Re:Intel’s Manufacturing Roadmap from 2019 to 2029
by david-gpu on Thursday December 12, 2019 @09:00AM
(#21771880)
Not my area of expertise, but I was under the impression that finite element analysis, like other sparse algebra problems, are reasonably well suited for GPUs, which are much more parallel than 2 or 3 cores. Have you looked into that?
[ Parent
| on HN ]
Re:Intel’s Manufacturing Roadmap from 2019 to 2029
by madengr on Thursday December 12, 2019 @12:27PM
(#21773969)
The time domain codes work well with GPUs and multiple cores, but the frequency domain ones don’t. I don’t know enough of what’s going on under the hood, but it’s like that for all of them.