I Have Seen the Future with ChipAgents Autonomous Root Cause Analysis

I have seen a lot of EDA tool demos in my time. More than I want to admit. The perceived quality of the demo usually came down to a combination of the speed of the tool, quality of results and the ease of navigating through the graphical user interface. For the last item, how easy the interface was on the eyes, how clear were the relationships of the elements highlighted, things like that. I was recently treated to an EDA demonstration that shattered all these norms. Watching this demonstration took me to a new level of interaction with EDA tools. One that felt like asking an expert human who had infinite knowledge what the answer to various hard questions would be. What follows is a short summary of how I have seen the future with ChipAgents autonomous root cause analysis.

Framing the Problem

ChipAgents AI is pioneering an AI-native approach to EDA that aims to transform how chips are designed and verified. Its flagship product, ChipAgents targets a 10X productivity improvement in RTL design and verification. The company has a focus to improve innovation across industries with smarter, more efficient chip design.

Zackary Glazewski is a founding AI engineer for ChipAgents. He described how the tool can be applied to root cause analysis (RCA) of complex circuits. Performing RCA is a particularly vexing problem since it requires an iterative exploration of cause and effect across huge amounts of data to find the combination of conditions and events that is causing a particular failure. Zackary explained how ChipAgents works on problems like this. He then provided a live demo that was different from anything I had ever seen before. This is when I realized I was seeing the future.

The Demo

The demo circuit that Zack used was a PCIe Gen 3 design that contained about 50,000 lines of code. An error was added to the design and finding that error became the RCA task. I am used to the tasks of assembling the files and setting up the tool taking up a significant amount of time before the actual demo starts to run. That was not the case this time. Zack communicated with ChipAgents using natural language. The instructions provided were the following:

Find and resolve the design bug.

The location of the failing simulation and waveforms was specified.

A medium level of effort was requested.

Where the output should be stored was specified.

That’s it. The tool then began to run. The effort level influenced how much compute would be used. Zack explained that ChipAgents runs in an synchronous manner. Initially five agents were running in parallel, each working to find and fix the root cause of the design bug. Zack explained that finding candidate root causes of the problem is a key piece of the process. Exploring the entire solution space can take huge amounts of resources. Rating a candidate root cause requires far less resources.

ChipAgents has a built-in system that rates the confidence that a potential cause is correct on a high, medium, low scale. Zack explained that independent agents can exhibit variability in results since they are non-deterministic systems. How the parallel agents are orchestrated to converge on a set of high probability solution candidates is part of the proprietary technology under the hood. He explained that getting a set of high probability solutions helps to converge on the final result.

This felt a bit like multiple expert designers working on the same problem independently. If multiple engineers come up with the same answer, the confidence of a true solution would be high. Zack also explained that the analysis that was being done examined both the waveforms and the design source code that created those waveforms. So multi-dimensional cause/effect analysis was occurring as the demo proceeded.

In about 20 minutes, the system isolated the actual root cause bug and specified a minimal fix to correct it. Ultimately about 20 agents were deployed to solve the problem. The efficiency and accuracy of this result stand out for me. We discussed what typical engineers estimated in terms of time required to solve this problem and all estimates were in dozens of hours. The benefits of this system are quite clear.

The final step was a request to ChipAgents (also in natural language) to implement the suggested fix, re-run the simulation and verify the waveforms were now correct. This took a few more minutes. At that point, I was convinced I had seen the future. The figure below illustrates the overall flow of this remarkable system.

To Learn More

AI is clearly changing chip design. The contributions are less about faster simulators or more accurate timing tools and more about combing through massive data sets to find and fix problems or create optimal guidance. This is the future and ChipAgents AI is paving the way.

You can learn more about this unique company on its website here, or on SemiWiki here. And if you want to dive into more details about ChipAgents RCA, there is a detailed description available here. And that’s how I have seen the future with ChipAgents Autonomous root cause analysis.

Also Read:

AI RTL Generation versus AI RTL Verification

AI-Powered Waveform Debugging: Revolutionizing Semiconductor Verification

ChipAgents Tackles Debug. This is Important