Lincoln AI Computing Survey (LAICS) and Trends

2025-10-23

AI Summary

The rapid advancement of generative AI (GenAI) has introduced unprecedented computational demands for both training and inference, necessitating systematic characterization of AI accelerator evolution. Method: This study comprehensively tracks publicly released AI accelerators from 2017 to 2024, proposing a novel taxonomy integrating dataflow, memory architecture, and workload characteristics. It constructs a standardized benchmark database covering peak compute, energy efficiency (TOPS/W), process node, and other key metrics—incorporating, for the first time, parameters of mainstream commercial GenAI chips. Using performance-power scatter plots, market-segmented scaling visualizations, and trend modeling, it analyzes technical trajectories and energy-efficiency bottlenecks across domains (e.g., cloud training, edge inference). Contribution/Results: The work establishes a sustainable, authoritative benchmark that provides quantitative foundations for AI hardware architecture design, industry roadmap planning, and evidence-based policy formulation.

Technology Category

• Machine Learning: Hardware-aware ML
• Humans and AI: Other Foundations of Human Computation & AI
• Philosophy and Ethics of AI: Artificial General Intelligence

Application Category

• Social Networks and Social Media: Generative AI / large language models and their impact on social systems
• Economics, Online Markets and Human Computation: Economic ramifications for generative AI infrastructure and applications
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs

Abstract

In the past year, generative AI (GenAI) models have received a tremendous amount of attention, which in turn has increased attention to computing systems for training and inference for GenAI. Hence, an update to this survey is due. This paper is an update of the survey of AI accelerators and processors from past seven years, which is called the Lincoln AI Computing Survey -- LAICS (pronounced "lace"). This multi-year survey collects and summarizes the current commercial accelerators that have been publicly announced with peak performance and peak power consumption numbers. In the same tradition of past papers of this survey, the performance and power values are plotted on a scatter graph, and a number of dimensions and observations from the trends on this plot are again discussed and analyzed. Market segments are highlighted on the scatter plot, and zoomed plots of each segment are also included. A brief description of each of the new accelerators that have been added in the survey this year is included, and this update features a new categorization of computing architectures that implement each of the accelerators.

Problem

• Updates AI accelerator survey with latest performance and power consumption data
• Analyzes trends in computing systems for generative AI training and inference
• Categorizes new computing architectures implementing commercial AI accelerators

Innovation

• Survey updates AI accelerators performance data
• Plots performance power on scatter graph trends
• Introduces new computing architectures categorization