NVIDIA GeForce GTX 780 Ti To Cost Around $650 ? GeForce GTX 780 Reciving Price Cut To Tackle Radeon R9 290
Read more: http://wccftech.com/nvidia-geforce-g...#ixzz2iSx9lsMX
Xtreme SUPERCOMPUTER
Nov 1 - Nov 8 Join Now!
Athlon64 3700+ KACAE 0605APAW @ 3455MHz 314x11 1.92v/Vapochill || Core 2 Duo E8500 Q807 @ 6060MHz 638x9.5 1.95v LN2 @ -120'c || Athlon64 FX-55 CABCE 0516WPMW @ 3916MHz 261x15 1.802v/LN2 @ -40c || DFI LP UT CFX3200-DR || DFI LP UT NF4 SLI-DR || DFI LP UT NF4 Ultra D || Sapphire X1950XT || 2x256MB Kingston HyperX BH-5 @ 290MHz 2-2-2-5 3.94v || 2x256MB G.Skill TCCD @ 350MHz 3-4-4-8 3.1v || 2x256MB Kingston HyperX BH-5 @ 294MHz 2-2-2-5 3.94v
I was under the impression that the 780 Ti and the Titan Ultra were different things. Which cards will become EOL?
TITAN is going to be EOL.
Xtreme SUPERCOMPUTER
Nov 1 - Nov 8 Join Now!
Athlon64 3700+ KACAE 0605APAW @ 3455MHz 314x11 1.92v/Vapochill || Core 2 Duo E8500 Q807 @ 6060MHz 638x9.5 1.95v LN2 @ -120'c || Athlon64 FX-55 CABCE 0516WPMW @ 3916MHz 261x15 1.802v/LN2 @ -40c || DFI LP UT CFX3200-DR || DFI LP UT NF4 SLI-DR || DFI LP UT NF4 Ultra D || Sapphire X1950XT || 2x256MB Kingston HyperX BH-5 @ 290MHz 2-2-2-5 3.94v || 2x256MB G.Skill TCCD @ 350MHz 3-4-4-8 3.1v || 2x256MB Kingston HyperX BH-5 @ 294MHz 2-2-2-5 3.94v
Xtreme SUPERCOMPUTER
Nov 1 - Nov 8 Join Now!
Athlon64 3700+ KACAE 0605APAW @ 3455MHz 314x11 1.92v/Vapochill || Core 2 Duo E8500 Q807 @ 6060MHz 638x9.5 1.95v LN2 @ -120'c || Athlon64 FX-55 CABCE 0516WPMW @ 3916MHz 261x15 1.802v/LN2 @ -40c || DFI LP UT CFX3200-DR || DFI LP UT NF4 SLI-DR || DFI LP UT NF4 Ultra D || Sapphire X1950XT || 2x256MB Kingston HyperX BH-5 @ 290MHz 2-2-2-5 3.94v || 2x256MB G.Skill TCCD @ 350MHz 3-4-4-8 3.1v || 2x256MB Kingston HyperX BH-5 @ 294MHz 2-2-2-5 3.94v
Intel Core i7-3770K
ASUS P8Z77-I DELUXE
EVGA GTX 970 SC
Corsair 16GB (2x8GB) Vengeance LP 1600
Corsair H80
120GB Samsung 840 EVO, 500GB WD Scorpio Blue, 1TB Samsung Spinpoint F3
Corsair RM650
Cooler Master Elite 120 Advanced
OC: 5Ghz | +0.185 offset : 1.352v
3 GB or 6 GB? Would be weird to downgrade from Titans memory amount. But $649 for > Titan performance would be quite uncharacteristic of Nvidia, even more so with 6 GB.
My last 2 vga purchases i really try to get a nvidia for cuda development also wanted physx for games but amd both times offered a better bang for buck deal. Especially the last one. I decided to but 680 without a doubt but amd came with game bundles and i immediately change my decision. If amd was 1 day late today i will be using a 680.
Now my idea changed. 5870 then 7970 both times i wanted an nvidia but amd's offer changed my mind. But this time i want an amd so nvidia should came with an offer like it's bundle.
Sent from my SM-N9000Q using Tapatalk
When i'm being paid i always do my job through.
Also what about the DP rate? If the 780 Ti has 1/24 DP rate like the 780 then that would also be a downgrade relative to the Titan.
On the memory, maybe there could be 3 GB and 6 GB official variants, like the 460-768 and 460-1024 (but with no bus width or ROP changes)?
Well, DP is irrelevant for gamers, isn't it? Both cards bear the GeForce label, not Tesla or Quadro
But... Titan is already an idiotic purchase for games outside of a few extreme situations. However it's a really cheap way to get things you'd normally have to get a Tesla or Quadro to get. Nvidia even pushes the cards GPU computing prowess as a reason to buy one.
The best justification for Titan is that you play games and want to do some other stuff that would normally require Tesla or Quadro products. At that point it starts looking like an amazing deal.
AMD Phenom II BE, ASUS Crosshair II formula, 8gb ddr2 800, 470 SLI, PC P&C 750, arcera RAID, 4x OCZ Vertex2, 2x samsung 7200 1tb, HT Omega Clario +
780 Ti is 3 GB.
Xtreme SUPERCOMPUTER
Nov 1 - Nov 8 Join Now!
Athlon64 3700+ KACAE 0605APAW @ 3455MHz 314x11 1.92v/Vapochill || Core 2 Duo E8500 Q807 @ 6060MHz 638x9.5 1.95v LN2 @ -120'c || Athlon64 FX-55 CABCE 0516WPMW @ 3916MHz 261x15 1.802v/LN2 @ -40c || DFI LP UT CFX3200-DR || DFI LP UT NF4 SLI-DR || DFI LP UT NF4 Ultra D || Sapphire X1950XT || 2x256MB Kingston HyperX BH-5 @ 290MHz 2-2-2-5 3.94v || 2x256MB G.Skill TCCD @ 350MHz 3-4-4-8 3.1v || 2x256MB Kingston HyperX BH-5 @ 294MHz 2-2-2-5 3.94v
I don't think the 780 Ti having a low DP rate would be a problem - it wasn't with the 780 either. Having 3 GB vs 6 on Titan and 4 on 290 and 290X would be, though.
Afaik, Titan was a spontaneous creation (AMDs Crysis 2 deal, cough) more for marketing reasons than for anything else.
Damn. Partner models with 6 GB allowed? If not, Nvidia is shooting themselves in the foot, especially with SLI in mind.
The 780 Ti isn't tied down the way TITAN was. 3 GB should be AMPLE for most people, there's no reason to have to charge more for the small handful of people that might need it. Hell, last year (or year before, time goes so quickly...) I was gaming at 3840x1080 on SLI'd GTX 580s (1.5 GB cards).
Xtreme SUPERCOMPUTER
Nov 1 - Nov 8 Join Now!
Athlon64 3700+ KACAE 0605APAW @ 3455MHz 314x11 1.92v/Vapochill || Core 2 Duo E8500 Q807 @ 6060MHz 638x9.5 1.95v LN2 @ -120'c || Athlon64 FX-55 CABCE 0516WPMW @ 3916MHz 261x15 1.802v/LN2 @ -40c || DFI LP UT CFX3200-DR || DFI LP UT NF4 SLI-DR || DFI LP UT NF4 Ultra D || Sapphire X1950XT || 2x256MB Kingston HyperX BH-5 @ 290MHz 2-2-2-5 3.94v || 2x256MB G.Skill TCCD @ 350MHz 3-4-4-8 3.1v || 2x256MB Kingston HyperX BH-5 @ 294MHz 2-2-2-5 3.94v
But at what resolution. If it does use faster memory, we should see improvements at higher resolution compared to titan. Exactly where it needs it the most to compete against r290x. If they use 7ghz ddr, they should in theory have more bandwidth than a 290x.
If they are open about the cooling on the card and the mods like they were with the gtx 780, then they have a monster base for performance increase.
At the same clocks as titan, they should be somewhere along the lines of 5-12% faster because of 7% more shaders and 16.7 percent more bandwidth. Add in 100-150mhz OC models like gtx 780, and you have a card that is 25 percent faster than titan at high resolutions.
In gaming tests, higher factory OC cards like the gtx 780 HOF or lightning are already 10% faster than titan, add in 25 % more shaders and more bandwidth and you should have something that performs like a gtx 690 or 7990.
Last edited by tajoh111; 10-22-2013 at 12:21 PM.
Core i7 920@ 4.66ghz(H2O)
6gb OCZ platinum
4870x2 + 4890 in Trifire
2*640 WD Blacks
750GB Seagate.
Hold onto your seats for the Hall of Fame, SuperOverclock, Classified (unconfirmed), Lightning and more - it's going to be a bumpy ride over the speed bump affectionately called TITAN
Xtreme SUPERCOMPUTER
Nov 1 - Nov 8 Join Now!
Athlon64 3700+ KACAE 0605APAW @ 3455MHz 314x11 1.92v/Vapochill || Core 2 Duo E8500 Q807 @ 6060MHz 638x9.5 1.95v LN2 @ -120'c || Athlon64 FX-55 CABCE 0516WPMW @ 3916MHz 261x15 1.802v/LN2 @ -40c || DFI LP UT CFX3200-DR || DFI LP UT NF4 SLI-DR || DFI LP UT NF4 Ultra D || Sapphire X1950XT || 2x256MB Kingston HyperX BH-5 @ 290MHz 2-2-2-5 3.94v || 2x256MB G.Skill TCCD @ 350MHz 3-4-4-8 3.1v || 2x256MB Kingston HyperX BH-5 @ 294MHz 2-2-2-5 3.94v
Lol! But they couldn't go too far with those OC versions, unless Nvidia somehow improved efficiency. Titan@1 GHz already draws 250W, 265 if you have to increase power- and temperature targets to get there. What Nvidia really really needs to do is to raise the stock targets...80?C is just not enough, the card would get stuck at base clock almost all the time.
Edit:
Is the 780 Ti by any chance based on GK180? It seems that GK110 cannot be used to enable all 15 SMX. K40 and probably K6000 use GK180 and both have the full 2880 cores.
If we examine the specs between gk110 based k20x tesla, the clocks of the cards were only 732 mhz, yet it had a rated tdp of 235watts. Pretty low clocks, but GK110 based titan still goes to 876mhz(even more in practice).
Look at GK180 based K6000 and you have a card that is clocked at 900mhz, has more shaders and has a tdp 10 watts lower TDP than k20x. That's a massive improvement. Before you say they aren't comparable since Tesla is different than the workstation quadro, lets look at the fermi generation.
Tesla M2070 and Quadro 6000 are both based on the same GF100 and if you look at the clocks, they are exactly the same at 574mhz and not only that, they have the same TDP at 225 Watts. They have the same clocks and TDP rating
So now lets look at GK110 to GK180 again for the professional class of cards.
732mhz -->900mhz
2688 shaders --> 2880 shaders
235watt TDP --> 225 watt tdp
Now lets fill in the blanks for titan to gtx 780 ti
876mhz --> ????
2688 shaders --> 2880 shaders
250watt TDP --> ???
So if any of GK180's improvements carry over, even just a little bit(and they used GK180 instead of Gk110), then you have room for monster clocked cards, just as much as gtx 780 if not more.
The 900mhz clocks and 225 watt TDP on a fully enabled big keplar is very impressive for quadro.
Last edited by tajoh111; 10-22-2013 at 02:45 PM.
Core i7 920@ 4.66ghz(H2O)
6gb OCZ platinum
4870x2 + 4890 in Trifire
2*640 WD Blacks
750GB Seagate.
Bookmarks