Wait 8 ms once for a pipeline met for the first time, and carry the compute variants in the pipeline list.

A draw that met a new pipeline waited 3 ms for its fast link, in every frame, which is just under what the link takes with the stage libraries in the driver's cache: in a first-visit session on a new install 66 of 87 such draws gave up at the end of the wait and their frame was held back. The wait is now 8 ms for each pipeline, counted from its first miss and shared by all its draws, and 16 ms for a frame, so a pipeline the driver has to compile costs one frame the wait and the frames after it nothing.

The pipeline list tool also takes the compute variants a game folder dispatched, which no pipeline record names and which were translated in the middle of play, and reads a list made before as one of its inputs.

Co-Authored-By: Claude Fable 5.2 <noreply@anthropic.com>
This commit is contained in:
chrg6
2026-11-12 08:25:42 -05:00
parent d31c3a1036
commit 9f7c8ae810
8 changed files with 89 additions and 22 deletions

View File

@@ -291,8 +291,9 @@ def main():
recs += [(LIST_PRIORITY, r) for r in extra]
(out / SEED_KEYS).write_bytes(plist[1])
n_keys = len(pipeline_list.read_keys(plist[1])[3])
print(f'pipeline list: {n_keys} pipelines; of the {len(plist[0])} shader variants they name, {len(extra)} join the '
f'seed, {absent} are of shaders {a.version} does not have, the others are in it already', flush=True)
print(f'pipeline list: {n_keys} pipelines; of its {len(plist[0])} shader variants (the ones they name and the '
f'compute variants), {len(extra)} join the seed, {absent} are of shaders {a.version} does not have, the '
'others are in it already', flush=True)
recs.sort(key=lambda r: r[0]) # stable: list order within a priority
with open(out / 'seed-programs.bin', 'wb') as f:
f.write(b'NX2NSPRG' + struct.pack('<II', 1, 0))