supercomputer progress

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>

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

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.

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.

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

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

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

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.

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

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