Skip to main content

v2n-two-models

Run two models at the same time on an E1M-V2M: one on the RZ/V2N's on-die DRP-AI3 and one on the DEEPX DX-M1, each in its own thread, through <alp/inference.h>. Prints per-NPU latency and the combined FPS. A Linux/Yocto user-space app on the Cortex-A55 cluster.

Source: examples/v2n/v2n-two-models/. New in alp-sdk v0.17.0.

warning
[UNTESTED on silicon]

Nothing here has run on an E1M-V2M, and the two backends have never been run together. Each NPU has been run alone on silicon (DRP-AI3 with YOLOX-S, the DX-M1 with yolo11n). The HIL specs exist but are not bench-verified.

What it shows​

  1. NPU per handle, chosen by model format. backend stays ALP_INFERENCE_BACKEND_AUTO and format names the model: ALP_INFERENCE_MODEL_DRPAI resolves to DRP-AI3, ALP_INFERENCE_MODEL_DXNN to the DX-M1. There is no SoM-specific code; on a SoM without one of the NPUs, that open fails with ALP_ERR_NOSUPPORT.
  2. One thread per NPU. The two NPUs are independent hardware, so a thread on each overlaps their work. Two threads on the same NPU would only take turns.
  3. Only the NPUs a mode needs are opened, so one process per NPU is safe. DRP-AI is one process per board — a second process opening DRP-AI gets ALP_ERR_BUSY.
  4. Solo, then both. The default all mode runs DRP-AI alone, the DX-M1 alone, then both, so the numbers show what sharing the A55 cores and DDR costs each NPU.
  5. CPU budget. Unless you exported them, the program sets TVM_NUM_THREADS=2 and TVM_BIND_THREADS=0 so the DRP-AI TVM runtime's worker pool does not fight the DX-M1 runtime for the four A55 cores. The values are a starting point; their effect is unmeasured.
  6. A failed DRP-AI job is not detectable — the runtime's Run() returns void — so a fast result is not proof of a correct one.

Run​

No compiled model ships in the repository. Provide both:

ArgumentWhat
<drpai-model.tar>a drpai_dir bundle (see v2n-drpai-inference)
<drpai-frame.bin>the raw bytes of that model's input tensor
<model.dxnn>a DEEPX model compiled with dxcom
<dxnn-frame.bin>the raw bytes of that model's input tensor
[seconds]length of each phase, default 10
[mode]all (default), solo-drpai, solo-dx or both
v2n-two-models drpai.tar drpai_frame.bin yolo11n.dxnn dx_frame.bin 30

Expected output​

Shape only — the numbers depend on the models:

[two-npu] v2n-two-models: mode all, 30 s per phase
[two-npu] drpai: handle open (1 input, 1 output)
[two-npu] deepx: handle open (1 input, 1 output)
[two-npu] temp start: thermal_zone0 = <n> mC
[two-npu] phase: solo drpai
[two-npu] drpai: <n> invokes, avg <ms> ms, max <ms> ms, <fps> FPS
[two-npu] phase: solo deepx
[two-npu] deepx: <n> invokes, avg <ms> ms, max <ms> ms, <fps> FPS
[two-npu] phase: both
[two-npu] drpai: ...
[two-npu] deepx: ...
[two-npu] combined: <n> invokes in <s> s = <fps> FPS
[two-npu] temp end: thermal_zone0 = <n> mC
[two-npu] done

board.yaml​

som:
sku: E1M-V2M103

preset: e1m-x-evk

cores:
a55_cluster:
app: ./src # Linux userspace app -- <alp/inference.h> only
recipe: alp-two-models-inference # meta-alp-sdk/recipes-examples/alp-two-models-inference
m33_sm:
os: "off" # Both NPUs are A55/Linux-owned; no M33 app.

diagnostics:
log_level: info

Image requirements​

Linux-only — there is no Zephyr target. Build it with the alp-two-models-inference recipe (add the package to your image). Both NPU stacks must be in the image and in libalp_sdk:

  • DEEPX: meta-deepx-m1 in bblayers.conf (the V2M machine configs enable it).
  • DRP-AI3: meta-rz-drpai in bblayers.conf, and RUHMI_DRPAI_TVM_DIR set to an account-gated Renesas RUHMI checkout. Without RUHMI the SDK's DRP-AI backend is not compiled and a DRP-AI model fails with ALP_ERR_NOSUPPORT.

On V2M, libdxrt turns SIGSEGV / SIGBUS / SIGABRT into a silent exit(1) for every SDK application — see E1M-X V2N-M1.

See also​

Questions about this page? Email contact@alplab.ai