diff options
| author | Arthur Hanson Rasmusson <arthur@vgpu.io> | 2026-10-08 07:54:29 -0400 |
|---|---|---|
| committer | Arthur Hanson Rasmusson <arthur@vgpu.io> | 2026-10-08 07:54:29 -0400 |
| commit | 54cb61b70968c7c8cbc41f669041f4e28d5aa7c4 (patch) | |
| tree | 9b1b4acad8d5438ea122d0948f3eea246ac99b93 /tools/vm/cloud-init.yaml | |
| parent | 5bb2d53ec14f0d802726bc879b994c0286f85415 (diff) | |
| download | open-iov-54cb61b70968c7c8cbc41f669041f4e28d5aa7c4.tar.gz open-iov-54cb61b70968c7c8cbc41f669041f4e28d5aa7c4.zip | |
sema: fix GR counter-slot mapping to fixed pool total (20)
The counter slot for GR rank r is 0x20400fec0 + (TOTAL-1-r)*0x10 with
TOTAL the fixed pool total. The autoreg used a live high-water channel
count instead; channels register progressively, so an early pass with a
partial count (16) registered the ranks present at the wrong slots and
every later rank's correct slot was then rejected as owned. Result:
ranks 10..19 never got a counter, no counter was ever published, and the
client's userspace tracker never advanced (cudaMalloc stall while the
guest RM polled MC_SERVICE_INTERRUPTS).
Validated on a live boot: 20/20 slots registered with 0 collisions
(previously ranks 6..9 installed at the n_gr=16 mapping and ranks 10..19
rejected).
Diffstat (limited to 'tools/vm/cloud-init.yaml')
0 files changed, 0 insertions, 0 deletions
