Interestingly, only 1 test from the PDS-H1 benchmark at scale factor 80 experiences a performance regression. Looks like it's test 6 and comes in at 0.8 of the CPU execution performance the standard polars engine.<p>Seems like there's a more concrete user guide here: <a href="https://docs.pola.rs/user-guide/gpu-support/#whats-supported-on-the-gpu" rel="nofollow">https://docs.pola.rs/user-guide/gpu-support/#whats-supported...</a><p>It seems like they've done a great job of supporting most ops on the GPU already. The main one that is a really bummer is the categorical datatypes. Those are so common in ML workflows and using the native categorical datatype saves a lot of boiler plate as well as prevents you from messing something up during training!