
Mailing List Archive
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]
[tlug] CUDA: Getting started
- Date: Mon, 8 Apr 2013 19:05:15 +0900
- From: Kalin KOZHUHAROV <me.kalin@example.com>
- Subject: [tlug] CUDA: Getting started
Last Saturday's meeting there was some discussion about CUDA on linux...
It is fairly easy to start using CUDA on Gentoo:
$ emerge nvidia-{drivers,cuda-sdk,cuda-toolkit}
But check if your nvidia card has CUDA capability first:
http://en.wikipedia.org/wiki/CUDA#Supported_GPUs
Test that it works:
$ /opt/cuda/sdk/bin/linux/release/deviceQuery
/opt/cuda/sdk/bin/linux/release/deviceQuery Starting...
CUDA Device Query (Runtime API) version (CUDART static linking)
Detected 1 CUDA Capable device(s)
Device 0: "GeForce GT 640"
CUDA Driver Version / Runtime Version 5.0 / 5.0
CUDA Capability Major/Minor version number: 3.0
Total amount of global memory: 2047 MBytes (2146762752 bytes)
( 2) Multiprocessors x (192) CUDA Cores/MP: 384 CUDA Cores
GPU Clock rate: 902 MHz (0.90 GHz)
....
Get something to run, e.g. this "Hello world" :
http://computer-graphics.se/hello-world-for-cuda.html
Compile it with `nvcc hello.cu` and run it with `./a.out`
Also check the examples in /opt/cuda/sdk/?_*
If you are into cracking RAR files check this: http://www.crark.net/
I am checking this now: https://github.com/bkase/CUDA-grep
Cheers,
Kalin.
Home |
Main Index |
Thread Index