Changho Hwang

Senior Researcher at Microsoft, studying scalable AI and large-scale GPU systems. Received Ph.D. in Electrical Engineering from KAIST in February 2022, advised by Prof. KyoungSoo Park.

Systems support for deep learning, scalable networked systems, GPU systems, system performance optimization

Korea Advanced Institute of Science and Technology (KAIST), Daejeon, Republic of Korea

Pre-gated MoE: An Algorithm-System Co-Design for Fast and Scalable Mixture-of-Expert Inference

Ranggi Hwang, Jianyu Wei, Shijie Cao, Changho Hwang, Xiaohu Tang, Ting Cao, and Mao Yang

In the 51st International Symposium on Computer Architecture (ISCA)

Buenos Aires, Argentina, June 2024

Tutel: Adaptive Mixture-of-Experts at Scale

Changho Hwang, Wei Cui, Yifan Xiong, Ziyue Yang, Ze Liu, Han Hu, Zilong Wang, Rafael Salas, Jithin Jose, Prabhat Ram, Joe Chau, Peng Cheng, Fan Yang, Mao Yang, and Yongqiang Xiong

In the 6th Conference on Machine Learning and Systems (MLSys)

Miami, FL, June 2023

ARK: GPU-driven Code Execution for Distributed Deep Learning

Changho Hwang, KyoungSoo Park, Ran Shu, Xinyuan Qu, Peng Cheng, and Yongqiang Xiong

In the 20th USENIX Symposium on Networked Systems Design and Implementation (NSDI)

Boston, MA, April 2023

Elastic Resource Sharing for Distributed Deep Learning

Changho Hwang, Taehyun Kim, Sunghyun Kim, Jinwoo Shin, and KyoungSoo Park

In the 18th USENIX Symposium on Networked Systems Design and Implementation (NSDI)

Virtual Event, April 2021

Confident Multiple Choice Learning

Kimin Lee, Changho Hwang, KyoungSoo Park, and Jinwoo Shin

In the 34th International Conference on Machine Learning (ICML)

Sydney, Austrailia, August 2017

APUNet: Revitalizing GPU as Packet Processing Accelerator

Younghwan Go, Muhammad Jamshed, YoungGyoun Moon, Changho Hwang, and KyoungSoo Park

In the 14th USENIX Symposium on Networked Systems Design and Implementation (NSDI)

Boston, MA, March 2017

Immediate Communication for Distributed AI Tasks

Jihao Xin, Seongjong Bae, KyoungSoo Park, Marco Canini, Changho Hwang, Peng Cheng

In the 2nd Workshop on Hot Topics in System Infrastructure (HotInfra)

Austin, TX, November 2024 (to appear)

Towards GPU-driven Code Execution for Distributed Deep Learning (Awarded Best Paper)

Changho Hwang, KyoungSoo Park, Ran Shu, Xinyuan Qu, Peng Cheng, and Yongqiang Xiong

In the 3rd Machine Learning for Computer Architecture and Systems (MLArchSys@ISCA)

New York City, NY, June 2022

Accelerating GNN Training with Locality-Aware Partial Execution (Awarded Best Paper)

Taehyun Kim, Changho Hwang, KyoungSoo Park, Zhiqi Lin, Peng Cheng, Youshan Miao, Lingxiao Ma, and Yongqiang Xiong

In the 12th ACM SIGOPS Asia-Pacific Workshop on Systems (APSys)

Virtual Event, August 2021

A Case for Two-stage Inference with Knowledge Caching

Geonha Park, Changho Hwang, and KyoungSoo Park

In the 3rd International Workshop on Embedded and Mobile Deep Learning (EMDL@MobiSys)

Seoul, Republic of Korea, June 2019

Efficient Resource Sharing for Distributed Deep Learning

Changho Hwang, Taehyun Kim, Kyuho Son, Jinwoo Shin, and KyoungSoo Park

In the 13th USENIX Symposium on Operating Systems Design and Implementation (OSDI) — poster

Carlsbad, CA, October 2018