Kernels
Kernels copied to clipboard
[STF] Use a reduce access mode to compute residuals
Compute residuals using a reduce access mode rather than a sequential code on the host
Which kernels are implemented?
- [ ] synch_p2p (p2p)
- [ ] stencil
- [ ] transpose
- [ ] nstream
- [x] dgemm
- [ ] reduce
- [ ] sparse
- [ ] branch
- [ ] random
- [ ] refcount
- [ ] synch_global
- [ ] PIC
- [ ] AMR
Do you certify that your contribution is made in good faith and does not attempt to introduce any negative behavior into this project?
- [x] Yes
- [ ] No
You tested this locally already, right?
Yes but it is not ready for merge (i thought it was a draft PR actually !), i need to adapt more kernels