NVIDIA OpenCL Linux Benchmarks

Why does PTS not install the headers locally?

Quote:

---

Originally Posted by deanjo

Let me highlight for you:

http://img13.imageshack.us/img13/676...eprecision.jpg

http://en.wikipedia.org/wiki/Double_...g-point_format

---

Hehe, that's a CC 1.3 feature and GT220 only supports CC 1.2.

In short, I was wrong, there were some changes with regard to CC since the 8000 thousand series. But my point was there's a mistake (two actually) in the article. It claims that the GT220 is faster than 9800GTX (48 vs 128 CUDA cores, who are we kidding here?) and also that we should expect it to be faster.

Quote:

---

Originally Posted by bug77

Hehe, that's a CC 1.3 feature and GT220 only supports CC 1.2.

In short, I was wrong, there were some changes with regard to CC since the 8000 thousand series. But my point was there's a mistake (two actually) in the article. It claims that the GT220 is faster than 9800GTX (48 vs 128 CUDA cores, who are we kidding here?) and also that we should expect it to be faster.

---

Understandable, when I was thinking of "200 series" I was thinking of the GTX line. Anyways I noticed that my previous bench of the GTX-580 was running the wrong mandel test. Here are the complete results again with the correct test included.

http://img25.imageshack.us/img25/9671/gpgpu.png

Quote:

---

Originally Posted by dyna

You mean something like this? As described on the last page...

---

I did not. Michael failed to describe an architectural change that made that possible. For all I know, the performance discrepancy is a bug.