By: David Kanter (dkanter.delete@this.realworldtech.com), July 25, 2012 11:14 am
Room: Moderated Discussions
sf (pc.delete@this.email.com) on July 25, 2012 6:46 am wrote:
> David Kanter (dkanter.delete@this.realworldtech.com) on July 25, 2012 1:37 am
> wrote:
> > New computational efficiency data shows GPUs with a clear edge over
> CPUs, but
> > the gap is narrowing as CPUs adopt wide vectors (e.g. AVX).
> Surprisingly, a
> > throughput CPU is the most energy efficient processor,
> offering hope for future
> > architectures. Our data also shows some
> advantages of AMD's Bulldozer, and the
> > overhead associated with highly
> scalable server CPUs.
> >
> > Comments and feedback
> > welcome!
> >
>
> > David
>
> For GPU compute, a CPU is needed to be "driving".
Yes, I mentioned that in page 1 : )
> What will
> the graph look like if the driver is included in the calculation?
Well that's hard to say. It will be worse, but by how much?
Is the host CPU doing real calculations as well, or is it just doing setup?
It also depends on the workload, for some the CPU is still more efficient.
> What is the
> currently best ratio of GPU to CPU?
That depends on your workload.
> Will the best future design be a
> BlueGene/Q (for best I/O) driving an optimum number of GPUs (for best Compute)?
If you look at the chart, it should be clear that BGQ stands alone and doesn't need GPUs. From a power perspective, it's superior to all existing GPUs - and it can run a far wider range of workloads.
David
> David Kanter (dkanter.delete@this.realworldtech.com) on July 25, 2012 1:37 am
> wrote:
> > New computational efficiency data shows GPUs with a clear edge over
> CPUs, but
> > the gap is narrowing as CPUs adopt wide vectors (e.g. AVX).
> Surprisingly, a
> > throughput CPU is the most energy efficient processor,
> offering hope for future
> > architectures. Our data also shows some
> advantages of AMD's Bulldozer, and the
> > overhead associated with highly
> scalable server CPUs.
> >
> > Comments and feedback
> > welcome!
> >
>
> > David
>
> For GPU compute, a CPU is needed to be "driving".
Yes, I mentioned that in page 1 : )
> What will
> the graph look like if the driver is included in the calculation?
Well that's hard to say. It will be worse, but by how much?
Is the host CPU doing real calculations as well, or is it just doing setup?
It also depends on the workload, for some the CPU is still more efficient.
> What is the
> currently best ratio of GPU to CPU?
That depends on your workload.
> Will the best future design be a
> BlueGene/Q (for best I/O) driving an optimum number of GPUs (for best Compute)?
If you look at the chart, it should be clear that BGQ stands alone and doesn't need GPUs. From a power perspective, it's superior to all existing GPUs - and it can run a far wider range of workloads.
David
