NVIDIA GPU 0: GeForce GT 240 (driver version 19562, CUDA version 3000, compute capability 1.2, 512MB, 257 GFLOPS peak)

Seem about the same as my 9600GSO hopefully the GT 240 is faster. Can't tell as you both have hidden computers...

Would not matter if you could see my computer in any case... Didn't get to run any WUs before I fried the BIOS.

Processor: 4 GenuineIntel Intel(R) Core(TM)2 Quad CPU Q6600 @ 2.40GHz [x86 Family 6 Model 15 Stepping 11]

NVIDIA GPU 0: GeForce 8800 GT (driver version 19562, CUDA version 3000, compute capability 1.1, 512MB, 339 GFLOPS peak)

---

NVIDIA GPU 0: GeForce GT 240 (driver version 19562, CUDA version 3000, compute capability 1.2, 512MB, 257 GFLOPS peak)

Seem about the same as my 9600GSO hopefully the GT 240 is faster. Can't tell as you both have hidden computers...

Would not matter if you could see my computer in any case... Didn't get to run any WUs before I fried the BIOS.

I really fried a bios chip once. Asus sent 2 new chips pre=programmed for free. A truck hit the pole right in front of my house right as I was updating the bios.
EDIT, did you try clearing the CMOS?

---

Official Abuser of Boinc Buttons...
And no good credit hound!

NVIDIA GPU 0: GeForce GT 240 (driver version 19562, CUDA version 3000, compute capability 1.2, 512MB, 257 GFLOPS peak)

Thanks Pepi, Looks like the GT240 and the 9600GSO are quite simular. It's hard to wade thru my cache but think I found some simular to compare. Yours seems a tiny bit faster.

---

Official Abuser of Boinc Buttons...
And no good credit hound!

NVIDIA GPU 0: GeForce GT 240 (driver version 19562, CUDA version 3000, compute capability 1.2, 512MB, 257 GFLOPS peak)

Thanks Pepi, Looks like the GT240 and the 9600GSO are quite simular. It's hard to wade thru my cache but think I found some simular to compare. Yours seems a tiny bit faster.

No problem :)
Now it compute some "huge" results about 39-40 min: but average time is 25 min.

---

I am cruncher :)
I LOVE SETI BOINC :)

NVIDIA GPU 0: GeForce GT 240 (driver version 19562, CUDA version 3000, compute capability 1.2, 512MB, 257 GFLOPS peak)

Thanks Pepi, Looks like the GT240 and the 9600GSO are quite simular. It's hard to wade thru my cache but think I found some simular to compare. Yours seems a tiny bit faster.

No problem :)
Now it compute some "huge" results about 39-40 min: but average time is 25 min.

Mine are pretty close I feel my average is around 27 min. It would be so nice if someone could come up with a good way to compare card for card.

---

Official Abuser of Boinc Buttons...
And no good credit hound!

Hi guys. I'll post my two 8800GTS's. These are the G92 core. I typically run these at stock speeds, which are 678 mhz gpu clock, 1728 mhz shader clock, and 1944 mhz on the memory.

12/7/2009 5:21:22 PM NVIDIA GPU 0: GeForce 8800 GTS 512 (driver version 19562, CUDA version 3000, compute capability 1.1, 512MB, 442 GFLOPS peak)
12/7/2009 5:21:22 PM NVIDIA GPU 1: GeForce 8800 GTS 512 (driver version 19562, CUDA version 3000, compute capability 1.1, 512MB, 442 GFLOPS peak)

It would be so nice if someone could come up with a good way to compare card for card.

Well, there is CUDA-Z, available on Sourceforge at http://sourceforge.net/projects/cuda-z/files/cuda-z/0.5/CUDA-Z-0.5.95.exe/download

I had to use the direct link button to get the download going.

Martin

It would be so nice if someone could come up with a good way to compare card for card.

Well, there is CUDA-Z, available on Sourceforge at http://sourceforge.net/projects/cuda-z/files/cuda-z/0.5/CUDA-Z-0.5.95.exe/download

I had to use the direct link button to get the download going.

Martin

Have it, doesn't really say much more than specs. Guess posting the start up is best so far.

---

Official Abuser of Boinc Buttons...
And no good credit hound!

It would be so nice if someone could come up with a good way to compare card for card.

Well, there is CUDA-Z, available on Sourceforge at http://sourceforge.net/projects/cuda-z/files/cuda-z/0.5/CUDA-Z-0.5.95.exe/download

I had to use the direct link button to get the download going.

Martin

Have it, doesn't really say much more than specs. Guess posting the start up is best so far.

"GPU Core Performance" isn't enough?

CUDA-Z is not BOINC specific, of course, but it provides numbers for any CUDA capable card, not just those running a BOINC recognized GPU app.

NVIDIA GPU 0: GeForce GT 240 (driver version 19107, CUDA version 2030, compute capability 1.2, 1024MB, 280 GFLOPS peak)

Another GT240 from Gigabyte with 1 GB DDR3 memory
Clock are at 600 and shaders are at 1460
Memory is at 800 MHz

---

I am cruncher :)
I LOVE SETI BOINC :)

only to compare with a stock-speed Sparkle GTX 260-216:

NVIDIA GPU 0: GeForce GTX 260 (driver version 19562, CUDA version 3000, compute capability 1.3, 896MB, 498 GFLOPS peak)

---

- Performance is not a simple linear function of the number of CPUs you throw at the problem. -

Hmm.. strange..

GT240 - no OpenCL
GTX260-216 - no DirectCompute

What will be used in future at SETI@home?

Wouldn't be OpenCL well for ATI and nVIDIA, so only one GPU app?





EDIT: Ops.. after small search.. ATI 'can' also DirectCompute..
Hmm.. but if a/the project will select one of the upper mentioned 'languages' for to have only one GPU app for both manufacturer, it will exclude one nVIDIA GPU.

---

Hmm.. strange..

GT240 - no OpenCL
GTX260-216 - no DirectCompute


EDIT: Ops.. after small search.. ATI 'can' also DirectCompute..
Hmm.. but if a/the project will select one of the upper mentioned 'languages' for to have only one GPU app for both manufacturer, it will exclude one nVIDIA GPU.

Thats only because of my WinXP -> only DirectX9 here, DirectCompute starts with DirectX10 and up.
Im only confused about the OpenCL box of the GT 240. nVidia website tells that this card can do it? But i mostly think, this is a failure in this GPU-Z version.

---

- Performance is not a simple linear function of the number of CPUs you throw at the problem. -

OpenCL depends on the driver version, it was just implemented in 195.62, it isn't in the older drivers.

---

here are some my cuda cards info taken from boinc client.

12/10/2009 12:41:23 AM NVIDIA GPU 0: GeForce GTX 275 (driver version 19107, CUDA version 2030, compute capability 1.3, 896MB, 726 GFLOPS peak)


12/10/2009 2:00:10 AM NVIDIA GPU 0: GeForce GTS 250 (driver version 19107, CUDA version 2030, compute capability 1.1, 1024MB, 473 GFLOPS peak)
12/10/2009 2:00:10 AM NVIDIA GPU 1: GeForce GTS 250 (driver version 19107, CUDA version 2030, compute capability 1.1, 1024MB, 473 GFLOPS peak)

It would be so nice if someone could come up with a good way to compare card for card.

How about?
http://en.wikipedia.org/wiki/Comparison_of_Nvidia_graphics_processing_units
and
http://en.wikipedia.org/wiki/Comparison_of_AMD_graphics_processing_units

---

It would be so nice if someone could come up with a good way to compare card for card.

How about?
http://en.wikipedia.org/wiki/Comparison_of_Nvidia_graphics_processing_units
and
http://en.wikipedia.org/wiki/Comparison_of_AMD_graphics_processing_units

I guess you tech heads get all you need out of specs...But I was talking about RAC comparisons.
Like what RAC should I expect out of my 9600GSO or my GTX275? If a card gets 275 Gflops what RAC would that be?

---

Official Abuser of Boinc Buttons...
And no good credit hound!

If a card gets 275 Gflops what RAC would that be?

I'm one of the few who doesn't care. :-)

---

BOINC V6.6.x

Manufacturer OCed

EVGA GTX260 Core216 SSC - 675/1458/1152 -> 112 GFLOPS
GIGABYTE GTX260(-216) SOC - 680/1500/1250 -> 117 GFLOPS

[GPU/shader/RAM]

A stock GTX260-216 -> 576/1242/999
[...]

After update to BOINC V6.10.18:

The EVGA brothers :
NVIDIA GPU 0: GeForce GTX 260 (driver version 19038, CUDA version 2030, compute capability 1.3, 896MB, 630 GFLOPS peak)
NVIDIA GPU 1: GeForce GTX 260 (driver version 19038, CUDA version 2030, compute capability 1.3, 896MB, 630 GFLOPS peak)
NVIDIA GPU 2: GeForce GTX 260 (driver version 19038, CUDA version 2030, compute capability 1.3, 896MB, 630 GFLOPS peak)
NVIDIA GPU 3: GeForce GTX 260 (driver version 19038, CUDA version 2030, compute capability 1.3, 896MB, 630 GFLOPS peak)

The GIGABYTE:
NVIDIA GPU 0: GeForce GTX 260 (driver version 19038, CUDA version 2030, compute capability 1.3, 896MB, 653 GFLOPS peak)

The 'normal' AR WU 0.448x is well for to compare..

The EVGA ~ 570 sec. - 9 m : 30 s
The GIGABYTE ~ 550 sec. - 9 m : 10 s

---