Batch executor: the round's fewest-left marks at the end of Batch: put after spare_count they moved its large arrays and knapsack ran 7% slower at the same instructions (8.79 against 8.29 ms), at its end about 2% (8.45); research 139's afterword: 026 not taken heavily (the user's word), the one light cut made (a nested count loop's rounds sweeping only when few lanes are left: matmul 25.85 to 24.3 ms), the walk loops kept sweeping each round (held, BFS's batches ran out), and the stop; 041 runs of b21

1 files changed, 1 insertions, 1 deletions

diff --git a/core/module-batch.c b/core/module-batch.c
index 56f9e18..3b9df87 100644
--- a/core/module-batch.c
+++ b/core/module-batch.c
@@ -212,7 +212,6 @@ typedef struct {
     bool none;                  /* no lane runs here */
     Split splits[SPLITS];
     unsigned split_count, buffers, masks, read_count, store_count, spare_count;
-    unsigned low_buffers, low_masks; /* the fewest left since a round began (tide) */
     void *spare[BUFFERS];       /* lanes no value holds any more */
     Read reads[READS];
     Store stores[STORES];
@@ -233,6 +232,7 @@ typedef struct {
     unsigned cells_count;
     const uint32_t *sel;        /* a selection running (NULL: none): its lanes */
     Selection selection;
+    unsigned low_buffers, low_masks; /* the fewest left since a round began (tide) */
 } Batch;
 
 static _Thread_local Batch batch;