diff options
| author | Arthur Hanson Rasmusson <arthur@vgpu.io> | 2026-10-06 22:50:15 -0400 |
|---|---|---|
| committer | Arthur Hanson Rasmusson <arthur@vgpu.io> | 2026-10-06 22:50:15 -0400 |
| commit | 3a163f9b65c2d9f50d84f3fb4a738cba09acb567 (patch) | |
| tree | 18eb012ec95fea6326ffa74698113978dc87268b /userspace/cuda/tools/cudatool.py | |
| parent | 5441bdc3a16b12947a5cf9af88e1539da3c9228a (diff) | |
| download | open-iov-3a163f9b65c2d9f50d84f3fb4a738cba09acb567.tar.gz open-iov-3a163f9b65c2d9f50d84f3fb4a738cba09acb567.zip | |
vgsp: mode 35 m62 readback + m63 E2 lane-enable tail
m62 diagnostic: V7 instance/ramfc on host-visible sysmem chunks so the
server's WFI-pointer/TARGET-bit writes are decodable (captured lane uses
unreadable FBMEM slices); decode calls post-promotes and post-construct.
m63 E2: send the real CUDA lane-enable tail after stage-4 schedules
(R2 #1059 NV2080_CTRL_CMD_GR_SET_CTXSW_PREEMPTION_MODE flags=CILP_SET
hChannelGroup=TSG cilp=CILP on the subdevice, #1061
NVA06C_CTRL_CMD_SET_TIMESLICE 0x800 on the TSG, #1063 NV01 device
0x00802009 enable=1). Ground truth: live real CUDA runs with
FECS_CURRENT_CTX VALID=1; our m61 snapshots show V7's context never valid,
and the SKED CWD table never leaves the cold value. Best-effort, mode-35
only.
Diffstat (limited to 'userspace/cuda/tools/cudatool.py')
0 files changed, 0 insertions, 0 deletions