date:20070716

Re: Links to decent 'why the mainframe thrives' article

2007-07-16 Thread Timothy Sipples

Dean Kent wrote:
I find it hard to believe
that IBM would spend the money for mainframe
processors to keep pace when there isn't really
much of an incentive to do so.

Why is it hard to believe that IBM would invest huge sums in a fast growing
market with significant demand elasticity?  That's logical and rational
business behavior.

Ted MacNEIL wrote:
Proof, please!

That's a strange request. You'd think the person making the extraordinary
claim that emulation offers higher performance than non-emulation would be
the one challenged to prove such a claim. But OK

Phil Payne did an analysis of MIPS performance via emulation, and it's
quite easy to find his comments online.  Whether you agree or disagree with
him, he provides some numbers at which to throw darts.  In his analysis he
asserts that 4 Itanium processors, combined, just might manage 170 zMIPS,
to be generous.  For comparison, that figure is lower than the smallest
original (non-turbo) z900 processor (2064 Model 101) that shipped nearly 7
years ago.

Tom Marchant writes:
I was disputing the statement that an Itanium
can emulate instructions faster than z silicon.

Listen to Tom Marchant, for he is smart here.

Tom Marchant also writes:
Actually, IBM is an acknowledged leader in processor design and
microelectronics technology.

Smart again. :-)

- - - - -
Timothy Sipples
IBM Consulting Enterprise Software Architect
Specializing in Software Architectures Related to System z
Based in Tokyo, Serving IBM Japan and IBM Asia-Pacific
E-Mail: [EMAIL PROTECTED]
--
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

Re: Links to decent 'why the mainframe thrives' article

2007-07-16 Thread Ted MacNEIL

Phil Payne did an analysis of MIPS performance via emulation, and it's quite 
easy to find his comments online.

Phil also states that his zMIPS are fiction and have not been subjected to any 
rigour!

-
Too busy driving to stop for gas!

--
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

Re: IBM Doco....

2007-07-16 Thread Van Dalsen, Herbie

Mark Zelden wrote:

 How much of the internals detail are you looking for in a command 
 description?

Thanks for that everyone, Mark, I will have a look on your site... I
have just been looking in the wrong places, the info is out there...

Regards

Herbie

*
This email and any attachments are confidential and intended for the sole use 
of the intended recipient(s).If you receive this email in error please notify 
[EMAIL PROTECTED] and delete it from your system. Any unauthorized 
dissemination, retransmission, or copying of this email and any attachments is 
prohibited. Euroconex does not accept any responsibility for any breach of 
confidence, which may arise from the use of email. Please note that any views 
or opinions presented in this email are solely those of the author and do not 
necessarily represent those of the Company. This message has been scanned for 
known computer viruses. 
*

--
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

Re: IBM obsoleting mainframe hardware

2007-07-16 Thread Van Dalsen, Herbie

David wrote:
 Keeping the old iron going on -say- a 10 year commitment while
rolling
 out new iron every two years means that you're supporting six
 generations of mainframes, four or five of which use parts no longer
 manufactured.  So you warehouse parts, and you don't just store them
in
 a Public Storage warehouse, 'cause you're IBM -- you have to have
 distributed depots, trained FE personnel, test gear, documentation,
 guaranteed response time.  That costs money (and is one of the big
 reasons that mainframes are uncompetitive in many situations).

David,

I fully agree with this, it would be impossible to keep it up if they
had to keep HW for 10 generations knocking around in a warehouse
somewhere. IMHO the time has probably come for IBM to beat the rest of
the pack with a new marketing strategy. 

Background...
This coming week, we will be donating 25 Dell PC's to a school( 2nd
generation), yes, 3 years ago we gave this school 25 PC's, and now
because our maintenance/lease has run out on the next generation, we
have convinced them to take another 25 off us, what a cost to the
company, which is part of a large US bank that has the policy that once
the maintenance/lease contract is over the PC's needs to be replaced. 

If IBM starts to sell the service instead of the Hardware, the whole
thing will change, and they will not have to keep unnecessary HW in
warehouses all over the world. A company contacts IBM, buys 230 MIPS for
10 years with the relevant software that goes with it. This will include
HW that is current and maintainable, but... the customers must allow for
at least 2 major maintenance slots during the 10 years during which
3390-3392, ESS810-ESS???, and Z890-Z9 upgrades can take place...

Regards

Herbie
*
This email and any attachments are confidential and intended for the sole use 
of the intended recipient(s).If you receive this email in error please notify 
[EMAIL PROTECTED] and delete it from your system. Any unauthorized 
dissemination, retransmission, or copying of this email and any attachments is 
prohibited. Euroconex does not accept any responsibility for any breach of 
confidence, which may arise from the use of email. Please note that any views 
or opinions presented in this email are solely those of the author and do not 
necessarily represent those of the Company. This message has been scanned for 
known computer viruses. 
*

--
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

PSI MIPS (was: Links to decent 'why the mainframe thrives' article)

2007-07-16 Thread Bruce Hewson

Interesting,

Them guys gave a presentation over here some time ago.
The numbers they quoted for a HP Superdome was 80 MIPS per engine, with 
up to 64 engines.

Are they now stating that using Itaniums can generate 350 MIPS per engine, 
that means that upgrading from the original HP Superdome, to an Itanium 
based system, is a 400% improvement. 

(gossip about unqualifiable numbers :-D )

On Sun, 15 Jul 2007 17:13:42 -0500, Tom Marchant m42tom-
[EMAIL PROTECTED] wrote:

On Sun, 15 Jul 2007 12:44:34 -0700, Dean Kent wrote:

- Original Message -
From: Timothy Sipples [EMAIL PROTECTED]

 Dean Kent:
 Itanium likely could emulate zArch instructions faster than
 native zSeries systems can execute them

 No.


If you have any published numbers to verify that, it would be very nice to
see them.

PSI claims that they can provide up to 350 MIPS using Itanium processors.
They do not say how many processors they use to attain that  A z9 UP is
closer to 600 MIPS.

--
Tom Marchant


Regards
Bruce Hewson

--
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

Re: Track size and maximum single volume data set size

2007-07-16 Thread R.S.

I don't think so. Nevermind, let's drop out interpretations.
IMHO 3380 is still in use, in most cases generally because of staff lazyness/lack of comptence.
Yes, I mean it.

AFAIR 3390 was introduced in 1990. 17 years ago. Enough time to perform
migration.
All the shops I know use 3380 without any real reason. For example they use
Adabas, however other shops, running the same application migrated to 3390
years ago. Another examples: JES2 SPOOL, RACF db. No comments.
Of course my experience is limited, that's why I didn't say in every case;
YMMV

Regards
--
Radoslaw Skorupka
Lodz, Poland

Joel C. Ewing wrote:

I think you misinterpreted Tom's remarks.

He wasn't disputing that 3380 emulation was in use, only the logical
inconsistency of your use of the existence of 3380 emulation as an
argument supporting the ability of installations to easily handle some
new DASD architecture.

3380 emulation is most likely in use precisely because transitioning to
the 3390 DASD architecture was not trivial and involved costs the
installation wished to avoid. Add a new DASD architecture to the
picture, and those running 3380 emulation today will probably still be
wanting to run 3380 emulation on the new DASD.

If you are emulating old DASD architecture on new architecture hardware,
you haven't yet migrated applications to the new architecture - and you
run the risk that at some point the latest hardware or Operating System
may cease to support the older architecture. That installations choose
to run these risks is an indication of the difficulty of utilizing new
DASD architecture, not an indication of the ease of supporting multiple
DASD architectures.

R.S. wrote:

Tom Marchant wrote:
[...]

I disagree. Completely. Mainframe users had to do with different
track sizes, some dataceneters still have 3380 emulation.

It sounds like you are disagreeing with yourself here. Why do you
think some data centers still use 3380 emulation?

I don't see logic conflict here. As I said, many people worked in
datacenters where various geometries were in use. I also wrote there
are shops still using 3380 geometry. Why do I think so ? Because I was
in one of them about week ago. It's still on the place. I know few
other shops using 3380. I don't *think* they do it, I *know* it.

--
BRE Bank SA
ul. Senatorska 18
00-950 Warszawa
www.brebank.pl

Sd Rejonowy dla m. st. Warszawy
XII Wydzia Gospodarczy Krajowego Rejestru Sdowego,
nr rejestru przedsibiorców KRS 025237

NIP: 526-021-50-88
Wedug stanu na dzie 01.01.2007 r. kapita zakadowy BRE Banku SA (w caoci
opacony) wynosi 118.064.140 z. W zwizku z realizacj warunkowego
podwyszenia kapitau zakadowego, na podstawie uchwa XVI WZ z dnia 21.05.2003
r., kapita zakadowy BRE Banku SA moe ulec podwyszeniu do kwoty 118.760.528
z. Akcje w podwyszonym kapitale zakadowym bd w caoci opacone.

--
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

99 matches

Mail list logo