diff options
Diffstat (limited to 'STATE-CURRENT.md')
| -rw-r--r-- | STATE-CURRENT.md | 23 |
1 files changed, 20 insertions, 3 deletions
diff --git a/STATE-CURRENT.md b/STATE-CURRENT.md index a3605a0..2b04c0c 100644 --- a/STATE-CURRENT.md +++ b/STATE-CURRENT.md @@ -1,6 +1,6 @@ # Open-IOV Current State -> **Snapshot: 2026-10-02 ~17:12.** This is a dated public status page, not live +> **Snapshot: 2026-10-02 ~22:12.** This is a dated public status page, not live > state; it is refreshed on every progress check. Live working notes are > maintained outside this repository; the public known-knowns/unknowns document > is authoritative here: @@ -81,6 +81,20 @@ chain succeeds. ## Right now (frontier) +- **First real guest CUDA program exercised against the physical backend + (2026-10-02 ~22:01).** A fresh supervised module-owned cycle (claim + full + GSP-RM boot + guest RAM + hardware-primary work forwarding) booted the real + server (`stage 3e complete`, init event `0x1001`, `rpc_result=0` in ~952 ms), + the host ladder ran its `REAL COPY OK`, and the guest enumerated + `NVIDIA GeForce RTX 2080 SUPER`. The static-runtime victory program + (`tools/cuda-ab/victory_mail.cu`) was pushed and started: it printed + `DEVICE ... cc=7.5 sm=48 mem=134152192`, so device-property enumeration now + returns in the guest, then stalled in its first device allocation / UVM + channel path before any kernel executed (only a handful of forwarded ops + reached the host, `work_guest req=3 ok=3`). Teardown was clean (QEMU stopped, + mdev removed, protected region down, host driver healthy, pstore empty). This + is the first time a real CUDA program ran that far in the guest against the + real backend; it is not yet a green execution. - **GR context campaign: the promote-side wall is root-caused; the current wall is the shared-management GR object alloc (2026-10-02 ~17:35).** The long-running context-promote wall was the ladder's virtual address space @@ -110,8 +124,11 @@ chain succeeds. in the commit helper, root-cause the V5 assert's first failure, or rehost the promote flow in risc-v-gsp-rm-debugger. All parameters remain default off; the software path is unchanged with them off. The guest-runnable - victory client (`tools/cuda-ab/victory_mail.cu`, host-oracle green) is ready - for the first green guest execution. + victory client (`tools/cuda-ab/victory_mail.cu`, host-oracle green) has now + run under the full physical-backed stack (front bullet above): the guest + enumerates and reads device properties, then stalls in its first device + allocation / UVM channel path before any kernel executes - the first green + guest execution remains the immediate goal. - **Guest-submission relay and fault relay landed, default off (P6c C0/C1/C3, 2026-10-02 07:43-08:07).** With `gsp_phys_relay=1` the physical engine authors the guest CE copy and the release semaphore: the |