diff options
| author | Arthur Hanson Rasmusson <arthur@vgpu.io> | 2026-10-17 01:15:00 -0400 |
|---|---|---|
| committer | Arthur Hanson Rasmusson <arthur@vgpu.io> | 2026-10-17 01:15:00 -0400 |
| commit | 0bb52e0e3cdc86b31dce2daa23eafd099461604a (patch) | |
| tree | 5d194cf768445884396369e4dc4675ec5bf749e8 /wiki/open-iov.org/index.php?title=File:Figure_2-_Intel_vGPU_Scheduler.png&oldid=5644.html | |
| parent | 01994e83c3754c98c065489daabd980fa001d5ba (diff) | |
| download | open-iov-0bb52e0e3cdc86b31dce2daa23eafd099461604a.tar.gz open-iov-0bb52e0e3cdc86b31dce2daa23eafd099461604a.zip | |
vgsp: m171 event completion fixes (minimal cudaEventSynchronize repro now passes) + AGENT-F R2 write/read consistency ledger
- gsp_rm_emulation: the event burst budget becomes a time-windowed rate
(1 s) with completion posts allowed headroom over hint re-posts; the
periodic hint dedups events posted within 250 ms (strictly below its own
500 ms cadence - an equal window races the boundary and skips forever);
force_post skips retired slots (rc=22 spam was an artifact). Verified:
the minimal cudaEventCreate/Record/Synchronize repro and a second repro
with cross-stream waits and elapsed-time now complete on a live boot;
previously cudaEventSynchronize hung forever.
- gsp_sema_service: write/read consistency ledger (AGENT-F R2). Large
device-destination writes record {va_page -> pa, aperture}; the launch
data fill and device-source reads prefer the recorded page whenever
their own resolution disagrees (sema-ledger DIVERGE log). Session
scoped, zero cost while empty.
Diffstat (limited to 'wiki/open-iov.org/index.php?title=File:Figure_2-_Intel_vGPU_Scheduler.png&oldid=5644.html')
0 files changed, 0 insertions, 0 deletions
