Recent News

• [12/2023] A paper "Thorough Characterization and Analysis of Large Transformer Model Training At-Scale" is accepted into ACM SIGMETRICS'24.
• [11/2023] Two workshop papers are accepted into SC'23.
• [05/2023] A paper "TrainBF: High-Performance DNN Training Engine using BFloat16 on AI Accelerators" is accepted into Euro-Par'23.
• [02/2023] A paper "Transfer Learning Across Heterogeneous Features For Efficient Tensor Program Generation" is accepted into ExHET'23.
• [01/2023] Zhen has been awarded two Impact Argonne Awards in recognition of the contributions to AI for science for High Performance Computing and Enhancement of Argonne’s Reputation.
• [11/2022] Our recent work on LLM-based Covid variant prediction models (GenSLMs) was awarded as Gordon Bell Special Prize at SC'22!!! ACM HPCwire EurekAlert NVIDIA Newswise
• [11/2022] A paper "Merchandiser: Data Placement on Heterogeneous Memory for Task-Parallel HPC Applications with Load-Balance Awareness" is accepted into PPoPP'23.
• [10/2022] Zhen will serve as a shadow PC member at EuroSys'23 Link
• [09/2022] A paper "A Comprehensive Evaluation of Novel AI Accelerators for Deep Learning Workloads" is accepted at the 13th IEEE International Workshop on Performance Modeling, Benchmarking and Simulation of High Performance Computer Systems (PMBS) at SC'22.
• [09/2022] A tutorial on "Programming New AI Accelerators for Scientific Computing" is accepted and will be presented at SC'22 Link
• [08/2022] Zhen gave an invited talk on Argonne Training Program on Extreme-Scale Computing (ATPESC 2022) Link Video
• [04/2022] Zhen gave an invited talk and service as panellist at Berkeley Lab: "Throughput-oriented and Accuracy-aware DNN Training with BFloat16 on GPU" Link
• [03/2022] A paper "Throughput-oriented and Accuracy-aware DNN Training with BFloat16 on GPU" is accepted at IPDPSW'22.
• [12/2021] A paper "TLB-pilot: Mitigating TLB Contention Attack on GPUs with Microarchitecture-Aware Scheduling" is accepted by ACM Transactions on Architecture and Code Optimization (TACO).
• [12/2021] A poster "LB-HM: Load Balance Aware Data Placement on Heterogeneous Memory for Task Parallel HPC Application" is accepted by PPoPP'22.
• [10/2021] Zhen is invited to be TPDS (IEEE Transactions on Parallel and Distributed Systems) reviewer.
• [8/2021] A paper "Flame: A Self-Adaptive Auto-Labeling System for Heterogeneous Mobile Processors" is accepted by SEC'21.
• [8/2021] Zhen gave an invited talk at ANL: "Performance Optimization of ML and HPC Applications on Heterogeneous Systems"
• [6/2021] A paper "A Pattern Based SpGEMM Library for Multi-core and Many-core Architectures" is accepted by TPDS.
• [1/2021] A paper "MD-HM: Memoization-based Molecular Dynamics Simulations on Big Memory System" is accepted in ICS'21.
• [1/2021] A paper "Enabling Energy-Efficient DNN Training on Hybrid GPU-FPGA Accelerators" is accepted in ICS'21.
• [1/2021] A paper "Tahoe: Tree Structure-Aware High Performance Inference Engine for Decision Tree Ensemble on GPU" is accepted in EuroSys'21.
• [9/2020] A paper "Smart-PGSim: Using Neural Network to Accelerate AC-OPF Power Grid Simulation" is accepted in SC'20.
• [3/2020] A paper, "RIANN: Real-time Incremental Learning with Approximate Nearest Neighbor on Mobile Devices", is accepted in OpML 2020.
• [2/2020] A paper, "Flame: A Self-Adaptive Auto-Labeling System for Heterogeneous Mobile Processors", is accepted in MLSys-W 2020.