We may not have `vlast.m` but at least we can still compute it.
The RISC-V Vector Extension (RVV) includes several instructions to operate on masks and compute interesting things. One of them is vfirst.m that compute the lowest-numbered element of the mask that is set. However, there is no vlast.m instruction that computes the highest-numbered element of the mask that is set.
Tenstorrent submitted the full rvv-bench results for Ascalon-X and Ascalon-S:
https://camel-cdr.github.io/rvv-bench-results/tt_asc_x/index.html
https://camel-cdr.github.io/rvv-bench-results/tt_asc_s/index.html
Het voorjaar van Matteo Trentin is geëindigd met een val en opgave in de Ronde van Vlaanderen. Hij belandde na een slipper van Magnus Sheffield in een gracht en brak zijn sleutelbeen.
Vollering throws herself in the decend. All in. I can't look, she's not the best bike handler. In the chase group are 2 mountain bikers who should be way better in this stuff. They visual look slower. It's done. They're riding for 2nd place.
What a teammate is Franziska Koch! Always there to pull, keeping with the group when Vollering attacks and when they get back straight to the front. She reminds me of what Marlen Reusser used to do at SDWorx.
Roger Ferrer Ibáñez
camelcdr
Grégory Ienco
Touaregtweet
sam
R_Stieltjes
Mateusz