Connor McMahon

Papers

1

Total Citations

5

H-Index

1

About

Connor McMahon is a leading researcher in computer architecture, with a focus on energy-efficient accelerators for machine learning and robotics. His most notable contribution is the introduction of NeCTAr (Near-Cache Transformer Accelerator), a 16nm heterogeneous multicore RISC-V SoC that seamlessly integrates near-core and near-memory accelerators for both sparse and dense machine learning kernels. This work, published in 2024, demonstrates a prototype chip operating at 400MHz and 0.85V, achieving 109 GOPS for matrix-vector multiplications—a significant step toward efficient language model inference. McMahon’s research addresses the critical challenge of balancing performance and power in edge and robotic systems, where real-time AI processing is essential. His work has already garnered 5 citations, reflecting its immediate relevance to the architecture community. By bridging the gap between specialized accelerators and general-purpose processors, McMahon is shaping the future of intelligent, low-power computing for autonomous systems.

Research Focus

Key Achievements

1
H-Index
1
Papers
5
Total Citations
5
Avg Citations/Paper
🏆 Most Cited Paper
NeCTAr and RASoC: Tale of Two Class SoCs for Language Model Interference and Robotics in Intel 16
5 citations · 2024
📈 Most Prolific Year: 2024 (1 Papers)
🤝 Key Collaborators: 27

Top Papers

  1. 1

Key Collaborators

Contact & Links

Available for collaboration
Content generated · 11 days ago