On 2019-03-13 16:39, Charles Mills wrote:
Little need for dual path now, unless you are writing for a very specialized
market. All current releases of z/OS demand a machine of at least a recent
enough vintage as to support STCKF.
Agreed. I did mention that I was going back in time. The point
On Wed, 13 Mar 2019 13:34:03 -0700, Charles Mills wrote:
>No excuse for this one. STCKF is, if you will, a subset of STCK.
>
Conway's Law explains, though not excuses, many such misbehaviors.
>-Original Message-
>From: Farley, Peter x23353
>Sent: Wednesday, March 13, 2019 1:21 PM
>
>Ot
@LISTSERV.UA.EDU] On Behalf
Of Gord Tomlin
Sent: Tuesday, March 12, 2019 9:55 AM
To: IBM-MAIN@LISTSERV.UA.EDU
Subject: Re: STCKE faster than STCK! (was: instruction clock speed)
On 2019-03-12 12:32, Charles Mills wrote:
> Yes, STCK guarantees a unique value. If the clock has not ticked since the
>
-MAIN@LISTSERV.UA.EDU
Subject: Re: STCKE faster than STCK! (was: instruction clock speed)
Probably doesn't matter here, but note that on the zPDT, STCKF is actually
about exactly an order of magnitude SLOWER at some rev levels. I found this,
reported it, it's presumably fixed (but not on
faster than STCK! (was: instruction clock speed)
Probably doesn't matter here, but note that on the zPDT, STCKF is actually
about exactly an order of magnitude SLOWER at some rev levels. I found this,
reported it, it's presumably fixed (but not on the zPDT I have access to, which
I
Probably doesn't matter here, but note that on the zPDT, STCKF is actually
about exactly an order of magnitude SLOWER at some rev levels. I found this,
reported it, it's presumably fixed (but not on the zPDT I have access to, which
I don't own).
Doing 100,000,000 iterations of each:
stck
On Tue, 12 Mar 2019 09:32:18 -0700, Charles Mills wrote:
>Yes, STCK guarantees a unique value. If the clock has not ticked since the
>last STCK, the CPU has no choice but to spin until it does. STCKE has smaller
>"ticks" and so has less of (or no) need for a spin. STCKF is just like STCK
>excep
On 2019-03-12 12:32, Charles Mills wrote:
Yes, STCK guarantees a unique value. If the clock has not ticked since the last STCK, the CPU has no choice
but to spin until it does. STCKE has smaller "ticks" and so has less of (or no) need for a spin.
STCKF is just like STCK except that it does not
Yes, STCK guarantees a unique value. If the clock has not ticked since the last
STCK, the CPU has no choice but to spin until it does. STCKE has smaller
"ticks" and so has less of (or no) need for a spin. STCKF is just like STCK
except that it does not guarantee a unique value, and so there is n
