From All-in-One IP to Cervell™: How Semidynamics Reimagined AI Compute with RISC-V
In an era where artificial intelligence workloads are growing in scale, complexity, and diversity, chipmakers are facing increasing pressure to deliver solutions that are not only fast, but also flexible and programmable. Semidynamics recently announced Cervell™, a fully programmable Neural Processing Unit (NPU) designed to handle scalable AI compute from the edge to the datacenter. Cervell represents a fundamental shift in how AI processors are conceived and deployed. It is the culmination of Semidynamics’ IP offerings evolution from modular IP components to a tightly integrated, unified architecture, rooted in the open RISC-V ecosystem.
Key Takeaways
- Cervell™ is a fully programmable Neural Processing Unit (NPU) designed for scalable AI compute from the edge to the datacenter.
- Cervell integrates CPU, vector units, and tensor engines into a single processing entity, eliminating the need for external CPUs and reducing performance bottlenecks.
- The architecture is based on the open RISC-V ecosystem, allowing for deep customization and flexibility in processor design.
To read the full article, click here
Related Semiconductor IP
- All-In-One RISC-V NPU
- NPU
- NPU IP Core for Mobile
- NPU IP Core for Edge
- Specialized Video Processing NPU IP
Related Blogs
- Custom Compute for Edge AI: Accelerating innovation with Lund University and Codasip University Program
- Semidynamics – Customizable RISC-V Technology for the Next Five AI Revolutions
- RISC-V customization, HW/SW co-optimization, and custom compute
- Effectively hiding sensitive data with RISC-V Zk and custom instructions
Latest Blogs
- ML-KEM explained: Quantum-safe Key Exchange for secure embedded Hardware
- Rivos Collaborates to Complete Secure Provisioning of Integrated OpenTitan Root of Trust During SoC Production
- From GPUs to Memory Pools: Why AI Needs Compute Express Link (CXL)
- Verification of UALink (UAL) and Ultra Ethernet (UEC) Protocols for Scalable HPC/AI Networks using Synopsys VIP
- Enhancing PCIe6.0 Performance: Flit Sequence Numbers and Selective NAK Explained