Mersenne Digest           Friday, 29 January 1999      Volume 01 : Number 502


----------------------------------------------------------------------

From: "Brian J Beesley" <[EMAIL PROTECTED]>
Date: Thu, 28 Jan 1999 11:45:12 GMT
Subject: Re: Mersenne: Meganet's alleged fast primality prover

The Mathtrek article in Science News 16-Jan-1999 is interesting, I 
wonder if there is any connection?

See http://www.sciencenews.org/sn_arc99/1_16_99/mathland.htm

Regards
Brian Beesley

------------------------------

From: [EMAIL PROTECTED]
Date: Thu, 28 Jan 1999 08:41:25 -0800 (PST)
Subject: Re: Mersenne: Problems with ATI graphics

I think we talked about this a while ago, but it manifested itself in
noisy RAM (or was it cache chips???). The conclusion was that it was the
extensive heat/EMF given off by a very active processor. Perhaps ATI video
cards are more susceptible to interference. Try moving your video card a
slot or two away from the CPU.

On Wed, 27 Jan 1999, Paul Victor Novarese wrote:

> 
> Has anyone experienced probelems with ATI graphics cards?
> 
> I've been running prime95 on some evaluation machines here and the display
> gets fuzzy when prime is running.  
> 
> ----------------------------------------------
> PGP Fingerprint
> 413D 8BEE 88B3 087B 630D  30A4 951A A435 3D01 AFF4
> [EMAIL PROTECTED]
> 
> 

 --
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~
: WWW: http://www.silverlink.net/poke : Boycott Microsot                :
: E-Mail:  [EMAIL PROTECTED]      : http://www.vcnet.com/bms        :
 ~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~~


------------------------------

From: [EMAIL PROTECTED]
Date: Thu, 28 Jan 1999 10:48:18 -0600
Subject: Re: Mersenne: Problems with ATI graphics

I have the same problem with a 400MHz PII Compaq, I think it has a ATI
      graphics card.

James Escamilla





From: novarese @ job.cba.ua.edu on 01/27/99 04:11 PM


To:   mersenne @ base.com
cc:    (bcc: James Escamilla/TXN)
Subject:  Mersenne: Problems with ATI graphics





Has anyone experienced probelems with ATI graphics cards?
I've been running prime95 on some evaluation machines here and the display
gets fuzzy when prime is running.
- ----------------------------------------------
PGP Fingerprint
413D 8BEE 88B3 087B 630D  30A4 951A A435 3D01 AFF4
[EMAIL PROTECTED]





------------------------------

From: Paul Victor Novarese <[EMAIL PROTECTED]>
Date: Thu, 28 Jan 1999 10:55:39 -0600 (CST)
Subject: Re: Mersenne: Problems with ATI graphics

On Thu, 28 Jan 1999 [EMAIL PROTECTED] wrote:

> I think we talked about this a while ago, but it manifested itself in
> noisy RAM (or was it cache chips???). The conclusion was that it was the
> extensive heat/EMF given off by a very active processor. Perhaps ATI video
> cards are more susceptible to interference. Try moving your video card a
> slot or two away from the CPU.

Could someone explain this "noisy" cache/RAM?  That sounds like it may be
the problem.

More facts for you detectives out there:

1) This is a Dell Optiplex.  All three models (slimline, desktop,
midtower) exhibit this behavior.  

2) I don't think heat is the problem.  The problems start within 5-10
seconds of starting prime and stop as soon as prime is halted.

3) The on-board ATI graphics chip is about 2 cm away from the Slot1,
directly underneath the CPU's big heat sink.

4) The distributed.net client does not cause this behavior.  My
understanding is that it does not use either FPU or cache.



- ----------------------------------------------
PGP Fingerprint
413D 8BEE 88B3 087B 630D  30A4 951A A435 3D01 AFF4
[EMAIL PROTECTED]


------------------------------

From: Andrew Isaacson <[EMAIL PROTECTED]>
Date: Thu, 28 Jan 1999 14:23:58 -0500
Subject: Re: Mersenne: Problems with ATI graphics

On Thu, Jan 28, 1999 at 10:55:39AM -0600, Paul Victor Novarese wrote:
> Could someone explain this "noisy" cache/RAM?  That sounds like it may be
> the problem.

As I recall, someone reported a similar symptom to what you're
reporting:  i.e. a "noisy" video signal.  One possible cause that was
advanced on the mailing list was that Mersenne's heavy usage of the
FPU or cache might be generating enough interference to cause the
problem.

> More facts for you detectives out there:
> 
> 1) This is a Dell Optiplex.  All three models (slimline, desktop,
> midtower) exhibit this behavior.  

They probably all share the same motherboard design.

> 4) The distributed.net client does not cause this behavior.  My
> understanding is that it does not use either FPU or cache.

That's certainly not true.  Distributed.net's program _does_ use
memory (and hence, the cache).  It may use it _less_ than mersenne,
but less is not "does not use".  That difference could conceivably be
enough to cause the behavior you're seeing.  Depending on which core
you're using, Distributed.net might use MMX (which use the FPU
registers, but perhaps not the FPU itself) or solely integer
instructions.

Do you see the same behavior in all video modes?  If you switch to
text mode (DOS mode), do you still see it?  Could you take a picture
of the interference or try to describe it?

I'm very curious about this...

Here's some speculation:  since you're not reporting screen corruption
(just picture instability), I'll speculate that the corruption is
occurring either between the frame buffer memory (VRAM) and the
RAMDAC, or in the analog video signal after it leaves the RAMDAC.  The
second makes the most sense, since that's an analog signal and is more
susceptible to interference than the digital signals from the VRAM.
The question in my mind is how the CPU can generate a strong enough
signal to interfere with the video signal...

- -andy
- -- 
Andy Isaacson [EMAIL PROTECTED] [EMAIL PROTECTED]    Fight Spam, join CAUCE:
http://www.csl.mtu.edu/~adisaacs/              http://www.cauce.org/

------------------------------

From: "Aaron Blosser" <[EMAIL PROTECTED]>
Date: Thu, 28 Jan 1999 14:33:52 -0600
Subject: RE: Mersenne: Problems with ATI graphics

> Could someone explain this "noisy" cache/RAM?  That sounds like it may be
> the problem.

Since the cache on the PII's is built in, saying it's a cache problem might
as well be the same as calling it a CPU problem.

> More facts for you detectives out there:
>
> 1) This is a Dell Optiplex.  All three models (slimline, desktop,
> midtower) exhibit this behavior.

I assume the video card is similarly close to the CPU in all those models?

> 2) I don't think heat is the problem.  The problems start within 5-10
> seconds of starting prime and stop as soon as prime is halted.

Then we can say it's related with some certainty.

> 3) The on-board ATI graphics chip is about 2 cm away from the Slot1,
> directly underneath the CPU's big heat sink.

That's *way* too close, I would think.

> 4) The distributed.net client does not cause this behavior.  My
> understanding is that it does not use either FPU or cache.

Since you don't see the problem normally, my gut instinct tells me it's
related to FPU activity.

The cache and integer bits of a PII are used with some regularity even if
the machine is just sitting there.

One good test would be to use any other program that uses the FPU alot and
see if the flicker shows up.  Can anyone think of another program that
would?  I suppose any benchmark that tests FLOPS should do the trick.


------------------------------

From: "Aaron Blosser" <[EMAIL PROTECTED]>
Date: Thu, 28 Jan 1999 17:28:33 -0600
Subject: RE: Mersenne: Problems with ATI graphics

> As I recall, someone reported a similar symptom to what you're
> reporting:  i.e. a "noisy" video signal.  One possible cause that was
> advanced on the mailing list was that Mersenne's heavy usage of the
> FPU or cache might be generating enough interference to cause the
> problem.

And besides, most anything running on the machine will cause the CPU to use
it's cache.  That's just unavoidable.

> I'm very curious about this...
>
> Here's some speculation:  since you're not reporting screen corruption
> (just picture instability), I'll speculate that the corruption is
> occurring either between the frame buffer memory (VRAM) and the
> RAMDAC, or in the analog video signal after it leaves the RAMDAC.  The
> second makes the most sense, since that's an analog signal and is more
> susceptible to interference than the digital signals from the VRAM.
> The question in my mind is how the CPU can generate a strong enough
> signal to interfere with the video signal...

Your basic PII probably consumes 18W or so.  That's a guess by the way,
don't quote me on that.  Some of that gets radiated as heat, some will
invariably be EMF.  I would hazard a guess that Intel never reckoned on a
video card being so darn close to the CPU.  Either that, or the ATI
graphics card is especially sensitive to EMF.

One other consideration might be a slightly higher voltage applied to the
CPU.  PII's core voltage is somewhere in the neighborhood of 2.1V I think,
but again, I'm guessing (I actually *do* have the PII specs, just not right
now).  If the applied voltage were a bit higher, that could result in an
unusually high amount of EMF.

Either way...EMF from the CPU definitely appears to be the culprit.  One
possibility which I emailed the original person was to place some braided
copper between the CPU and video card, and tie that to a good ground.
That's not practical though. :-)  We don't all have copper braiding lying
around.

Another option is moving the card to another slot which is the BEST idea if
it's a PCI card.  If it's an AGP card, you can't move it.  Oh drat.

Remember those old hobby computers from back in the 70's that generated so
much EMF you could make a TV flicker from the other side of your house?  Or
how you could place a radio nearby and run a program that generated so much
noise in such a way that you could actually try to play a tune?  Oh, for
fun...  (Okay, I'm not quite old enough to have used a hobby computer in
the 70's...but close, so close).


------------------------------

From: "Louis Towles" <[EMAIL PROTECTED]>
Date: Thu, 28 Jan 1999 18:49:38 -0500
Subject: Re: Mersenne: Problems with ATI graphics

I tried this a few months ago on our E series Gateways (ATI Rage Pro)

Prime95 LL test - yes interference
Prime95 factoring - no interference
Distributed Net Client - no interference
FPU benchmark (I think it was ZD winbench's FPU test) - yes interference
The no FPU benchmark - no interference
It's is in all video modes (although harder to see on some)
It start as soon as you start pegging the FPU (can be right after boot with
the chip still cold to the touch)
Stop as soon as the FPU backs off

Louis Towles

- ----- Original Message -----
From: Aaron Blosser <[EMAIL PROTECTED]>
To: <[EMAIL PROTECTED]>
Sent: Thursday, January 28, 1999 3:33 PM
Subject: RE: Mersenne: Problems with ATI graphics


>
>One good test would be to use any other program that uses the FPU alot and
>see if the flicker shows up.  Can anyone think of another program that
>would?  I suppose any benchmark that tests FLOPS should do the trick.
>


------------------------------

From: Jefferson M Wolski <[EMAIL PROTECTED]>
Date: Thu, 28 Jan 1999 18:29:55 -0800
Subject: Re: Mersenne: Rewards for prime stuff??

At 12:19 PM 1/27/99 -0500, Michel Lacoursiere wrote:
>> 3 is a factor of M(4) = 15, I claim the prize, since no-one will
>ever
>> find a smaller prime factor of any Mersenne number ;-)
>
>What about 1 ? Isn't it a factor?
>
>Michel Lacoursière
>[EMAIL PROTECTED]
> 

What about -15, isn't it a factor?

Respectfully,
Jeff Wolski


------------------------------

From: Jefferson M Wolski <[EMAIL PROTECTED]>
Date: Thu, 28 Jan 1999 18:46:57 -0800
Subject: Re: Mersenne: old prime source code?

At 04:17 PM 1/27/99 -0600, brandon j whitehead wrote:
>i didn't know exactly where to send this, so i sent it here.
>
>i'm new to this prime number scene, and i was wondering if there was some
>old c++ source code lying around anywhere that anyone knew of that you
>wouldn't mind tossing my way.  i've been writing a simple math program,
>for experience, fun, and to aid my sisters, and i thought i'd put in a
>prime number function.  i know (or at least my understanding is) that to
>find all the primes less than a number you get rid of all the multiples
>of the sq rt of that number.  then you're left with primes.  well i've
>been racking my brains and i can't think of exactly how to do that in
>c++.  i'm a first-yr programmer, (17 & still in hs), and it's not
>surprising to me that i can't figure it out.  right now.  that's why i
>was wondering if there was some code around.  i don't want to copy it.  i
>want to learn from it.  DriverDown......Brandon Whitehead       
>[EMAIL PROTECTED]
>
>ps my version of juno doesn't support attatchments, so please don't send
>one or i won't get the message.  thanks
>
>___________________________________________________________________
>You don't need to buy Internet access to use free Internet e-mail.
>Get completely free e-mail from Juno at http://www.juno.com/getjuno.html
>or call Juno at (800) 654-JUNO [654-5866]
> 

Check out the following link.

http://www.utm.edu/research/primes/index.html#software

Jeff Wolski


------------------------------

From: Leo Feret <[EMAIL PROTECTED]>
Date: Thu, 28 Jan 1999 20:06:23 -0500
Subject: Re: Mersenne: Problems with ATI graphics

Aaron Blosser wrote:

> > Could someone explain this "noisy" cache/RAM?  That sounds like it may be
> > the problem.
>
> Since the cache on the PII's is built in, saying it's a cache problem might
> as well be the same as calling it a CPU problem.
>
>
> The cache and integer bits of a PII are used with some regularity even if
> the machine is just sitting there.
>
> One good test would be to use any other program that uses the FPU alot and
> see if the flicker shows up.  Can anyone think of another program that
> would?  I suppose any benchmark that tests FLOPS should do the trick.

It might be interesting to run CPUmark 99 from
 http://www.zdnet.com/zdtv/screensavers/projects/story/0,3656,2175057,00.html

Leo



------------------------------

From: Henrik Olsen <[EMAIL PROTECTED]>
Date: Fri, 29 Jan 1999 04:36:31 +0100 (CET)
Subject: Re: Mersenne: Problems with ATI graphics

On Thu, 28 Jan 1999, Louis Towles wrote:
> I tried this a few months ago on our E series Gateways (ATI Rage Pro)
> 
> Prime95 LL test - yes interference
> Prime95 factoring - no interference
> Distributed Net Client - no interference
> FPU benchmark (I think it was ZD winbench's FPU test) - yes interference
> The no FPU benchmark - no interference
> It's is in all video modes (although harder to see on some)
> It start as soon as you start pegging the FPU (can be right after boot with
> the chip still cold to the touch)
> Stop as soon as the FPU backs off
> 
> Louis Towles
All this sounds like an excellent time to test the warranty on those
motherboards, as they're obviously defective, and fundamentally flawed
in their design.

Henrik
- -- 
Henrik Olsen,  Dawn Solutions I/S
URL=http://www.iaeste.dk/~henrik/
Get the rest there.


------------------------------

From: "Scott Kurowski" <[EMAIL PROTECTED]>
Date: Thu, 28 Jan 1999 21:23:43 -0800
Subject: Mersenne: RE: Mersenne Digest V1 #501

> Perhaps Scott Kurowski is reading this...maybe he'd like to input
> some thoughts since we would probably rely on the Primenet server to find
> the winner...

In the next 4 to 10 weeks, Entropia.com is willing to put up $1500 for an ECM
largest-factor prize with a qualifier or two on our terms, using PrimeNet 4.0.
The only catch is George has not yet built Prime95's ECM feature to use
PrimeNet.  If there's enough interest you can collectively rattle him about it.
:-)


>   Of course the pool for the next Mersenne prime could always be
> increased.  $10,000 for decrypting a message and only $1,500 for a new
> Mersenne prime just doesn't right to me :)

This should soon change at least a little.


> What is up with  http://project.vobis.de/gimps/
>
> I just get
>
> faliled to open configuration file: "/usr/local/Counter/conf/count.cfg"

What did they say when you emailed them?

Regards,
scott


------------------------------

From: Johnson Kent D <[EMAIL PROTECTED]>
Date: Fri, 29 Jan 1999 08:07:32 -0600
Subject: RE: Mersenne: Problems with ATI graphics

POV-Ray is a multi-platform freeware raytracing program that makes heavy use
of of the FPU.  You can download it from http://www.povray.org/ .

The Windows version will actually even render a test scene for you upon
installation so you don't have to know anything about using the program.

Kent D. Johnson
[EMAIL PROTECTED]

Jesus is Alive...Elvis Isn't!

> -----Original Message-----
> One good test would be to use any other program that uses the 
> FPU alot and
> see if the flicker shows up.  Can anyone think of another program that
> would?  I suppose any benchmark that tests FLOPS should do the trick.
> 

------------------------------

From: "Aaron Blosser" <[EMAIL PROTECTED]>
Date: Fri, 29 Jan 1999 09:44:54 -0600
Subject: RE: Mersenne: RE: Mersenne Digest V1 #501

> In the next 4 to 10 weeks, Entropia.com is willing to put up
> $1500 for an ECM
> largest-factor prize with a qualifier or two on our terms, using
> PrimeNet 4.0.
> The only catch is George has not yet built Prime95's ECM feature to use
> PrimeNet.  If there's enough interest you can collectively
> rattle him about it.
> :-)

C'mon Geroge...get with it!! :-)

> >   Of course the pool for the next Mersenne prime could always be
> > increased.  $10,000 for decrypting a message and only $1,500 for a new
> > Mersenne prime just doesn't right to me :)
>
> This should soon change at least a little.

Scott - Since myself and others have expressed interest in contributing to
a pool for a prize, perhaps you could explain to us all how that might
work, where you're holding the money for the current prize, etc.  Make us
all feel more comfortable about someone holding the prize money in escrow.


------------------------------

From: Leo Feret <[EMAIL PROTECTED]>
Date: Fri, 29 Jan 1999 12:19:02 -0500
Subject: Re: Mersenne: Problems with ATI graphics

I should have made explicit that "when we examined
             the processor usage of the mainstream business
             applications in the Winstone test, we found that
             they do not use any floating point or MMX
             instructions. Consequently, CPUmark99 doesn't
             include those types of instructions either. "
per  http://www.zdnet.com/pcmag/pclabs/bench/cpumark99.html
so this is an elimination benchmark.  But Louis Towles' response
seems definitive.  Leo

Leo Feret wrote:

> Aaron Blosser wrote:
>
> > > Could someone explain this "noisy" cache/RAM?  That sounds like it may be
> > > the problem.
> >
> > Since the cache on the PII's is built in, saying it's a cache problem might
> > as well be the same as calling it a CPU problem.
> >
> >
> > The cache and integer bits of a PII are used with some regularity even if
> > the machine is just sitting there.
> >
> > One good test would be to use any other program that uses the FPU alot and
> > see if the flicker shows up.  Can anyone think of another program that
> > would?  I suppose any benchmark that tests FLOPS should do the trick.
>
> It might be interesting to run CPUmark 99 from
>  http://www.zdnet.com/zdtv/screensavers/projects/story/0,3656,2175057,00.html
>
> Leo


------------------------------

From: Jonathan A Zylstra <[EMAIL PROTECTED]>
Date: Fri, 29 Jan 1999 11:07:30 -0800
Subject: Re: Mersenne: Rewards for prime stuff??

On Thu, 28 Jan 1999 18:29:55 -0800 Jefferson M Wolski
<[EMAIL PROTECTED]> writes:
>At 12:19 PM 1/27/99 -0500, Michel Lacoursiere wrote:
>>> 3 is a factor of M(4) = 15, I claim the prize, since no-one will
>>ever
>>> find a smaller prime factor of any Mersenne number ;-)
>>
>>What about 1 ? Isn't it a factor?
>>
>>Michel Lacoursière
>>[EMAIL PROTECTED]
>> 
>
>What about -15, isn't it a factor?
>
>Respectfully,
>Jeff Wolski
>
>
Unfortunately, M(4) is not a Mersenne number, because the exponent, 4, is
not prime.

Also, what about imaginary numbers as factors?
- -3i and 5i are factors of 15
(i = square root of -1)

Jonathan Zylstra
[EMAIL PROTECTED]

___________________________________________________________________
You don't need to buy Internet access to use free Internet e-mail.
Get completely free e-mail from Juno at http://www.juno.com/getjuno.html
or call Juno at (800) 654-JUNO [654-5866]

------------------------------

From: "Chris K. Caldwell" <[EMAIL PROTECTED]>
Date: Fri, 29 Jan 1999 15:15:00 -0600
Subject: Re: Mersenne: Rewards for prime stuff??

Kidding aside, suppose there was a real prize.  For example, suppose a
third party offered a real prize, say $314,159, for the next Mersenne
prime.  How would GIMPS split the money?  Should it all go to the
individual?  Seems that a fair amount should go to Woltman for writing the
program.  Perhaps also some to PrimeNet and some to those clearing other
exponents...  

How could it be set up so that a large prize would unify rather than
fragment the search?

------------------------------

From: brandon j whitehead <[EMAIL PROTECTED]>
Date: Fri, 29 Jan 1999 15:52:15 -0600
Subject: [none]

Hi.

 i was thanking each person individually for the help with the source
code and explanations, but what with the large response, i decided it
would be easier to just do it this way.  thanks everyone for your help. 
brandon whitehead

___________________________________________________________________
You don't need to buy Internet access to use free Internet e-mail.
Get completely free e-mail from Juno at http://www.juno.com/getjuno.html
or call Juno at (800) 654-JUNO [654-5866]

------------------------------

End of Mersenne Digest V1 #502
******************************

Reply via email to