1. Welcome to TechPowerUp Forums, Guest! Please check out our forum guidelines for info related to our community.

New NVIDIA GeForce GTX280 Three Times Faster than HD 3870 in Folding@Home

Discussion in 'News' started by zekrahminator, May 26, 2008.

  1. panchoman

    panchoman Sold my stars!

    Joined:
    Jul 16, 2007
    Messages:
    9,595 (3.64/day)
    Thanks Received:
    1,200
    nvidia has so much bullshit out there.. its amazing..
     
  2. imperialreign

    imperialreign New Member

    Joined:
    Jul 19, 2007
    Messages:
    7,043 (2.67/day)
    Thanks Received:
    909
    Location:
    Sector ZZ₉ Plural Z Alpha
    that's kinda what I was trying to get across -


    there's differences in WUs as they're intended for specific hardware. A GPU can't run the SMP client, and it would buckle under the work load even if you could; just like a single-core CPU can't efficiently handle SMP workloads, either.

    Perhaps nVidia's GPUs will end up with their own specific folding client - which, I figure they probably would seeing as how different their GPU architecture is over ATIs - one that is more optimized for their GPUs?

    Not saying that's a bad thing, having seperate GPU clients - but, perhaps nVidia's GPU can only work with simple molecules, which is where they get such an astronomical mol/day figure from . . . it makes sense, IMO.

    I guess, really, the only way to see for sure, is when their new GPUs are on the market, and people start folding with them. It'd be interesting to keep an eye on the ppd earned as compared to ATI's cards - if nVidia's are earning fewer ppd as compared to a 3870, then we would know that it's working with less complex WUs.
     
  3. panchoman

    panchoman Sold my stars!

    Joined:
    Jul 16, 2007
    Messages:
    9,595 (3.64/day)
    Thanks Received:
    1,200
    yup, it all comes down to points in the end
     
  4. DrPepper

    DrPepper The Doctor is in the house

    Joined:
    Jan 16, 2008
    Messages:
    7,483 (3.05/day)
    Thanks Received:
    813
    Location:
    Scotland (It rains alot)
    You would think if they were touting how great their gpu was they would pull out 'real' benchmarks :) and say F you crysis "this many" fps
     
  5. imperialreign

    imperialreign New Member

    Joined:
    Jul 19, 2007
    Messages:
    7,043 (2.67/day)
    Thanks Received:
    909
    Location:
    Sector ZZ₉ Plural Z Alpha
    My final .02 cents on this topic before I brush it off entirelly:


    TBH, I think it's great nVidia have finally decided to work with F@H and get their new GPUs ready to help out with the project. Really, the F@H project has the potential to affect everyone sooner or later, in some shape or form.

    I just personally feel this is lacking any sense of tact, though - I really don't think nVidia should be making their new GPUs F@H capability a marketing point to help sell their new hardware; if they've twisted or misrepresented the facts, even more shameful, IMO. There's no point for such points that they are trying to make, when the hardware isn't even here yet to prove what it's truly capable of; and all of us know how the nVidia fanbois will run rampant over these images trying to claim how 1337 the new hardware will be.

    IIRC, I can't recall ATI, nor any other hardware manufacturer making radical claims when they joined up - hell, ATI was rather quiet about it.
     
  6. Megasty New Member

    Joined:
    Mar 18, 2008
    Messages:
    1,263 (0.53/day)
    Thanks Received:
    82
    Location:
    The Kingdom of Au
    I'm brushing this bull off now. WTH does a mol have to do with computing power. Theoretical BS is still BS. If someone has the time to give us some gd numbers we don't understand then why don't they give us some gaming results.
     
    pentastar111 says thanks.
  7. panchoman

    panchoman Sold my stars!

    Joined:
    Jul 16, 2007
    Messages:
    9,595 (3.64/day)
    Thanks Received:
    1,200
    thank you! you're absolutely right
     
  8. phanbuey

    phanbuey

    Joined:
    Nov 13, 2007
    Messages:
    5,205 (2.07/day)
    Thanks Received:
    975
    Location:
    Miami
    some people cant stand the fact that nVidia makes good hardware... I believe it for one, the GTX 280 has shaders that run at twice the speed of ATI's and theyre all full stream processing units, as opposed to one stream processing unit with four whatever attached. that and they said that they changed the architecture of the SP's to make them more efficient per-clock...

    ATi is great, but nVidia got it right. Some people are just haters.
     
    btarunr says thanks.
  9. PVTCaboose1337

    PVTCaboose1337 Graphical Hacker

    Joined:
    Feb 1, 2006
    Messages:
    9,512 (3.01/day)
    Thanks Received:
    1,143
    Location:
    San Antonio, Texas
    Although this might be faster I wanna wait till the card comes out cause these tend to be a bit inaccurate.
     
  10. simlariver New Member

    Joined:
    Jul 17, 2007
    Messages:
    91 (0.03/day)
    Thanks Received:
    6
    Years after years, pre-launch speculation is still the same ... The promise you a 250% better card, which end up been 30% more powerfull. :rolleyes:
     
  11. KainXS

    KainXS

    Joined:
    Sep 25, 2007
    Messages:
    5,600 (2.18/day)
    Thanks Received:
    501
    well you have to take into account that nvidia vs ati has been this way for a while now, these numbers mean nothing, nvidia makes high powered gpu's which can usually crunch much more data than ati's while ati sticks with a complicated but effective combination of a ton of shaders and a decent gpu, I'm pretty sure the 8800GT would do better in folding than the 3870 as well.

    so yeah, a card thats proably 30% faster
     
  12. btarunr

    btarunr Editor & Senior Moderator Staff Member

    Joined:
    Oct 9, 2007
    Messages:
    28,611 (11.22/day)
    Thanks Received:
    13,648
    Location:
    Hyderabad, India
    LOL at some posts. :laugh:

    "mols" in that chart isn't a quantity of a single molecule, they meant number of molecules folded / time, where time is constant.


    The job F@H does is take a protein molecule and simulate its folding in accordance to the raw data F@H servers provide. After simulation of a protein folding, the parameters of the folded molecule (which differ from that of the original) are sent back to the server. This simulation requires computational power.

    I don't think the NVidia graph is exaggerated considering they built the core (F@H core) using NVidia CUDA, and CUDA apps get the most computational power out of both geometry and shader domains of a CUDA-supportive GPU, in this case the fastest NVidia ever made, the GTX 280. There still isn't an IDE that lets you get the most out of ATI's Stream Computing though ATI is working on one.
     
  13. wolf2009 Guest

    whats dr pepper's joke ?
     
  14. Megasty New Member

    Joined:
    Mar 18, 2008
    Messages:
    1,263 (0.53/day)
    Thanks Received:
    82
    Location:
    The Kingdom of Au
    I taught HS chem for 3 yrs b4 moving on to greater pastures. Its not really a joke to me either but that's just how silly those figures are. I don't care one bit about how many times a card can fold over a protein molecule. The only statistics I care about are framerates. I have 10 yrs of college under my belt & this junk tells me nothing about the card.

    Leave the proteins for shakes & stakes & give me some framerates :roll:

    I think I need to lie dowm after that one :rolleyes:
     
  15. newtekie1

    newtekie1 Semi-Retired Folder

    Joined:
    Nov 22, 2005
    Messages:
    19,967 (6.17/day)
    Thanks Received:
    6,047
    PPD isn't a good guage in unit complexity and actual work being done. When you actually look at how the numbers are generated, you realize this.

    How many points each unit is worth depends on how long it would take a P4 2.8GHz(Socket 478 Northwood) with SSE2 disabled to complete. Then they plug the number of days it takes that processor to complete the work unit into the formula 110*(Number of Days) and that is your points per WU for CPUs. Now in the case of the SMP client, the same method is used, but then a 50% bonus is given to each WU's score just because it is an SMP WU. Does that mean the work is any more complex? No. Does that mean the multi-core CPUs are doing more work per WU than a single core CPU? No. But they still get more points per WU and hence more PPD than a single core doing the same work.

    Now, in terms of GPU folding. The new GPU2 client that runs on the new HD2000 and HD3000 are done the same way. They benchmark each WU on a 3850 and then multiply the number of days it take for the WU to complete by 1000. Why 1000? It is just a number they picked. If they pick a lower number to muptiply by when doing the nVidia calculations or begin the benchmarking process with a weaker GPU, then the PPD vs. ATi cards won't be a good guage on performance.
     
    Last edited: May 26, 2008
    Crunching for Team TPU More than 25k PPD
  16. a111087

    a111087

    Joined:
    Apr 2, 2007
    Messages:
    2,745 (1.00/day)
    Thanks Received:
    196
    Location:
    US
    lol, why would you say that? its a comparison of cards from different generations :rolleyes:
     
  17. hat

    hat Maximum Overclocker

    Joined:
    Nov 20, 2006
    Messages:
    16,922 (5.89/day)
    Thanks Received:
    2,064
    Location:
    Ohio
    so when can we expect to be able to download this, and will it work on my 8600gts?
     
    Crunching for Team TPU
  18. Basard

    Basard

    Joined:
    Dec 15, 2006
    Messages:
    586 (0.21/day)
    Thanks Received:
    38
    Location:
    Oshkosh
    yeah, just what i wanna do all day with my new graphics card, fold at home... why not make a FPU (fold processing unit,) instead, and better yet, why dont you get your own computer to put it in--instead of using mine to fold your crap, you cheap bastards, lol.

    why dont they fold us a way to get rid of fossil fuels.
     
  19. Haytch

    Haytch New Member

    Joined:
    Apr 7, 2008
    Messages:
    510 (0.22/day)
    Thanks Received:
    28
    Location:
    Australia
    Wouldnt mind seeing the 280 compared to the G80.
    Would be nicer to see how the 3870 competes against the G92.
     
  20. hat

    hat Maximum Overclocker

    Joined:
    Nov 20, 2006
    Messages:
    16,922 (5.89/day)
    Thanks Received:
    2,064
    Location:
    Ohio
    ignorance is bliss...
     
    Crunching for Team TPU
  21. Rebo&Zooty

    Rebo&Zooty New Member

    Joined:
    May 17, 2008
    Messages:
    490 (0.21/day)
    Thanks Received:
    30
    this is like saying somebody who posts 1 line replys 20times a day is better then somebody who posts long informitive diatribes 5x a day.........
     
  22. Hayder_Master

    Hayder_Master

    Joined:
    Apr 21, 2008
    Messages:
    5,176 (2.20/day)
    Thanks Received:
    638
    Location:
    IRAQ-Baghdad
    well is looking good so we just wait to compare with hd 4870
     
  23. btarunr

    btarunr Editor & Senior Moderator Staff Member

    Joined:
    Oct 9, 2007
    Messages:
    28,611 (11.22/day)
    Thanks Received:
    13,648
    Location:
    Hyderabad, India
    Yes, any GeForce 8, 9 and upcoming series GPU.

    If you can condense a paragraph into 1~2 sentences, it carries equal weight.
     
    hat says thanks.
  24. Rebo&Zooty

    Rebo&Zooty New Member

    Joined:
    May 17, 2008
    Messages:
    490 (0.21/day)
    Thanks Received:
    30
    not if it dosnt make any sence or isnt understood by 1/2 the people.

    i could cut down alot of things i say to 1-3 sentances, but only a few people would get what i was saying.
     
  25. btarunr

    btarunr Editor & Senior Moderator Staff Member

    Joined:
    Oct 9, 2007
    Messages:
    28,611 (11.22/day)
    Thanks Received:
    13,648
    Location:
    Hyderabad, India
    I come across a lot of posts that span across several paragraphs all conveying a point that can fit into a couple of sentences. That's why I used the word condense and not 'cut down'.
     

Currently Active Users Viewing This Thread: 1 (0 members and 1 guest)

Share This Page