Electronic Design Automation Applications Research Articles

Enhancing Electronic Design Automation Tools with an ML-Based Information Retrieval System

Over the past fifty years, Electronic Design Automation (EDA) tools have played a crucial role in the semiconductor industry, assisting in the design, simulation, and manufacturing of integrated circuits (ICs). However, the sophisticated nature of these tools often demands extensive expertise, which can be a barrier for many users. Mastery of these tools necessitates specialized knowledge and skills, including comprehension of complex algorithms, design methodologies, and tool-specific workflows. To address this challenge, this paper introduces a machine learning (ML) based information retrieval system designed to enhance the usability of EDA tools. The objective of this system is to simplify user interactions and make EDA tools more accessible to designers, regardless of their expertise level. The main idea of this ML-driven system is to provide a chatbot-like interface that facilitates efficient, context-aware searches and offers interactive, step-by-step guidance on using various tool functionalities. By integrating natural language processing and machine learning techniques, the system can understand user queries, extract relevant information from the tool's documentation, and provide context-specific guidance. This approach helps to mitigate the steep learning curve associated with advanced EDA applications and enhances tool accessibility. Consequently, it promotes a more intuitive interaction with sophisticated EDA software, thus fostering enhanced usability of complex tools in the semiconductor industry. This work exemplifies the transformative potential of integrating machine learning with conversational user interfaces in making sophisticated software applications more user-friendly.

CircuitNet: an open-source dataset for machine learning applications in electronic design automation (EDA)

CircuitNet: an open-source dataset for machine learning applications in electronic design automation (EDA)

DeepPlacer: A custom integrated OpAmp placement tool using deep models

Mechanisms towards the automatic analog integrated circuit layout design have been an intensive research topic in the past few decades. Still, the industrial environment has no automatic approach established. The advances of machine learning applications in electronic design automation come with the promise to change this reality. This paper proposes a deep learning generative model for the placement “optimization” of analog integrated circuit basic blocks. The model behaves as an argmin operator for the placement cost function and can provide placement solutions instantly. Moreover, the model can be fed with unlabeled data, greatly facilitating data collection. A generic and innovative circuits’ representation at the network’s input layer is proposed, encoding the devices’ dimensions, connectivity, and topological constraints. Besides, the randomness found in generative models is embedded directly into the feature vector, as the order of the features per device is shuffled in the input vector. Shuffling the order of the devices’ features in the input not only brings multi-modality but also solves a generalization problem, as there is not any natural order defined to place devices in the feature vector. As a proof of concept, a deep artificial neural network capable of proposing different placement solutions, in less than 150 ms each, for six amplifier topologies and, in multiple technology nodes ranging from 350 nm down to 65 nm, is demonstrated. DeepPlacer was capable of producing correct solutions for topologies and technology nodes not present in the training set, showing good generalization while not hindering circuit performance due to the placement.

Boolean Satisfiability Solvers and Their Applications in Model Checking

Boolean satisfiability (SAT)—the problem of determining whether there exists an assignment satisfying a given Boolean formula—is a fundamental intractable problem in computer science. SAT has many applications in electronic design automation (EDA), notably in synthesis and verification. Consequently, SAT has received much attention from the EDA community, who developed algorithms that have had a significant impact on the performance of SAT solvers. EDA researchers introduced techniques such as conflict-driven clause learning, novel branching heuristics, and efficient unit propagation. These techniques form the basis of all modern SAT solvers. Using these ideas, contemporary SAT solvers can often handle practical instances with millions of variables and constraints. The continuing advances of SAT solvers are the driving force of modern model checking tools, which are used to check the correctness of hardware designs. Contemporary automated verification techniques such as bounded model checking, proof-based abstraction, interpolation-based model checking, and IC3 have in common that they are all based on SAT solvers and their extensions. In this paper, we trace the most important contributions made to modern SAT solvers by the EDA community, and discuss applications of SAT in hardware model checking.

Towards accelerating irregular EDA applications with GPUs

Recently graphic processing units (GPUs) are rising as a new vehicle for high-performance, general purpose computing. It is attractive to unleash the power of GPU for Electronic Design Automation (EDA) computations to cut the design turn-around time of VLSI systems. EDA algorithms, however, generally depend on irregular data structures such as sparse matrix and graphs, which pose major challenges for efficient GPU implementations. In this paper, we propose high-performance GPU implementations for a set of important irregular EDA computing patterns including sparse matrix, graph algorithms and message-passing algorithms. In the sparse matrix domain, we solve a core problem, sparse-matrix vector product (SMVP). On a wide range of EDA problem instances, our SMVP implementation outperforms all prior work and achieves a speedup up to 50× over the CPU baseline implementation. The GPU based SMVP procedure is applied to successfully accelerate two core EDA computing engines, timing analysis and linear system solution. In the graph algorithm domain, we developed a SMVP based formulation to efficiently solve the breadth-first search (BFS) problem on GPUs. We also developed efficient solutions for two message-passing algorithms, survey propagation (SP) based SAT solution and a register-transfer level (RTL) simulation. Our results prove that GPUs have a strong potential to accelerate EDA computing through designing GPU-friendly algorithms and/or re-organizing computing structures of sequential algorithms.

GPU-based Acceleration of System-level Design Tasks

Many system-level design tasks (e.g., high-level timing analysis, hardware/software partitioning and design space exploration) involve computational kernels that are intractable (usually NP-hard). As a result, they involve high running times even for mid-sized problems. In this paper we explore the possibility of using commodity graphics processing units (GPUs) to accelerate such tasks that commonly arise in the electronic design automation (EDA) domain. We demonstrate this idea via two detailed case studies. The first explores the possibility of using GPUs to speedup standard schedulability analysis problems. The second proposes a GPU-based engine for a general hardware/software design space exploration problem. Not only do these problems commonly arise in the embedded systems domain, their computational kernels turn out to be variants of a combinatorial optimization problem—viz., the knapsack problem—that lies at the heart of several EDA applications. Experimental results show that our GPU-based implementations offer very attractive speedups for the computational kernels (up to 100×), and speedups of up to 17× for the full problem. In contrast to ASIC/FPGA-based accelerators—given that even low-end desktop and notebook computers are now equipped with GPUs—our solution involves no extra hardware cost. Although recent research has shown the benefits of using GPUs for a variety of non-graphics applications (e.g., in databases and bioinformatics), harnessing the parallelism of GPUs to accelerate problems from the EDA domain has not been sufficiently explored so far. We believe that our results and the generality of the core problem that we address will motivate researchers from this community to explore the possibility of using GPUs for a wider variety of problems from the EDA domain.

An ant colony algorithm for minimum unsatisfiable core extraction

Explaining the causes of infeasibility of Boolean formulas has many practical applications in electronic design automation and formal verification of hardware. Furthermore, a minimum explanation of infeasibility that excludes all irrelevant information is generally of interest. A smallest-cardinality unsatisfiable subset called a minimum unsatisfiable core can provide a succinct explanation of infeasibility and is valuable for applications. However, little attention has been concentrated on extraction of minimum unsatisfiable core. In this paper, the relationship between maximal satisfiability and minimum unsatisfiability is presented and proved, then an efficient ant colony algorithm is proposed to derive an exact or nearly exact minimum unsatisfiable core based on the relationship. Finally, experimental results on practical benchmarks compared with the best known approach are reported, and the results show that the ant colony algorithm strongly outperforms the best previous algorithm.

Boosting SAT Solver Performance via a New Hybrid Approach1

Due to the widespread demands for efficient SAT solvers in Electronic Design Automation applications, methods to boost the performance of the SAT solver are highly desired. We propose a Hybrid Solution to boost SAT solver performance in this paper, via an integration of local and DPLL-based search approaches. A local search is used to identify a subset of clauses from the original formula to be passed to a DPLL SAT solver incrementally until all the clauses have been passed. In addition, the solution obtained by the DPLL solver on the subset of clauses is fed back to the local search solver to jump over any locally optimal points. The proposed solution is highly portable to the existing SAT solvers. For satisfiable instances, up to an order of magnitude speedup was obtained via the proposed hybrid solver. For unsatisfiable instances, the speedup was smaller due to the overhead.

Using SAT-based techniques in power estimation

Recent algorithmic advances in Boolean satisfiability (SAT), along with highly efficient solver implementations, have enabled the successful deployment of SAT technology in a wide range of applications domains, and particularly in electronic design automation (EDA). SAT is increasingly being used as the underlying model for a number of applications in EDA. This paper describes how to formulate two problems in power estimation of CMOS combinational circuits as SAT problems or 0–1 integer linear programming (ILP). In these circuits, it was proven that maximizing dissipation is equivalent to maximizing gate output activity, appropriately weighted to account for differing load capacitances. The first problem in this work deals with identifying an input vector pair that maximizes the weighted circuit activity. In the second application we attempt to find an estimate for the maximum power-up current in circuits where power cut-off or gating techniques are used to reduce leakage current. Both problems were successfully formulated as SAT problems. SAT-Based and generic Integer Linear Programming (ILP) solvers are then used to find a solution. The experimental results obtained on a large number of benchmark circuits provide promising evidence that the proposed complete approach is both viable and useful and outperforms the random approach.

B-Cubing: New Possibilities for Efficient SAT-Solving

SAT (Boolean satisfiability) has become the primary Boolean reasoning engine for many EDA (electronic design automation) applications, so the efficiency of SAT-solving is of great practical importance. B-cubing is our extension and generalization of Goldberg et al.'s supercubing, an approach to pruning in SAT-solving completely different from the standard approach used in leading solvers. We have built a B-cubing-based solver that is competitive with, and often outperforms, leading conventional solvers (e.g., ZChaff II) on a wide range of EDA benchmarks. However, B-cubing is hard to understand and even the correctness of the algorithm is not obvious. This paper presents the theoretical basis for B-cubing, proves our approach correct, details our implementation and experimental results, and maps out other correct possibilities for further improving SAT-solving

Minimum-congestion hypergraph embedding in a cycle

The minimum-congestion hypergraph embedding in a cycle (MCHEC) problem is to embed the n edges in an m-vertex hypergraph as paths in a cycle on the same number of vertices, such that congestion-the maximum number of paths that use any single edge in the cycle-is minimized. The MCHEC problem has applications in electronic design automation and parallel computing. In this paper, it is proven that the MCHEC problem is NP-complete. An O((nm)/sup k+1/) algorithm is described that computes an embedding with congestion k or determines that such an embedding does not exist. Finally, a linear-time approximation algorithm for arbitrary instances is presented that computes an embedding whose congestion is at most three times optimal.

Parallel circuit partitioning on a reduced array architecture

The physical design of a VLSI circuit involves circuit partitioning as a subtask. Typically, it is necessary to partition a large electrical circuit into several smaller circuits such that the total cross-wiring is minimized. This problem is a variant of the more general graph partitioning problem, and it is known that there does not exist a polynomial time algorithm to obtain an optimal partition. The heuristic procedure proposed by Kernighan and Lin1,2 requires O(n2 log2n) time to obtain a near-optimal two-way partition of a circuit with n modules. In the VLSI context, due to the large problem size involved, this computational requirement is unacceptably high. This paper is concerned with the hardware acceleration of the Kernighan-Lin procedure on an SIMD architecture. The proposed parallel partitioning algorithm requires O(n) processors, and has a time complexity of O(n log2n). In the proposed scheme, the reduced array architecture is employed with due considerations towards cost effectiveness and VLSI realizability of the architecture.The authors are not aware of any earlier attempts to parallelize a circuit partitioning algorithm in general or the Kernighan-Lin algorithm in particular. The use of the reduced array architecture is novel and opens up the possibilities of using this computing structure for several other applications in electronic design automation.