summaryrefslogtreecommitdiffstats
path: root/debug/risc-v-gsp-rm-vm/docs/22-PORTING-CUDA-AND-DEVICES.md
diff options
context:
space:
mode:
Diffstat (limited to 'debug/risc-v-gsp-rm-vm/docs/22-PORTING-CUDA-AND-DEVICES.md')
-rw-r--r--debug/risc-v-gsp-rm-vm/docs/22-PORTING-CUDA-AND-DEVICES.md6
1 files changed, 3 insertions, 3 deletions
diff --git a/debug/risc-v-gsp-rm-vm/docs/22-PORTING-CUDA-AND-DEVICES.md b/debug/risc-v-gsp-rm-vm/docs/22-PORTING-CUDA-AND-DEVICES.md
index 63fbffa..8570d0d 100644
--- a/debug/risc-v-gsp-rm-vm/docs/22-PORTING-CUDA-AND-DEVICES.md
+++ b/debug/risc-v-gsp-rm-vm/docs/22-PORTING-CUDA-AND-DEVICES.md
@@ -9,7 +9,7 @@
## 1. The three churn axes and the anchor discipline
NVIDIA ships three things on independent schedules, and any one of them can
-break `open-iov-vfio` while the other two stay still:
+break `vgsp` while the other two stay still:
| Axis | Examples | Primary evidence path |
|---|---|---|
@@ -76,7 +76,7 @@ tools/cudatool.py delta <old>/run/libcuda.so.<old> <new>/run/libcuda.so.<new>
| Name transfer + corpus annotation | `ApplyNameMap.java` (`--dry-run` first), `tools/annotate_corpus.py` | `./risc-v-gsp-rm-debugger.sh symbols export` builds a runtime-address symbol DB from the same index/names |
| Driver-API smoke | `tools/test/cuda_drv_test.c` compiled as `/tmp/cdt` (prints `ALL OK`) | `./risc-v-gsp-rm-debugger.sh symbols resolve --db ... <addr>` spot-checks transferred addresses per call path |
| Runtime workload | `tools/cuda-ab/ab.sh all` (`vector_add.cu`; `RESULT`/`STATUS` must match host) | session-format evidence and `./risc-v-gsp-rm-debugger.sh compare` when firmware-side sessions exist |
-| Guest-side control observation | `tools/guest-diag/ioctl_trace.c`, host module trace (`gsp-resman-vfio:`) | annotation of the firmware-side RPC path with the per-version symbol DB |
+| Guest-side control observation | `tools/guest-diag/ioctl_trace.c`, host module trace (`vgsp:`) | annotation of the firmware-side RPC path with the per-version symbol DB |
| Firmware-side confirmation | — | `./risc-v-gsp-rm-debugger.sh probe` / `record` / `compare` against the paired firmware |
**Be honest about the execution boundary.** `cdt` and `vectorAdd` are x86_64
@@ -182,7 +182,7 @@ remains the dynamic oracle.
| Engine inventory | host oracle `rmtool engine list --format=json`, guest `guest_engines.c` | inventory table |
| Interrupt topology | MSI-X tables, guest `lspci -vvv` | profile notes |
| ROM/VBIOS quirks | ROM read, laptop/Surface variants | profile overrides |
-| Probe-time register values | guest driver init trace (`gsp-resman-vfio:`) | expected-value list |
+| Probe-time register values | guest driver init trace (`vgsp:`) | expected-value list |
The host oracle (`rmharness`, docs/17) is read-only and safe alongside a live
CUDA job; capture it into a session so the numbers carry SHA-256 provenance: