Designed to enable end-to-end execution of the latest agentic and physical AI networks on advanced SoCs it is based on the existing architecture of the Tensilica Vision DSP family.
The NeuroEdge 130 AICP delivers more than 30% area savings and over 20% savings in dynamic power and energy without impacting on performance while leveraging existing software, AI compilers, libraries and frameworks.
“With the rapid proliferation of AI processing in physical AI applications such as autonomous vehicles, robotics, drones, industrial automation and healthcare, NPUs are assuming a more critical role,” said Karl Freund, founder and principal analyst of Cambrian AI Research. “Today, NPUs handle the bulk of the computationally intensive AI/ML workloads, but many non-MAC layers include pre- and post-processing tasks that are better offloaded to specialised processors.
“Current CPU, GPU and DSP solutions involve different trade-offs, and the industry needs a low-power, high-performance solution that is optimised for co-processing and allows future proofing for rapidly evolving AI processing needs.”
The Tensilica NeuroEdge 130 AICP features an extensible design that provides seamless compatibility with in-house NPUs and performs offloaded tasks more efficiently than many application-specific predecessors.
Benefits include:
- VLIW-based SIMD architecture with configurable options enables high performance and low power consumption
- Issues instructions and commands to the NPU as a control processor
- Optimised ISA and instructions run non-NPU optimal tasks such as ReLU, sigmoid, tanh and more
- Provides programmability, flexibility and future-readiness to the AI subsystem, allowing end-to-end execution of unseen and future AI workloads
“Cadence has proven AI co-processor use cases with our Tensilica DSPs. With AI workloads transforming and becoming less domain-specific, our AI SoC and systems customers have been seeking a small and efficient AI-focused co-processor for better PPA and future-proofing,” explained Boyd Phelps, senior vice president and general manager of the Silicon Solutions Group at Cadence. “Designed as an NPU companion, we believe the Tensilica NeuroEdge 130 AICP raises the bar for performance efficiency to address our customers’ most demanding AI applications.”
The Tensilica NeuroEdge 130 AICP is supported by the Cadence NeuroWeave Software Development Kit (SDK), a single SDK used across all of Cadence’s AI IP. Leveraging the Tensor Virtual Machine (TVM) stack, the NeuroWeave SDK allows architects to tune, optimise and deploy their AI models for Cadence’s AI IP.
The Tensilica NeuroEdge 130 AICP also comes equipped with a lightweight standalone AI library, allowing customers to directly program AI layers on the new processor and bypass potential overheads of some compiler frameworks.
