COST

Very cool, will digest all this! For my use-case CPU + lots of RAM has been fast enough, and there's a balance between per-thread latency and throughput (serving data concurrently). I'm definitely interested in compressing down the graph data further to see if I can drop latency further, will see if I can adapt some of this. Super neat to see this on GPUs, will check that out too. Also a fan of https://github.com/frankmcsherry/COST if you've seen it before as well!

Martin’s writing and thinking has been hugely inspirational for me too — thanks for highlighting the automerge work here! Next, regarding your other thoughts, two notes, one on performance and one on “common themes”. Re performance: while in my initial comment I linked directly to McSherry & friends’ work on differential dataflow mostly because I value it as a principled and effective framework for incrementalizing many kinds of computation I care about, I would be remiss if I failed to also highlight here their complementary “COST” project of using this framework to demonstrate how carefully engineered (single-threaded!) implementations of graph computations in Rust can often considerably outperform more complex but more wasteful pre-existing approaches (at least in the database world). (Whether the same flavor of result will also appear