the same STCKE value.
-Victor-
On Thu, 26 Feb 2009 16:28:17 -0500, Bob Rutledge
<[email protected]> wrote:
Assuming that the TOD Programmable Register uniquely identifies a machine
in a
parallel sysplex and given that successive STCKs yield different values on a
single machine, why not STCKE to get the TOD Programmable Register and
STCK to
get a "reference number". Ten bytes. Fewer moving parts.
Bob
----------------------------------------------------------------------
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
