NVIDIA has good laugh with "FASTRA" Super Computer - Page 2

jmke · 4th February 2010, 10:15

DP is useful because it delivers more accurate results

Quote:

Refers to a type of floating-point number that has more precision (that is, more digits to the right of the decimal point) than a single-precision number. The term double precision is something of a misnomer because the precision is not really double. The word double derives from the fact that a double-precision number uses twice as many bits as a regular floating-point number. For example, if a single-precision number requires 32 bits, its double-precision counterpart will be 64 bits long.

The extra bits increase not only the precision but also the range of magnitudes that can be represented. The exact amount by which the precision and range of magnitudes are increased depends on what format the program is using to represent floating-point values.

Kougar · 4th February 2010, 21:22

Quote:

Originally Posted by wutske

Then don't use DP

As most scientific computing groups consider accuracy to be paramount most of them use double-precision workloads. It was specifically done to ensure groups couldn't build FASTRA computers without paying more for Tesla cards. They'd get better performance from RV870 instead of GeForce now.

wutske · 5th February 2010, 10:23

Quote:

Originally Posted by Kougar

As most scientific computing groups consider accuracy to be paramount most of them use double-precision workloads. It was specifically done to ensure groups couldn't build FASTRA computers without paying more for Tesla cards. They'd get better performance from RV870 instead of GeForce now.

The first CUDA cards introduced a while ago also sucked at DP, so Tesla cards aren't the reason why the 'older' cards don't do DP very well.
DP is indeed interesting for scientific groups who want accuracy, but sometimes real-time processing is more important that a bit more accurate results.

Kougar · 5th February 2010, 22:45

Quote:

Originally Posted by wutske

The first CUDA cards introduced a while ago also sucked at DP, so Tesla cards aren't the reason why the 'older' cards don't do DP very well.
DP is indeed interesting for scientific groups who want accuracy, but sometimes real-time processing is more important that a bit more accurate results.

Why are you comparing to older cards? GF100 hasn't yet been sold as CUDA/Tesla cards, so it's rather silly to compare to past models. GF100 was designed especially for DP performance unlike GT200.

DP FMA rate:
GT200 offers 88.5 Gflops
GF100 Tesla offers 744 Gflops
GF100 GeForce offers 186 Gflops
(Source TheTechReport)

I'm not sure what percentage of the market writes for SP FMA and runs calculations twice versus DP FMA and runs them once, but there are enough organizations that built GT200 GeForce computing platforms that this will certainly affect quite a few of them.

Similar Threads
Thread	Thread Starter	Forum	Replies	Last Post
Super Talent Develops Green DDR3 Memory	jmke	WebNews	0	31st August 2009 10:00
NVIDIA Now Providing Notebook Graphics Drivers	jmke	WebNews	0	20th December 2008 15:27
NVIDIA Brings SLI Technology to Intel Bloomfield CPU Platforms	jmke	WebNews	1	14th July 2008 22:13
KANDALF SUPER BLACK TOWER CASE / AMD v's INTEL	vichy	General Madness - System Building Advice	0	19th February 2006 00:46
Antec Super Lanboy Aluminum ATX Computer Case	Sidney	WebNews	0	15th November 2005 14:42
List of fixes included in Windows XP Service Pack 2	jmke	WebNews	1	17th August 2004 15:03
Super Talent 350W 4-in-1 Computer Combo	Sidney	WebNews	0	26th July 2004 05:22
NVIDIA Launches Revolutionary New Multi-GPU Technology	Sidney	WebNews	1	29th June 2004 07:21
NVIDIA Driving Next-Generation Serial ATA Storage Technology to the PC Desktop	Sidney	WebNews	0	2nd June 2004 05:06
Things that happen after u come home from a 10 hours nightshift ..... ( good laugh :)	Sh4rke	Off-Topic Hangout	3	28th April 2004 18:44