I understand now, I can say NVIDIA simply does not understand target CUDA developers. Almost every move in CUDA development cries about it. NVIDIA confused CUDA developers with 3D game engine developers, and may get setback. Point of no return was removing of device emulation mode. CUDA developers are scientists, who develop parallel algorithms. If a program does not work properly, they will nor debug every line of the code, they will simply rewrite algorithm. And warp tricks are not for them, cause their CUDA program is totally parallel anyway. CUDA has number of almost useless features, but main features are hard to get. Also they were troublesome too long. So, now CUDA is becoming more special architecture again, where was it some years ago.
Related topics
| Topic | Replies | Views | Activity | |
|---|---|---|---|---|
| Why is CUDA faster then OpenCL | 2 | 1139 | July 5, 2017 | |
| CUDA in emulation mode | 1 | 1652 | March 31, 2009 | |
| Is CUDA good for games? CUDA question. | 2 | 43868 | January 3, 2008 | |
| CUDA on Laptops NVIDIA's lack of support for CUDA on mobile GPUs | 4 | 4636 | November 25, 2008 | |
| Divergent warps Divegent warps | 2 | 995 | October 30, 2011 | |
| For enthusiasts Future CUDA versions | 3 | 2718 | June 10, 2008 | |
| DIfference betweem CUDA and GPGPU | 5 | 7956 | October 27, 2009 | |
| ia it possible to rewrite/port the linux kernel in... CUDA | 1 | 851 | December 7, 2011 | |
| What does Compute Unified Device Architecture mean? | 1 | 1469 | February 4, 2023 | |
| CUDA SUCKS!!! Why <block, thread> cannot be judged by itself | 20 | 8143 | February 17, 2015 |