[Beowulf] Nvidia Tesla GPU clusters?
toon.knapen at fft.be
Wed Jul 18 23:26:17 PDT 2007
Mark Hahn wrote:
>>> Anyone can point me to more information about the 'thread execution
>>> manager' and how threads can enable getting optimal performance out
>>> of this hardware ?
> afaikt, that phrase is what would normally be "instruction scheduler"
> on a normal CPU. I don't believe it's actually managing separate
> (MIMD) threads.
>> much a wasteland these days) asking how jobs were going to be
>> scheduled on a GPU. Nobody knew. I would think this would be
> the GPU, at least as currently conceived, is an exclusive resource
> which the kernel can arbitrate access to. if you really do have several
> GPU-using processes, the kernel would need to swap in/out the GPU state
> on each transition, which would be painful. GPUs don't have protection
> for shared access afaikt.
I thought so too: I always considered the GPU to be a real good
vector-processor. But seeing the 'thread execution manager' stuff I was
now wondering if it would also be able to exploit the power of the GPU
using multiple (non-vector) threads.
More information about the Beowulf