Access tu more GPU nodes

[StefaniaOliviero]

Hi all,
I need to execute a Levember Marquardt fit on an acquisition with more than 1000 spatial directions and I verified that this calls for more than 64 GB of VRAM - GPU. I would like to know if MDT could work on more nodes of GPUs.

[robbert-harms]

Hi Stefania,

Unfortunately also that won't work. You hit a roadblock in the current design of MDT. I have some plans for changing this whenever OpenCL 3.0 gets more widely supported, but for now I am afraid this won't work. I would love to have it as much as you do.

Best,

Robbert

[StefaniaOliviero]

Thanks so much Robbert for your answer... Maybe I could fix the issue with a Virtual Machine on Google, I HOPE. Thanks again and have a good job. Cheers Ottieni Outlook per Android<https://aka.ms/ghei36>

…

________________________________ From: Robbert Harms ***@***.***> Sent: Wednesday, April 28, 2021 5:31:28 PM To: robbert-harms/MDT ***@***.***> Cc: StefaniaOliviero ***@***.***>; Author ***@***.***> Subject: Re: [robbert-harms/MDT] Access tu more GPU nodes (#35) Hi Stefania, Unfortunately also that won't work. You hit a roadblock in the current design of MDT. I have some plans for changing this whenever OpenCL 3.0 gets more widely supported, but for now I am afraid this won't work. I would love to have it as much as you do. Best, Robbert — You are receiving this because you authored the thread. Reply to this email directly, view it on GitHub<#35 (comment)>, or unsubscribe<https://github.com/notifications/unsubscribe-auth/AOYBVSB32HOGQZ7XNBZVLADTLAS5BANCNFSM43SJCXTA>.

[robbert-harms]

At your service. If you need anything else you know where to find me.