| Commit message (Expand) | Author | Age | Files | Lines |
|---|
| * | Research 133: register tiles measured (132's deciding experiment): past the b... | eunhhu | 12 days | 2 | -1/+89 |
| * | Research 132 (no code): where the batch executor's cost sits (an element's pa... | eunhhu | 12 days | 1 | -0/+166 |
| * | Research 131: the batch executor's general cuts, by the user's choice of the ... | eunhhu | 12 days | 1 | -0/+95 |
| * | Research 130: the batch executor's frontiers (a count's guard, walks in a bat... | eunhhu | 13 days | 1 | -0/+114 |
| * | Research 129: the batch executor's costs cut (appends at once 5.18 to 0.65 ms... | eunhhu | 2026-10-06 | 1 | -0/+124 |
| * | Research 128: the batch executor's appends, recurrences, sums into cells and ... | eunhhu | 2026-10-06 | 1 | -0/+147 |
| * | 024, 126, 127: the lanes are 24 buffers (stage 2), about 200 KB a thread; sta... | eunhhu | 2026-10-05 | 2 | -2/+4 |
| * | Research 127: the batch executor's stage 2 (nested loops' rounds run together... | eunhhu | 2026-10-05 | 1 | -0/+65 |
| * | Research 126: the batch executor's first stage (024) as built and measured: k... | eunhhu | 2026-10-05 | 1 | -0/+100 |
| * | 125: forms and newton runs named; BFS's time after the graph's load is the ge... | eunhhu | 2026-10-05 | 1 | -3/+5 |
| * | Research 125: the tier's first steps against C (e2e56dd: roots 1.40, knapsack... | eunhhu | 2026-10-05 | 1 | -0/+80 |
| * | Research 124: 022's BFS past C only by reading ahead (15.7 ms against 9.9 wit... | eunhhu | 2026-10-05 | 1 | -0/+89 |
| * | Measure 021: BFS 190 to 90 ms over HTTP against C's 9.1, short of C; Pure's f... | eunhhu | 2026-10-05 | 1 | -0/+216 |
| * | The same answers on the final build and the same pure-runs on the Pi, WSL2 an... | eunhhu | 2026-10-04 | 1 | -1/+5 |
| * | Check a pushed view that computes gets the newest value of writes made meanwh... | eunhhu | 2026-10-04 | 1 | -0/+3 |
| * | Measure views off the connection threads: writes' tail as with the CPU shared... | eunhhu | 2026-10-04 | 1 | -0/+84 |
| * | Measure computing faster: a search 2.1 times as fast, TPC-C 4.1%, four finger... | eunhhu | 2026-10-04 | 1 | -0/+160 |
| * | Say why the dashboard's push-to-poll CPU sits at a tenth: an event costs what... | eunhhu | 2026-10-04 | 1 | -0/+4 |
| * | Wake each thread at most once a push, end streams only of stopped apps, and s... | eunhhu | 2026-10-04 | 1 | -0/+15 |
| * | Say what pushing views costs and how fresh it keeps them (019, research 120) | eunhhu | 2026-10-04 | 1 | -0/+91 |
| * | Say what views that compute cost the writes beside them (018 stage 3, researc... | eunhhu | 2026-10-04 | 1 | -0/+82 |
| * | Say what computing in one event costs and finds (018 stage 2, research 118) | eunhhu | 2026-10-04 | 1 | -0/+90 |
| * | Say what a transient state saves a write (018 stage 1, research 117) | eunhhu | 2026-10-04 | 1 | -0/+53 |
| * | Say what an app's tokens cost (017 3b, research 116) | eunhhu | 2026-10-04 | 1 | -0/+58 |
| * | Say that reading the code found stage 3's two races, and how a host changes apps | eunhhu | 2026-10-04 | 1 | -2/+5 |
| * | Say what apps that change on a running host showed (017 stage 3, research 115) | eunhhu | 2026-10-04 | 1 | -0/+115 |
| * | Trade stores with the WSL2 too: its bytes are the Pi's (029, research 114) | eunhhu | 2026-10-04 | 1 | -7/+6 |
| * | Say what running on an x86_64 WSL2 and an M3 Mac showed (research 114) | eunhhu | 2026-10-02 | 1 | -0/+122 |
| * | Say what one sending loop showed (017 2b, research 113) | eunhhu | 2026-10-01 | 1 | -0/+107 |
| * | Measure sending between two apps of a host: local outlet or link (112) | eunhhu | 2026-10-01 | 1 | -0/+56 |
| * | Measure one host of many apps against a process each (111) | eunhhu | 2026-10-01 | 1 | -0/+109 |
| * | Measure 07047c3 again on a quiet Pi (110) | eunhhu | 2026-09-30 | 1 | -3/+20 |
| * | Count instructions where timing cannot tell 3% apart (110) | eunhhu | 2026-09-30 | 1 | -0/+104 |
| * | Say what 109 inferred and what it did not measure | eunhhu | 2026-09-30 | 1 | -1/+3 |
| * | Say that prefetching items did not pay, and why (109) | eunhhu | 2026-09-30 | 1 | -0/+57 |
| * | Say what finding items should gain, before measuring it (109) | eunhhu | 2026-09-30 | 1 | -0/+34 |
| * | Say what the screen showed of a value, and what Vega now keeps from acting (0... | eunhhu | 2026-09-30 | 1 | -2/+21 |
| * | Say what a value means at each boundary, and what checking it found (015, 108) | eunhhu | 2026-09-30 | 1 | -0/+45 |
| * | Say what pinning a value across every boundary checks, before writing the che... | eunhhu | 2026-09-30 | 1 | -0/+37 |
| * | Say TPC-C's RAM numbers since snapshot nodes are reused | eunhhu | 2026-09-30 | 1 | -0/+1 |
| * | Say what snapshots cost the owner, and what reusing their nodes gave (107) | eunhhu | 2026-09-30 | 1 | -0/+141 |
| * | Compare TPC-C on the SD card with SQLite committing in groups, not each trans... | eunhhu | 2026-09-30 | 1 | -0/+2 |
| * | Say what TPC-C costs when SQLite commits in groups too, and with four warehou... | eunhhu | 2026-09-30 | 1 | -2/+175 |
| * | Say what the TPC-C comparison decides, before running it (106) | eunhhu | 2026-09-30 | 1 | -0/+44 |
| * | Say where the shared board now lives, and what is left (105) | eunhhu | 2026-09-30 | 1 | -1/+9 |
| * | Say that sends and applies now spread their fields (105) | eunhhu | 2026-09-30 | 1 | -4/+8 |
| * | Say what laying a record out anew costs (014) | eunhhu | 2026-09-30 | 1 | -1/+1 |
| * | Say how growing a board two nodes share went (105) | eunhhu | 2026-09-30 | 1 | -0/+119 |
| * | Say what the windows and checkpoints cost (013 steps 2 and 3, 104) | eunhhu | 2026-09-30 | 1 | -1/+41 |
| * | Say where a node's memory goes, and the budget it now keeps (104, 013) | eunhhu | 2026-09-30 | 2 | -0/+111 |
