Happy New Year Crunchers!

Per the plans we announced last year year, the CUDA 4.2 application is now terminated leaving the CUDA 6.0 and CUDA 6.5 applications in production.

Henceforth, the CUDA 6.0 application will become the "compatibility" application, providing support to older systems. It will not receive any feature updates.

All new feature releases - new GPU support, performance improvements, etc - will be introduced in the CUDA 6.5 application. Baring any unhappy surprises, CUDA 6.5 will be our build platform throughout 2015 and into 2016.

As you can see from our statistics graph http://www.gpugrid.net/graphs/trend-appver.png , showing the fraction of our results produced by each application version, currently some 20% of our results are produced by the CUDA 6.0 application.

We'd very much like to reduce that to a minimum, so that as many people as possible are using the better application. To ensure you are getting the CUDA 6.5 application, please ensure that your NVIDIA driver is on branch 343 or higher.

Matt

Will CC1.3 support be dropped?

CC1.3 cards:

1.3 	Tesla: GT200, GT200b 	GeForce GTX 280, GeForce GTX 275, GeForce GTX 260, Quadro FX 5800, Quadro FX 4800, Quadro FX 4800 for Mac, Quadro FX 3800, Quadro CX, Quadro Plex 2200 D2, Tesla C1060, Tesla S1070, Tesla M1060

Current contribution is <1%

Compute capable 2.0 and above:

2.0 	Fermi: GF100, GF110 				GeForce GTX 590, GeForce GTX 580, GeForce GTX 570, GeForce GTX 480, GeForce GTX 470, GeForce GTX 465, GeForce GTX 480M, Quadro 6000, Quadro 5000, Quadro 4000, Quadro 4000 for Mac, Quadro Plex 7000, Quadro 5010M, Quadro 5000M, Tesla C2075, Tesla C2050/C2070, Tesla M2050/M2070/M2075/M2090
2.1 	GF104, GF106, GF108, GF114, GF116, GF119 	GeForce GTX 560 Ti, GeForce GTX 550 Ti, GeForce GTX 460, GeForce GTS 450, GeForce GTS 450*, GeForce GT 640 (GDDR3), GeForce GT 630, GeForce GT 620, GeForce GT 610, GeForce GT 520, GeForce GT 440, GeForce GT 440*, GeForce GT 430, GeForce GT 430*, GeForce GTX 675M, GeForce GTX 670M, GeForce GT 635M, GeForce GT 630M, GeForce GT 625M, GeForce GT 720M, GeForce GT 620M, GeForce 710M, GeForce 610M, GeForce GTX 580M, GeForce GTX 570M, GeForce GTX 560M, GeForce GT 555M, GeForce GT 550M, GeForce GT 540M, GeForce GT 525M, GeForce GT 520MX, GeForce GT 520M, GeForce GTX 485M, GeForce GTX 470M, GeForce GTX 460M, GeForce GT 445M, GeForce GT 435M, GeForce GT 420M, GeForce GT 415M, GeForce 710M, GeForce 410M, Quadro 2000, Quadro 2000D, Quadro 600, Quadro 410, Quadro 4000M, Quadro 3000M, Quadro 2000M, Quadro 1000M, NVS 5400M, NVS 5200M, NVS 4200M
3.0 	Kepler: GK104, GK106, GK107 			GeForce GTX 770, GeForce GTX 760, GeForce GT 740, GeForce GTX 690, GeForce GTX 680, GeForce GTX 670, GeForce GTX 660 Ti, GeForce GTX 660, GeForce GTX 650 Ti BOOST, GeForce GTX 650 Ti, GeForce GTX 650, GeForce GTX 780M, GeForce GTX 770M, GeForce GTX 765M, GeForce GTX 760M, GeForce GTX 680MX, GeForce GTX 680M, GeForce GTX 675MX, GeForce GTX 670MX, GeForce GTX 660M, GeForce GT 750M, GeForce GT 650M, GeForce GT 745M, GeForce GT 645M, GeForce GT 740M, GeForce GT 730M, GeForce GT 640M, GeForce GT 640M LE, GeForce GT 735M, GeForce GT 730M, Quadro K5000, Quadro K4200, Quadro K4000, Quadro K2000, Quadro K2000D, Quadro K600, Quadro K420, Quadro K500M, Quadro K510M, Quadro K610M, Quadro K1000M, Quadro K2000M, Quadro K1100M, Quadro K2100M, Quadro K3000M, Quadro K3100M, Quadro K4000M, Quadro K5000M, Quadro K4100M, Quadro K5100M, Tesla K10
3.5 	GK110, GK208 					GeForce GTX TITAN Z, GeForce GTX TITAN Black, GeForce GTX TITAN, GeForce GTX 780 Ti, GeForce GTX 780, GeForce GT 640 (GDDR5), GeForce GT 630 v2, Quadro K6000, Quadro K5200, Tesla K40, Tesla K20x, Tesla K20
3.7 	GK210 						Tesla K80
5.0 	Maxwell: GM107, GM108 				GeForce GTX 750 Ti, GeForce GTX 750, GeForce GTX 860M, GeForce GTX 850M, GeForce 845M, GeForce 840M, GeForce 830M, Quadro K2200, Quadro K620, Quadro K620M
5.2 	GM204 						GeForce GTX 980, GeForce GTX 970, GeForce GTX 980M, GeForce GTX 970M, GeForce GTX 965M

---

FAQ's

HOW TO:
- Opt out of Beta Tests
- Ask for Help

Will CC1.3 support be dropped?

Yes, very soon. This will be effected with a change to the scheduler.

Matt

Thanks for the heads-up Matt :)

---

[CSF] Thomas H.V. Dupont
Founder of the team CRUNCHERS SANS FRONTIERES 2.0
www.crunchersansfrontieres

...and CUDA 7 Release Candidate becomes available to download!

http://www.gpugrid.net/forum_thread.php?id=3977#39469
as pointed out by [CSF] Thomas Dupont - thanks.

I knew it was on the near horizon, but for this came out on the same day Matt predicts the future is :))

"cuFFT 7.0 improves FFT performance by up to 3.5x on Tesla K20c for sizes that are composite powers of 2, 3, 5, and 7. Figure 2 shows speedups of cuFFT 7.0 vs. cuFFT 6.5 for 3D FFTs." - any use?

---

FAQ's

HOW TO:
- Opt out of Beta Tests
- Ask for Help

You're welcome my dear skgiven :)

---

[CSF] Thomas H.V. Dupont
Founder of the team CRUNCHERS SANS FRONTIERES 2.0
www.crunchersansfrontieres

Already been working with CUDA 7. The CUFFT enhancements aren't relevant for GPUGRID. We'll only move now if new hardware makes it necessary (which the reason why we had to bump to 6.5 soon after moving to 6.0).

Matt

A good decision then.
IMO its highly likely that any more GM204's or new GM206 & GM207 cards will remain at CC5.2. I don't expect any compute capability changes until GM210 turns up, and I can't see that happening any time soon. A 28nm GM210 might turn up, but I see little point in that. Even if it does it could be many months, there might not be too many available, prices could be exclusively high and if you have a high end GK110 why move to another 28nm card? That all suggests a late 20nm or 16nm model a long way from now (next year) which would probably see significant CC changes and might take a lot of work on your part (months) to accommodate.

---

FAQ's

HOW TO:
- Opt out of Beta Tests
- Ask for Help