Files
aare/python/tests
Ferjaoui d3a5f842bf
Build on RHEL8 / build (push) Successful in 4m17s
Build on RHEL9 / build (push) Successful in 4m33s
Run tests using data on local RHEL8 / build (push) Failing after 4m54s
perf: unprofiled ClusterFinderCUDA throughput script and A100 results
throughput.py measures wall-clock FPS without nsys, for the copy-out
(find_clusters_batched) and zero-copy (BatchView) paths, at 3x3 to 9x9
and 1 and 4 streams. On the A100, zero-copy with 4 streams reaches
94-102 % of the bound predicted by the nsys probes.
2026-10-29 14:21:12 +01:00
..
2025-11-20 09:01:28 +01:00
2025-11-20 09:01:28 +01:00
2026-09-24 09:09:37 +02:00
2026-09-24 09:09:37 +02:00
2025-11-20 09:01:28 +01:00
2026-09-24 09:09:37 +02:00
2025-11-20 09:01:28 +01:00
2026-09-24 09:09:37 +02:00
2026-09-24 09:09:37 +02:00