Qiaoyi Liu

Qiaoyi Liu's work centers on designing programmable computer chips called coarse-grained reconfigurable arrays (CGRAs), which are hardware accelerators that speed up tasks like machine learning, image processing, and linear algebra while using less power. This involves building both the physical chip designs (e.g., the Onyx and Amber accelerators) and the software toolchains and compilers needed to program them efficiently. A smaller portion of the publication record also touches on measuring scientific contributions and data practices, though this may reflect co-authored work outside the core hardware focus.

Publication output has grown over the last decade, rising from occasional single-digit yearly counts earlier on to a more active and sustained pace of 5-6 papers per year since 2022.

Generated by claude-sonnet-5 from public bibliographic data · Jul 20, 2026