Multiple kernels in cuda 4.0
是否有可能从cuda 4.0中的单个线程同时在多个GPU上启动多个内核？
To use multiple GPUs from a single thread, you can switch between cuda contexts (each of which is bound is bound to a GPU) and launch kernels asynchronously. In effect you will be running multiple kernels across multiple GPUs this way.
However if you have cards with compute capability > 2.0, you can also run kernels concurrently as shown in the comments above. You can find the post about concurrent kernel execution over here.
Ofcourse you can use both if you have multiple cards with compute capability >= 2.0.
yes. If there are 2 devices you can run kernel1<<<>>> at device0 and kernel2<<<>>> at device1. there is an option setdevice() with which you choose the device on which the kernel will be executed. google it, it is in the cuda library 4.0
链接地址: http://www.djcxy.com/p/47414.html上一篇: 使用OpenCV进行并行GPU计算
下一篇: 多个内核在cuda 4.0中