perf: updated nsys kernel probe tests

This commit is contained in:
kferjaoui committed 2026-10-06 10:31:44 +02:00
1 parent 47d89446e2
commit 931a8b52d6
2 files changed
+8 -4

No files matched your search

+3 -2
View File
@@ -19,8 +19,9 @@ n_streams, N, cdim, cap, batch = (int(a) for a in sys.argv[1:6])
f = File(common.DATA_FILE)
pd = File(common.PEDESTAL_FILE)
cf = ClusterFinderCUDA((f.rows, f.cols), (cdim, cdim), n_sigma=common.N_SIGMA,
max_clusters_per_frame=cap, n_streams=n_streams)
cf = ClusterFinderCUDA((f.rows, f.cols), cluster_size=(cdim, cdim),
n_sigma=common.N_SIGMA, max_clusters_per_frame=cap,
n_streams=n_streams)
for _ in range(common.N_PEDESTAL_FRAMES):
cf.push_pedestal_frame(pd.read_frame().copy())
+5 -2
View File
@@ -51,8 +51,11 @@ def run_one(cdim, cap, streams, label, n_frames, batch, outdir) -> dict | None:
for line in p.stdout.splitlines():
if line.strip().startswith(("n_streams", "H2D/frame", "wall")):
print(" ", line.strip())
if not rep.with_suffix(".nsys-rep").exists():
print(f" FAILED: {p.stderr.strip()[-400:]}")
# nsys writes a report even when the traced process crashes, and returns
# the child's exit code: check it, or a dead probe surfaces later as a
# missing CUPTI table in the export.
if p.returncode != 0 or not rep.with_suffix(".nsys-rep").exists():
print(f" FAILED (exit {p.returncode}): {p.stderr.strip()[-400:]}")
return None
subprocess.run([common.NSYS, "stats", "--force-export=true", "--report",