Commit Graph
2 Commits
Author SHA1 Message Date
dtourolle ef71bb3289 Time OpenVINO and WebGPU in ep_probe
The Intel and vendor-neutral rungs need a measurement before they join
the ladder (docs/dev/inference.md §2). Both register through the generic
key/value entry point with the option names ONNX Runtime reads at the
wheel's version: OpenVINO 1.24 (`openvino_provider_factory.cc`), WebGPU
1.27 (`webgpu_provider_options.h`, prefixed by the runtime).
DARKROOM_EPS narrows the list to the families a runtime carries.
2026-10-04 21:00:15 -04:00
dtourolleandClaude Opus 5 39a22875b1 Add the MIGraphX rung for AMD GPUs
Benchmarks / CPU and I/O (per commit) (push) Failing after 6m20s
Benchmarks / Frame budget (on demand) (push) Skipped
Build and test / Desktop (Linux) (push) Failing after 45s
Build and test / Layer separation (push) Successful in 26s
Traceability / Requirement traces (push) Failing after 46s
🐳 Android image / Build and push (push) Successful in 1s
Build and test / android-image (push) Successful in 1s
🐳 Windows image / Build and push (push) Successful in 1s
Build and test / windows-image (push) Successful in 1s
Build and test / Android (aarch64) (push) Failing after 2m19s
Build and test / Windows (x86_64, cross) (push) Failing after 3m2s
Measured on a Radeon RX 7900 XT against Arch's onnxruntime-rocm 1.29
(docs/inference.md §1.3): MIGraphX fp16 runs the detectors at 2.4–3.4 ms
against 10–58 ms on the CPU provider, the inpainter at 8 ms against 514,
with a 15–135 s compile per graph the first time and under a second from
its cache after. A compiling rung on TensorRT's terms, wired the same way.

The ROCm execution provider is gone (removed in ONNX Runtime 1.23), so the
AMD ladder is MIGraphX then the CPU, with no non-compiling rung between.

MIGraphX is registered through the runtime's generic key/value entry
point rather than ort's builder: 1.29 reads the legacy options struct for
its precision flags only, and the compiled-program cache directory
(`migraphx_model_cache_dir`) only travels the generic way. The provider's
cache key omits the precision, so f32 and fp16 programs get their own
directories. The probe fingerprint now includes the provider libraries
beside the runtime and the ROCm version, since a distribution's CPU and
ROCm builds are the same file at the same path.

`status().failed` reports only the rungs above the selection, so an AMD
desktop's About line says why MIGraphX won rather than that the NVIDIA
providers are not in the build.

Two examples: `ep_probe` times each provider cold and from cache, and
`ladder` drives `init` as the app does to watch the first-run sequence.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
2026-09-20 19:23:00 +02:00