Key Takeaways
- Synopsys and NVIDIA collaborate to advance agentic AI for chip design and electronics system design
- Synopsys develops fully autonomous, long-running agentic capabilities for chip design, enabled by NVIDIA Nemotron and secured by NVIDIA OpenShell runtime
- The solution promises to transform time-consuming chip verification and thermal simulation into automated insight delivery and engineering productivity
- Synopsys' fully autonomous design verification (DV) workflow achieves up to 50X faster time-to-validated RTL with an additional 20% improvement in coverage
Introduction to Agentic AI for Chip Design
Synopsys, Inc. and NVIDIA have announced a significant advancement in agentic AI for engineering, specifically in chip design and electronics system design. This collaboration has resulted in the development of fully autonomous, long-running agentic capabilities, enabled by NVIDIA Nemotron on NVIDIA's accelerated computing platform and secured by the NVIDIA OpenShell runtime.
Fully Autonomous Design Verification (DV) Workflow
The traditional design verification process has been a significant bottleneck in chip design, with coverage closure being a major challenge. Despite the use of assistive tools, engineering teams have had to spend considerable labor and compute resources on incremental improvements. Synopsys' new solution, built on its agentic AI platform and powered by Synopsys AgentEngineer technology and NVIDIA's agentic AI infrastructure, aims to transform this process.
Comparison of Traditional and Agentic AI-based DV Workflows
| Traditional DV Workflow | Agentic AI-based DV Workflow | |
|---|---|---|
| Coverage Closure | Manual, time-consuming | Autonomous, goal-driven |
| Root Failure Cause Analysis | Manual, labor-intensive | Autonomous, automated |
| Time-to-Validated RTL | Weeks | Hours (up to 50X faster) |
| Coverage Improvement | Limited | Up to 20% additional improvement |
Technical Specifications and Benefits
The solution features a fully autonomous, long-running orchestrator agent that deconstructs DV goals from specification, design, test repository, and user inputs. This agent orchestrates specialized agents and tools in a closed-loop workflow, spanning the full chip verification lifecycle. The results demonstrate a significant reduction in manual labor, with weeks of work compressed into hours of agentic execution.
Bottom Line
The collaboration between Synopsys and NVIDIA has resulted in a groundbreaking advancement in agentic AI for chip design and electronics system design. With its fully autonomous, long-running agentic capabilities, Synopsys' solution promises to transform the design verification process, achieving up to 50X faster time-to-validated RTL and an additional 20% improvement in coverage. This innovation has the potential to revolutionize the chip design industry, enabling faster, more efficient, and more accurate design verification and validation.