Rocksolid Light

Welcome to novaBBS (click a section below)

mail  files  register  newsreader  groups  login

Message-ID:  

Dammit Jim, I'm an actor, not a doctor.


tech / sci.electronics.design / Re: supercomputer progress

SubjectAuthor
* supercomputer progressjlarkin
+* Re: supercomputer progressCydrome Leader
|`- Re: supercomputer progressJan Panteltje
+* Re: supercomputer progressJohn Robertson
|`* Re: supercomputer progressJohn Larkin
| +* Re: supercomputer progressJan Panteltje
| |`- Re: supercomputer progressJeroen Belleman
| +- Re: supercomputer progressDecadentLinuxUserNumeroUno
| `* Re: supercomputer progressboB
|  +- Re: supercomputer progressjlarkin
|  +* Re: supercomputer progressDennis
|  |`* Re: supercomputer progressJohn Larkin
|  | `* Re: supercomputer progressPhil Hobbs
|  |  +* Re: supercomputer progressMike Monett
|  |  |`* Re: supercomputer progressPhil Hobbs
|  |  | `* Re: supercomputer progressJoe Gwinn
|  |  |  `* Re: supercomputer progressPhil Hobbs
|  |  |   +* Re: supercomputer progressJoe Gwinn
|  |  |   |`- Re: supercomputer progressRicky
|  |  |   `* Re: supercomputer progressMartin Brown
|  |  |    `- Re: supercomputer progressPhil Hobbs
|  |  +* Re: supercomputer progressMartin Brown
|  |  |`- Re: supercomputer progressPhil Hobbs
|  |  `* Re: supercomputer progressjlarkin
|  |   +- Re: supercomputer progressMartin Brown
|  |   `* Re: supercomputer progresswhit3rd
|  |    `- Re: supercomputer progressDecadentLinuxUserNumeroUno
|  `* Re: supercomputer progressJeroen Belleman
|   +- Re: supercomputer progressRicky
|   +* Re: supercomputer progressMartin Brown
|   |+* Re: supercomputer progressRicky
|   ||`- Re: supercomputer progressMartin Brown
|   |+* Re: supercomputer progressCydrome Leader
|   ||+* Re: supercomputer progressrbowman
|   |||+* Re: supercomputer progressMartin Brown
|   ||||`- Re: supercomputer progressrbowman
|   |||`* Re: supercomputer progressCydrome Leader
|   ||| `- Re: supercomputer progressrbowman
|   ||`- Re: supercomputer progressRicky
|   |`* Re: supercomputer progressLes Cargill
|   | `- Re: supercomputer progressMartin Brown
|   +* Re: supercomputer progressPhil Hobbs
|   |`- Re: supercomputer progressRicky
|   `* Re: supercomputer progressjlarkin
|    `- Re: supercomputer progressRicky
`* Re: supercomputer progressa a
 +* Re: supercomputer progressa a
 |+* Re: supercomputer progressa a
 ||`- Re: supercomputer progressAnass Luca
 |`- Re: supercomputer progressa a
 `* Re: supercomputer progresswhit3rd
  `* Re: supercomputer progressa a
   +* Re: supercomputer progresswhit3rd
   |+- Re: supercomputer progressa a
   |+* Re: supercomputer progressa a
   ||`* Re: supercomputer progresswhit3rd
   || `* Re: supercomputer progressa a
   ||  `- Re: supercomputer progressa a
   |`- Re: supercomputer progressa a
   `- Re: supercomputer progressa a

Pages:123
Re: supercomputer progress

<9c639e8e-98f8-4d99-90ae-37010c03a549n@googlegroups.com>

 copy mid

https://www.novabbs.com/tech/article-flat.php?id=95758&group=sci.electronics.design#95758

 copy link   Newsgroups: sci.electronics.design
X-Received: by 2002:ae9:e30c:0:b0:69f:9086:777b with SMTP id v12-20020ae9e30c000000b0069f9086777bmr7803540qkf.527.1651243804523;
Fri, 29 Apr 2022 07:50:04 -0700 (PDT)
X-Received: by 2002:a5b:98a:0:b0:633:c93e:3e17 with SMTP id
c10-20020a5b098a000000b00633c93e3e17mr36901604ybq.512.1651243804333; Fri, 29
Apr 2022 07:50:04 -0700 (PDT)
Path: i2pn2.org!i2pn.org!weretis.net!feeder6.news.weretis.net!news.misty.com!border2.nntp.dca1.giganews.com!nntp.giganews.com!news-out.google.com!nntp.google.com!postnews.google.com!google-groups.googlegroups.com!not-for-mail
Newsgroups: sci.electronics.design
Date: Fri, 29 Apr 2022 07:50:04 -0700 (PDT)
In-Reply-To: <tktn6h1p1h1mh3k7lmlcch7546u4130ld3@4ax.com>
Injection-Info: google-groups.googlegroups.com; posting-host=24.138.223.107; posting-account=I-_H_woAAAA9zzro6crtEpUAyIvzd19b
NNTP-Posting-Host: 24.138.223.107
References: <tj4g6hd8omp97pbbs6dn146suop2dds5n6@4ax.com> <mZKdnQszLo_T3_X_nZ2dnUU7-LXNnZ2d@giganews.com>
<fpmg6hhot88ajjqkcb6nv9mkbjm7s9q85k@4ax.com> <0lfl6hhee2j23gr7j5epb3obpdn8s7sj3f@4ax.com>
<t4ejuo$7n8$1@gioia.aioe.org> <tktn6h1p1h1mh3k7lmlcch7546u4130ld3@4ax.com>
User-Agent: G2/1.0
MIME-Version: 1.0
Message-ID: <9c639e8e-98f8-4d99-90ae-37010c03a549n@googlegroups.com>
Subject: Re: supercomputer progress
From: gnuarm.d...@gmail.com (Ricky)
Injection-Date: Fri, 29 Apr 2022 14:50:04 +0000
Content-Type: text/plain; charset="UTF-8"
Lines: 27
 by: Ricky - Fri, 29 Apr 2022 14:50 UTC

On Friday, April 29, 2022 at 10:32:07 AM UTC-4, jla...@highlandsniptechnology.com wrote:
> On Thu, 28 Apr 2022 19:47:03 +0200, Jeroen Belleman
> <jer...@nospam.please> wrote:
>
> >On 2022-04-28 18:26, boB wrote:
> >[...]
> >> I would love to have a super computer to run LTspice.
> >>
> >> boB
> >>
> >
> >
> >In fact, what you have on your desk *is* a super computer,
> >in the 1970's meaning of the words. It's just that it's
> >bogged down running bloatware.
> >
> >Jeroen Belleman
> My phone probably has more compute power than all the computers in the
> world about 1960.

And lets you watch cat videos anywhere you go.

--

Rick C.

-+ Get 1,000 miles of free Supercharging
-+ Tesla referral code - https://ts.la/richard11209

Re: supercomputer progress

<t4h0qg$1gkj$1@gioia.aioe.org>

 copy mid

https://www.novabbs.com/tech/article-flat.php?id=95763&group=sci.electronics.design#95763

 copy link   Newsgroups: sci.electronics.design
Path: i2pn2.org!i2pn.org!aioe.org!woWShB6DIQvlDBD7PkJe+g.user.46.165.242.75.POSTED!not-for-mail
From: '''newsp...@nonad.co.uk (Martin Brown)
Newsgroups: sci.electronics.design
Subject: Re: supercomputer progress
Date: Fri, 29 Apr 2022 16:38:55 +0100
Organization: Aioe.org NNTP Server
Message-ID: <t4h0qg$1gkj$1@gioia.aioe.org>
References: <tj4g6hd8omp97pbbs6dn146suop2dds5n6@4ax.com>
<mZKdnQszLo_T3_X_nZ2dnUU7-LXNnZ2d@giganews.com>
<fpmg6hhot88ajjqkcb6nv9mkbjm7s9q85k@4ax.com>
<0lfl6hhee2j23gr7j5epb3obpdn8s7sj3f@4ax.com> <t4ejuo$7n8$1@gioia.aioe.org>
<t4g872$ll$1@gioia.aioe.org>
<b8223175-9f6a-4c64-b91c-40ed762588b2n@googlegroups.com>
Mime-Version: 1.0
Content-Type: text/plain; charset=UTF-8; format=flowed
Content-Transfer-Encoding: 7bit
Injection-Info: gioia.aioe.org; logging-data="49811"; posting-host="woWShB6DIQvlDBD7PkJe+g.user.gioia.aioe.org"; mail-complaints-to="abuse@aioe.org";
User-Agent: Mozilla/5.0 (Windows NT 6.1; Win64; x64; rv:91.0) Gecko/20100101
Thunderbird/91.8.1
X-Notice: Filtered by postfilter v. 0.9.2
Content-Language: en-GB
 by: Martin Brown - Fri, 29 Apr 2022 15:38 UTC

On 29/04/2022 14:46, Ricky wrote:
> On Friday, April 29, 2022 at 4:39:05 AM UTC-4, Martin Brown wrote:
>> On 28/04/2022 18:47, Jeroen Belleman wrote:
>>> On 2022-04-28 18:26, boB wrote: [...]
>>>> I would love to have a super computer to run LTspice.
>>>>
>>>> boB
>>>
>>> In fact, what you have on your desk *is* a super computer, in the
>>> 1970's meaning of the words. It's just that it's bogged down
>>> running bloatware.
>> Indeed. The Cray X-MP in its 4 CPU configuration with a 105MHz
>> clock and a whopping for the time 128MB of fast core memory with
>> 40GB of disk. The one I used had an amazing for the time 1TB tape
>> cassette backing store. It did 600 MFLOPs with the right sort of
>> parallel vector code.
>>
>> That was back in the day when you needed special permission to use
>> more than 4MB of core on the timesharing IBM 3081 (approx 7 MIPS).
>>
>> Current Intel 12 gen CPU desktops are ~4GHz, 16GB ram and >1TB of
>> disk. (and the upper limits are even higher) That combo does
>> ~66,000 MFLOPS.
>>
>> Spice simulation doesn't scale particularly well to large scale
>> multiprocessor environments to many long range interractions.
>
> The Crays were nice if you had a few million dollars to spend. I
> worked for a startup building more affordable supercomputers in the
> same ball park of performance at a fraction of the price. Star
> Technologies, ST-100 supported 100 MFLOPS and 32 MB of memory,
> costing around $200,000 with 256 KB of RAM was a fraction of the cost
> of the only slightly faster Cray X-MP, available at the same time.

At the time I was doing that stuff the FPS-120 array processor attached
to a PDP-11 or Vax was the poor man's supercomputer. Provided you had
the right sort of problem it was very good indeed for price performance.
(it was still fairly pricey)

I got to port our code to everything from a humble Z80 (where it could
only solve trivial toy problems) upwards to the high end Cray. The more
expensive the computer the more tolerant of IBM extensions they tended
to be. The Z80 FORTRAN IV I remember as being a stickler for the rules.

--
Regards,
Martin Brown

Re: supercomputer progress

<t4h12m$1v55$1@gioia.aioe.org>

 copy mid

https://www.novabbs.com/tech/article-flat.php?id=95766&group=sci.electronics.design#95766

 copy link   Newsgroups: sci.electronics.design
Path: i2pn2.org!i2pn.org!aioe.org!woWShB6DIQvlDBD7PkJe+g.user.46.165.242.75.POSTED!not-for-mail
From: '''newsp...@nonad.co.uk (Martin Brown)
Newsgroups: sci.electronics.design
Subject: Re: supercomputer progress
Date: Fri, 29 Apr 2022 16:43:17 +0100
Organization: Aioe.org NNTP Server
Message-ID: <t4h12m$1v55$1@gioia.aioe.org>
References: <tj4g6hd8omp97pbbs6dn146suop2dds5n6@4ax.com>
<mZKdnQszLo_T3_X_nZ2dnUU7-LXNnZ2d@giganews.com>
<fpmg6hhot88ajjqkcb6nv9mkbjm7s9q85k@4ax.com>
<0lfl6hhee2j23gr7j5epb3obpdn8s7sj3f@4ax.com> <t4eha8$ofb$1@dont-email.me>
<g5ql6h5rutblfd2busa8uops80f3j2brjv@4ax.com>
<5ec1cf9b-63f2-b060-5d37-2b534bf39d10@electrooptical.net>
<1itn6h5p41i7js3cq6tao96udor44ccvlm@4ax.com>
Mime-Version: 1.0
Content-Type: text/plain; charset=UTF-8; format=flowed
Content-Transfer-Encoding: 7bit
Injection-Info: gioia.aioe.org; logging-data="64677"; posting-host="woWShB6DIQvlDBD7PkJe+g.user.gioia.aioe.org"; mail-complaints-to="abuse@aioe.org";
User-Agent: Mozilla/5.0 (Windows NT 6.1; Win64; x64; rv:91.0) Gecko/20100101
Thunderbird/91.8.1
Content-Language: en-GB
X-Notice: Filtered by postfilter v. 0.9.2
 by: Martin Brown - Fri, 29 Apr 2022 15:43 UTC

On 29/04/2022 15:30, jlarkin@highlandsniptechnology.com wrote:
> On Fri, 29 Apr 2022 02:09:19 -0400, Phil Hobbs
> <pcdhSpamMeSenseless@electrooptical.net> wrote:
>
>> John Larkin wrote:
>>> On Thu, 28 Apr 2022 12:01:59 -0500, Dennis <dennis@none.none> wrote:
>>>
>>>> On 4/28/22 11:26, boB wrote:
>>>>
>>>>> I would love to have a super computer to run LTspice.
>>>>>
>>>> I thought one of the problems with LTspice (and spice in general)
>>>> performance is that the algorithms don't parallelize very well.
>>>
>>> LT runs on multiple cores now. I'd love the next gen LT Spice to run
>>> on an Nvidia card. 100x at least.
>>>
>>
>> The "number of threads" setting doesn't do anything very dramatic,
>> though, at least last time I tried. Splitting up the calculation
>> between cores would require all of them to communicate a couple of times
>> per time step, but lots of other simulation codes do that.
>>
>> The main trouble is that the matrix defining the connectivity between
>> nodes is highly irregular in general.
>>
>> Parallellizing that efficiently might well need a special-purpose
>> compiler, sort of similar to the profile-guided optimizer in the guts of
>> the FFTW code for computing DFTs. Probably not at all impossible, but
>> not that straightforward to implement.
>>
>> Cheers
>>
>> Phil Hobbs
>
> Climate simulation uses enormous multi-CPU supercomputer rigs.

They are basically fluid in cell models with a fair number of parameters
per cell but depending on your exact choice of geometry only 6 nearest
neighbours in a 3D cubic computational grid (worst case 26 cells).

That is a very regular interconnectivity and lends itself to vector
processing (which is why we were using them) though for another problem.

A handful of FLIC practitioners used tetrahedral or hexagonal close
packed grids (4 nearest neighbours or 12 nearest neighbours).
> OK, I suppose that makes your point.

When I was involved in such codes for relativistic particle beams we
used its cylindrical symmetry to make the problem more tractable in 2D.
The results agreed remarkably well with experiments so I see no need to
ridicule other FLIC models as used in weather and climate research.

--
Regards,
Martin Brown

Re: supercomputer progress

<hkeo6htsjjj9sqpkron34durofbg4rrnv2@4ax.com>

 copy mid

https://www.novabbs.com/tech/article-flat.php?id=95784&group=sci.electronics.design#95784

 copy link   Newsgroups: sci.electronics.design
Path: i2pn2.org!i2pn.org!weretis.net!feeder6.news.weretis.net!news.misty.com!border2.nntp.dca1.giganews.com!nntp.giganews.com!buffer2.nntp.dca1.giganews.com!news.giganews.com.POSTED!not-for-mail
NNTP-Posting-Date: Fri, 29 Apr 2022 14:25:05 -0500
From: joegw...@comcast.net (Joe Gwinn)
Newsgroups: sci.electronics.design
Subject: Re: supercomputer progress
Date: Fri, 29 Apr 2022 15:25:05 -0400
Message-ID: <hkeo6htsjjj9sqpkron34durofbg4rrnv2@4ax.com>
References: <tj4g6hd8omp97pbbs6dn146suop2dds5n6@4ax.com> <mZKdnQszLo_T3_X_nZ2dnUU7-LXNnZ2d@giganews.com> <fpmg6hhot88ajjqkcb6nv9mkbjm7s9q85k@4ax.com> <0lfl6hhee2j23gr7j5epb3obpdn8s7sj3f@4ax.com> <t4eha8$ofb$1@dont-email.me> <g5ql6h5rutblfd2busa8uops80f3j2brjv@4ax.com> <5ec1cf9b-63f2-b060-5d37-2b534bf39d10@electrooptical.net> <XnsAE882CD53DA0Fidtokenpost@144.76.35.252> <t4gr7b$10eu$1@gioia.aioe.org>
User-Agent: ForteAgent/8.00.32.1272
MIME-Version: 1.0
Content-Type: text/plain; charset=ISO-8859-1
Content-Transfer-Encoding: 8bit
Lines: 65
X-Usenet-Provider: http://www.giganews.com
X-Trace: sv3-BBB6olYUxnMjEgYXhhVURaGyTvO+1tJADoti6KfEgRCqCK4MoULt3L3PS6NmwyBSaR0u5GvNO4TJtst!fUsHBZ0jOIRT4b0fDRBAsjn0stJcV9slBAwThelG5BDdfuY9Me6KLM4roylGnMf/Rt6yHi8=
X-Complaints-To: abuse@giganews.com
X-DMCA-Notifications: http://www.giganews.com/info/dmca.html
X-Abuse-and-DMCA-Info: Please be sure to forward a copy of ALL headers
X-Abuse-and-DMCA-Info: Otherwise we will be unable to process your complaint properly
X-Postfilter: 1.3.40
X-Original-Bytes: 4005
 by: Joe Gwinn - Fri, 29 Apr 2022 19:25 UTC

On Fri, 29 Apr 2022 10:03:23 -0400, Phil Hobbs
<pcdhSpamMeSenseless@electrooptical.net> wrote:

>Mike Monett wrote:
>> Phil Hobbs <pcdhSpamMeSenseless@electrooptical.net> wrote:
>>
>>> John Larkin wrote:
>>>> On Thu, 28 Apr 2022 12:01:59 -0500, Dennis <dennis@none.none> wrote:
>>>>
>>>>> On 4/28/22 11:26, boB wrote:
>>>>>
>>>>>> I would love to have a super computer to run LTspice.
>>>>>>
>>>>> I thought one of the problems with LTspice (and spice in general)
>>>>> performance is that the algorithms don't parallelize very well.
>>>>
>>>> LT runs on multiple cores now. I'd love the next gen LT Spice to run
>>>> on an Nvidia card. 100x at least.
>>>>
>>>
>>> The "number of threads" setting doesn't do anything very dramatic,
>>> though, at least last time I tried. Splitting up the calculation
>>> between cores would require all of them to communicate a couple of times
>>> per time step, but lots of other simulation codes do that.
>>>
>>> The main trouble is that the matrix defining the connectivity between
>>> nodes is highly irregular in general.
>>>
>>> Parallellizing that efficiently might well need a special-purpose
>>> compiler, sort of similar to the profile-guided optimizer in the guts of
>>> the FFTW code for computing DFTs. Probably not at all impossible, but
>>> not that straightforward to implement.
>>>
>>> Cheers
>>>
>>> Phil Hobbs
>>
>> Supercomputers have thousands or hundreds of thousands of cores.
>>
>> Quote:
>>
>> "Cerebras Systems has unveiled its new Wafer Scale Engine 2 processor with
>> a record-setting 2.6 trillion transistors and 850,000 AI-optimized cores.
>> ItÂ’s built for supercomputing tasks, and itÂ’s the second time since 2019
>> that Los Altos, California-based Cerebras has unveiled a chip that is
>> basically an entire wafer."
>>
>> https://venturebeat.com/2021/04/20/cerebras-systems-launches-new-ai-
>> supercomputing-processor-with-2-6-trillion-transistors/
>
>Number of cores isn't the problem. For fairly tightly-coupled tasks
>such as simulations, the issue is interconnect latency between cores,
>and the required bandwidth goes roughly as the cube or Moore's law, so
>it ran out of gas long ago.
>
>One thing that zillions of cores could do for SPICE is to do all the
>stepped parameter runs simultaneously. At that point all you need is
>infinite bandwidth to disk.

This whole hairball is summarized in Amdahl's Law:

..<https://en.wikipedia.org/wiki/Amdahl%27s_law#:~:text=In%20computer%20architecture%2C%20Amdahl's%20law,system%20whose%20resources%20are%20improved>

Joe Gwinn

Re: supercomputer progress

<fbe6187c-c816-a168-4bdd-e840556ae7bc@electrooptical.net>

 copy mid

https://www.novabbs.com/tech/article-flat.php?id=95793&group=sci.electronics.design#95793

 copy link   Newsgroups: sci.electronics.design
Path: i2pn2.org!i2pn.org!eternal-september.org!reader02.eternal-september.org!.POSTED!not-for-mail
From: pcdhSpam...@electrooptical.net (Phil Hobbs)
Newsgroups: sci.electronics.design
Subject: Re: supercomputer progress
Date: Fri, 29 Apr 2022 20:51:43 -0400
Organization: A noiseless patient Spider
Lines: 89
Message-ID: <fbe6187c-c816-a168-4bdd-e840556ae7bc@electrooptical.net>
References: <tj4g6hd8omp97pbbs6dn146suop2dds5n6@4ax.com>
<mZKdnQszLo_T3_X_nZ2dnUU7-LXNnZ2d@giganews.com>
<fpmg6hhot88ajjqkcb6nv9mkbjm7s9q85k@4ax.com>
<0lfl6hhee2j23gr7j5epb3obpdn8s7sj3f@4ax.com> <t4eha8$ofb$1@dont-email.me>
<g5ql6h5rutblfd2busa8uops80f3j2brjv@4ax.com>
<5ec1cf9b-63f2-b060-5d37-2b534bf39d10@electrooptical.net>
<XnsAE882CD53DA0Fidtokenpost@144.76.35.252> <t4gr7b$10eu$1@gioia.aioe.org>
<hkeo6htsjjj9sqpkron34durofbg4rrnv2@4ax.com>
Mime-Version: 1.0
Content-Type: text/plain; charset=UTF-8; format=flowed
Content-Transfer-Encoding: 8bit
Injection-Info: reader02.eternal-september.org; posting-host="0c88100fd2aad7fe74b868fcfd3139c5";
logging-data="10520"; mail-complaints-to="abuse@eternal-september.org"; posting-account="U2FsdGVkX182H7JMY82BYOCpdD2ooeak"
User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:68.0) Gecko/20100101
Thunderbird/68.0
Cancel-Lock: sha1:5quItiJgbu9VhVnjDRecUY65ZBc=
In-Reply-To: <hkeo6htsjjj9sqpkron34durofbg4rrnv2@4ax.com>
 by: Phil Hobbs - Sat, 30 Apr 2022 00:51 UTC

Joe Gwinn wrote:
> On Fri, 29 Apr 2022 10:03:23 -0400, Phil Hobbs
> <pcdhSpamMeSenseless@electrooptical.net> wrote:
>
>> Mike Monett wrote:
>>> Phil Hobbs <pcdhSpamMeSenseless@electrooptical.net> wrote:
>>>
>>>> John Larkin wrote:
>>>>> On Thu, 28 Apr 2022 12:01:59 -0500, Dennis <dennis@none.none>
>>>>> wrote:
>>>>>
>>>>>> On 4/28/22 11:26, boB wrote:
>>>>>>
>>>>>>> I would love to have a super computer to run LTspice.
>>>>>>>
>>>>>> I thought one of the problems with LTspice (and spice in
>>>>>> general) performance is that the algorithms don't
>>>>>> parallelize very well.
>>>>>
>>>>> LT runs on multiple cores now. I'd love the next gen LT Spice
>>>>> to run on an Nvidia card. 100x at least.
>>>>>
>>>>
>>>> The "number of threads" setting doesn't do anything very
>>>> dramatic, though, at least last time I tried. Splitting up the
>>>> calculation between cores would require all of them to
>>>> communicate a couple of times per time step, but lots of other
>>>> simulation codes do that.
>>>>
>>>> The main trouble is that the matrix defining the connectivity
>>>> between nodes is highly irregular in general.
>>>>
>>>> Parallellizing that efficiently might well need a
>>>> special-purpose compiler, sort of similar to the profile-guided
>>>> optimizer in the guts of the FFTW code for computing DFTs.
>>>> Probably not at all impossible, but not that straightforward to
>>>> implement.
>>>>
>>>> Cheers
>>>>
>>>> Phil Hobbs
>>>
>>> Supercomputers have thousands or hundreds of thousands of cores.
>>>
>>> Quote:
>>>
>>> "Cerebras Systems has unveiled its new Wafer Scale Engine 2
>>> processor with a record-setting 2.6 trillion transistors and
>>> 850,000 AI-optimized cores. It’s built for supercomputing tasks,
>>> and it’s the second time since 2019 that Los Altos,
>>> California-based Cerebras has unveiled a chip that is basically
>>> an entire wafer."
>>>
>>> https://venturebeat.com/2021/04/20/cerebras-systems-launches-new-ai-
supercomputing-processor-with-2-6-trillion-transistors/
>>
>> Number of cores isn't the problem. For fairly tightly-coupled
>> tasks such as simulations, the issue is interconnect latency
>> between cores, and the required bandwidth goes roughly as the cube
>> or Moore's law, so it ran out of gas long ago.
>>
>> One thing that zillions of cores could do for SPICE is to do all
>> the stepped parameter runs simultaneously. At that point all you
>> need is infinite bandwidth to disk.
>
> This whole hairball is summarized in Amdahl's Law:
>
> .<https://en.wikipedia.org/wiki/Amdahl%27s_law#:~:text=In%20computer%20architecture%2C%20Amdahl's%20law,system%20whose%20resources%20are%20improved>

Not exactly. There's very little serial execution required to
parallellize parameter stepping, or even genetic-algorithm optimization.

Communications overhead isn't strictly serial either--N processors can
have several times N communication channels. It's mostly a latency issue.

Cheers

Phil Hobbs

--
Dr Philip C D Hobbs
Principal Consultant
ElectroOptical Innovations LLC / Hobbs ElectroOptics
Optics, Electro-optics, Photonics, Analog Electronics
Briarcliff Manor NY 10510

http://electrooptical.net
http://hobbs-eo.com

Re: supercomputer progress

<fkcq6hdho1lol8s3anvl0470ifchg6mmc4@4ax.com>

 copy mid

https://www.novabbs.com/tech/article-flat.php?id=95829&group=sci.electronics.design#95829

 copy link   Newsgroups: sci.electronics.design
Path: i2pn2.org!i2pn.org!weretis.net!feeder6.news.weretis.net!news.misty.com!border2.nntp.dca1.giganews.com!nntp.giganews.com!buffer2.nntp.dca1.giganews.com!buffer1.nntp.dca1.giganews.com!news.giganews.com.POSTED!not-for-mail
NNTP-Posting-Date: Sat, 30 Apr 2022 08:04:38 -0500
From: joegw...@comcast.net (Joe Gwinn)
Newsgroups: sci.electronics.design
Subject: Re: supercomputer progress
Date: Sat, 30 Apr 2022 09:04:37 -0400
Message-ID: <fkcq6hdho1lol8s3anvl0470ifchg6mmc4@4ax.com>
References: <mZKdnQszLo_T3_X_nZ2dnUU7-LXNnZ2d@giganews.com> <fpmg6hhot88ajjqkcb6nv9mkbjm7s9q85k@4ax.com> <0lfl6hhee2j23gr7j5epb3obpdn8s7sj3f@4ax.com> <t4eha8$ofb$1@dont-email.me> <g5ql6h5rutblfd2busa8uops80f3j2brjv@4ax.com> <5ec1cf9b-63f2-b060-5d37-2b534bf39d10@electrooptical.net> <XnsAE882CD53DA0Fidtokenpost@144.76.35.252> <t4gr7b$10eu$1@gioia.aioe.org> <hkeo6htsjjj9sqpkron34durofbg4rrnv2@4ax.com> <fbe6187c-c816-a168-4bdd-e840556ae7bc@electrooptical.net>
User-Agent: ForteAgent/8.00.32.1272
MIME-Version: 1.0
Content-Type: text/plain; charset=ISO-8859-1
Content-Transfer-Encoding: 8bit
Lines: 88
X-Usenet-Provider: http://www.giganews.com
X-Trace: sv3-2mQKQRM42NyzMaJKcnA+Fgl5HlXj+ZcqXdi43+eepnppno4zQR0vqbMM97eOk6XmX6Nsle1+IFbY/US!5vR+BBQCAVatZagfHrNd/fEv70orRvYYFY7beXkUQ2c1xVtF/oRNYWDu5ferLTMgWXacoz4=
X-Complaints-To: abuse@giganews.com
X-DMCA-Notifications: http://www.giganews.com/info/dmca.html
X-Abuse-and-DMCA-Info: Please be sure to forward a copy of ALL headers
X-Abuse-and-DMCA-Info: Otherwise we will be unable to process your complaint properly
X-Postfilter: 1.3.40
X-Original-Bytes: 5001
 by: Joe Gwinn - Sat, 30 Apr 2022 13:04 UTC

On Fri, 29 Apr 2022 20:51:43 -0400, Phil Hobbs
<pcdhSpamMeSenseless@electrooptical.net> wrote:

>Joe Gwinn wrote:
>> On Fri, 29 Apr 2022 10:03:23 -0400, Phil Hobbs
>> <pcdhSpamMeSenseless@electrooptical.net> wrote:
>>
>>> Mike Monett wrote:
>>>> Phil Hobbs <pcdhSpamMeSenseless@electrooptical.net> wrote:
>>>>
>>>>> John Larkin wrote:
>>>>>> On Thu, 28 Apr 2022 12:01:59 -0500, Dennis <dennis@none.none>
>>>>>> wrote:
>>>>>>
>>>>>>> On 4/28/22 11:26, boB wrote:
>>>>>>>
>>>>>>>> I would love to have a super computer to run LTspice.
>>>>>>>>
>>>>>>> I thought one of the problems with LTspice (and spice in
>>>>>>> general) performance is that the algorithms don't
>>>>>>> parallelize very well.
>>>>>>
>>>>>> LT runs on multiple cores now. I'd love the next gen LT Spice
>>>>>> to run on an Nvidia card. 100x at least.
>>>>>>
>>>>>
>>>>> The "number of threads" setting doesn't do anything very
>>>>> dramatic, though, at least last time I tried. Splitting up the
>>>>> calculation between cores would require all of them to
>>>>> communicate a couple of times per time step, but lots of other
>>>>> simulation codes do that.
>>>>>
>>>>> The main trouble is that the matrix defining the connectivity
>>>>> between nodes is highly irregular in general.
>>>>>
>>>>> Parallellizing that efficiently might well need a
>>>>> special-purpose compiler, sort of similar to the profile-guided
>>>>> optimizer in the guts of the FFTW code for computing DFTs.
>>>>> Probably not at all impossible, but not that straightforward to
>>>>> implement.
>>>>>
>>>>> Cheers
>>>>>
>>>>> Phil Hobbs
>>>>
>>>> Supercomputers have thousands or hundreds of thousands of cores.
>>>>
>>>> Quote:
>>>>
>>>> "Cerebras Systems has unveiled its new Wafer Scale Engine 2
>>>> processor with a record-setting 2.6 trillion transistors and
>>>> 850,000 AI-optimized cores. ItÂ’s built for supercomputing tasks,
>>>> and itÂ’s the second time since 2019 that Los Altos,
>>>> California-based Cerebras has unveiled a chip that is basically
>>>> an entire wafer."
>>>>
>>>> https://venturebeat.com/2021/04/20/cerebras-systems-launches-new-ai-
>supercomputing-processor-with-2-6-trillion-transistors/
>>>
>>> Number of cores isn't the problem. For fairly tightly-coupled
>>> tasks such as simulations, the issue is interconnect latency
>>> between cores, and the required bandwidth goes roughly as the cube
>>> or Moore's law, so it ran out of gas long ago.
>>>
>>> One thing that zillions of cores could do for SPICE is to do all
>>> the stepped parameter runs simultaneously. At that point all you
>>> need is infinite bandwidth to disk.
>>
>> This whole hairball is summarized in Amdahl's Law:
>>
>> .<https://en.wikipedia.org/wiki/Amdahl%27s_law#:~:text=In%20computer%20architecture%2C%20Amdahl's%20law,system%20whose%20resources%20are%20improved>
>
>Not exactly. There's very little serial execution required to
>parallellize parameter stepping, or even genetic-algorithm optimization.
>
>Communications overhead isn't strictly serial either--N processors can
>have several times N communication channels. It's mostly a latency issue.

In general, yes. But far too far down in the weeds.

Amdahl's Law is easier to explain to a business manager that thinks
that parallelism solves all performance issues, if only the engineers
would stop carping and do their jobs.

And then there are the architectures that would do wondrous things, if
only light were not so damn slow.

Joe Gwinn

Re: supercomputer progress

<8112aa60-77c1-493d-80f0-9bd48a3b47b3n@googlegroups.com>

 copy mid

https://www.novabbs.com/tech/article-flat.php?id=95836&group=sci.electronics.design#95836

 copy link   Newsgroups: sci.electronics.design
X-Received: by 2002:ad4:5f06:0:b0:446:e96:b193 with SMTP id fo6-20020ad45f06000000b004460e96b193mr3088978qvb.100.1651327363691;
Sat, 30 Apr 2022 07:02:43 -0700 (PDT)
X-Received: by 2002:a81:855:0:b0:2f8:9123:c97e with SMTP id
82-20020a810855000000b002f89123c97emr3968970ywi.343.1651327363432; Sat, 30
Apr 2022 07:02:43 -0700 (PDT)
Path: i2pn2.org!i2pn.org!weretis.net!feeder6.news.weretis.net!news.misty.com!border2.nntp.dca1.giganews.com!nntp.giganews.com!news-out.google.com!nntp.google.com!postnews.google.com!google-groups.googlegroups.com!not-for-mail
Newsgroups: sci.electronics.design
Date: Sat, 30 Apr 2022 07:02:43 -0700 (PDT)
In-Reply-To: <fkcq6hdho1lol8s3anvl0470ifchg6mmc4@4ax.com>
Injection-Info: google-groups.googlegroups.com; posting-host=24.138.223.107; posting-account=I-_H_woAAAA9zzro6crtEpUAyIvzd19b
NNTP-Posting-Host: 24.138.223.107
References: <mZKdnQszLo_T3_X_nZ2dnUU7-LXNnZ2d@giganews.com>
<fpmg6hhot88ajjqkcb6nv9mkbjm7s9q85k@4ax.com> <0lfl6hhee2j23gr7j5epb3obpdn8s7sj3f@4ax.com>
<t4eha8$ofb$1@dont-email.me> <g5ql6h5rutblfd2busa8uops80f3j2brjv@4ax.com>
<5ec1cf9b-63f2-b060-5d37-2b534bf39d10@electrooptical.net> <XnsAE882CD53DA0Fidtokenpost@144.76.35.252>
<t4gr7b$10eu$1@gioia.aioe.org> <hkeo6htsjjj9sqpkron34durofbg4rrnv2@4ax.com>
<fbe6187c-c816-a168-4bdd-e840556ae7bc@electrooptical.net> <fkcq6hdho1lol8s3anvl0470ifchg6mmc4@4ax.com>
User-Agent: G2/1.0
MIME-Version: 1.0
Message-ID: <8112aa60-77c1-493d-80f0-9bd48a3b47b3n@googlegroups.com>
Subject: Re: supercomputer progress
From: gnuarm.d...@gmail.com (Ricky)
Injection-Date: Sat, 30 Apr 2022 14:02:43 +0000
Content-Type: text/plain; charset="UTF-8"
Content-Transfer-Encoding: quoted-printable
Lines: 112
 by: Ricky - Sat, 30 Apr 2022 14:02 UTC

On Saturday, April 30, 2022 at 9:04:50 AM UTC-4, Joe Gwinn wrote:
> On Fri, 29 Apr 2022 20:51:43 -0400, Phil Hobbs
> <pcdhSpamM...@electrooptical.net> wrote:
>
> >Joe Gwinn wrote:
> >> On Fri, 29 Apr 2022 10:03:23 -0400, Phil Hobbs
> >> <pcdhSpamM...@electrooptical.net> wrote:
> >>
> >>> Mike Monett wrote:
> >>>> Phil Hobbs <pcdhSpamM...@electrooptical.net> wrote:
> >>>>
> >>>>> John Larkin wrote:
> >>>>>> On Thu, 28 Apr 2022 12:01:59 -0500, Dennis <den...@none.none>
> >>>>>> wrote:
> >>>>>>
> >>>>>>> On 4/28/22 11:26, boB wrote:
> >>>>>>>
> >>>>>>>> I would love to have a super computer to run LTspice.
> >>>>>>>>
> >>>>>>> I thought one of the problems with LTspice (and spice in
> >>>>>>> general) performance is that the algorithms don't
> >>>>>>> parallelize very well.
> >>>>>>
> >>>>>> LT runs on multiple cores now. I'd love the next gen LT Spice
> >>>>>> to run on an Nvidia card. 100x at least.
> >>>>>>
> >>>>>
> >>>>> The "number of threads" setting doesn't do anything very
> >>>>> dramatic, though, at least last time I tried. Splitting up the
> >>>>> calculation between cores would require all of them to
> >>>>> communicate a couple of times per time step, but lots of other
> >>>>> simulation codes do that.
> >>>>>
> >>>>> The main trouble is that the matrix defining the connectivity
> >>>>> between nodes is highly irregular in general.
> >>>>>
> >>>>> Parallellizing that efficiently might well need a
> >>>>> special-purpose compiler, sort of similar to the profile-guided
> >>>>> optimizer in the guts of the FFTW code for computing DFTs.
> >>>>> Probably not at all impossible, but not that straightforward to
> >>>>> implement.
> >>>>>
> >>>>> Cheers
> >>>>>
> >>>>> Phil Hobbs
> >>>>
> >>>> Supercomputers have thousands or hundreds of thousands of cores.
> >>>>
> >>>> Quote:
> >>>>
> >>>> "Cerebras Systems has unveiled its new Wafer Scale Engine 2
> >>>> processor with a record-setting 2.6 trillion transistors and
> >>>> 850,000 AI-optimized cores. It’s built for supercomputing tasks,
> >>>> and it’s the second time since 2019 that Los Altos,
> >>>> California-based Cerebras has unveiled a chip that is basically
> >>>> an entire wafer."
> >>>>
> >>>> https://venturebeat.com/2021/04/20/cerebras-systems-launches-new-ai-
> >supercomputing-processor-with-2-6-trillion-transistors/
> >>>
> >>> Number of cores isn't the problem. For fairly tightly-coupled
> >>> tasks such as simulations, the issue is interconnect latency
> >>> between cores, and the required bandwidth goes roughly as the cube
> >>> or Moore's law, so it ran out of gas long ago.
> >>>
> >>> One thing that zillions of cores could do for SPICE is to do all
> >>> the stepped parameter runs simultaneously. At that point all you
> >>> need is infinite bandwidth to disk.
> >>
> >> This whole hairball is summarized in Amdahl's Law:
> >>
> >> .<https://en.wikipedia.org/wiki/Amdahl%27s_law#:~:text=In%20computer%20architecture%2C%20Amdahl's%20law,system%20whose%20resources%20are%20improved>
> >
> >Not exactly. There's very little serial execution required to
> >parallellize parameter stepping, or even genetic-algorithm optimization.
> >
> >Communications overhead isn't strictly serial either--N processors can
> >have several times N communication channels. It's mostly a latency issue..
> In general, yes. But far too far down in the weeds.
>
> Amdahl's Law is easier to explain to a business manager that thinks
> that parallelism solves all performance issues, if only the engineers
> would stop carping and do their jobs.
>
> And then there are the architectures that would do wondrous things, if
> only light were not so damn slow.

People often focus on the fact that the size of the chip limits the speed without considering how the size might be reduced (and the speed increased) using multi-valued logic. I suppose the devil is in the details, but if more information can be carried on fewer wires, the routing area of a chip can be reduced, speeding the entire chip.

I've only heard of memory type circuits being implemented with multivalued logic, since the bulk of the die area is storage and that shrinks considerably. I believe they are up to 16 values, so four bits in place of one, but I only see TLC which has 8 values per cell. Logic chips are much harder to find using multi-valued logic. Obviously there are issues with making them work well.

--

Rick C.

+- Get 1,000 miles of free Supercharging
+- Tesla referral code - https://ts.la/richard11209

Re: supercomputer progress

<t4lkuk$1hrf$1@gioia.aioe.org>

 copy mid

https://www.novabbs.com/tech/article-flat.php?id=95921&group=sci.electronics.design#95921

 copy link   Newsgroups: sci.electronics.design
Path: i2pn2.org!i2pn.org!aioe.org!woWShB6DIQvlDBD7PkJe+g.user.46.165.242.75.POSTED!not-for-mail
From: '''newsp...@nonad.co.uk (Martin Brown)
Newsgroups: sci.electronics.design
Subject: Re: supercomputer progress
Date: Sun, 1 May 2022 10:46:58 +0100
Organization: Aioe.org NNTP Server
Message-ID: <t4lkuk$1hrf$1@gioia.aioe.org>
References: <tj4g6hd8omp97pbbs6dn146suop2dds5n6@4ax.com>
<mZKdnQszLo_T3_X_nZ2dnUU7-LXNnZ2d@giganews.com>
<fpmg6hhot88ajjqkcb6nv9mkbjm7s9q85k@4ax.com>
<0lfl6hhee2j23gr7j5epb3obpdn8s7sj3f@4ax.com> <t4eha8$ofb$1@dont-email.me>
<g5ql6h5rutblfd2busa8uops80f3j2brjv@4ax.com>
<5ec1cf9b-63f2-b060-5d37-2b534bf39d10@electrooptical.net>
<XnsAE882CD53DA0Fidtokenpost@144.76.35.252> <t4gr7b$10eu$1@gioia.aioe.org>
<hkeo6htsjjj9sqpkron34durofbg4rrnv2@4ax.com>
<fbe6187c-c816-a168-4bdd-e840556ae7bc@electrooptical.net>
Mime-Version: 1.0
Content-Type: text/plain; charset=UTF-8; format=flowed
Content-Transfer-Encoding: 8bit
Injection-Info: gioia.aioe.org; logging-data="51055"; posting-host="woWShB6DIQvlDBD7PkJe+g.user.gioia.aioe.org"; mail-complaints-to="abuse@aioe.org";
User-Agent: Mozilla/5.0 (Windows NT 6.1; Win64; x64; rv:91.0) Gecko/20100101
Thunderbird/91.8.1
Content-Language: en-GB
X-Notice: Filtered by postfilter v. 0.9.2
 by: Martin Brown - Sun, 1 May 2022 09:46 UTC

On 30/04/2022 01:51, Phil Hobbs wrote:
> Joe Gwinn wrote:
>> On Fri, 29 Apr 2022 10:03:23 -0400, Phil Hobbs
>> <pcdhSpamMeSenseless@electrooptical.net> wrote:
>>

>>> Number of cores isn't the problem.  For fairly tightly-coupled
>>> tasks such as simulations, the issue is interconnect latency
>>> between cores, and the required bandwidth goes roughly as the cube
>>> or Moore's law, so it ran out of gas long ago.
>>>
>>> One thing that zillions of cores could do for SPICE is to do all
>>> the stepped parameter runs simultaneously.  At that point all you
>>> need is infinite bandwidth to disk.

Parallelism for exploring a wide range starting parameters and then
evolving them based on how well the model fits seems to be in vogue now. eg

https://arxiv.org/abs/1804.04737

>> This whole hairball is summarized in Amdahl's Law:
>>
>> .<https://en.wikipedia.org/wiki/Amdahl%27s_law#:~:text=In%20computer%20architecture%2C%20Amdahl's%20law,system%20whose%20resources%20are%20improved>
>>
>
> Not exactly.  There's very little serial execution required to
> parallellize parameter stepping, or even genetic-algorithm optimization.
>
> Communications overhead isn't strictly serial either--N processors can
> have several times N communication channels.  It's mostly a latency issue.

Anyone who has ever done it quickly learns that by far the most
important highest priority task is the not the computation itself but
the management required to keep all of the cores doing useful work!

It is easy to have all cores working flat out but if most of the
parallelised work being done so quickly will be later shown to be
redundant due to some higher level pruning algorithm all you are doing
is generating more heat and only a miniscule performance gain (if that).

SIMD has made quite a performance improvement for some problems on the
Intel and AMD platforms. The compilers still haven't quite caught up
with the hardware though. Alignment is now a rather annoying issue if
you care about avoiding unnecessary cache misses and pipeline stalls.

You can align your own structures correctly but can do nothing about
virtual structures that the compiler creates and puts on the stack
misaligned spanning two cache lines. The result is code which executes
with two distinct characteristic times depending on where the cache line
boundaries are in relation the top of stack when it is called!

It really only matters in the very deepest levels of computationally
intensive code which is probably why they don't try quite hard enough.
Most people probably wouldn't notice ~5% changes unless they were
benchmarking or monitoring MSRs for cache misses and pipeline stalls.

--
Regards,
Martin Brown

Re: supercomputer progress

<969a1e76-0c38-31fd-3e9d-363884a078c2@electrooptical.net>

 copy mid

https://www.novabbs.com/tech/article-flat.php?id=95924&group=sci.electronics.design#95924

 copy link   Newsgroups: sci.electronics.design
Path: i2pn2.org!i2pn.org!eternal-september.org!reader02.eternal-september.org!.POSTED!not-for-mail
From: pcdhSpam...@electrooptical.net (Phil Hobbs)
Newsgroups: sci.electronics.design
Subject: Re: supercomputer progress
Date: Sun, 1 May 2022 06:08:49 -0400
Organization: A noiseless patient Spider
Lines: 87
Message-ID: <969a1e76-0c38-31fd-3e9d-363884a078c2@electrooptical.net>
References: <tj4g6hd8omp97pbbs6dn146suop2dds5n6@4ax.com>
<mZKdnQszLo_T3_X_nZ2dnUU7-LXNnZ2d@giganews.com>
<fpmg6hhot88ajjqkcb6nv9mkbjm7s9q85k@4ax.com>
<0lfl6hhee2j23gr7j5epb3obpdn8s7sj3f@4ax.com> <t4eha8$ofb$1@dont-email.me>
<g5ql6h5rutblfd2busa8uops80f3j2brjv@4ax.com>
<5ec1cf9b-63f2-b060-5d37-2b534bf39d10@electrooptical.net>
<XnsAE882CD53DA0Fidtokenpost@144.76.35.252> <t4gr7b$10eu$1@gioia.aioe.org>
<hkeo6htsjjj9sqpkron34durofbg4rrnv2@4ax.com>
<fbe6187c-c816-a168-4bdd-e840556ae7bc@electrooptical.net>
<t4lkuk$1hrf$1@gioia.aioe.org>
Mime-Version: 1.0
Content-Type: text/plain; charset=UTF-8; format=flowed
Content-Transfer-Encoding: 8bit
Injection-Info: reader02.eternal-september.org; posting-host="d58d56c4e9a39e5836a1531e4c897e7a";
logging-data="24594"; mail-complaints-to="abuse@eternal-september.org"; posting-account="U2FsdGVkX18cb2lk72JeYr5Qz53zKIoq"
User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:68.0) Gecko/20100101
Thunderbird/68.0
Cancel-Lock: sha1:JHwu6PvhHb05AvSmhMN5piuAlcA=
In-Reply-To: <t4lkuk$1hrf$1@gioia.aioe.org>
 by: Phil Hobbs - Sun, 1 May 2022 10:08 UTC

Martin Brown wrote:
> On 30/04/2022 01:51, Phil Hobbs wrote:
>> Joe Gwinn wrote:
>>> On Fri, 29 Apr 2022 10:03:23 -0400, Phil Hobbs
>>> <pcdhSpamMeSenseless@electrooptical.net> wrote:
>>>
>
>>>> Number of cores isn't the problem.  For fairly tightly-coupled
>>>> tasks such as simulations, the issue is interconnect latency
>>>> between cores, and the required bandwidth goes roughly as the cube
>>>> or Moore's law, so it ran out of gas long ago.
>>>>
>>>> One thing that zillions of cores could do for SPICE is to do all
>>>> the stepped parameter runs simultaneously.  At that point all you
>>>> need is infinite bandwidth to disk.
>
> Parallelism for exploring a wide range starting parameters and then
> evolving them based on how well the model fits seems to be in vogue now. eg
>
> https://arxiv.org/abs/1804.04737
>
>>> This whole hairball is summarized in Amdahl's Law:
>>>
>>> .<https://en.wikipedia.org/wiki/Amdahl%27s_law#:~:text=In%20computer%20architecture%2C%20Amdahl's%20law,system%20whose%20resources%20are%20improved>
>>>
>>
>> Not exactly.  There's very little serial execution required to
>> parallellize parameter stepping, or even genetic-algorithm optimization.
>>
>> Communications overhead isn't strictly serial either--N processors can
>> have several times N communication channels.  It's mostly a latency
>> issue.
>
> Anyone who has ever done it quickly learns that by far the most
> important highest priority task is the not the computation itself but
> the management required to keep all of the cores doing useful work!

Yup. In my big EM code, that's handled by The Cluster Script From Hell. ;)

>
> It is easy to have all cores working flat out but if most of the
> parallelised work being done so quickly will be later shown to be
> redundant due to some higher level pruning algorithm all you are doing
> is generating more heat and only a miniscule performance gain (if that).
>
> SIMD has made quite a performance improvement for some problems on the
> Intel and AMD platforms. The compilers still haven't quite caught up
> with the hardware though. Alignment is now a rather annoying issue if
> you care about avoiding unnecessary cache misses and pipeline stalls.
>
> You can align your own structures correctly but can do nothing about
> virtual structures that the compiler creates and puts on the stack
> misaligned spanning two cache lines. The result is code which executes
> with two distinct characteristic times depending on where the cache line
> boundaries are in relation the top of stack when it is called!
>
> It really only matters in the very deepest levels of computationally
> intensive code which is probably why they don't try quite hard enough.
> Most people probably wouldn't notice ~5% changes unless they were
> benchmarking or monitoring MSRs for cache misses and pipeline stalls.

Well, your average hardcore numerical guy would proably just buy two
clusters and pick the one that finished first. ;)

Fifteen or so years ago, I got about a 3:1 improvement in FDTD speed by
precomputing a strategy that let me iterate over a list containing runs
of voxels with the same material, vs. just putting a big switch
statement inside a triply-nested loop (the usual approach).

I mentioned it to another EM simulation guy at a conference once, who
said, "So what? I'd just get a bigger cluster."

Cheers

Phil Hobbs

--
Dr Philip C D Hobbs
Principal Consultant
ElectroOptical Innovations LLC / Hobbs ElectroOptics
Optics, Electro-optics, Photonics, Analog Electronics
Briarcliff Manor NY 10510

http://electrooptical.net
http://hobbs-eo.com

Re: supercomputer progress

<t4s5sj$4v$1@reader1.panix.com>

 copy mid

https://www.novabbs.com/tech/article-flat.php?id=96148&group=sci.electronics.design#96148

 copy link   Newsgroups: sci.electronics.design
Path: i2pn2.org!i2pn.org!weretis.net!feeder6.news.weretis.net!panix!.POSTED.panix2.panix.com!not-for-mail
From: prese...@MUNGEpanix.com (Cydrome Leader)
Newsgroups: sci.electronics.design
Subject: Re: supercomputer progress
Date: Tue, 3 May 2022 21:12:52 -0000 (UTC)
Organization: PANIX Public Access Internet and UNIX, NYC
Message-ID: <t4s5sj$4v$1@reader1.panix.com>
References: <tj4g6hd8omp97pbbs6dn146suop2dds5n6@4ax.com> <mZKdnQszLo_T3_X_nZ2dnUU7-LXNnZ2d@giganews.com> <fpmg6hhot88ajjqkcb6nv9mkbjm7s9q85k@4ax.com> <0lfl6hhee2j23gr7j5epb3obpdn8s7sj3f@4ax.com> <t4ejuo$7n8$1@gioia.aioe.org> <t4g872$ll$1@gioia.aioe.org>
Injection-Date: Tue, 3 May 2022 21:12:52 -0000 (UTC)
Injection-Info: reader1.panix.com; posting-host="panix2.panix.com:166.84.1.2";
logging-data="159"; mail-complaints-to="abuse@panix.com"
User-Agent: tin/2.6.0-20210823 ("Coleburn") (NetBSD/9.2 (amd64))
 by: Cydrome Leader - Tue, 3 May 2022 21:12 UTC

Martin Brown <'''newspam'''@nonad.co.uk> wrote:
> On 28/04/2022 18:47, Jeroen Belleman wrote:
>> On 2022-04-28 18:26, boB wrote:
>> [...]
>>> I would love to have a super computer to run LTspice.
>>>
>>> boB
>>
>> In fact, what you have on your desk *is* a super computer,
>> in the 1970's meaning of the words. It's just that it's
>> bogged down running bloatware.
>
> Indeed. The Cray X-MP in its 4 CPU configuration with a 105MHz clock and
> a whopping for the time 128MB of fast core memory with 40GB of disk. The

what is fast core memory?

> one I used had an amazing for the time 1TB tape cassette backing store.
> It did 600 MFLOPs with the right sort of parallel vector code.
>
> That was back in the day when you needed special permission to use more
> than 4MB of core on the timesharing IBM 3081 (approx 7 MIPS).
>
> Current Intel 12 gen CPU desktops are ~4GHz, 16GB ram and >1TB of disk.
> (and the upper limits are even higher) That combo does ~66,000 MFLOPS.
>
> Spice simulation doesn't scale particularly well to large scale
> multiprocessor environments to many long range interractions.
>

Re: supercomputer progress

<a7f5b2f5-3b81-4298-985c-1bbec41ed982n@googlegroups.com>

 copy mid

https://www.novabbs.com/tech/article-flat.php?id=96153&group=sci.electronics.design#96153

 copy link   Newsgroups: sci.electronics.design
X-Received: by 2002:a05:6214:d85:b0:449:96f7:6194 with SMTP id e5-20020a0562140d8500b0044996f76194mr15962135qve.48.1651623887652;
Tue, 03 May 2022 17:24:47 -0700 (PDT)
X-Received: by 2002:a81:1051:0:b0:2f7:e466:fcd0 with SMTP id
78-20020a811051000000b002f7e466fcd0mr17200141ywq.294.1651623887513; Tue, 03
May 2022 17:24:47 -0700 (PDT)
Path: i2pn2.org!i2pn.org!weretis.net!feeder6.news.weretis.net!news.misty.com!border2.nntp.dca1.giganews.com!nntp.giganews.com!news-out.google.com!nntp.google.com!postnews.google.com!google-groups.googlegroups.com!not-for-mail
Newsgroups: sci.electronics.design
Date: Tue, 3 May 2022 17:24:47 -0700 (PDT)
In-Reply-To: <1itn6h5p41i7js3cq6tao96udor44ccvlm@4ax.com>
Injection-Info: google-groups.googlegroups.com; posting-host=209.221.140.126; posting-account=vKQm_QoAAADOaDCYsqOFDAW8NJ8sFHoE
NNTP-Posting-Host: 209.221.140.126
References: <tj4g6hd8omp97pbbs6dn146suop2dds5n6@4ax.com> <mZKdnQszLo_T3_X_nZ2dnUU7-LXNnZ2d@giganews.com>
<fpmg6hhot88ajjqkcb6nv9mkbjm7s9q85k@4ax.com> <0lfl6hhee2j23gr7j5epb3obpdn8s7sj3f@4ax.com>
<t4eha8$ofb$1@dont-email.me> <g5ql6h5rutblfd2busa8uops80f3j2brjv@4ax.com>
<5ec1cf9b-63f2-b060-5d37-2b534bf39d10@electrooptical.net> <1itn6h5p41i7js3cq6tao96udor44ccvlm@4ax.com>
User-Agent: G2/1.0
MIME-Version: 1.0
Message-ID: <a7f5b2f5-3b81-4298-985c-1bbec41ed982n@googlegroups.com>
Subject: Re: supercomputer progress
From: whit...@gmail.com (whit3rd)
Injection-Date: Wed, 04 May 2022 00:24:47 +0000
Content-Type: text/plain; charset="UTF-8"
Lines: 8
 by: whit3rd - Wed, 4 May 2022 00:24 UTC

On Friday, April 29, 2022 at 7:30:55 AM UTC-7, jla...@highlandsniptechnology.com wrote:

> Climate simulation uses enormous multi-CPU supercomputer rigs.

Not so; it's WEATHER mapping and prediction that uses the complex data sets
for a varied bunch of globe locations doing sensing, to make a 3-d map for
the planet's atmosphere. Climate is a much cruder problem, no details
required. Much of the greenhouse gas analysis comes out of models
that a PC spreadsheet would handle easily.

Re: supercomputer progress

<jde73uFj8b1U1@mid.individual.net>

 copy mid

https://www.novabbs.com/tech/article-flat.php?id=96162&group=sci.electronics.design#96162

 copy link   Newsgroups: sci.electronics.design
Path: i2pn2.org!i2pn.org!weretis.net!feeder8.news.weretis.net!news.szaf.org!fu-berlin.de!uni-berlin.de!individual.net!not-for-mail
From: bow...@montana.com (rbowman)
Newsgroups: sci.electronics.design
Subject: Re: supercomputer progress
Date: Tue, 3 May 2022 20:35:45 -0600
Lines: 21
Message-ID: <jde73uFj8b1U1@mid.individual.net>
References: <tj4g6hd8omp97pbbs6dn146suop2dds5n6@4ax.com>
<mZKdnQszLo_T3_X_nZ2dnUU7-LXNnZ2d@giganews.com>
<fpmg6hhot88ajjqkcb6nv9mkbjm7s9q85k@4ax.com>
<0lfl6hhee2j23gr7j5epb3obpdn8s7sj3f@4ax.com> <t4ejuo$7n8$1@gioia.aioe.org>
<t4g872$ll$1@gioia.aioe.org> <t4s5sj$4v$1@reader1.panix.com>
Mime-Version: 1.0
Content-Type: text/plain; charset=windows-1252; format=flowed
Content-Transfer-Encoding: 7bit
X-Trace: individual.net P8d6wgLybybx6FBcfC86YgN4WyjpyN5lM1pZM5GIgBNqkhoG4f
Cancel-Lock: sha1:WYL2sun7My42hH3441rxu9sNqOM=
User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:45.0) Gecko/20100101
Thunderbird/45.6.0
In-Reply-To: <t4s5sj$4v$1@reader1.panix.com>
 by: rbowman - Wed, 4 May 2022 02:35 UTC

On 05/03/2022 03:12 PM, Cydrome Leader wrote:
> Martin Brown <'''newspam'''@nonad.co.uk> wrote:
>> On 28/04/2022 18:47, Jeroen Belleman wrote:
>>> On 2022-04-28 18:26, boB wrote:
>>> [...]
>>>> I would love to have a super computer to run LTspice.
>>>>
>>>> boB
>>> In fact, what you have on your desk *is* a super computer,
>>> in the 1970's meaning of the words. It's just that it's
>>> bogged down running bloatware.
>> Indeed. The Cray X-MP in its 4 CPU configuration with a 105MHz clock and
>> a whopping for the time 128MB of fast core memory with 40GB of disk. The
> what is fast core memory?
>

A very expensive item:

https://en.wikipedia.org/wiki/Magnetic-core_memory

Fortunately by the X-MP's time SRAMs had replaced magnetic core.

Re: supercomputer progress

<72c66b4e-42dc-45bb-b019-3cab71493113n@googlegroups.com>

 copy mid

https://www.novabbs.com/tech/article-flat.php?id=96178&group=sci.electronics.design#96178

 copy link   Newsgroups: sci.electronics.design
X-Received: by 2002:a05:6214:21a7:b0:441:1434:eafd with SMTP id t7-20020a05621421a700b004411434eafdmr16181390qvc.77.1651640958587;
Tue, 03 May 2022 22:09:18 -0700 (PDT)
X-Received: by 2002:a25:35c5:0:b0:641:dab1:5ef9 with SMTP id
c188-20020a2535c5000000b00641dab15ef9mr16602142yba.396.1651640958371; Tue, 03
May 2022 22:09:18 -0700 (PDT)
Path: i2pn2.org!i2pn.org!weretis.net!feeder6.news.weretis.net!news.misty.com!border2.nntp.dca1.giganews.com!nntp.giganews.com!news-out.google.com!nntp.google.com!postnews.google.com!google-groups.googlegroups.com!not-for-mail
Newsgroups: sci.electronics.design
Date: Tue, 3 May 2022 22:09:18 -0700 (PDT)
In-Reply-To: <t4s5sj$4v$1@reader1.panix.com>
Injection-Info: google-groups.googlegroups.com; posting-host=24.139.221.223; posting-account=I-_H_woAAAA9zzro6crtEpUAyIvzd19b
NNTP-Posting-Host: 24.139.221.223
References: <tj4g6hd8omp97pbbs6dn146suop2dds5n6@4ax.com> <mZKdnQszLo_T3_X_nZ2dnUU7-LXNnZ2d@giganews.com>
<fpmg6hhot88ajjqkcb6nv9mkbjm7s9q85k@4ax.com> <0lfl6hhee2j23gr7j5epb3obpdn8s7sj3f@4ax.com>
<t4ejuo$7n8$1@gioia.aioe.org> <t4g872$ll$1@gioia.aioe.org> <t4s5sj$4v$1@reader1.panix.com>
User-Agent: G2/1.0
MIME-Version: 1.0
Message-ID: <72c66b4e-42dc-45bb-b019-3cab71493113n@googlegroups.com>
Subject: Re: supercomputer progress
From: gnuarm.d...@gmail.com (Ricky)
Injection-Date: Wed, 04 May 2022 05:09:18 +0000
Content-Type: text/plain; charset="UTF-8"
Lines: 24
 by: Ricky - Wed, 4 May 2022 05:09 UTC

On Tuesday, May 3, 2022 at 5:12:59 PM UTC-4, Cydrome Leader wrote:
> Martin Brown <'''newspam'''@nonad.co.uk> wrote:
> > On 28/04/2022 18:47, Jeroen Belleman wrote:
> >> On 2022-04-28 18:26, boB wrote:
> >> [...]
> >>> I would love to have a super computer to run LTspice.
> >>>
> >>> boB
> >>
> >> In fact, what you have on your desk *is* a super computer,
> >> in the 1970's meaning of the words. It's just that it's
> >> bogged down running bloatware.
> >
> > Indeed. The Cray X-MP in its 4 CPU configuration with a 105MHz clock and
> > a whopping for the time 128MB of fast core memory with 40GB of disk. The
> what is fast core memory?

An oxymoron.

--

Rick C.

++ Get 1,000 miles of free Supercharging
++ Tesla referral code - https://ts.la/richard11209

Re: supercomputer progress

<t4t36f$v27$1@gioia.aioe.org>

 copy mid

https://www.novabbs.com/tech/article-flat.php?id=96198&group=sci.electronics.design#96198

 copy link   Newsgroups: sci.electronics.design
Path: i2pn2.org!i2pn.org!aioe.org!5U2ooNuM5UP0Ynf/GmOnCg.user.46.165.242.91.POSTED!not-for-mail
From: Decadent...@decadence.org
Newsgroups: sci.electronics.design
Subject: Re: supercomputer progress
Date: Wed, 4 May 2022 05:33:04 -0000 (UTC)
Organization: Aioe.org NNTP Server
Message-ID: <t4t36f$v27$1@gioia.aioe.org>
References: <tj4g6hd8omp97pbbs6dn146suop2dds5n6@4ax.com> <mZKdnQszLo_T3_X_nZ2dnUU7-LXNnZ2d@giganews.com> <fpmg6hhot88ajjqkcb6nv9mkbjm7s9q85k@4ax.com> <0lfl6hhee2j23gr7j5epb3obpdn8s7sj3f@4ax.com> <t4eha8$ofb$1@dont-email.me> <g5ql6h5rutblfd2busa8uops80f3j2brjv@4ax.com> <5ec1cf9b-63f2-b060-5d37-2b534bf39d10@electrooptical.net> <1itn6h5p41i7js3cq6tao96udor44ccvlm@4ax.com> <a7f5b2f5-3b81-4298-985c-1bbec41ed982n@googlegroups.com>
Injection-Info: gioia.aioe.org; logging-data="31815"; posting-host="5U2ooNuM5UP0Ynf/GmOnCg.user.gioia.aioe.org"; mail-complaints-to="abuse@aioe.org";
User-Agent: Xnews/5.04.25
X-Notice: Filtered by postfilter v. 0.9.2
 by: Decadent...@decadence.org - Wed, 4 May 2022 05:33 UTC

whit3rd <whit3rd@gmail.com> wrote in
news:a7f5b2f5-3b81-4298-985c-1bbec41ed982n@googlegroups.com:

> On Friday, April 29, 2022 at 7:30:55 AM UTC-7,
> jla...@highlandsniptechnology.com wrote:
>
>> Climate simulation uses enormous multi-CPU supercomputer rigs.
>
> Not so; it's WEATHER mapping and prediction that uses the complex
> data sets for a varied bunch of globe locations doing sensing, to
> make a 3-d map for the planet's atmosphere. Climate is a much
> cruder problem, no details required. Much of the greenhouse gas
> analysis comes out of models that a PC spreadsheet would handle
> easily.
>

We have real time sat imagery of our weather patterns.

*I* can see what is coming or not. The forecasting tool does not
do that great a job and is it my phone's computer's forcast or coming
from the site feeding me the weather imagery? Either way it aint that
great and hardly the main utilization factor.

Weather modeling is done on a bigger scale looking at storm systems
crossing the ocean in our direction (US).

Our local stuff used to be predicted by individual opinions of
local meteorologists. Now even they all rely on a nationally
available data set, which is where my app from a Michigan TV station
sources its data. The app works fine here, hundreds of miles away.

My phone is great. I also have an anatomy app on there and I can
look at individual piece of cartilage and it will tell me what its
name is. It looks real cool on my iPad. I have one for the brain as
well.

Movies used to take hours and hours of frame rendering time to
'render' a frame of movie video and all the CGI was in its infancy.

Now I have a multi-core Xeon and a Quadro graphics card and can do
3D rendering at 4K resolution.
And they just came out with Unreal Engine 5. It is friggin'
amazing how far they've come.

<https://www.youtube.com/watch?v=7ZLibi6s_ew>

Re: supercomputer progress

<t4tc7j$ddp$1@gioia.aioe.org>

 copy mid

https://www.novabbs.com/tech/article-flat.php?id=96212&group=sci.electronics.design#96212

 copy link   Newsgroups: sci.electronics.design
Path: i2pn2.org!i2pn.org!aioe.org!woWShB6DIQvlDBD7PkJe+g.user.46.165.242.75.POSTED!not-for-mail
From: '''newsp...@nonad.co.uk (Martin Brown)
Newsgroups: sci.electronics.design
Subject: Re: supercomputer progress
Date: Wed, 4 May 2022 09:07:13 +0100
Organization: Aioe.org NNTP Server
Message-ID: <t4tc7j$ddp$1@gioia.aioe.org>
References: <tj4g6hd8omp97pbbs6dn146suop2dds5n6@4ax.com>
<mZKdnQszLo_T3_X_nZ2dnUU7-LXNnZ2d@giganews.com>
<fpmg6hhot88ajjqkcb6nv9mkbjm7s9q85k@4ax.com>
<0lfl6hhee2j23gr7j5epb3obpdn8s7sj3f@4ax.com> <t4ejuo$7n8$1@gioia.aioe.org>
<t4g872$ll$1@gioia.aioe.org> <t4s5sj$4v$1@reader1.panix.com>
<jde73uFj8b1U1@mid.individual.net>
Mime-Version: 1.0
Content-Type: text/plain; charset=UTF-8; format=flowed
Content-Transfer-Encoding: 7bit
Injection-Info: gioia.aioe.org; logging-data="13753"; posting-host="woWShB6DIQvlDBD7PkJe+g.user.gioia.aioe.org"; mail-complaints-to="abuse@aioe.org";
User-Agent: Mozilla/5.0 (Windows NT 6.1; Win64; x64; rv:91.0) Gecko/20100101
Thunderbird/91.8.1
X-Notice: Filtered by postfilter v. 0.9.2
Content-Language: en-GB
 by: Martin Brown - Wed, 4 May 2022 08:07 UTC

On 04/05/2022 03:35, rbowman wrote:
> On 05/03/2022 03:12 PM, Cydrome Leader wrote:
>> Martin Brown <'''newspam'''@nonad.co.uk> wrote:
>>> On 28/04/2022 18:47, Jeroen Belleman wrote:
>>>> On 2022-04-28 18:26, boB wrote:
>>>> [...]
>>>>> I would love to have a super computer to run LTspice.
>>>>>
>>>>> boB
>>>> In fact, what you have on your desk *is* a super computer,
>>>> in the 1970's meaning of the words. It's just that it's
>>>> bogged down running bloatware.

>>> Indeed. The Cray X-MP in its 4 CPU configuration with a 105MHz clock and
>>> a whopping for the time 128MB of fast core memory with 40GB of disk. The
>> what is fast core memory?
>
> A very expensive item:
>
> https://en.wikipedia.org/wiki/Magnetic-core_memory
>
> Fortunately by the X-MP's time SRAMs had replaced magnetic core.

But at the time it was still often called core (bulk) memory as opposed
to faster cache memory. ISTR the memory chips were only 4k bits of SRAM.

Keeping the thing compact and cool was a major part of the engineering.

There is a rather nice article about its design online here.

http://www.chilton-computing.org.uk/ccd/supercomputers/p005.htm

--
Regards,
Martin Brown

Re: supercomputer progress

<jdffjgFqjsdU1@mid.individual.net>

 copy mid

https://www.novabbs.com/tech/article-flat.php?id=96249&group=sci.electronics.design#96249

 copy link   Newsgroups: sci.electronics.design
Path: i2pn2.org!i2pn.org!usenet.goja.nl.eu.org!news.freedyn.de!speedkom.net!fu-berlin.de!uni-berlin.de!individual.net!not-for-mail
From: bow...@montana.com (rbowman)
Newsgroups: sci.electronics.design
Subject: Re: supercomputer progress
Date: Wed, 4 May 2022 08:06:43 -0600
Lines: 50
Message-ID: <jdffjgFqjsdU1@mid.individual.net>
References: <tj4g6hd8omp97pbbs6dn146suop2dds5n6@4ax.com>
<mZKdnQszLo_T3_X_nZ2dnUU7-LXNnZ2d@giganews.com>
<fpmg6hhot88ajjqkcb6nv9mkbjm7s9q85k@4ax.com>
<0lfl6hhee2j23gr7j5epb3obpdn8s7sj3f@4ax.com> <t4ejuo$7n8$1@gioia.aioe.org>
<t4g872$ll$1@gioia.aioe.org> <t4s5sj$4v$1@reader1.panix.com>
<jde73uFj8b1U1@mid.individual.net> <t4tc7j$ddp$1@gioia.aioe.org>
Mime-Version: 1.0
Content-Type: text/plain; charset=utf-8; format=flowed
Content-Transfer-Encoding: 7bit
X-Trace: individual.net NNEiDTLChPi5BvCcL3vT8AO4QrBU0DTexwI5i2lJHOD3L9iilN
Cancel-Lock: sha1:DvHJmqRqTCPc/k786+o7NyIeG6w=
User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:45.0) Gecko/20100101
Thunderbird/45.6.0
In-Reply-To: <t4tc7j$ddp$1@gioia.aioe.org>
 by: rbowman - Wed, 4 May 2022 14:06 UTC

On 05/04/2022 02:07 AM, Martin Brown wrote:
> On 04/05/2022 03:35, rbowman wrote:
>> On 05/03/2022 03:12 PM, Cydrome Leader wrote:
>>> Martin Brown <'''newspam'''@nonad.co.uk> wrote:
>>>> On 28/04/2022 18:47, Jeroen Belleman wrote:
>>>>> On 2022-04-28 18:26, boB wrote:
>>>>> [...]
>>>>>> I would love to have a super computer to run LTspice.
>>>>>>
>>>>>> boB
>>>>> In fact, what you have on your desk *is* a super computer,
>>>>> in the 1970's meaning of the words. It's just that it's
>>>>> bogged down running bloatware.
>
>>>> Indeed. The Cray X-MP in its 4 CPU configuration with a 105MHz clock
>>>> and
>>>> a whopping for the time 128MB of fast core memory with 40GB of disk.
>>>> The
>>> what is fast core memory?
>>
>> A very expensive item:
>>
>> https://en.wikipedia.org/wiki/Magnetic-core_memory
>>
>> Fortunately by the X-MP's time SRAMs had replaced magnetic core.
>
> But at the time it was still often called core (bulk) memory as opposed
> to faster cache memory. ISTR the memory chips were only 4k bits of SRAM.
>
> Keeping the thing compact and cool was a major part of the engineering.
>
> There is a rather nice article about its design online here.
>
> http://www.chilton-computing.org.uk/ccd/supercomputers/p005.htm
>

We still examine core dumps. Compact and cool is still a problem not
only for server farms but for things like the Intel NUC. Just can't
escape history.

Most of the buildings at RPI dated back to the early 20th century and AC
was not an option. The new building to house the System 360/30 was an
oasis on hot days. That thing was not compact and used magnetic core. I
don't think it had enough computing power to run a modern refrigerator.

iirc during the startup of the new NSA computing center in Bluffdale UT
they found they had enough power to either run the servers or keep them
cool. Back to the drawing board. It also boggles my mind that bitcoin
mining is a major draw on the power grid.

Re: supercomputer progress

<t4uh1p$o0u$2@reader1.panix.com>

 copy mid

https://www.novabbs.com/tech/article-flat.php?id=96270&group=sci.electronics.design#96270

 copy link   Newsgroups: sci.electronics.design
Path: i2pn2.org!i2pn.org!weretis.net!feeder6.news.weretis.net!panix!.POSTED.panix2.panix.com!not-for-mail
From: prese...@MUNGEpanix.com (Cydrome Leader)
Newsgroups: sci.electronics.design
Subject: Re: supercomputer progress
Date: Wed, 4 May 2022 18:35:37 -0000 (UTC)
Organization: PANIX Public Access Internet and UNIX, NYC
Message-ID: <t4uh1p$o0u$2@reader1.panix.com>
References: <tj4g6hd8omp97pbbs6dn146suop2dds5n6@4ax.com> <mZKdnQszLo_T3_X_nZ2dnUU7-LXNnZ2d@giganews.com> <fpmg6hhot88ajjqkcb6nv9mkbjm7s9q85k@4ax.com> <0lfl6hhee2j23gr7j5epb3obpdn8s7sj3f@4ax.com> <t4ejuo$7n8$1@gioia.aioe.org> <t4g872$ll$1@gioia.aioe.org> <t4s5sj$4v$1@reader1.panix.com> <jde73uFj8b1U1@mid.individual.net>
Injection-Date: Wed, 4 May 2022 18:35:37 -0000 (UTC)
Injection-Info: reader1.panix.com; posting-host="panix2.panix.com:166.84.1.2";
logging-data="24606"; mail-complaints-to="abuse@panix.com"
User-Agent: tin/2.6.0-20210823 ("Coleburn") (NetBSD/9.2 (amd64))
 by: Cydrome Leader - Wed, 4 May 2022 18:35 UTC

rbowman <bowman@montana.com> wrote:
> On 05/03/2022 03:12 PM, Cydrome Leader wrote:
>> Martin Brown <'''newspam'''@nonad.co.uk> wrote:
>>> On 28/04/2022 18:47, Jeroen Belleman wrote:
>>>> On 2022-04-28 18:26, boB wrote:
>>>> [...]
>>>>> I would love to have a super computer to run LTspice.
>>>>>
>>>>> boB
>>>> In fact, what you have on your desk *is* a super computer,
>>>> in the 1970's meaning of the words. It's just that it's
>>>> bogged down running bloatware.
>>> Indeed. The Cray X-MP in its 4 CPU configuration with a 105MHz clock and
>>> a whopping for the time 128MB of fast core memory with 40GB of disk. The
>> what is fast core memory?
>>
>
> A very expensive item:
>
> https://en.wikipedia.org/wiki/Magnetic-core_memory
>
> Fortunately by the X-MP's time SRAMs had replaced magnetic core.

I'm not aware of any cray systems that used core memory. It just makes no
sense for the speeds they ran at.

Re: supercomputer progress

<jdgsd6F48u1U1@mid.individual.net>

 copy mid

https://www.novabbs.com/tech/article-flat.php?id=96298&group=sci.electronics.design#96298

 copy link   Newsgroups: sci.electronics.design
Path: i2pn2.org!i2pn.org!weretis.net!feeder8.news.weretis.net!news.szaf.org!fu-berlin.de!uni-berlin.de!individual.net!not-for-mail
From: bow...@montana.com (rbowman)
Newsgroups: sci.electronics.design
Subject: Re: supercomputer progress
Date: Wed, 4 May 2022 20:51:21 -0600
Lines: 18
Message-ID: <jdgsd6F48u1U1@mid.individual.net>
References: <tj4g6hd8omp97pbbs6dn146suop2dds5n6@4ax.com>
<mZKdnQszLo_T3_X_nZ2dnUU7-LXNnZ2d@giganews.com>
<fpmg6hhot88ajjqkcb6nv9mkbjm7s9q85k@4ax.com>
<0lfl6hhee2j23gr7j5epb3obpdn8s7sj3f@4ax.com> <t4ejuo$7n8$1@gioia.aioe.org>
<t4g872$ll$1@gioia.aioe.org> <t4s5sj$4v$1@reader1.panix.com>
<jde73uFj8b1U1@mid.individual.net> <t4uh1p$o0u$2@reader1.panix.com>
Mime-Version: 1.0
Content-Type: text/plain; charset=windows-1252; format=flowed
Content-Transfer-Encoding: 7bit
X-Trace: individual.net jRHUKp0LJSHOP8CFajxuMgmawhnuxAwX6aPPkJHa33wmOHmHLP
Cancel-Lock: sha1:wbo8czBvbZRtkJ+yGgsh75gA3M0=
User-Agent: Mozilla/5.0 (X11; Linux x86_64; rv:45.0) Gecko/20100101
Thunderbird/45.6.0
In-Reply-To: <t4uh1p$o0u$2@reader1.panix.com>
 by: rbowman - Thu, 5 May 2022 02:51 UTC

On 05/04/2022 12:35 PM, Cydrome Leader wrote:
> I'm not aware of any cray systems that used core memory. It just makes no
> sense for the speeds they ran at.

I believe the CDC 7600 was the last Cray design to use magnetic core. He
then left CDC and the Cray-1 was SRAM.

The CDC 7600 was no slouch for its time.

https://en.wikipedia.org/wiki/CDC_7600

Control Data was ahead of its time and started the Committee for Social
Responsibility shorty before Cray left (no correlation). Like many of
the early giants time did not treat them well.

https://www.nytimes.com/1979/01/07/archives/how-control-data-turns-a-profit-on-its-good-works-making-it-work.html

https://gallery.lib.umn.edu/items/show/5867

Re: supercomputer progress

<t8gl32$4it$1@dont-email.me>

 copy mid

https://www.novabbs.com/tech/article-flat.php?id=99543&group=sci.electronics.design#99543

 copy link   Newsgroups: sci.electronics.design
Path: i2pn2.org!rocksolid2!i2pn.org!eternal-september.org!reader02.eternal-september.org!.POSTED!not-for-mail
From: lcargi...@gmail.com (Les Cargill)
Newsgroups: sci.electronics.design
Subject: Re: supercomputer progress
Date: Thu, 16 Jun 2022 20:23:45 -0500
Organization: A noiseless patient Spider
Lines: 34
Message-ID: <t8gl32$4it$1@dont-email.me>
References: <tj4g6hd8omp97pbbs6dn146suop2dds5n6@4ax.com>
<mZKdnQszLo_T3_X_nZ2dnUU7-LXNnZ2d@giganews.com>
<fpmg6hhot88ajjqkcb6nv9mkbjm7s9q85k@4ax.com>
<0lfl6hhee2j23gr7j5epb3obpdn8s7sj3f@4ax.com> <t4ejuo$7n8$1@gioia.aioe.org>
<t4g872$ll$1@gioia.aioe.org>
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8; format=flowed
Content-Transfer-Encoding: 7bit
Injection-Date: Fri, 17 Jun 2022 01:23:46 -0000 (UTC)
Injection-Info: reader02.eternal-september.org; posting-host="673b5a1fb956fddf7f741aab2f4e4238";
logging-data="4701"; mail-complaints-to="abuse@eternal-september.org"; posting-account="U2FsdGVkX19fGWanxWRBjqSb76M95L75VpjOef9jvZU="
User-Agent: Mozilla/5.0 (Windows NT 10.0; Win64; x64; rv:68.0) Gecko/20100101
Firefox/68.0 SeaMonkey/2.53.12
Cancel-Lock: sha1:c23MRt6Oj7w+ictzxE9U5pSZvhU=
In-Reply-To: <t4g872$ll$1@gioia.aioe.org>
 by: Les Cargill - Fri, 17 Jun 2022 01:23 UTC

Martin Brown wrote:
> On 28/04/2022 18:47, Jeroen Belleman wrote:
>> On 2022-04-28 18:26, boB wrote:
>> [...]
>>> I would love to have a super computer to run LTspice.
>>>
>>> boB
>>
>> In fact, what you have on your desk *is* a super computer,
>> in the 1970's meaning of the words. It's just that it's
>> bogged down running bloatware.
>
> Indeed. The Cray X-MP in its 4 CPU configuration with a 105MHz clock and
> a whopping for the time 128MB of fast core memory with 40GB of disk. The
> one I used had an amazing for the time 1TB tape cassette backing store.
> It did 600 MFLOPs with the right sort of parallel vector code.
>
> That was back in the day when you needed special permission to use more
> than 4MB of core on the timesharing IBM 3081 (approx 7 MIPS).
>
> Current Intel 12 gen CPU desktops are ~4GHz, 16GB ram and >1TB of disk.
> (and the upper limits are even higher) That combo does ~66,000 MFLOPS.
>
> Spice simulation doesn't scale particularly well to large scale
> multiprocessor environments to many long range interractions.
>

If you search for "circuit sim and CUDA" it's out there. There's a
Github of "CUDA SPICE Circuit Simulator" .

No clue if it's worthwhile.

--
Les Cargill

Re: supercomputer progress

<t8pon9$q2h$1@gioia.aioe.org>

 copy mid

https://www.novabbs.com/tech/article-flat.php?id=99798&group=sci.electronics.design#99798

 copy link   Newsgroups: sci.electronics.design
Path: i2pn2.org!i2pn.org!aioe.org!iRAiJCxKFnRf4KmbmeYOrQ.user.46.165.242.75.POSTED!not-for-mail
From: '''newsp...@nonad.co.uk (Martin Brown)
Newsgroups: sci.electronics.design
Subject: Re: supercomputer progress
Date: Mon, 20 Jun 2022 13:20:57 +0100
Organization: Aioe.org NNTP Server
Message-ID: <t8pon9$q2h$1@gioia.aioe.org>
References: <tj4g6hd8omp97pbbs6dn146suop2dds5n6@4ax.com>
<mZKdnQszLo_T3_X_nZ2dnUU7-LXNnZ2d@giganews.com>
<fpmg6hhot88ajjqkcb6nv9mkbjm7s9q85k@4ax.com>
<0lfl6hhee2j23gr7j5epb3obpdn8s7sj3f@4ax.com> <t4ejuo$7n8$1@gioia.aioe.org>
<t4g872$ll$1@gioia.aioe.org> <t8gl32$4it$1@dont-email.me>
Mime-Version: 1.0
Content-Type: text/plain; charset=UTF-8; format=flowed
Content-Transfer-Encoding: 7bit
Injection-Info: gioia.aioe.org; logging-data="26705"; posting-host="iRAiJCxKFnRf4KmbmeYOrQ.user.gioia.aioe.org"; mail-complaints-to="abuse@aioe.org";
User-Agent: Mozilla/5.0 (Windows NT 6.1; Win64; x64; rv:91.0) Gecko/20100101
Thunderbird/91.10.0
X-Notice: Filtered by postfilter v. 0.9.2
Content-Language: en-GB
 by: Martin Brown - Mon, 20 Jun 2022 12:20 UTC

On 17/06/2022 02:23, Les Cargill wrote:
> Martin Brown wrote:
>>
>> Spice simulation doesn't scale particularly well to large scale
>> multiprocessor environments too many long range interractions.
>
> If you search for "circuit sim and CUDA" it's out there. There's a
> Github of "CUDA SPICE Circuit Simulator" .
>
> No clue if it's worthwhile.

My instinct is that it will generate a lot more heat to solve the
problem a little bit quicker than a conventional system (unless you are
able to split the problem into a large number of distinct separate
simulations with different starting parameters.

That is what happens on the system I am working on (not Spice). My bit
of it is strictly single threaded but it runs a on every CPU. The next
tier up manages the whole thing to keep them busy doing useful work.

--
Regards,
Martin Brown

Re: supercomputer progress

<98cb967f-edf7-4ee7-b4fc-96332247abd5n@googlegroups.com>

 copy mid

https://www.novabbs.com/tech/article-flat.php?id=99799&group=sci.electronics.design#99799

 copy link   Newsgroups: sci.electronics.design
X-Received: by 2002:adf:eb4d:0:b0:218:45b6:8fdb with SMTP id u13-20020adfeb4d000000b0021845b68fdbmr24124130wrn.77.1655729223010;
Mon, 20 Jun 2022 05:47:03 -0700 (PDT)
X-Received: by 2002:a25:d204:0:b0:668:c913:966b with SMTP id
j4-20020a25d204000000b00668c913966bmr15754126ybg.267.1655729222487; Mon, 20
Jun 2022 05:47:02 -0700 (PDT)
Path: i2pn2.org!i2pn.org!weretis.net!feeder8.news.weretis.net!proxad.net!feeder1-2.proxad.net!209.85.128.88.MISMATCH!news-out.google.com!nntp.google.com!postnews.google.com!google-groups.googlegroups.com!not-for-mail
Newsgroups: sci.electronics.design
Date: Mon, 20 Jun 2022 05:47:02 -0700 (PDT)
In-Reply-To: <tj4g6hd8omp97pbbs6dn146suop2dds5n6@4ax.com>
Injection-Info: google-groups.googlegroups.com; posting-host=46.134.190.3; posting-account=XS5sXwoAAABKU0kHcsk_nashWaidAu0Q
NNTP-Posting-Host: 46.134.190.3
References: <tj4g6hd8omp97pbbs6dn146suop2dds5n6@4ax.com>
User-Agent: G2/1.0
MIME-Version: 1.0
Message-ID: <98cb967f-edf7-4ee7-b4fc-96332247abd5n@googlegroups.com>
Subject: Re: supercomputer progress
From: manta1...@gmail.com (a a)
Injection-Date: Mon, 20 Jun 2022 12:47:03 +0000
Content-Type: text/plain; charset="UTF-8"
 by: a a - Mon, 20 Jun 2022 12:47 UTC

On Tuesday, 26 April 2022 at 17:44:53 UTC+2, jla...@highlandsniptechnology.com wrote:
> Lawrence Berkeley Lab announced the results from a new supercomputer
> analysis of climate change. They analyzed five west coast "extreme
> storms" from 1982 to 2014.
>
> The conclusion from a senior scientist is that "it rains a lot more
> during the worst storms."
>
>
>
> --
>
> Anybody can count to one.
>
> - Robert Widlar
Climate Change is an old fake by Al Gore, Prof. Mann and their team to make money fast.

Freon is another fake.

Climate is clocked by solar activity and by fluctuations in solar activity.

So it's a waste of time and money to study Climate Change, living on the Earth, if you can easily study fluctuations in solar activity to get science on what really controls the Climate.

Removing trees within city limits, you can turn any city in heat island swith rising temperatures.=, since removing trees, grass, you destroy rainwater retension mechanism.

Water absorbs heat from the sun by evaporation.

So if no water in the ground, no water evaporated and heat accumulates, making local temperatures to rise.

Re: supercomputer progress

<eff63bea-1c36-4cb4-a998-3e3b91481a11n@googlegroups.com>

 copy mid

https://www.novabbs.com/tech/article-flat.php?id=99801&group=sci.electronics.design#99801

 copy link   Newsgroups: sci.electronics.design
X-Received: by 2002:a05:600c:4f51:b0:39c:7f6c:a8d6 with SMTP id m17-20020a05600c4f5100b0039c7f6ca8d6mr24844030wmq.143.1655732158684;
Mon, 20 Jun 2022 06:35:58 -0700 (PDT)
X-Received: by 2002:a05:690c:97:b0:2f1:9582:6685 with SMTP id
be23-20020a05690c009700b002f195826685mr27930234ywb.395.1655732158134; Mon, 20
Jun 2022 06:35:58 -0700 (PDT)
Path: i2pn2.org!i2pn.org!weretis.net!feeder8.news.weretis.net!proxad.net!feeder1-2.proxad.net!209.85.128.87.MISMATCH!news-out.google.com!nntp.google.com!postnews.google.com!google-groups.googlegroups.com!not-for-mail
Newsgroups: sci.electronics.design
Date: Mon, 20 Jun 2022 06:35:57 -0700 (PDT)
In-Reply-To: <afbb1b1a-689f-4990-aad5-127505f8d73dn@googlegroups.com>
Injection-Info: google-groups.googlegroups.com; posting-host=46.134.190.3; posting-account=XS5sXwoAAABKU0kHcsk_nashWaidAu0Q
NNTP-Posting-Host: 46.134.190.3
References: <tj4g6hd8omp97pbbs6dn146suop2dds5n6@4ax.com> <98cb967f-edf7-4ee7-b4fc-96332247abd5n@googlegroups.com>
<afbb1b1a-689f-4990-aad5-127505f8d73dn@googlegroups.com>
User-Agent: G2/1.0
MIME-Version: 1.0
Message-ID: <eff63bea-1c36-4cb4-a998-3e3b91481a11n@googlegroups.com>
Subject: Re: supercomputer progress
From: manta1...@gmail.com (a a)
Injection-Date: Mon, 20 Jun 2022 13:35:58 +0000
Content-Type: text/plain; charset="UTF-8"
Content-Transfer-Encoding: quoted-printable
 by: a a - Mon, 20 Jun 2022 13:35 UTC

On Monday, 20 June 2022 at 15:13:10 UTC+2, bill....@ieee.org wrote:
> On Monday, June 20, 2022 at 2:47:09 PM UTC+2, a a wrote:
> > On Tuesday, 26 April 2022 at 17:44:53 UTC+2, jla...@highlandsniptechnology.com wrote:
> > > Lawrence Berkeley Lab announced the results from a new supercomputer
> > > analysis of climate change. They analyzed five west coast "extreme
> > > storms" from 1982 to 2014.
> > >
> > > The conclusion from a senior scientist is that "it rains a lot more
> > > during the worst storms."
> >
> > Climate Change is an old fake by Al Gore, Prof. Mann and their team to make money fast.
> What a load of nonsense. Al Gore's 1992 book
>
> https://en.wikipedia.org/wiki/Earth_in_the_Balance
>
> was a remarkably expert bit of science popularisation. He got the science right, not that the denialist propaganda machine is willing to admit it.
> The book did make money, but not all that much. A decade later it did put Al Gore in a position to make money out of climate change, but that didn't mean that he wrote it with that in mind.
>
> > Freon is another fake.
>
> In what sense? Chlorofluorocarbons do damage the ozone layer. We know exactly how - and we know that reducing their concentrations in the atmosphere is letting the ozone layer get denser again. The fakery here lies in your lie.
> > Climate is clocked by solar activity and by fluctuations in solar activity.
> And the amount of CO2 and other green-house gases in the atmosphere. As Joseph Fourier worked out in 1824, if they weren't there the temperature of the surface of the Earth would be -18C. The difference between ice ages (atmospheric CO2 levels around 180 ppm) and interglacials (atmospheric CO2 levels around 270 ppm) also depends on the more extensive ice cover during interglacials, but the CO2 levels do account for a lot of the difference.
> > So it's a waste of time and money to study Climate Change, living on the Earth, if you can easily study fluctuations in solar activity to get science on what really controls the Climate.
> Except that you can't. Solar activity doesn't explain the ice age to interglacial transitions, and only an ignorant idiot could imagine that they did
>
> > Removing trees within city limits, you can turn any city in heat island with rising temperatures, since removing trees, grass, you destroy rainwater retention mechanism.
>
> Total nonsense.
> > Water absorbs heat from the sun by evaporation.
> But the water vapour retains the heat at the bottom of the atmosphere.
> > So if no water in the ground, no water evaporated and heat accumulates, making local temperatures to rise.
> So what?
>
> --
> Bill Sloman, Sydney
You are exactly "Total nonsense. "

Sydney is low science city, so we don't care

Call prof. Mann and tell him, there has been no sea level rise at Pacific islands at all, on the Maledives, for the last 1,000 years

If Kremlin funds hundreds of so called pseudo scientists world-wide to sell more natural gas,
so call Greta and ask her, where is she with the Global Warming fake today

where is UNFCC Bonn agency, where is UN New York SIDS agency today
(Small Island Developing States)

If $Bs are pumped into your bank account, so you sell every paranoia as a genuine science

Global Warming is an old fake funded by Putin to sell more natural gas

Re: supercomputer progress

<8e5f2b9f-47cd-41da-9eb9-af9194fdd9fdn@googlegroups.com>

 copy mid

https://www.novabbs.com/tech/article-flat.php?id=99811&group=sci.electronics.design#99811

 copy link   Newsgroups: sci.electronics.design
X-Received: by 2002:a7b:cc8e:0:b0:39c:829d:609b with SMTP id p14-20020a7bcc8e000000b0039c829d609bmr26595754wma.160.1655740013003;
Mon, 20 Jun 2022 08:46:53 -0700 (PDT)
X-Received: by 2002:a25:ac59:0:b0:668:bd26:7c1a with SMTP id
r25-20020a25ac59000000b00668bd267c1amr16722951ybd.141.1655740012437; Mon, 20
Jun 2022 08:46:52 -0700 (PDT)
Path: i2pn2.org!i2pn.org!aioe.org!news.uzoreto.com!feeder1.cambriumusenet.nl!feed.tweak.nl!209.85.128.88.MISMATCH!news-out.google.com!nntp.google.com!postnews.google.com!google-groups.googlegroups.com!not-for-mail
Newsgroups: sci.electronics.design
Date: Mon, 20 Jun 2022 08:46:52 -0700 (PDT)
In-Reply-To: <db3c26ec-6579-48e3-8320-7cc4e506d00bn@googlegroups.com>
Injection-Info: google-groups.googlegroups.com; posting-host=46.134.11.78; posting-account=XS5sXwoAAABKU0kHcsk_nashWaidAu0Q
NNTP-Posting-Host: 46.134.11.78
References: <tj4g6hd8omp97pbbs6dn146suop2dds5n6@4ax.com> <98cb967f-edf7-4ee7-b4fc-96332247abd5n@googlegroups.com>
<afbb1b1a-689f-4990-aad5-127505f8d73dn@googlegroups.com> <eff63bea-1c36-4cb4-a998-3e3b91481a11n@googlegroups.com>
<db3c26ec-6579-48e3-8320-7cc4e506d00bn@googlegroups.com>
User-Agent: G2/1.0
MIME-Version: 1.0
Message-ID: <8e5f2b9f-47cd-41da-9eb9-af9194fdd9fdn@googlegroups.com>
Subject: Re: supercomputer progress
From: manta1...@gmail.com (a a)
Injection-Date: Mon, 20 Jun 2022 15:46:52 +0000
Content-Type: text/plain; charset="UTF-8"
Content-Transfer-Encoding: quoted-printable
 by: a a - Mon, 20 Jun 2022 15:46 UTC

On Monday, 20 June 2022 at 16:27:36 UTC+2, bill....@ieee.org wrote:
> On Monday, June 20, 2022 at 3:36:04 PM UTC+2, a a wrote:
> > On Monday, 20 June 2022 at 15:13:10 UTC+2, bill....@ieee.org wrote:
> > > On Monday, June 20, 2022 at 2:47:09 PM UTC+2, a a wrote:
> > > > On Tuesday, 26 April 2022 at 17:44:53 UTC+2, jla...@highlandsniptechnology.com wrote:
> > > > > Lawrence Berkeley Lab announced the results from a new supercomputer
> > > > > analysis of climate change. They analyzed five west coast "extreme
> > > > > storms" from 1982 to 2014.
> > > > >
> > > > > The conclusion from a senior scientist is that "it rains a lot more
> > > > > during the worst storms."
> > > >
> > > > Climate Change is an old fake by Al Gore, Prof. Mann and their team to make money fast.
> > > What a load of nonsense. Al Gore's 1992 book
> > >
> > > https://en.wikipedia.org/wiki/Earth_in_the_Balance
> > >
> > > was a remarkably expert bit of science popularisation. He got the science right, not that the denialist propaganda machine is willing to admit it.
> > > The book did make money, but not all that much. A decade later it did put Al Gore in a position to make money out of climate change, but that didn't mean that he wrote it with that in mind.
> > >
> > > > Freon is another fake.
> > >
> > > In what sense? Chlorofluorocarbons do damage the ozone layer. We know exactly how - and we know that reducing their concentrations in the atmosphere is letting the ozone layer get denser again. The fakery here lies in your lie.
> > > > Climate is clocked by solar activity and by fluctuations in solar activity.
> > > And the amount of CO2 and other green-house gases in the atmosphere. As Joseph Fourier worked out in 1824, if they weren't there the temperature of the surface of the Earth would be -18C. The difference between ice ages (atmospheric CO2 levels around 180 ppm) and interglacials (atmospheric CO2 levels around 270 ppm) also depends on the more extensive ice cover during interglacials, but the CO2 levels do account for a lot of the difference.
> > > > So it's a waste of time and money to study Climate Change, living on the Earth, if you can easily study fluctuations in solar activity to get science on what really controls the Climate.
> > > Except that you can't. Solar activity doesn't explain the ice age to interglacial transitions, and only an ignorant idiot could imagine that they did
> > >
> > > > Removing trees within city limits, you can turn any city in heat island with rising temperatures, since removing trees, grass, you destroy rainwater retention mechanism.
> > >
> > > Total nonsense.
> > >
> > > > Water absorbs heat from the sun by evaporation.
> > >
> > > But the water vapour retains the heat at the bottom of the atmosphere..
> > >
> > > > So if no water in the ground, no water evaporated and heat accumulates, making local temperatures to rise.
> > >
> > > So what?
> >
> > You are exactly "Total nonsense. "
> You may like to think so, but you haven't explained why you think that. It's blindingly obvious that you couldn't, even if you were silly enough to try.
>
> > Sydney is low science city, so we don't care.
>
> https://www.fqt.unsw.edu.au/news/top-physics-prizes-awarded-to-unsw-researchers
>
> I got in on a tour of that lab. I was impressed by their Raith electron beam microfabricator, which is a pretty impressive kind of lab tool.
>
> > Call prof. Mann and tell him, there has been no sea level rise at Pacific islands at all, on the Maledives, for the last 1,000 years.
>
> The Maledives are in the Indian Ocean, not too far south of Ceylon. I'd prefer not to get jeered at as an ignorant idiot. And they do seem to be worried about
> sea level rise.
>
> https://en.wikipedia.org/wiki/Maldives#Sea_level_rise
>
> > If Kremlin funds hundreds of so called pseudo scientists world-wide to sell more natural gas, so call Greta and ask her, where is she with the Global Warming fake today.
>
> It's not the Kremlin that's funding the lying that is going on. Exxon-Mobile does a lot of that, but they are funding the climate change denial propaganda that seems to be fooling you.
> > where is UNFCC Bonn agency, where is UN New York SIDS agency today (Small Island Developing States)
> Why should I care?
>
> > If $Bs are pumped into your bank account, so you sell every paranoia as a genuine science.
>
> If only.
>
> > Global Warming is an old fake funded by Putin to sell more natural gas.
>
> https://history.aip.org/climate/index.htm
>
> It's been around for rather longer than Putin, and it's not great way of selling natural gas. We'll have to stop burning that as fuel as well as coal and oil if we are going to stop raising the CO2 level in the atmosphere, which is getting to be urgently necessary, even if ignorant idiots like you don't understand why.
>
> --
> Bill Sloman, Sydney
==. And they do seem to be worried about sea level rise.

since Global Warming fake is long lasting fake, funded by Kremlin

It was my excellent long-year job to move UN agencies from Global Warming fake to Climate Change

Climate Change is pure tautology by Heraclitus
Everything flows - Panta rhei

BTW
Australia, Sydney is low on science due low population, not attracting foreign scientists, researchers
and low AUD exchange rate

Re: supercomputer progress

<ccb0cfd1-e7b9-42d1-9c4f-75cfd45b1da0n@googlegroups.com>

 copy mid

https://www.novabbs.com/tech/article-flat.php?id=99813&group=sci.electronics.design#99813

 copy link   Newsgroups: sci.electronics.design
X-Received: by 2002:adf:d22b:0:b0:21b:90be:2dc8 with SMTP id k11-20020adfd22b000000b0021b90be2dc8mr4863914wrh.423.1655740324395;
Mon, 20 Jun 2022 08:52:04 -0700 (PDT)
X-Received: by 2002:a81:4fc5:0:b0:317:7792:9a5f with SMTP id
d188-20020a814fc5000000b0031777929a5fmr23803799ywb.413.1655740323887; Mon, 20
Jun 2022 08:52:03 -0700 (PDT)
Path: i2pn2.org!i2pn.org!weretis.net!feeder8.news.weretis.net!proxad.net!feeder1-2.proxad.net!209.85.128.87.MISMATCH!news-out.google.com!nntp.google.com!postnews.google.com!google-groups.googlegroups.com!not-for-mail
Newsgroups: sci.electronics.design
Date: Mon, 20 Jun 2022 08:52:03 -0700 (PDT)
In-Reply-To: <db3c26ec-6579-48e3-8320-7cc4e506d00bn@googlegroups.com>
Injection-Info: google-groups.googlegroups.com; posting-host=46.134.11.78; posting-account=XS5sXwoAAABKU0kHcsk_nashWaidAu0Q
NNTP-Posting-Host: 46.134.11.78
References: <tj4g6hd8omp97pbbs6dn146suop2dds5n6@4ax.com> <98cb967f-edf7-4ee7-b4fc-96332247abd5n@googlegroups.com>
<afbb1b1a-689f-4990-aad5-127505f8d73dn@googlegroups.com> <eff63bea-1c36-4cb4-a998-3e3b91481a11n@googlegroups.com>
<db3c26ec-6579-48e3-8320-7cc4e506d00bn@googlegroups.com>
User-Agent: G2/1.0
MIME-Version: 1.0
Message-ID: <ccb0cfd1-e7b9-42d1-9c4f-75cfd45b1da0n@googlegroups.com>
Subject: Re: supercomputer progress
From: manta1...@gmail.com (a a)
Injection-Date: Mon, 20 Jun 2022 15:52:04 +0000
Content-Type: text/plain; charset="UTF-8"
Content-Transfer-Encoding: quoted-printable
 by: a a - Mon, 20 Jun 2022 15:52 UTC

On Monday, 20 June 2022 at 16:27:36 UTC+2, bill....@ieee.org wrote:
> On Monday, June 20, 2022 at 3:36:04 PM UTC+2, a a wrote:
> > On Monday, 20 June 2022 at 15:13:10 UTC+2, bill....@ieee.org wrote:
> > > On Monday, June 20, 2022 at 2:47:09 PM UTC+2, a a wrote:
> > > > On Tuesday, 26 April 2022 at 17:44:53 UTC+2, jla...@highlandsniptechnology.com wrote:
> > > > > Lawrence Berkeley Lab announced the results from a new supercomputer
> > > > > analysis of climate change. They analyzed five west coast "extreme
> > > > > storms" from 1982 to 2014.
> > > > >
> > > > > The conclusion from a senior scientist is that "it rains a lot more
> > > > > during the worst storms."
> > > >
> > > > Climate Change is an old fake by Al Gore, Prof. Mann and their team to make money fast.
> > > What a load of nonsense. Al Gore's 1992 book
> > >
> > > https://en.wikipedia.org/wiki/Earth_in_the_Balance
> > >
> > > was a remarkably expert bit of science popularisation. He got the science right, not that the denialist propaganda machine is willing to admit it.
> > > The book did make money, but not all that much. A decade later it did put Al Gore in a position to make money out of climate change, but that didn't mean that he wrote it with that in mind.
> > >
> > > > Freon is another fake.
> > >
> > > In what sense? Chlorofluorocarbons do damage the ozone layer. We know exactly how - and we know that reducing their concentrations in the atmosphere is letting the ozone layer get denser again. The fakery here lies in your lie.
> > > > Climate is clocked by solar activity and by fluctuations in solar activity.
> > > And the amount of CO2 and other green-house gases in the atmosphere. As Joseph Fourier worked out in 1824, if they weren't there the temperature of the surface of the Earth would be -18C. The difference between ice ages (atmospheric CO2 levels around 180 ppm) and interglacials (atmospheric CO2 levels around 270 ppm) also depends on the more extensive ice cover during interglacials, but the CO2 levels do account for a lot of the difference.
> > > > So it's a waste of time and money to study Climate Change, living on the Earth, if you can easily study fluctuations in solar activity to get science on what really controls the Climate.
> > > Except that you can't. Solar activity doesn't explain the ice age to interglacial transitions, and only an ignorant idiot could imagine that they did
> > >
> > > > Removing trees within city limits, you can turn any city in heat island with rising temperatures, since removing trees, grass, you destroy rainwater retention mechanism.
> > >
> > > Total nonsense.
> > >
> > > > Water absorbs heat from the sun by evaporation.
> > >
> > > But the water vapour retains the heat at the bottom of the atmosphere..
> > >
> > > > So if no water in the ground, no water evaporated and heat accumulates, making local temperatures to rise.
> > >
> > > So what?
> >
> > You are exactly "Total nonsense. "
> You may like to think so, but you haven't explained why you think that. It's blindingly obvious that you couldn't, even if you were silly enough to try.
>
> > Sydney is low science city, so we don't care.

> It's been around for rather longer than Putin, and it's not great way of selling natural gas. We'll have to stop burning that as fuel as well as coal and oil if we are going to stop raising the CO2 level in the atmosphere,
>
> --
> Bill Sloman, Sydney
----Sydney is low science city, so we don't care.

CO2 is welcome
CO2 is Plant Food
Plants are Animal Food
Animals are Human Food

More CO2 more Human Food
to end the world hunger

Re: supercomputer progress

<9d2ec319-3d85-4d89-b91d-4930f89f880cn@googlegroups.com>

 copy mid

https://www.novabbs.com/tech/article-flat.php?id=99916&group=sci.electronics.design#99916

 copy link   Newsgroups: sci.electronics.design
X-Received: by 2002:a5d:514d:0:b0:21b:932b:be77 with SMTP id u13-20020a5d514d000000b0021b932bbe77mr8879207wrt.231.1655833676246;
Tue, 21 Jun 2022 10:47:56 -0700 (PDT)
X-Received: by 2002:a25:cc4c:0:b0:668:a68a:b9fa with SMTP id
l73-20020a25cc4c000000b00668a68ab9famr29920273ybf.396.1655833675781; Tue, 21
Jun 2022 10:47:55 -0700 (PDT)
Path: i2pn2.org!i2pn.org!usenet.blueworldhosting.com!feed1.usenet.blueworldhosting.com!peer03.iad!feed-me.highwinds-media.com!news.highwinds-media.com!news-out.google.com!nntp.google.com!postnews.google.com!google-groups.googlegroups.com!not-for-mail
Newsgroups: sci.electronics.design
Date: Tue, 21 Jun 2022 10:47:55 -0700 (PDT)
In-Reply-To: <98cb967f-edf7-4ee7-b4fc-96332247abd5n@googlegroups.com>
Injection-Info: google-groups.googlegroups.com; posting-host=209.221.140.126; posting-account=vKQm_QoAAADOaDCYsqOFDAW8NJ8sFHoE
NNTP-Posting-Host: 209.221.140.126
References: <tj4g6hd8omp97pbbs6dn146suop2dds5n6@4ax.com> <98cb967f-edf7-4ee7-b4fc-96332247abd5n@googlegroups.com>
User-Agent: G2/1.0
MIME-Version: 1.0
Message-ID: <9d2ec319-3d85-4d89-b91d-4930f89f880cn@googlegroups.com>
Subject: Re: supercomputer progress
From: whit...@gmail.com (whit3rd)
Injection-Date: Tue, 21 Jun 2022 17:47:56 +0000
Content-Type: text/plain; charset="UTF-8"
X-Received-Bytes: 2983
 by: whit3rd - Tue, 21 Jun 2022 17:47 UTC

On Monday, June 20, 2022 at 5:47:09 AM UTC-7, a a wrote:

> Climate Change is an old fake by Al Gore, Prof. Mann and their team to make money fast.

False, of course. Al Gore had some election-year lies aimed that way, and as for 'make money',
all Mann got was some frivolous lawsuits. The court had his legal team's fees reimbursed
by the jackals that brought the suit against him. The court did that because the suits
were found to be 'barratry', rather than being serious complaints.

> Freon is another fake.

Not so; that's a DuPont tradename for fluorocarbon products, under worldwide ban
due to ozone depletion.

> Climate is clocked by solar activity and by fluctuations in solar activity.

'clocked by'??? Climate is affected by solar heat (influx of heat dominates during the day) and
radiative cooling (heat dissipates into space, dominates the heatflow at night). The steady-state
average temperature isn't proportional to anything the Sun does, but is set by the difference of
those two heat flows (the difference is zero when steady-state temperature is achieved).
So, your identification of 'solar activity' is only a half-truth at best, and in most literature,
'solar activity' only means sunspot fluctuations, not solar heat output. Indeed, the solar
heat output is set by fusion rates in the sun's center, many thousands of miles away from
the photosphere where we see sunspots.

> So it's a waste of time and money to study Climate Change, living on the Earth, if you can easily study fluctuations in solar activity to get science on what really controls the Climate.

Utterance of nonsense is detected. Agriculture, forestry, water resources, sea life are all being hurt
by climate change, and gazing at Mr.Sun isn't a rational plan to deal with it.

Pages:123
server_pubkey.txt

rocksolid light 0.9.7
clearnet tor