diff options
| author | Arthur Hanson Rasmusson <arthur@vgpu.io> | 2026-10-26 15:01:25 -0400 |
|---|---|---|
| committer | Arthur Hanson Rasmusson <arthur@vgpu.io> | 2026-10-26 15:01:25 -0400 |
| commit | 87adc72977bf1e882b36a0597431f7e113559908 (patch) | |
| tree | dc3ac5ebcde8ba5b0a3ce702471b6ad78da3b045 /debug/risc-v-gsp-rm-vm/plugins/rmharness_plugin.py | |
| parent | a674c21cd101127481ee0fe46710b03216ce7505 (diff) | |
| download | open-iov-87adc72977bf1e882b36a0597431f7e113559908.tar.gz open-iov-87adc72977bf1e882b36a0597431f7e113559908.zip | |
docs/04-real-render-walls: SESSION 134/135 section 14 - the rank-blind first-submission capture caused the CUDA stall regression (fixed, a674c21c); the Vulkan CE rings live at 0x4020000/0x4100000/0x4160000 (above the 64 MB capture bound) and the frame chain reduces to the un-latched ring (copy pend -> dstpend -> black)
Records the instrument, the regression A/B (r746-era module passes, SESSION
133/134 code spins), the rank-aware fix and its r781 verification, the
Vulkan client's actual ring allocations from its own vidheap ioctl log, the
failed 4 GB RAM entry search, and the live frame dependency (GR launch
inline=8 + copy pend src 0xdff0d60000 -> vidmem 0x570000, dst framebuffer
0x50b0000) with ranked next steps.
Diffstat (limited to 'debug/risc-v-gsp-rm-vm/plugins/rmharness_plugin.py')
0 files changed, 0 insertions, 0 deletions