Solving Boolean satisfiability problems with resistive content addressable memories

2025-01-13

AI Summary

Traditional digital architectures face fundamental bottlenecks in parallelism and inefficient stochastic decision-making when solving high-order logical optimization problems such as Boolean satisfiability (SAT). To address this, we propose KLIMA, a hardware accelerator that pioneers tight co-design of SAT algorithms and analog in-memory computing. KLIMA integrates resistive content-addressable memory (CAM) with analog-domain dot-product engines (DPEs), augmented by custom stochastic heuristic circuits and an efficient problem-to-hardware mapping mechanism. Crucially, it natively supports industrial-scale high-order (beyond quadratic) constraints. Experimental evaluation on representative industrial SAT benchmarks demonstrates that KLIMA achieves a 182× speedup over state-of-the-art digital solvers, alongside substantial energy reduction. These results validate KLIMA’s efficacy and practicality for complex logical optimization.

Technology Category

• Machine Learning: Hardware-aware ML
• Constraint Satisfaction and Optimization: Satisfiability
• Search and Optimization: Sampling/Simulation-based Search

Application Category

• Search and Retrieval-Augmented AI: Large language models for search
• Economics, Online Markets and Human Computation: Cost models of using LLMs in production systems
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

Solving optimization problems is a highly demanding workload requiring high-performance computing systems. Optimization solvers are usually difficult to parallelize in conventional digital architectures, particularly when stochastic decisions are involved. Recently, analog computing architectures for accelerating stochastic optimization solvers have been presented, but they were limited to academic problems in quadratic polynomial format. Here we present KLIMA, a k-Local In-Memory Accelerator with resistive Content Addressable Memories (CAMs) and Dot-Product Engines (DPEs) to accelerate the solution of high-order industry-relevant optimization problems, in particular Boolean Satisfiability. By co-designing the optimization heuristics and circuit architecture we improve the speed and energy to solution up to 182x compared to the digital state of the art.

Problem

• Boolean optimization
• satisfiability problems
• parallel processing

Innovation

• KLIMA accelerator
• Boolean satisfiability optimization
• energy efficiency enhancement