Matteo Perotti

Hello @huanpass, You need `config=8_lanes make verilate`. This compiles the system with 8 lanes and creates the verilated model. Then, you need the `config=8_lanes make bin/${program}` in the `apps` folder,...

Hello Fog-cake, Thanks a lot for the inputs! We will have a deeper look at it. An FPGA project for Ara is planned, but not in the immediate future. Nevertheless,...

Thanks a lot, @yanghao! I answered here -> https://github.com/pulp-platform/ara/issues/87

Hello @yanghao, sorry for the very long delay. I should have fixed the hang issue in the PR https://github.com/pulp-platform/ara/pull/102. Check that out and see if your full program still hangs!...

What a shame! The number of fetched mask elements should be okay now; can you share the full program? If yes, I will work on it.

We have implemented new fixes for Ara. Two PRs should still be approved but are ready: https://github.com/pulp-platform/ara/pull/114 https://github.com/pulp-platform/ara/pull/123 Do you want to check them out with your full program?

The fixes are in the main branch now; feel free to try your program again and let us know! :-)

Hello @bonewp, Thanks for the question! Thus far, Ara deals with this by stalling when `LMUL` is changed (`WAIT_STATE` in the `ara_dispatcher`) until all the previous operations are over. In...

Hello @yanghao, Currently, Ara supports the following features: https://github.com/pulp-platform/ara/blob/main/FUNCTIONALITIES.md As @suehtamacv already pointed out, the `gather` instruction is in the working pipeline, but there is no concrete plan for `vrgather`...

Hi Fog-cake, Thanks for the question! `LMUL != 1` should be supported by all the instructions, and the indexed memory operations are now being merged into the main branch with...