Capturing Knowledge Within LLMs


At DAC this year, there was a lot of talk about AI and the impact it is likely to have. While EDA companies have been using it for optimization and improving iteration loops within the flow, the end users have been concentrating on how to use it to improve the user interface between engineers and tools. The feedback is very positive. Large language models (LLMs) have been trained on a huge a... » read more

Debugging SystemVerilog Constraint Randomization: A Comprehensive Guide


SystemVerilog constraint randomization is a powerful methodology for generating realistic and diverse test scenarios in the realm of hardware design verification. However, like any complex methodology, it can sometimes be challenging to debug when an unexpected issue arises. In this article, we will explore common debug techniques and strategies to help you effectively troubleshoot your SystemV... » read more

Understanding Scandump: A Key Silicon Debugging Technique


Scandump is an advanced silicon debugging technique that ingeniously repurposes DFT (Design For Testability) scan chains for functional debugging. This method allows for the extraction of states from registers or latches that are stitched into the scan chains, providing critical diagnostic insights. Scandump is particularly invaluable when the CPU is deadlocked or when the system hardware bec... » read more

Leveraging LLMs To Explain EDA Synthesis Errors And Help Train New Engineers 


A technical paper titled “Explaining EDA synthesis errors with LLMs” was published by researchers at University of New South Wales and University of Calgary. Abstract: "Training new engineers in digital design is a challenge, particularly when it comes to teaching the complex electronic design automation (EDA) tooling used in this domain. Learners will typically deploy designs in the Veri... » read more

Communication Is Key To Finding And Fixing Bugs In ICs


Experts at the Table: Finding and eliminating bugs at the source can be painstaking work, but it also can prevent even greater problems from developing later on. To examine the best ways to tackle this problem, Semiconductor Engineering sat down with Ashish Darbari, CEO at Axiomise; Ziyad Hanna, corporate vice president R&D at Cadence; Jim Henson, ASIC verification software product manager ... » read more

Can Models Created With AI Be Trusted?


EDA models that are created using AI need to pass more stringent quality and cost benefit analysis compared to many AI applications in the broader industry. Money is hanging on the line if AI gets it wrong, and all the associated costs must be factored into the equation. Models are some of the most expensive things a development team can create, and it is important to understand the value th... » read more

Challenges In RISC-V Verification


Designing a single-core RISC-V processor is relatively easy, but verifying it and debugging it is a different story. And it all becomes more complicated when multiple cores are involved, and when those cores need to be cache-coherent. Ashish Darbari, CEO of Axiomise, talks with Semiconductor Engineering about using assertions and formal verification technology to find bugs and prove coherency i... » read more

Engineers Or Their Tools: Which Is Responsible For Finding Bugs?


Experts at the table: Finding and eliminating bugs at the source can be painstaking work, but it can prevent bigger problems later in the design flow, when they are more difficult and expensive to fix.  Semiconductor Engineering sat down to discuss these issues with Ashish Darbari, CEO at Axiomise; Ziyad Hanna, corporate vice president R&D at Cadence; Jim Henson, ASIC verification software... » read more

Advanced Design Debug Demands Integrated Verification Management


Design verification has been the dominant portion of chip development for years, and the challenges grow bigger every day. Single dies continue to grow in transistor count and complexity. Advanced techniques such as 2.5D and 3D multi-die systems and emerging technologies such as wafer-scale integration pack even more transistors and functionality into a single device. This situation has created... » read more

Arm Statistical Profiling Extension: Performance Analysis Methodology


This paper presents a methodology for workload characterization and root cause analysis using the Arm Statistical Profiling Extension (SPE) demonstrated on a Neoverse N1 core. The target audience are software developers and performance analysts in software development, analysis, optimization, and tuning. This paper may also help silicon engineers to conduct performance analysis and debugging. T... » read more

← Older posts