Re: Vector processors on the 3090

[Rick Fochtman]

---


If this is the beast I think it is, it attached only to 360s as a
channel  that had outboard channels.  Memory (no bit correction) says
that was 44,  65, 75, 91, and 165/8 on 370.  May be more.  The
"programs" were channel  programs.  I was told that this was the
reason the 44 was created.  And  that it was 65 + lobotomy.
   



My understanding is that the 2044 was a hardwired machine unrelated to
the 2065. It was fast but had no SS instructions. There was a feature
that added shadow memory and a simulator for commercial instructions,
and it was possible to run OS/360 using that simulator.
 



The EMULATOR also added a few RS instructions, like STM, LM, BXH and BXLE.

Somewhere I have a copy of the last version of the EMULATOR we ran at 
Michigan Tech; it originated at Florida Power.


Rick


--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@bama.ua.edu with the message: GET IBM-MAIN INFO
Search the archives at http://bama.ua.edu/archives/ibm-main.html

Re: Vector processors on the 3090

[Anne & Lynn Wheeler]

rkueb...@tsys.com (Kirk Talman) writes:
> If this is the beast I think it is, it attached only to 360s as a channel 
> that had outboard channels.  Memory (no bit correction) says that was 44, 
> 65, 75, 91, and 165/8 on 370.  May be more.  The "programs" were channel 
> programs.  I was told that this was the reason the 44 was created.  And 
> that it was 65 + lobotomy.

bitsavers 360/44 funtional characteristics:
http://www.bitsavers.org/pdf/ibm/360/funcChar/A22-6875-5_360-44_funcChar.pdf

from above:

Although the Model 44 processing unis is about the same in physical size
(Figure 1) as that of its nearest neighbor, the Model 50, its
performance on problems for which it is optimized is 30 to 60 per cent
faster than that of Model 50.

.. snip ..

and:

Processor storage speed for the Model 44 is 1 microsecond. Four bytes
(one word or two halfwords) are stored or fetched in each
access. Processor stroage, alwasy housed within the CPU, is availabe in
the four capacities shown at the top of Figure 3.

Data paths throughout the CPU are one word wide. 

.. snip ...

functional characteristic for 360/40 (also on bitsaver) has two-byte
datapaths

bitsaver is missing 360/50 functional characteristics

360/65 had 8byte data paths with 750ns memory

low-end & mid-range 360s (up to 360/50) had integrated channels,
higher-end 360s (starting with 360/65) had external channels

-- 
virtualization experience starting Jan1968, online at home since Mar1970

--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@bama.ua.edu with the message: GET IBM-MAIN INFO
Search the archives at http://bama.ua.edu/archives/ibm-main.html

Re: Vector processors on the 3090

[Shmuel Metz (Seymour J.)]

In
,
on 07/01/2011
   at 04:36 PM, Kirk Talman  said:

>If this is the beast I think it is, it attached only to 360s as a
>channel  that had outboard channels.  Memory (no bit correction) says
>that was 44,  65, 75, 91, and 165/8 on 370.  May be more.  The
>"programs" were channel  programs.  I was told that this was the
>reason the 44 was created.  And  that it was 65 + lobotomy.

My understanding is that the 2044 was a hardwired machine unrelated to
the 2065. It was fast but had no SS instructions. There was a feature
that added shadow memory and a simulator for commercial instructions,
and it was possible to run OS/360 using that simulator.
 
-- 
 Shmuel (Seymour J.) Metz, SysProg and JOAT
 ISO position; see  
We don't care. We don't have to care, we're Congress.
(S877: The Shut up and Eat Your spam act of 2003)

--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@bama.ua.edu with the message: GET IBM-MAIN INFO
Search the archives at http://bama.ua.edu/archives/ibm-main.html

Re: Vector processors on the 3090

[Abe F. Kornelis]

Ivan,

VF has been deprecated (in its current form anyway) for quite some 
time.. To a point where the op codes for the VF have been reused for 
some z/Arch specific instructions.
**--> I know full well. It poses a problem, but there are various ways 
   around it. One would be to use an 'architecture bit' in the object

   module and load module headers respecively. That would allow the
   z390 emulator module to distinguish vector opcodes from non-vector
   opcodes. Disadvantage: Cannot mix Vector and Halfword Immediate
   instructions.
   Another solution would be to assign an (as yet) unused code
   (e.g. A1 or AB) tro replace A5, which is the only first-byte
   that has actually been reused. See www.bixoft.com\english\opcd00.htm
   where you can see X'A5' to be the only vector subset first-byte reused.
   Advantage: can mix with Halfword Immediate instructions.
   Disadvantage: not compatible with mainframe, and deviation from
   Vector-PoP documentation.
   Risk: IBM might choose to reuse other first-bytes we use for
   vector instructions.

It should not be too difficult to tackle this part of the issue.
Most of the work would go into testing and verifying proper operation,
hence my request for testcases.

Cheers,
Abe Kornelis.
=

--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@bama.ua.edu with the message: GET IBM-MAIN INFO
Search the archives at http://bama.ua.edu/archives/ibm-main.html

Re: Vector processors on the 3090

[Kirk Talman]

IBM Mainframe Discussion List  wrote on 07/01/2011 
03:37:31 AM:

> From: Timothy Sipples 

> And before *that* there was the IBM 2938 Array Processor which you 
attached
> to your System/360.

If this is the beast I think it is, it attached only to 360s as a channel 
that had outboard channels.  Memory (no bit correction) says that was 44, 
65, 75, 91, and 165/8 on 370.  May be more.  The "programs" were channel 
programs.  I was told that this was the reason the 44 was created.  And 
that it was 65 + lobotomy.

-
The information contained in this communication (including any
attachments hereto) is confidential and is intended solely for the
personal and confidential use of the individual or entity to whom
it is addressed. If the reader of this message is not the intended
recipient or an agent responsible for delivering it to the intended
recipient, you are hereby notified that you have received this
communication in error and that any review, dissemination, copying,
or unauthorized use of this information, or the taking of any
action in reliance on the contents of this information is strictly
prohibited. If you have received this communication in error,
please notify us immediately by e-mail, and delete the original
message. Thank you 

--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@bama.ua.edu with the message: GET IBM-MAIN INFO
Search the archives at http://bama.ua.edu/archives/ibm-main.html

Re: Vector processors on the 3090

[Rick Fochtman]

:


Rick:

OK will do. I disagree with the "none of the higher level languages support it". 
I have found several mentions of FORTRAN.

However I was not looking for usage techniques just some general information.
I haven't looked at all of the rich URL's given out by Lyn yet will get around 
to them tomarrow. As usual they are a rich treasure trove of information.

I did find some interesting HLL examples (general ones).
Which was fine I am not into details on the thing.
Consider it dropped.
Ed
 



Let me amend original statement: WE never found any HLL support for the 
Vector Processor.


Rick

--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@bama.ua.edu with the message: GET IBM-MAIN INFO
Search the archives at http://bama.ua.edu/archives/ibm-main.html

Re: Vector processors on the 3090

[W. Kevin Kelley]

On Fri, 1 Jul 2011 15:37:31 +0800, Timothy Sipples 
 wrote:

>
>Before that there was the IBM 3838 Array Processor which ran (eventually)
>the Vector Processing Subsystem (VPSS)/XA. I think the 3838 debuted in 
1976
>or 1977. Your VPSS stuff could run on the VFs using (what else) VPSS/VF.
>VPSS/XA was IBM Program Number 5665-301. VPS/XA also supported 
FORTRAN, at
>least.
>
 
For what its worth, the SUBSYS= support on the DD statement was invented 
by Barry Goldstein and myself to support the 3838. It allowed FORTRAN I/O to 
be redirected to VPSS for passing arrays into and out of the 3838. (The 3838 
looked like a tape device to FORTRAN).
 
Of course, many of you have found other uses for SUBSYS= since then...

W. Kevin Kelley -- IBM POK Lab -- z/OS Core Technical Development
 

--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@bama.ua.edu with the message: GET IBM-MAIN INFO
Search the archives at http://bama.ua.edu/archives/ibm-main.html

Re: Vector processors on the 3090

[Ivan Warren]

On 7/1/2011 7:39 PM, Abe F. Kornelis wrote:


Who would be able to contribute code samples (read: test cases) if such
an extension to z390 would be built? Anybody interested?


I doubt it...

VF has been deprecated (in its current form anyway) for quite some 
time.. To a point where the op codes for the VF have been reused for 
some z/Arch specific instructions.


--Ivan

--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@bama.ua.edu with the message: GET IBM-MAIN INFO
Search the archives at http://bama.ua.edu/archives/ibm-main.html

Re: Vector processors on the 3090

[Abe F. Kornelis]

All,

I still have an electronic copy of the SA22-7207-00 ESA390 Vector Operations
manual. I've been considering for a while to write an extension for Don 
Higgins'
z390 assembler to create Vector Facility support there. I haven't started 
yet,

as it seems a lot of work, and doubtful that anybody would be interested.

Who would be able to contribute code samples (read: test cases) if such
an extension to z390 would be built? Anybody interested?

Cheers,
Abe Kornelis.
=

--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@bama.ua.edu with the message: GET IBM-MAIN INFO
Search the archives at http://bama.ua.edu/archives/ibm-main.html

Re: Vector processors on the 3090

[Anne & Lynn Wheeler]

l...@garlic.com (Anne & Lynn Wheeler) writes:
> try search "linkpak 3090 vf" for various other refs

finger slip ... that should be linpack (not linkpak)
http://en.wikipedia.org/wiki/LINPACK

first top 500 doesn't have ibm mainframe
http://www.top500.org/list/1993/06/100

old post w/s-computer sep86 list of supercomputers on bitnet (post
previously refed):
http://www.garlic.com/~lynn/2000c.html#61 TF-1

lists a couple 3090/VF

-- 
virtualization experience starting Jan1968, online at home since Mar1970

--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@bama.ua.edu with the message: GET IBM-MAIN INFO
Search the archives at http://bama.ua.edu/archives/ibm-main.html

Re: Vector processors on the 3090

[David Crayford]

Why are we even talking about VPs? The z196 has OOO which enables HPC in 
any language.


On 1/07/2011 10:36 AM, Rick Fochtman wrote:

Ed Gould wrote:


All the google searches are mute (or Cost $$$)

As to the mega flops the facility had. Anyone have the numbers?

Sorry to ask these semi off topic question but I was asked about them 
and am at a loss to find documentation that doesn't. Cost $$


As a side question anyone work with the facility? Any stories you 
would like to share would be interesting.


Ed


--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@bama.ua.edu with the message: GET IBM-MAIN INFO
Search the archives at http://bama.ua.edu/archives/ibm-main.html



Unless you're a serious masochist, I suggest you drop that line of 
inquiry. None of the HLL's support the Vector Processor so you're 
stuck using Assembler Language if you want to use it. And setting up 
the mechanisms for true vector processing is a non-trivial exercise.  
:-(  BTDTGTSS


NEVER AGAIN!!!

Rick

--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@bama.ua.edu with the message: GET IBM-MAIN INFO
Search the archives at http://bama.ua.edu/archives/ibm-main.html


--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@bama.ua.edu with the message: GET IBM-MAIN INFO
Search the archives at http://bama.ua.edu/archives/ibm-main.html

Re: Vector processors on the 3090

[Anne & Lynn Wheeler]

timothy.sipp...@us.ibm.com (Timothy Sipples) writes:
> That's not really true. For example, there was the IBM Engineering and
> Scientific Subroutine Library (ESSL) Vector and Scalar/370 software. That
> software provided a library of mathematical functions you could call from
> FORTRAN, C, PL/I, APL2, or Assembler programs on MVS or VM. It was also
> supported for the languages that ran on AIX/ESA. Program number was
> 5688-226, and it was withdrawn from marketing in 2001. VS FORTRAN Version 2
> (not sure which release) also had some automatic vector support of its own.
>
> The Vector Facility for 3090s was announced on October 1, 1985.
> Announcement letter 185-121 is still available on IBM's announcements Web
> site (http://www.ibm.com/common/ssi). At the time you could rent your first
> Vector Facility for a list price of $30,830 per month and any subsequent
> VFs for $19,170 per month. The purchases prices were $370,000 and $230,000,
> respectively. All prices are in 1985 dollars, of course.
>
> Before that there was the IBM 3838 Array Processor which ran (eventually)
> the Vector Processing Subsystem (VPSS)/XA. I think the 3838 debuted in 1976
> or 1977. Your VPSS stuff could run on the VFs using (what else) VPSS/VF.
> VPSS/XA was IBM Program Number 5665-301. VPS/XA also supported FORTRAN, at
> least.
>
> And before *that* there was the IBM 2938 Array Processor which you attached
> to your System/360.
>
> By the way, you could think of today's zEnterprise BladeCenter Extension
> (zBX) as a mainframe vector processor...plus lots of other capabilities.

re:
http://www.garlic.com/~lynn/2011h.html#68 IBM Mainframe (1980's) on You tube
http://www.garlic.com/~lynn/2011h.html#69 IBM Mainframe (1980's) on You tube
http://www.garlic.com/~lynn/2011h.html#72 Vector processors on the 3090
http://www.garlic.com/~lynn/2011h.html#73 Vector processors on the 3090

there were a couple groups in kingston ... one was the E&S center that
had a 3090VF (as well as 20 Floating Point Systems boxes) and the group
that was supposedly designing an IBM supercomputer ... but was also
funding/supporting various other activities ... like the HiPPI I/O
interface for 3090 and providing funding for Chen Supercomputer company.
long winded thread in a.f.c. from last year
http://www.garlic.com/~lynn/2010b.html#71 Happy DEC-10 Day
http://www.garlic.com/~lynn/2010b.html#72 Happy DEC-10 Day
http://www.garlic.com/~lynn/2010b.html#73 Happy DEC-10 Day
http://www.garlic.com/~lynn/2010b.html#74 Happy DEC-10 Day 
and later thread in comp.arch 
http://www.garlic.com/~lynn/2010f.html#47 Nonlinear systems and nonlocal 
supercomputing
http://www.garlic.com/~lynn/2010f.html#48 Nonlinear systems and nonlocal 
supercomputing 
http://www.garlic.com/~lynn/2010f.html#49 Nonlinear systems and nonlocal 
supercomputing
http://www.garlic.com/~lynn/2010f.html#50 Nonlinear systems and nonlocal 
supercomputing

As mentioned in above, oct91, the senior executive sponsonsoring the
supercomputer effort retired and there was lots of review of various
projects. then there was an effort to canvas the company to find
something for supercomputer (they found the effort I was doing in
mid-jan92, and over a couple weeks, it was transferred to Kingston, we
were told we couldn't work on anything with than four more processors
and it was announced as supercomputer). misc. email from late 91 & early
92
http://www.garlic.com/~lynn/lhwemail.html#medusa

This old post describes the ('87) cornell national supercomputer
facility with 3090-400 VF and five FPS boxes
http://www.garlic.com/~lynn/200c.html#2000c.html#61 TF-1

some followon in this old thread:
http://www.garlic.com/~lynn/2000d.html#2 IBM's "ASCI White" and "Big Blue" 
architecture?
http://www.garlic.com/~lynn/2000d.html#3 IBM's "ASCI White" and "Big Blue" 
architecture?
http://www.garlic.com/~lynn/2000d.html#8 IBM's "ASCI White" and "Big Blue" 
architecture?

above references the 1.5gflops peak for 375mhz power3-ii chip is
approx. same as the aggregate for IBM Kingston E&S lab in 1985 (with all
the FPS boxes)

HiPPI was the standards version of Cray 100mbyte/sec parallel (aka
half-duplex) channel (standards effort driven out of LANL). 3090 I/O
wasn't capable of handle the rate ... so a hack was done in the side of
3090 extended store bus ... with peek/poke semantics; aka basicaly i/o
commands & data were read/written to special addresses on the 3090
extended store bus. Later there was serial-HiPPI (with fiber) which then
sort of merges with FCS (standards effort driven out of LLNL for 1gbit
fiber full-duplex; POK gets involved and there is now FICON flavor of
FCS).

-- 
virtualization experience starting Jan1968, online at home since Mar1970

--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@bama.ua.edu with the message: GET IBM-MAIN INFO
Search the archives at http://bama.ua.edu/archives/ibm-main.html

Re: Vector processors on the 3090

[Timothy Sipples]

The 1984 withdrawal announcement for the IBM 3838 Array Processor is still
available at IBM's announcements Web site. The announcement number is
184-060.

I found a list of several other high-level software products that
apparently supported the VFs, at least some of which could be used by high
level languages:

1. MSC/NASTRAN from MacNeal-Schwendler Corporation and NASA
Information on MSC/NASTRAN is still available here:
http://www.mscsoftware.com

2. CAEDS which was developed by Structural Dynamics Research Corporation
then sold by IBM
See IBM announcement 292-635, for example.

3. ANSYS from Swanson Analysis Systems, Inc.
Company is now known as ANSYS, Inc. (http://www.ansys.com)

4. FIDAP developed by Fluid Dynamics International, distributed/serviced by
Boeing
Here's some historical information:
http://web.utk.edu/~mnewman/ibmguide18.html#Header_446

5. EASY5 from Boeing
http://www.boeing.com/assocproducts/easy5/
http://www.mscsoftware.com/Products/CAE-Tools/Easy5.aspx

6. IMSL Library from IMSL, Inc.
http://www.roguewave.com/products/imsl-numerical-libraries.aspx

IBM also offered Vector Facility Simulator software which provided
instruction-level compatibility on machines that didn't have actual VF
hardware. Of course, it was slower. I can't find too much information about
the simulator, but in principle it would permit running VF software on
System z machines. If possible, it would be very interesting to benchmark
today's machines running the simulator against actual VF hardware. :-)

- - - - -
Timothy Sipples
Resident Enterprise Architect
Value Creation & Complex Deals Team
IBM Growth Markets (Based in Singapore)
E-Mail: timothy.sipp...@us.ibm.com
--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@bama.ua.edu with the message: GET IBM-MAIN INFO
Search the archives at http://bama.ua.edu/archives/ibm-main.html

Re: Vector processors on the 3090

[Timothy Sipples]

Rick Fochtman wrote:
>Unless you're a serious masochist, I suggest you drop that line
>of inquiry. None of the HLL's support the Vector Processor so you're
>stuck using Assembler Language if you want to use it.

That's not really true. For example, there was the IBM Engineering and
Scientific Subroutine Library (ESSL) Vector and Scalar/370 software. That
software provided a library of mathematical functions you could call from
FORTRAN, C, PL/I, APL2, or Assembler programs on MVS or VM. It was also
supported for the languages that ran on AIX/ESA. Program number was
5688-226, and it was withdrawn from marketing in 2001. VS FORTRAN Version 2
(not sure which release) also had some automatic vector support of its own.

The Vector Facility for 3090s was announced on October 1, 1985.
Announcement letter 185-121 is still available on IBM's announcements Web
site (http://www.ibm.com/common/ssi). At the time you could rent your first
Vector Facility for a list price of $30,830 per month and any subsequent
VFs for $19,170 per month. The purchases prices were $370,000 and $230,000,
respectively. All prices are in 1985 dollars, of course.

Before that there was the IBM 3838 Array Processor which ran (eventually)
the Vector Processing Subsystem (VPSS)/XA. I think the 3838 debuted in 1976
or 1977. Your VPSS stuff could run on the VFs using (what else) VPSS/VF.
VPSS/XA was IBM Program Number 5665-301. VPS/XA also supported FORTRAN, at
least.

And before *that* there was the IBM 2938 Array Processor which you attached
to your System/360.

By the way, you could think of today's zEnterprise BladeCenter Extension
(zBX) as a mainframe vector processor...plus lots of other capabilities.

- - - - -
Timothy Sipples
Resident Enterprise Architect
Value Creation & Complex Deals Team
IBM Growth Markets (Based in Singapore)
E-Mail: timothy.sipp...@us.ibm.com
--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@bama.ua.edu with the message: GET IBM-MAIN INFO
Search the archives at http://bama.ua.edu/archives/ibm-main.html

Re: Vector processors on the 3090

[Ted MacNEIL]

I don't care because I wouldn't be RUDE enough to bring  it up!
-
Ted MacNEIL
eamacn...@yahoo.ca
Twitter: @TedMacNEIL

-Original Message-
From: Gerhard Postpischil 
Sender: IBM Mainframe Discussion List 
Date: Fri, 1 Jul 2011 01:36:21 
To: 
Reply-To: IBM Mainframe Discussion List 
Subject: Re: Vector processors on the 3090

On 6/30/2011 11:09 PM, Ted MacNEIL wrote:
> Oh! Is this something that (again) only means anything to
> 3, as opposed to another 7 billion on the planet,
> where the 4th means nothing, on an international discussion
> forum?
>
> Yes. Go ahead and flame me. I can take it.

OK, you asked for it   What percentage cares about your 
having a happy Canada day?



Gerhard Postpischil
Bradford, VT

--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@bama.ua.edu with the message: GET IBM-MAIN INFO
Search the archives at http://bama.ua.edu/archives/ibm-main.html

--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@bama.ua.edu with the message: GET IBM-MAIN INFO
Search the archives at http://bama.ua.edu/archives/ibm-main.html

Re: Vector processors on the 3090

[Gerhard Postpischil]

On 6/30/2011 11:09 PM, Ted MacNEIL wrote:

Oh! Is this something that (again) only means anything to
3, as opposed to another 7 billion on the planet,
where the 4th means nothing, on an international discussion
forum?

Yes. Go ahead and flame me. I can take it.


OK, you asked for it   What percentage cares about your 
having a happy Canada day?




Gerhard Postpischil
Bradford, VT

--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@bama.ua.edu with the message: GET IBM-MAIN INFO
Search the archives at http://bama.ua.edu/archives/ibm-main.html

Re: Vector processors on the 3090

[Ed Gould]

Rick:

OK will do. I disagree with the "none of the higher level languages support 
it". 
I have found several mentions of FORTRAN.
However I was not looking for usage techniques just some general information.
I haven't looked at all of the rich URL's given out by Lyn yet will get around 
to them tomarrow. As usual they are a rich treasure trove of information.
I did find some interesting HLL examples (general ones).
Which was fine I am not into details on the thing.
Consider it dropped.
Ed





From: Rick Fochtman 
To: IBM-MAIN@bama.ua.edu
Sent: Thu, June 30, 2011 9:36:25 PM
Subject: Re: Vector processors on the 3090

Ed Gould wrote:

> All the google searches are mute (or Cost $$$)
>
>As to the mega flops the facility had. Anyone have the numbers?
>
>Sorry to ask these semi off topic question but I was asked about them and am 
>at 
>a loss to find documentation that doesn't. Cost $$
>
>As a side question anyone work with the facility? Any stories you would like 
>to 
>share would be interesting.
>
>Ed
>
>
>--
>For IBM-MAIN subscribe / signoff / archive access instructions,
>send email to lists...@bama.ua.edu with the message: GET IBM-MAIN INFO
>Search the archives at http://bama.ua.edu/archives/ibm-main.html
>
>  
>
Unless you're a serious masochist, I suggest you drop that line of 
inquiry. None of the HLL's support the Vector Processor so you're stuck 
using Assembler Language if you want to use it. And setting up the 
mechanisms for true vector processing is a non-trivial exercise.  :-(  
BTDTGTSS

NEVER AGAIN!!!

Rick

--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@bama.ua.edu with the message: GET IBM-MAIN INFO
Search the archives at http://bama.ua.edu/archives/ibm-main.html

--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@bama.ua.edu with the message: GET IBM-MAIN INFO
Search the archives at http://bama.ua.edu/archives/ibm-main.html

Re: Vector processors on the 3090

[Anne & Lynn Wheeler]

ps2...@yahoo.com (Ed Gould) writes:
>  All the google searches are mute (or Cost $$$)
>
> As to the mega flops the facility had. Anyone have the numbers?
>
> Sorry to ask these semi off topic question but I was asked about them
> and am at a loss to find documentation that doesn't. Cost $$
>
> As a side question anyone work with the facility? Any stories you
> would like to share would be interesting.

see previous post reference
http://www.garlic.com/~lynn/2011h.html#68 IBM Mainframe (1980's) on You tube

 ... which includes  mflop ranking numbers, here
http://www.garlic.com/~lynn/2002i.html#12 CDC6600 - just how powerful a machine 
was it?

references table that has gone 404 ... but still available
at wayback machine

from table:
IBM ES/9000-511 VF(1 proc 11ns)   30
IBM ES/9000-340 VF (14.5 ns)  23
IBM ES/9000-320 VF (1 proc 15 ns) 22
IBM ES/9000 Model 260 VF (15 ns)  19
IBM ES/9000 Model 210 VF (15 ns)  17
IBM 3090/180J VF (1 proc, 14.5 ns)16
IBM ES/9000 Model 190 VF(15 ns)   14
IBM 3090/180E VF  13

try search "linkpak 3090 vf" for various other refs
http://publishing.cdlib.org/ucpressebooks/view?docId=ft0f59n73z&chunk.id=d0e7046&toc.id=d0e7005&brand=ucpress;query=architecture
http://www.netlib.org/performance/rank/linpack/
ftp://icmsec.cc.ac.cn/pub/netlib/performance/html/linpack-peak.data.col0.html
http://www.taborcommunications.com/archives/3053.html
http://www.sdsc.edu/Xtal/Bm/benchmark_results

other posts in previous thread:
http://www.garlic.com/~lynn/2011h.html#69 IBM Mainframe (1980's) on You tube
http://www.garlic.com/~lynn/2011h.html#70 IBM Mainframe (1980's) on You tube

-- 
virtualization experience starting Jan1968, online at home since Mar1970

--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@bama.ua.edu with the message: GET IBM-MAIN INFO
Search the archives at http://bama.ua.edu/archives/ibm-main.html

Re: Vector processors on the 3090

[Ted MacNEIL]

>Happy Fourth! 

Oh! Is this something that (again) only means anything to 3, as opposed 
to another 7 billion on the planet, where the 4th means nothing, on an 
international discussion forum?

Yes. Go ahead and flame me.
I can take it.
-
Ted MacNEIL
eamacn...@yahoo.ca
Twitter: @TedMacNEIL

--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@bama.ua.edu with the message: GET IBM-MAIN INFO
Search the archives at http://bama.ua.edu/archives/ibm-main.html

Re: Vector processors on the 3090

[Ed Finnell]

I don't know what the deal was? Might check some of the SHARE archives.  
There was certainly an Amdahl VF1 Fortran that some of the techies used. Don't 
 know about costs. They were making progress and then the RISCs processors 
came  out and they jumped ship for mo power less money...
 
Sat through a UCLA professor's talk at SHARE. Ninety hours on a 3090-600J  
with six vectors to get a 15 second video of a plasma simulation...Happy  
Fourth! 
 
 
In a message dated 6/30/2011 9:37:00 P.M. Central Daylight Time,  
rfocht...@ync.net writes:

None of  the HLL's support the Vector Processor so you're stuck 
using Assembler  Language if you want to use it. And setting up the  


--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@bama.ua.edu with the message: GET IBM-MAIN INFO
Search the archives at http://bama.ua.edu/archives/ibm-main.html

Re: Vector processors on the 3090

[Rick Fochtman]

Ed Gould wrote:


All the google searches are mute (or Cost $$$)

As to the mega flops the facility had. Anyone have the numbers?

Sorry to ask these semi off topic question but I was asked about them and am at a 
loss to find documentation that doesn't. Cost $$

As a side question anyone work with the facility? Any stories you would like to 
share would be interesting.

Ed


--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@bama.ua.edu with the message: GET IBM-MAIN INFO
Search the archives at http://bama.ua.edu/archives/ibm-main.html

 

Unless you're a serious masochist, I suggest you drop that line of 
inquiry. None of the HLL's support the Vector Processor so you're stuck 
using Assembler Language if you want to use it. And setting up the 
mechanisms for true vector processing is a non-trivial exercise.  :-(  
BTDTGTSS


NEVER AGAIN!!!

Rick

--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@bama.ua.edu with the message: GET IBM-MAIN INFO
Search the archives at http://bama.ua.edu/archives/ibm-main.html

Vector processors on the 3090

[Ed Gould]

 All the google searches are mute (or Cost $$$)

As to the mega flops the facility had. Anyone have the numbers?

Sorry to ask these semi off topic question but I was asked about them and am at 
a loss to find documentation that doesn't. Cost $$

As a side question anyone work with the facility? Any stories you would like to 
share would be interesting.

Ed


--
For IBM-MAIN subscribe / signoff / archive access instructions,
send email to lists...@bama.ua.edu with the message: GET IBM-MAIN INFO
Search the archives at http://bama.ua.edu/archives/ibm-main.html