Jennifer Zhou
Papers
1
Total Citations
5
H-Index
1
About
Jennifer Zhou is a leading computer architect whose work bridges the gap between efficient hardware acceleration and real-world machine learning deployment. Her primary research areas include domain-specific architectures, near-memory computing, and energy-efficient SoC design for AI and robotics. Zhou’s most notable contribution is the NeCTAr (Near-Cache Transformer Accelerator) and RASoC systems, introduced in her 2024 paper, which present 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 prototype chip, operating at 400MHz and 0.85V, achieves 109 GOPS for matrix-vector multiplications, demonstrating a compelling balance of performance and energy efficiency. Although early in its citation impact, this work has already garnered attention for its practical approach to accelerating transformer models and robotic workloads. Zhou’s achievements highlight her talent for designing tangible, silicon-validated solutions that push the boundaries of what is possible in on-device AI, making her a rising figure in the architecture community.
Research Focus
Key Achievements
Top Papers
- 1