CUDA: Difference between revisions
No edit summary |
No edit summary |
||
| Line 153: | Line 153: | ||
|- | |- | ||
|} | |} | ||
===Compute Capabilities=== | |||
The original public CUDA revision was 1.0, implemented on the NV50 chipset corresponding to the GeForce 8 series. Compute capability, formed of a non-negative major and minor revision number, can be queried on CUDA-capable cards. | |||
{| border="1" | |||
! Revision | |||
! Changes | |||
|- | |||
| 1.1 | |||
| Atomic 32-bit instructions. | |||
Breakpoints and other debugging support. | |||
|- | |||
| 1.2 | |||
| 32 warps and 16K registers per MP. | |||
Vote instructions. | |||
Atomic 64-bit instructions. | |||
|- | |||
| 1.3 | |||
| Double-precision floating point | |||
|- | |||
|} | |||
====1.1==== | |||
==deviceQuery info== | ==deviceQuery info== | ||
===GeForce 310=== | ===GeForce 310=== | ||
| Line 202: | Line 223: | ||
Support host page-locked memory mapping: No | Support host page-locked memory mapping: No | ||
Compute mode: Default (multiple host threads can use this device simultaneously)</pre> | Compute mode: Default (multiple host threads can use this device simultaneously)</pre> | ||
==See Also== | |||
* The nouveau Wiki's [http://nouveau.freedesktop.org/wiki/CUDA CUDA page] | |||
* The [http://code.google.com/p/gpuocelot/ gpuocelot] project, hosted on Google Code. | |||