Partitioning to optimize AI inference for multi-core platforms
By Rami Drucker, Ceva
EDN (January 8, 2024)
Not so long ago, artificial intelligence (AI) inference at the edge was a novelty easily supported by a single neural processing unit (NPU) IP accelerator embedded in the edge device. Expectations have accelerated rapidly since then. Now we want embedded AI inference to handle multiple cameras, complex scene segmentation, voice recognition with intelligent noise suppression, fusion between multiple sensors, and now very large and complex generative AI models.
Such applications can deliver acceptable throughput for edge products only when run on multi-core AI processors. NPU IP accelerators are already available to meet this need, extending to eight or more parallel cores and able to handle multiple inference tasks in parallel. But how should you partition expected AI inference workloads for your product to take maximum advantage of all that horsepower?
To read the full article, click here
Related Semiconductor IP
- Root of Trust (RoT)
- Fixed Point Doppler Channel IP core
- Multi-protocol wireless plaform integrating Bluetooth Dual Mode, IEEE 802.15.4 (for Thread, Zigbee and Matter)
- Polyphase Video Scaler
- Compact, low-power, 8bit ADC on GF 22nm FDX
Related White Papers
- AI Edge Inference is Totally Different to Data Center
- The Expanding Markets for Edge AI Inference
- Why Interlaken is a great choice for architecting chip to chip communications in AI chips
- The Growing Importance of AI Inference and the Implications for Memory Technology
Latest White Papers
- Reimagining AI Infrastructure: The Power of Converged Back-end Networks
- 40G UCIe IP Advantages for AI Applications
- Recent progress in spin-orbit torque magnetic random-access memory
- What is JESD204C? A quick glance at the standard
- Open-Source Design of Heterogeneous SoCs for AI Acceleration: the PULP Platform Experience