pure/docs/design/022-arrays-and-registers.md, branch masterVerified execution runtime unifying state, persistence, and replication.
http://git.yeowoo.org/pure/atom?h=master2026-10-06T03:32:33ZResearch 128: the batch executor's appends, recurrences, sums into cells and walks (join 423 to 161 ms without machine code, the tier 74) and what a batch pays for, measured apart: an instruction about 20 ns a batch (0.02 ns a round at 1024 lanes), a reduction's end 4-9 ns a round, an append about 100 ns (the executor's), join's recurrence about 60 ns a round; BFS not batched (a count that grows, a filter that only grows, nested walks), so the JIT stays for now; the next in that order: appends at once, the recurrence's steps in registers, reductions' ends; 022 and 024 and CHECKPOINT say so2026-10-06T03:32:33Zeunhhunecpition205@gmail.com2026-10-06T03:32:33Zurn:sha1:9cb6985c0d9459ccf4dbbab4b05109168c362f75Say what finishing 022's stage 3 found: the books and the work in registers, reading ahead to the bucket's last cell, the edge loop's checks; that past C is the reading ahead (16.1 ms without it, C 9.8), and that the criteria move to 023's suite2026-10-05T12:21:39Zeunhhunecpition205@gmail.com2026-10-05T12:21:39Zurn:sha1:5a3466e8ff4d8f3c4271719b90858b7d08697dcdSay what 022 decided while building stages 1-4 and how stage 3 ends: integers assumed, the rest of a round in the executor when they break, the books in registers2026-10-05T10:47:41Zeunhhunecpition205@gmail.com2026-10-05T10:47:41Zurn:sha1:01699935e3f8007c07b143d26bd395bb869f82a6Design 022: stored lists as arrays with a bucket index fitted to the keys searched, narrow columns, a JIT with registers and loop guards, read ahead; criteria first2026-10-05T08:29:23Zeunhhunecpition205@gmail.com2026-10-05T08:29:23Zurn:sha1:58b8d5b291422a0c12db590eefbad6efe96cc6de