nghianguyenandClaude Fable 5 13180921c9 Pool dispatch: prefer slot on the GPU where inputs already reside
Two-pass slot acquisition in runInferenceFromPool: Pass A picks an idle
slot whose deviceIndex matches the input GpuMats' resident device
(zero-copy dispatch); Pass B falls back to plain round-robin, where
runInference migrates the inputs via the pinned-host two-hop copy.

Callers that prepare frames on GPU A no longer pay the ~1 ms/frame PCIe
migration when a same-GPU slot is idle, while spillover to the other GPU
under load still works. Input residency is queried outside the slot
mutex via cudaPointerGetAttributes (cheap driver lookup).

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
2026-07-06 20:05:00 +10:00
2026-06-18 05:55:31 +10:00
2026-04-22 16:52:40 +10:00
2026-05-14 17:48:09 +10:00
2026-06-18 05:55:31 +10:00
2026-06-12 14:13:26 +10:00
2026-06-18 05:55:31 +10:00
2026-06-12 14:13:26 +10:00
2026-06-18 05:55:31 +10:00
2026-03-29 14:10:05 +11:00
2026-05-07 23:35:18 +10:00
2026-06-18 05:55:31 +10:00
2026-03-28 16:54:11 +11:00
2026-05-01 11:16:47 +10:00
2026-03-29 14:10:05 +11:00
2026-03-28 16:54:11 +11:00
2026-03-29 14:10:05 +11:00
2026-03-29 14:10:05 +11:00
2026-03-29 14:10:05 +11:00
2026-06-18 05:55:31 +10:00
2026-03-28 13:13:41 +11:00
S
Description
No description provided
13 MiB
Languages
C 55.3%
C++ 43.4%
Python 0.5%
CMake 0.3%
Objective-C++ 0.2%
Other 0.2%