Graphic Card usable for Prime?

Riza · 2006-03-25, 04:55

nvidia wants to use graphic cards to calculate the phsical part in PC games.

When does Prime95 follow this idea and use the GPU for the math? Is it possible?

Regards

moo · 2006-03-25, 05:18

there are those physix cards being sold currently and they must have some wicked power because i saw things not even a 10000 dollar machine could do in a video game in gameplay.

dsouza123 · 2006-03-25, 05:20

This has been brought up before,
the issue is the precision/size of the numbers (data formats) available.

The GPUs have 32 bit single precision floating point (earlier 16 bit integer)
but 64 bit double precision is needed at least for the FFT routines
used by the Lucas-Lehmer algorithm with Prime95.

If the smaller range of numbers available with 32 bit floats can be
used by a math algorithm then the GPU could be used.

If the algorithm is enhanced by the parallel processing of the GPU then
it could have very good performance.

The physics calculations done on the nVidia GPUs in SLI could also
be done by the AGEIA PhysX Processor ( PPU ) that is starting to ship.

cheesehead · 2006-03-25, 19:24

As I wrote in an earlier thread:

Quote:

The potential use of graphics cards to do L-L testing or factoring has been discussed several times in the Hardware forum. (Search on "graphics" or "video" there.)

The main reason video cards are not suitable for GIMPS work is that GIMPS calculations require high precision and so use double-precision floating-point arithmetic, but video cards operate with only single-precision floating-point numbers. Single-precision FP is all that video work requires, so it is unlikely that any future video cards will be able to perform double-precision FP, not matter how advanced their other capabilities or speed.

Q: Why not use single-precision?
A: It has to do with the technical details of FFT arithmetic, especially the need to guard against losing low-order result bits because of FP rounding/truncation. For more information, search the Math forum threads discussing this subject.

wblipp · 2006-03-27, 00:20

Has anybody looked into Trial Factoring on a GPU? It seems like the data needs of that task are a better match for the hardware.

nucleon · 2006-04-02, 22:27

Looks like the dedicated physics cards won't be suitable for LL work either.

According to:

http://personal.inet.fi/atk/kjh2348fs/ageia_physx.html

The PPUs from Ageia are "optimized for 32-bit floating-point math"

(and yeah the demos using the PPUs looks absolutely awesome)

-- Craig

JHagerson · 2006-05-29, 16:56

Yes, 32-bit math only. Here is a link to the library distribution.

RMAC9.5 · 2006-09-21, 05:23

I recently saw a reference to http://www.peakstreaminc.com which describes the performance increase that is possible using their software libraries and ATI R580 graphics cards. According to this web site they support 64 bit floating point math for high performance computing needs using C and/or C++. They are also offering a no cost evaluation program for Linux workstation users.

guido72 · 2006-10-02, 16:12

Something new under the sun?
http://ir.ati.com/phoenix.zhtml?c=10...519&highlight=
Or are we always facing with double precision iussues?

Cruelty · 2006-11-09, 10:18

How about latest nVidia product?

Quote:

Full 128-bit floating point precision through the entire rendering pipeline

Dresdenboy · 2006-11-09, 11:38

What Nvidia means is actually the 4 component vector composed of 4 32bit floats. See as an example, how they handle the bit count:

Quote:

128-bit floating point high dynamic-range (HDR) lighting with anti-aliasing

* 32-bit per component floating point texture filtering and blending

2006-03-25, 04:55	#1
Riza Mar 2006 11 Posts	Graphic Card usable for Prime? nvidia wants to use graphic cards to calculate the phsical part in PC games. When does Prime95 follow this idea and use the GPU for the math? Is it possible? Regards

2006-09-21, 05:23	#8
RMAC9.5 Jun 2003 3²·17 Posts	64 bit Floating Point Math on ATI R580 graphics cards I recently saw a reference to http://www.peakstreaminc.com which describes the performance increase that is possible using their software libraries and ATI R580 graphics cards. According to this web site they support 64 bit floating point math for high performance computing needs using C and/or C++. They are also offering a no cost evaluation program for Linux workstation users.

Similar Threads
Thread	Thread Starter	Forum	Replies	Last Post
Needed: Graphic artist	Xyzzy	Forum Feedback	3	2015-12-16 18:35
Intel GPU usable?	tha	Hardware	4	2015-07-28 15:31
"Prime Rewards" Credit Card	ewmayer	Puzzles	109	2014-11-22 13:29
Sieving Graphic	masser	Sierpinski/Riesel Base 5	10	2010-10-11 02:25
Is the Fast Hartley Transform usable in DWT?	Dresdenboy	Math	17	2003-08-12 19:09

2006-03-25, 05:18	#2
moo Jul 2004 Nowhere 809 Posts	there are those physix cards being sold currently and they must have some wicked power because i saw things not even a 10000 dollar machine could do in a video game in gameplay.

2006-03-25, 05:20	#3
dsouza123 Sep 2002 2×331 Posts	This has been brought up before, the issue is the precision/size of the numbers (data formats) available. The GPUs have 32 bit single precision floating point (earlier 16 bit integer) but 64 bit double precision is needed at least for the FFT routines used by the Lucas-Lehmer algorithm with Prime95. If the smaller range of numbers available with 32 bit floats can be used by a math algorithm then the GPU could be used. If the algorithm is enhanced by the parallel processing of the GPU then it could have very good performance. The physics calculations done on the nVidia GPUs in SLI could also be done by the AGEIA PhysX Processor ( PPU ) that is starting to ship.

2006-03-27, 00:20	#5
wblipp "William" May 2003 New Haven 2³·5·59 Posts	Has anybody looked into Trial Factoring on a GPU? It seems like the data needs of that task are a better match for the hardware.

2006-04-02, 22:27	#6
nucleon Mar 2003 Melbourne 203₁₆ Posts	Looks like the dedicated physics cards won't be suitable for LL work either. According to: http://personal.inet.fi/atk/kjh2348fs/ageia_physx.html The PPUs from Ageia are "optimized for 32-bit floating-point math" (and yeah the demos using the PPUs looks absolutely awesome) -- Craig

2006-05-29, 16:56	#7
JHagerson May 2005 Naperville, IL, USA 304₈ Posts	Yes, 32-bit math only. Here is a link to the library distribution.

2006-10-02, 16:12	#9
guido72 Aug 2002 Rovereto (Italy) 3·53 Posts	Something new under the sun? http://ir.ati.com/phoenix.zhtml?c=10...519&highlight= Or are we always facing with double precision iussues?