Explaining EDA synthesis errors with LLMs

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 Verilog and VHDL hardware description languages to Field Programmable Gate Arrays (FPGAs) from Altera (Intel) and Xilinx (AMD) via proprietary closed-source toolchains (Quartus Prime and Vivado, respectively). These tools are complex and difficult to use -- yet, as they are the tools used in industry, they are an essential first step in this space. In this work, we examine how recent advances in artificial intelligence may be leveraged to address aspects of this challenge. Specifically, we investigate if Large Language Models (LLMs), which have demonstrated text comprehension and question-answering capabilities, can be used to generate novice-friendly explanations of compile-time synthesis error messages from Quartus Prime and Vivado. To perform this study we generate 936 error message explanations using three OpenAI LLMs over 21 different buggy code samples. These are then graded for relevance and correctness, and we find that in approximately 71% of cases the LLMs give correct & complete explanations suitable for novice learners.

Towards the Imagenets of ML4EDA

Despite the growing interest in ML-guided EDA tools from RTL to GDSII, there are no standard datasets or prototypical learning tasks defined for the EDA problem domain. Experience from the computer vision community suggests that such datasets are crucial to spur further progress in ML for EDA. Here we describe our experience curating two large-scale, high-quality datasets for Verilog code generation and logic synthesis. The first, VeriGen, is a dataset of Verilog code collected from GitHub and Verilog textbooks. The second, OpenABC-D, is a large-scale, labeled dataset designed to aid ML for logic synthesis tasks. The dataset consists of 870,000 And-Inverter-Graphs (AIGs) produced from 1500 synthesis runs on a large number of open-source hardware projects. In this paper we will discuss challenges in curating, maintaining and growing the size and scale of these datasets. We will also touch upon questions of dataset quality and security, and the use of novel data augmentation tools that are tailored for the hardware domain.

Are Emily and Greg Still More Employable than Lakisha and Jamal? Investigating Algorithmic Hiring Bias in the Era of ChatGPT

Large Language Models (LLMs) such as GPT-3.5, Bard, and Claude exhibit applicability across numerous tasks. One domain of interest is their use in algorithmic hiring, specifically in matching resumes with job categories. Yet, this introduces issues of bias on protected attributes like gender, race and maternity status. The seminal work of Bertrand & Mullainathan (2003) set the gold-standard for identifying hiring bias via field experiments where the response rate for identical resumes that differ only in protected attributes, e.g., racially suggestive names such as Emily or Lakisha, is compared. We replicate this experiment on state-of-art LLMs (GPT-3.5, Bard, Claude and Llama) to evaluate bias (or lack thereof) on gender, race, maternity status, pregnancy status, and political affiliation. We evaluate LLMs on two tasks: (1) matching resumes to job categories; and (2) summarizing resumes with employment relevant information. Overall, LLMs are robust across race and gender. They differ in their performance on pregnancy status and political affiliation. We use contrastive input decoding on open-source LLMs to uncover potential sources of bias.

Integrating Large Language Models into the Debugging C Compiler for generating contextual error explanations

This paper introduces a method for Large Language Models (LLM) to produce enhanced compiler error explanations, in simple language, within our Debugging C Compiler (DCC). It is well documented that compiler error messages have been known to present a barrier for novices learning how to program. Although our initial use of DCC in introductory programming (CS1) has been instrumental in teaching C to novice programmers by providing safeguards to commonly occurring errors and translating the usually cryptic compiler error messages at both compile- and run-time, we proposed that incorporating LLM-generated explanations would further enhance the learning experience for novice programmers. Through an expert evaluation, we observed that LLM-generated explanations for compiler errors were conceptually accurate in 90% of compile-time errors, and 75% of run-time errors. Additionally, the new DCC-help tool has been increasingly adopted by students, with an average of 1047 unique runs per week, demonstrating a promising initial assessment of using LLMs to complement compiler output to enhance programming education for beginners. We release our tool as open-source to the community.

VeriGen: A Large Language Model for Verilog Code Generation

In this study, we explore the capability of Large Language Models (LLMs) to automate hardware design by generating high-quality Verilog code, a common language for designing and modeling digital systems. We fine-tune pre-existing LLMs on Verilog datasets compiled from GitHub and Verilog textbooks. We evaluate the functional correctness of the generated Verilog code using a specially designed test suite, featuring a custom problem set and testing benches. Here, our fine-tuned open-source CodeGen-16B model outperforms the commercial state-of-the-art GPT-3.5-turbo model with a 1.1% overall increase. Upon testing with a more diverse and complex problem set, we find that the fine-tuned model shows competitive performance against state-of-the-art gpt-3.5-turbo, excelling in certain scenarios. Notably, it demonstrates a 41% improvement in generating syntactically correct Verilog code across various problem categories compared to its pre-trained counterpart, highlighting the potential of smaller, in-house LLMs in hardware design automation.

LLM-assisted Generation of Hardware Assertions

The security of computer systems typically relies on a hardware root of trust. As vulnerabilities in hardware can have severe implications on a system, there is a need for techniques to support security verification activities. Assertion-based verification is a popular verification technique that involves capturing design intent in a set of assertions that can be used in formal verification or testing-based checking. However, writing security-centric assertions is a challenging task. In this work, we investigate the use of emerging large language models (LLMs) for code generation in hardware assertion generation for security, where primarily natural language prompts, such as those one would see as code comments in assertion files, are used to produce SystemVerilog assertions. We focus our attention on a popular LLM and characterize its ability to write assertions out of the box, given varying levels of detail in the prompt. We design an evaluation framework that generates a variety of prompts, and we create a benchmark suite comprising real-world hardware designs and corresponding golden reference assertions that we want to generate with the LLM.

FLAG: Finding Line Anomalies (in code) with Generative AI

Code contains security and functional bugs. The process of identifying and localizing them is difficult and relies on human labor. In this work, we present a novel approach (FLAG) to assist human debuggers. FLAG is based on the lexical capabilities of generative AI, specifically, Large Language Models (LLMs). Here, we input a code file then extract and regenerate each line within that file for self-comparison. By comparing the original code with an LLM-generated alternative, we can flag notable differences as anomalies for further inspection, with features such as distance from comments and LLM confidence also aiding this classification. This reduces the inspection search space for the designer. Unlike other automated approaches in this area, FLAG is language-agnostic, can work on incomplete (and even non-compiling) code and requires no creation of security properties, functional tests or definition of rules. In this work, we explore the features that help LLMs in this classification and evaluate the performance of FLAG on known bugs. We use 121 benchmarks across C, Python and Verilog; with each benchmark containing a known security or functional weakness. We conduct the experiments using two state of the art LLMs in OpenAI's code-davinci-002 and gpt-3.5-turbo, but our approach may be used by other models. FLAG can identify 101 of the defects and helps reduce the search space to 12-17% of source code.

Chip-Chat: Challenges and Opportunities in Conversational Hardware Design

Modern hardware design starts with specifications provided in natural language. These are then translated by hardware engineers into appropriate Hardware Description Languages (HDLs) such as Verilog before synthesizing circuit elements. Automating this translation could reduce sources of human error from the engineering process. But, it is only recently that artificial intelligence (AI) has demonstrated capabilities for machine-based end-to-end design translations. Commercially-available instruction-tuned Large Language Models (LLMs) such as OpenAI's ChatGPT and Google's Bard claim to be able to produce code in a variety of programming languages; but studies examining them for hardware are still lacking. In this work, we thus explore the challenges faced and opportunities presented when leveraging these recent advances in LLMs for hardware design. Using a suite of 8 representative benchmarks, we examined the capabilities and limitations of the state of the art conversational LLMs when producing Verilog for functional and verification purposes. Given that the LLMs performed best when used interactively, we then performed a longer fully conversational case study where a hardware engineer co-designed a novel 8-bit accumulator-based microprocessor architecture. We sent the benchmarks and processor to tapeout in a Skywater 130nm shuttle, meaning that these 'Chip-Chats' resulted in what we believe to be the world's first wholly-AI-written HDL for tapeout.

Benchmarking Large Language Models for Automated Verilog RTL Code Generation

Automating hardware design could obviate a significant amount of human error from the engineering process and lead to fewer errors. Verilog is a popular hardware description language to model and design digital systems, thus generating Verilog code is a critical first step. Emerging large language models (LLMs) are able to write high-quality code in other programming languages. In this paper, we characterize the ability of LLMs to generate useful Verilog. For this, we fine-tune pre-trained LLMs on Verilog datasets collected from GitHub and Verilog textbooks. We construct an evaluation framework comprising test-benches for functional analysis and a flow to test the syntax of Verilog code generated in response to problems of varying difficulty. Our findings show that across our problem scenarios, the fine-tuning results in LLMs more capable of producing syntactically correct code (25.9% overall). Further, when analyzing functional correctness, a fine-tuned open-source CodeGen LLM can outperform the state-of-the-art commercial Codex LLM (6.5% overall). Training/evaluation scripts and LLM checkpoints are available: https://github.com/shailja-thakur/VGen.

Pop Quiz! Can a Large Language Model Help With Reverse Engineering?

Large language models (such as OpenAI's Codex) have demonstrated impressive zero-shot multi-task capabilities in the software domain, including code explanation. In this work, we examine if this ability can be used to help with reverse engineering. Specifically, we investigate prompting Codex to identify the purpose, capabilities, and important variable names or values from code, even when the code is produced through decompilation. Alongside an examination of the model's responses in answering open-ended questions, we devise a true/false quiz framework to characterize the performance of the language model. We present an extensive quantitative analysis of the measured performance of the language model on a set of program purpose identification and information extraction tasks: of the 136,260 questions we posed, it answered 72,754 correctly. A key takeaway is that while promising, LLMs are not yet ready for zero-shot reverse engineering.