Tensilica DSP IP supports efficient AI/ML processing

Overview

The Cadence AI IP platform includes the extensible DSP platform from Cadence, which provides flexible instruction sets designed to perform artificial intelligence and machine learning (AI/ML) workload operations efficiently. Mixing AI and DSP workloads in a single application is easy with Tensilica DSPs.

The Tensilica AI Base platform offers 8 GOPS to up to 2 TOPS of AI performance and includes the popular Tensilica HiFi DSPs for audio/voice, Vision DSPs, and ConnX DSPs for radar and communications. The DSPs are based on the VLIW and SIMD architectures, with instruction sets optimized for specific domains, including extensions for AI. Customers benefit from the domain-specificity, extensibility, and configurability they have come to expect from the trusted, mature Tensilica DSP architecture. SoC designers can extend the base architecture to address specific workload requirements and create differentiation. These DSPs also offer a scalable multiplier accumulator (MAC) block that can run custom AI workloads efficiently, as well as an optimized NN library and comprehensive software support.

Key Features

  • Powerful DSP Instruction Set Supporting AI/ML Operations.
    • Highly scalable IP portfolio, with AI Base built on successful and power-efficient domain-specific DSPs.
  • Mixed Workloads.
    • AI/ML processing can seamlessly combine with DSP in a unified application.
  • Industry-Leading Performance and Power Efficiency.
    • High Inferences per second per area (IPS/mm2) and per power (IPS/W).
  • End-to-End Software Toolchain for All Markets and a Large Number of Frameworks.
    • NeuroWeave SDK provides a common tool for compiling networks across IP, with flexibility for performance, accuracy, and run-time environments.

Deliverables

  • Free Software Evaluation
    • Try our SDK Software Development Toolkit for 15 days absolutely free. We want to show you how easy it is to use our Eclipse-based IDE.
  • Online Support:
    • The Cadence Online Support (COS) system fields our entire library of accessible materials for self-study and step-by-step instruction.
  • Xtensa Processor Generator (XPG):
    • The Xtensa Processor Generator (XPG) is the heart of our technology - the patented cloud-based system that creates your correct-by-construction processor and all associated software, models, etc. (Login Required)
  • Technical Forum Access:
    • Find community on the technical forums to discuss and elaborate on your design ideas.

Technical Specifications

×
Semiconductor IP