Research 138: the batch executor's stage 5, design 025 made: sums into cells at once in integers (join 116.0 to 110.5 ms, short of 108: what is left is the same cells' memory, read, add and write again), decide's bit found once (BFS 23.2, short of 21.5: the tail's time was its loads more than its instructions), and the batch executor's loops aligned to 64-byte lines (the hot loops' placement had swung knapsack 6% at the same instructions; the lists' loops aligned too cost the bank's queries 1-2% more instructions, so not they); against b9 matmul -36%, knapsack -28%, roots -7.6%, join -6.2%, BFS -3.9%, the executor alone, the bank queries and TPC-C (+0.7%) as they were; 025's bars and what each stage measured; 024 and CHECKPOINT say so

1 files changed, 2 insertions, 0 deletions

diff --git a/research/experiments/041-batches/runs.sh b/research/experiments/041-batches/runs.sh
index 4da74fb..ba168b9 100755
--- a/research/experiments/041-batches/runs.sh
+++ b/research/experiments/041-batches/runs.sh
@@ -67,3 +67,5 @@ esac
 # 2026-10-08-batch-costs.jsonl (design 025): knapsack's time a round by
 # function and line, b9's code at BATCH 1024 and 256 under a 2 kHz sampled
 # profile (ms by the in-process C's samples); sum0's times at both.
+# A series run over midnight writes two days' files (2026-10-08 and
+# 2026-10-09 for design 025's stage 5): read both.