Matthias Boehm

I'll try to have a look next week. In the meantime, you might want to revisit the integration approach - the large number of files you had to modify is...

These numbers are a bit puzzling. If there is a 1000s difference, how come that rangeReIndex (which also covers the lazy spark indexing) only requires 85s (from which the 80s...

Does this second cluster use 10Gb or 1Gb Ethernet?

I'm still not convinced by this PR because the experimental results were non-conclusive (especially in comparison to simple rewrites), it does not nicely fit into our the architecture of memory...

additional things to think about: (1) handling of updates in terms of assignments or left indexing (we would need to handle this during validate), and (2) the impact on codegen,...

Thanks for getting started on this issue @kev-inn. Unfortunately, I think the PR goes a bit in the wrong direction. We first want to do a basic cleanup of the...

Sorry for the late response but I would like to play around with this a bit before doing the review. I'll come back to this in a few days.

Meanwhile, I think not supporting global variables might be better in the long run as it keeps functions (except for explicit reads/writes) side-effect free. Back when discussing this feature, it...

That is a good point @phaniarnab - the UDF column encoder would not be valid for federated row-partitions we currently work with for the other benchmark use cases. However, for...