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
- Bluetooth Low Energy 6.0 Digital IP
- Ultra-low power high dynamic range image sensor
- Flash Memory LDPC Decoder IP Core
- SLM Signal Integrity Monitor
- Digital PUF IP
Related White Papers
- AI Edge Inference is Totally Different to Data Center
- 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
- Top 5 Reasons why CPU is the Best Processor for AI Inference
Latest White Papers
- How Next-Gen Chips Are Unlocking RISC-V’s Customization Advantage
- Efficient Hardware-Assisted Heap Memory Safety for Embedded RISC-V Systems
- Automatically Retargeting Hardware and Code Generation for RISC-V Custom Instructions
- How Mature-Technology ASICs Can Give You the Edge
- Exploring the Latest Innovations in MIPI D-PHY and MIPI C-PHY