Multi-Model Scheduling on Three NPU Cores: Detection + Recognition + Classification
RK3588’s NPU has three cores that run independently or together. The core question in multi-task scenarios: which model gets which core.
The art of core assignment
- Assign by priority: the main detector owns core0; secondary classifiers/OCR share core1/2;
- Avoid frequent switching: multi-model switching on one core costs context overhead; stagger by business peaks;
- Combined mode: for one oversized model (high-res segmentation), join all three cores — throughput over latency.
Hand-assign cores with the rknn core_mask parameter and measure — more instructive than any auto-scheduler.
Related products: RK3588 Mini PC, IPA-RK3588 industrial board. Datasheets, firmware and SDKs are free at the Hugsun Documentation Center; for selection advice or volume pricing, talk to us.
