über mich | Kangqi (Amos) Zhang

Aufgenommen in Chicago, IL

Ich bin Doktorand im ersten Jahr an der Elmore Family School of Electrical and Computer Engineering der Purdue University und werde von Prof. Jinghan Sun betreut. Meine Forschung liegt an der Schnittstelle von Rechnerarchitektur, EDA und Systemen für maschinelles Lernen.

Zuvor habe ich meinen B.S.E. in Computer Engineering (Summa Cum Laude) an der University of Michigan abgeschlossen. Dort habe ich bei Prof. Nathaniel Bleier in der Crucible Computing Group an stochastischem Rechnen für DNN-Inferenz mit gemischter Präzision, an Chiplet-basierten Systemen und an agilem Hardware-Design gearbeitet. Außerdem habe ich mit Prof. Jishen Zhao und Prof. Zhijian Liu an effizienter LLM-Inferenz für lange Kontexte geforscht. Darüber hinaus habe ich einen B.S. in Maschinenbau der Shanghai Jiao Tong University (Global College); dort war ich als wissenschaftliche Hilfskraft in der Gruppe von Prof. Yanming Wang tätig und habe an 3D-Multiphysik-Modellen von Lithium-Ionen-Batterien gearbeitet. Außerdem war ich für einen Austauschaufenthalt an der University of Auckland.

ausgewählte publikationen

HPCA

Precision As You Need: A Stochastic-Computing Mixture-of-Precision Neural Network Accelerator

Haoran Jin^*, Barry Lyu^*, Kangqi Zhang, Jirong Yang, Soren Walther, Jonathan Postelnik, Qiuyi Ding, Justin Shin, Cheng Chiu, Aaron Xiong, and Nathaniel Bleier

In IEEE International Symposium on High-Performance Computer Architecture (HPCA), 2027
NeurIPS

Precision As You Need: Stochastic Computing Is a Dense Adaptive Quantizer

Haoran Jin^*, Kangqi Zhang^*, Jirong Yang, Barry Lyu, Qiuyi Ding, Ruijie Gao, and Nathaniel Bleier

In Advances in Neural Information Processing Systems (NeurIPS), 2026

Abs arXiv

Matrix multiplications dominate the inference cost of modern transformer-based vision models, yet existing efficiency techniques such as post-training quantization and mixed-precision inference are largely limited to the small set of fixed-width formats (INT4, INT8, BF16, and FP16) supported by conventional accelerators. We revisit stochastic computing (SC) as a way to lift this constraint: viewed as a dense adaptive quantizer, SC controls precision by bit-stream length L rather than a fixed datapath, while each multiplication reduces to a single AND/XNOR gate. We build a GPU library that emulates SC matrix multiplication at scale, exposes stream lengths as first-class kernel arguments, and evaluates SC end-to-end on image classification, object detection and instance segmentation, class-conditional image generation, and visual world-model planning. On top of this substrate, we develop a dynamic per-row mixed-precision policy that assigns stream length per token or group at matched average budget, requires no retraining, and uses the same SC hardware across schedules. Across tasks, SC remains competitive with fixed-format INT quantization at matched bit budgets, while per-row mixed precision helps maintain accuracy at lower average stream lengths. These results provide software-level feasibility evidence that SC can serve as a dense-precision substrate for fine-grained mixed-precision inference on modern vision transformers.
ICCAD

TurnRL: Reinforcement-Learning Driven Turn-Restricted Adaptive Routing for Chiplet-Based System

Kangqi Zhang^*, J. Wang^*, Ronald Dreslinski, and Nathaniel Bleier

In IEEE/ACM International Conference on Computer-Aided Design (ICCAD), 2026
MICRO

Fengshui: Demystifying Chiplet Ecosystem and Bespoke Neural Network Accelerator Codesign

Haoran Jin, Jirong Yang, Zhiheng Zhang, Justin Shin, Barry Lyu, Kangqi Zhang, Yunpeng Liu, and Nathaniel Bleier

In IEEE/ACM International Symposium on Microarchitecture (MICRO), 2026

arXiv