gx fe330ca279 arch: close open question §6.6 — events as default for cross-process sync ...

См. spike-v2 (commit ad54305) + arch review 2026-05-15.

cudaStreamSynchronize-only фактически работает на single-host single-GPU
(0 torn в 4 scenarios PoC), но NVIDIA Programming Guide §3.2.8 не даёт
contractual гарантии. Переключаемся на cudaIpcEventHandle_t как default,
stream-sync остаётся опциональным fallback.

Net: +20µs mean latency, -3× max latency (predictable tail), future-proof
для multi-GPU.

2026-05-14 23:00:40 +01:00

..

measurements

spike-v2: validate sync semantics (R1/R2 architectural review)

2026-05-14 23:00:13 +01:00

architecture.md

arch: close open question §6.6 — events as default for cross-process sync

2026-05-14 23:00:40 +01:00

benchmarks-phase0.md

phase0: benchmark results — PASSED on RTX 5090 (Blackwell sm_120)

2026-05-14 22:02:49 +01:00