[Neurodebian-users] fsl-5.0-gpu

[Alex Waite]

On 02/26/2014 02:14 PM, Jonathan Berrebi wrote:
> Hi Alex,
>
> Hopefully it will take less time on a TESLA card since it is the aim to use such one on the server.
 > In that case we don't have any Intel HD/ Optimus issue. I assume 
anyway that people having NVIDIA
 > cards in their laptop use it more to have 3D acceleration or testing 
cuda program than to actually
 > use GPU power for computing.

Exactly.

> We looked at the dyad2.nii.gz file and it looked globally the same. But the histograms are slightly
 > different and substracting the images is (obvisously) not on the 
whole image. I guess this is more
> a question to the FSL mailing list, isn't it?

Yes, this is a question that is best directed to the devs of FSL.

> In the patch I sent earlier today I commented out the line at the origin of the zero padding warning.
 > In the bedpostx_gpu file (and hence in the "monitor" file created by 
the latter), in the "check"
 > routine, the parameters $FSLDIR and $part are not passed. So the 
program is looking for /bin/zeropad
> instead of $FSLDIR/bin/zeropad. Anyway the variable partzp does not seem to be used by "monitor"
 > so I commented it out.

I'll have to take a closer look, but $FSLDIR is an environmental 
variable, so it should be available. If not, then there's a bug/problem 
somewhere.

> And about Optimus, it seems that nvidia does not develop for linux

Correct. They do not develop Optimus for Linux, hence why the bumblebee 
project exists. Nvidia has been less-than-forthcoming with 
specs/documentation for the open source community.

> so the recommended settings for cuda by NVIDIA are the nvidia driver (you see an nvidia screen before login at boot).

Yes. Optimus has little to do with CUDA, so using the official nvidia 
driver is best for CUDA.

> Then when I run samples from the SDK it runs on GPU without issues on gdm. I can use the mouse, play
> around with  windows. But that works only with the following bios settings 
("Discrete Graphics" and
> not "Integrated Graphics" nor "Optimus"). But maybe is also dependent on the laptop?

It might be dependent on the laptop, but it really sounds like you're 
using the nvidia GPU for both display and CUDA. Perhaps CUDA routines 
can run on a GPU also used for a display but not non-CUDA computations.

In any case, it's working, and that's what matters.

> I'll probably contact you soon for the other gpu routines in fsl.

If you have problems or updates, feel free to contact me. That being 
said, I'm a sysadmin by trade rather than a scientist. So others may be 
better equipped to answer science questions :-)

---Alex