On 5/4/2017 9:01 PM, Steve Beaver wrote:
That would be a great project for Connor if IBM would let him tackle it
Steve
If they haven't RA'd him yet (oops, did I just say that out loud?).
Seems to me they're tackling this Fortran thing incorrectly. You can
make all the source changes you wa
Yeah, Intel has their version of Parallel Fortran for they're massively
Parallel processors.
https://goparallel.sourceforge.net/use-fortran-visual-studio/
Now whether it's gonna assimilate old Fortran is a formidable undertaking.
Time, cfmpub...@ns.sympatico.ca writes:
Knowing the
[Default] On 4 May 2017 15:53:17 -0700, in bit.listserv.ibm-main
ste...@copper.net (Steve Thompson) wrote:
>On 05/04/2017 06:08 PM, Clark Morris wrote:
>
>> Since this is old Fortran, I suspect that the given simulation can
>> only use one core. It also may be limited in the memory it can use or
runs competition to help make old Fortran code faster
Do I detect shades of Automatic Binary Optimizer for FORTRAN? Would developing
that app be worth $50K? Maybe a new project for Connor...
.
.
J.O.Skip Robinson
Southern California Edison Company
Electric Dragon Team Paddler
SHARE MVS Program Co
⇐=== NEW
robin...@sce.com
-Original Message-
From: IBM Mainframe Discussion List [mailto:IBM-MAIN@LISTSERV.UA.EDU] On Behalf
Of Steve Thompson
Sent: Thursday, May 04, 2017 3:54 PM
To: IBM-MAIN@LISTSERV.UA.EDU
Subject: (External):Re: Nasa runs competition to help make old Fortran code
On 05/04/2017 06:08 PM, Clark Morris wrote:
Since this is old Fortran, I suspect that the given simulation can
only use one core. It also may be limited in the memory it can use or
does use. Having a good optimizing compiler would help and one may or
may not be available for the box used. The
Amdahl had a Vector Fortran that really added some giddyup if you had a
Vector processor. Don't know if would scale to multinode processors.
In a message dated 5/4/2017 5:08:49 P.M. Central Daylight Time,
cfmpub...@ns.sympatico.ca writes:
Since this is old Fortran, I suspect that the give
[Default] On 4 May 2017 11:18:43 -0700, in bit.listserv.ibm-main
mp...@suse.com (Mark Post) wrote:
On 5/4/2017 at 09:56 AM, Phil Smith wrote:
>
>> http://www.bbc.com/news/technology-39803425
>>
>> So my question on this is, "If this old code ran anywhere near to acceptably
>> when it was
>>> On 5/4/2017 at 09:56 AM, Phil Smith wrote:
> http://www.bbc.com/news/technology-39803425
>
> So my question on this is, "If this old code ran anywhere near to acceptably
> when it was written, how can it possibly not be fast enough on modern
> hardware?!"
My guess would be that over time
200) (005OP6.3.10)
>> Information and Technology, IT Operations and Services
>>
>> -Original Message-
>> From: IBM Mainframe Discussion List [mailto:IBM-MAIN@LISTSERV.UA.EDU] On
>> Behalf Of Steve Beaver
>> Sent: Thursday, May 04, 2017 10:19 AM
>> To
mpfami
>
>
> -Original Message-
> From: IBM Mainframe Discussion List [mailto:IBM-MAIN@LISTSERV.UA.EDU] On
> Behalf Of IronSphere by SecuriTeam Software
> Sent: Thursday, May 4, 2017 9:28 AM
> To: IBM-MAIN@LISTSERV.UA.EDU
> Subject: Re: Nasa runs competition to he
y, IT Operations and Services
-Original Message-
From: IBM Mainframe Discussion List [mailto:IBM-MAIN@LISTSERV.UA.EDU] On Behalf
Of Steve Beaver
Sent: Thursday, May 04, 2017 10:19 AM
To: IBM-MAIN@LISTSERV.UA.EDU
Subject: [EXTERNAL] FW: Nasa runs competition to help make old Fortran code
f
On 5/4/2017 9:55 AM, Phil Smith wrote:
(Note to the Brits: That's "NASA", not "Nasa"-yeah, yeah, house style. But
stupid.)
http://www.bbc.com/news/technology-39803425
So my question on this is, "If this old code ran anywhere near to acceptably when it
was written, how can it possibly not be f
m Software
Sent: Thursday, May 4, 2017 9:28 AM
To: IBM-MAIN@LISTSERV.UA.EDU
Subject: Re: Nasa runs competition to help make old Fortran code faster
Old compilers that uses many branchs and short words?
Itschak
בתאריך 4 במאי 2017 16:57, "Phil Smith" כתב:
> (Note to the Brits: That
Old compilers that uses many branchs and short words?
Itschak
בתאריך 4 במאי 2017 16:57, "Phil Smith" כתב:
> (Note to the Brits: That's "NASA", not "Nasa"-yeah, yeah, house style. But
> stupid.)
>
> http://www.bbc.com/news/technology-39803425
>
> So my question on this is, "If this old code ran
(Note to the Brits: That's "NASA", not "Nasa"-yeah, yeah, house style. But
stupid.)
http://www.bbc.com/news/technology-39803425
So my question on this is, "If this old code ran anywhere near to acceptably
when it was written, how can it possibly not be fast enough on modern
hardware?!"
--
16 matches
Mail list logo
