https://tobiasweinzierl.webspace.durham.ac.uk/
In this paper, we extend our concept to let a compiler offload kernels to the GPU through annotations (so similar to OpenMP pragmas). Previously, it converted data SoA and rewrote the compute kernels automatically to work only on these slimmed down data views.
In this paper, we extend our concept to let a compiler offload kernels to the GPU through annotations (so similar to OpenMP pragmas). Previously, it converted data SoA and rewrote the compute kernels automatically to work only on these slimmed down data views.
- All the open WPs
- Our performance assessment worksheet
- Information on some of our recent events
- All the open WPs
- Our performance assessment worksheet
- Information on some of our recent events
together with our friends from @ucl.ac.uk, @manchester.ac.uk, @cake-dri.bsky.social , @imperialcollegeldn.bsky.social, University of Leeds and University of Warwick
Come and do some #SHAREing! 😎
together with our friends from @ucl.ac.uk, @manchester.ac.uk, @cake-dri.bsky.social , @imperialcollegeldn.bsky.social, University of Leeds and University of Warwick
Come and do some #SHAREing! 😎
We did it! A joint uk universities booth at Supercomputing! Congrats to the team.
We did it! A joint uk universities booth at Supercomputing! Congrats to the team.
SHAREing is ready to connect, learn and continue SHAREing what we are working on.
If you're attending the conference, feel free to stop by the UK University's booth to say hi 🙌
#DRI #SHAREing
SHAREing is ready to connect, learn and continue SHAREing what we are working on.
If you're attending the conference, feel free to stop by the UK University's booth to say hi 🙌
#DRI #SHAREing