Mike Schwab writes:
Maybe the z13 will execute multiple bytes in parallel? One byte being
looked up per core. Then a cycle to check the condition codes and how
many to accept.
Per-core or SMT wouldn't be suitable (as other responses have covered)
but your wish for processing multiple bytes
On 3/13/2015 4:50 PM, Mike Schwab wrote:
Maybe the z13 will execute multiple bytes in parallel? One byte being
looked up per core. Then a cycle to check the condition codes and how
many to accept.
An instruction pipeline cannot span cores. In fact, when a z13 core is
in SMT-2 mode, there
to quickly get second and third DS qualifiers
On Fri, 13 Mar 2015 18:50:44 -0500, Mike Schwab wrote:
Maybe the z13 will execute multiple bytes in parallel? One byte being
looked up per core.
A core is a CPU. You are proposing running two tasks (or SRBs).
Then a cycle to check the condition
: Friday, March 13, 2015 1:28 PM
To: IBM-MAIN@LISTSERV.UA.EDU
Subject: Need assembler trick to quickly get second and third DS qualifiers
I have a dataset FIRST.SECOND.THIRD, and I want to get SECOND.THIRD.
Normally I would loop to one character at a time to get to the '.', but
I need
...@sce.com
-Original Message-
From: IBM Mainframe Discussion List [mailto:IBM-MAIN@LISTSERV.UA.EDU] On Behalf
Of Paul Gilmartin
Sent: Friday, March 13, 2015 11:41 AM
To: IBM-MAIN@LISTSERV.UA.EDU
Subject: Re: Need assembler trick to quickly get second and third DS qualifiers
On Fri, 13
-
From: IBM Mainframe Discussion List [mailto:IBM-MAIN@LISTSERV.UA.EDU] On
Behalf Of Paul Gilmartin
Sent: Friday, March 13, 2015 11:41 AM
To: IBM-MAIN@LISTSERV.UA.EDU
Subject: Re: Need assembler trick to quickly get second and third DS
qualifiers
On Fri, 13 Mar 2015 10:43:34 -0700, Charles Mills
Development
IBM Corporation
IBM Mainframe Discussion List IBM-MAIN@LISTSERV.UA.EDU wrote on
03/13/2015 10:28:18 AM:
From: Pinnacle pinnc...@rochester.rr.com
To: IBM-MAIN@LISTSERV.UA.EDU
Date: 03/13/2015 10:28 AM
Subject: Need assembler trick to quickly get second and third DS
qualifiers
Sent
: IBM Mainframe Discussion List [mailto:IBM-MAIN@LISTSERV.UA.EDU] On Behalf
Of Pinnacle
Sent: Friday, March 13, 2015 1:28 PM
To: IBM-MAIN@LISTSERV.UA.EDU
Subject: Need assembler trick to quickly get second and third DS qualifiers
I have a dataset FIRST.SECOND.THIRD, and I want to get SECOND.THIRD
-
From: IBM Mainframe Discussion List [mailto:IBM-MAIN@LISTSERV.UA.EDU] On Behalf
Of Pinnacle
Sent: Friday, March 13, 2015 10:28 AM
To: IBM-MAIN@LISTSERV.UA.EDU
Subject: Need assembler trick to quickly get second and third DS qualifiers
I have a dataset FIRST.SECOND.THIRD, and I want to get
Date: 03/13/2015 10:28 AM
Subject: Need assembler trick to quickly get second and third DS
qualifiers
Sent by: IBM Mainframe Discussion List IBM-MAIN@LISTSERV.UA.EDU
I have a dataset FIRST.SECOND.THIRD, and I want to get SECOND.THIRD.
Normally I would loop to one character at a time to get
On 03/13/2015 01:43 PM, Charles Mills wrote:
The classic approach is TRT, which is a little bit of a PITA (R2 anyone?) but
does the job. It is a single machine instruction but that does not mean it's
fast!
There is a new instruction (new relative to a lot of us LOL) search string
(as I
I sometimes did a TRT to scan the string for one, or more, characters.
Initialize GPR1 to point to the end of the string. But TRT is
sometimes slow. Looping is not necessarily bad. The following code
will likely run quite fast:
LA R3,STRING
LA R4,1
LA
I have a dataset FIRST.SECOND.THIRD, and I want to get SECOND.THIRD.
Normally I would loop to one character at a time to get to the '.', but
I need performance here. I sure some of you assembler gurus could give
me some inscrutable assembler to get there in like one or two
instructions.
On Fri, 13 Mar 2015 10:43:34 -0700, Charles Mills wrote:
Watch out for the no second qualifier special case. FOOBAR is a valid
dataset name.
Can it be catalogued? Is it copacetic to SMS? (I think SMPMCS is prevalent
on SMP/E installation tapes, and the OP didn't require that the data set was
In 55031e32.7030...@rochester.rr.com, on 03/13/2015
at 01:28 PM, Pinnacle pinnc...@rochester.rr.com said:
I have a dataset FIRST.SECOND.THIRD,
Do you also want to validate the input as well? What if an index level
is empty or longer than 8? What if there are more than 3 levels?
I need
In
cy1pr0101mb076377151f6a78639bf43e6cce...@cy1pr0101mb0763.prod.exchangelabs.com,
on 03/13/2015
at 06:51 PM, J O Skip Robinson jo.skip.robin...@sce.com said:
I imagine that TRT was invented back in the day because so many
routines needed to parse on delimiters.
It's kind of clunky if you're
List [mailto:IBM-MAIN@LISTSERV.UA.EDU] On Behalf
Of Tom Marchant
Sent: Friday, March 13, 2015 1:54 PM
To: IBM-MAIN@LISTSERV.UA.EDU
Subject: Re: Need assembler trick to quickly get second and third DS qualifiers
On Fri, 13 Mar 2015 21:19:03 +0200, Itschak Mugzach wrote:
The main difference between
On Fri, 13 Mar 2015 21:19:03 +0200, Itschak Mugzach wrote:
The main difference between srtr and trt is that trt looks for one or more
delimitets and srtr for a single on and requires less storage (the
translate table).
I suspect that SRST is also considerably faster. TRT is notoriously slow.
On Fri, 13 Mar 2015 18:50:44 -0500, Mike Schwab wrote:
Maybe the z13 will execute multiple bytes in parallel? One byte being
looked up per core.
A core is a CPU. You are proposing running two tasks (or SRBs).
Then a cycle to check the condition codes and how
many to accept.
And you want to
At 16:09 -0400 on 03/13/2015, Shmuel Metz (Seymour J.) wrote about
Re: Need assembler trick to quickly get second and third DS:
I imagine that TRT was invented back in the day because so many
routines needed to parse on delimiters.
It's kind of clunky if you're only searching for one
On Fri, 13 Mar 2015 15:12:50 -0700, Ed Jaffe edja...@phoenixsoftware.com
wrote:
Poor TRT has become a casualty of modern hardware economics. It's a
complex instruction, with no analog on other platforms, that is no
longer used often enough to rate prime-location silicon chip
real-estate. It was
Maybe the z13 will execute multiple bytes in parallel? One byte being
looked up per core. Then a cycle to check the condition codes and how
many to accept.
On Fri, Mar 13, 2015 at 5:12 PM, Ed Jaffe edja...@phoenixsoftware.com wrote:
On 3/13/2015 11:51 AM, J O Skip Robinson wrote:
SRST looks
On 3/13/2015 11:51 AM, J O Skip Robinson wrote:
SRST looks very cool. Thanks for the pointer! A simple loop searching for '.'
works but is not something to put on your resume. ;-) TRT is snazzier but
requires TLC for registers, especially R2. I imagine that TRT was invented back
in the day
23 matches
Mail list logo