venue: SC
year: 2025
papers:
- title: 'Cosmological Hydrodynamics at Exascale: A Trillion-Particle Leap in Capability'
  authors:
  - Nicholas Frontiere
  - J. D. Emberson
  - Michael Buehlmann
  - Esteban M. Rangel
  - Salman Habib 0002
  - Katrin Heitmann
  - Patricia Larsen
  - Vitali A. Morozov
  - Adrian Pope
  - Claude-André Faucher-Giguère
  - Antigoni Georgiadou
  - Damien Lebrun-Grandié
  - Andrey Prokopenko
  reason: "Delivers the first trillion-particle cosmological hydrodynamics simulation on exascale hardware, demonstrating sustained petaflop-scale performance on a flagship scientific application."

- title: Ab-initio Quantum Transport with the GW Approximation, 42, 240 Atoms, and Sustained Exascale Performance
  authors:
  - Nicolas Vetsch
  - Alexander Maeder
  - Vincent Maillou
  - Anders Winka
  - Jiang Cao
  - Grzegorz Kwasniewski
  - Leonard Deuschle
  - Torsten Hoefler
  - Alexandros Nikolaos Ziogas
  - Mathieu Luisier
  reason: "Achieves sustained exascale performance for first-principles quantum transport at 42,240 atoms, establishing a new scale record for the GW many-body perturbation method."

- title: Kilometer-Scale AI-Powered and Performance-Portable Earth System Model (AP3ESM) to Achieve Year-Scale Simulation Speed on Heterogeneous Supercomputers
  authors:
  - Kai Xu
  - Maoxue Yu
  - Yuhu Chen
  - Jie Gao
  - Shuang Wang
  - Jiaying Song
  - Xiaohui Duan
  - Junwei Wei
  - Jiangfeng Yu
  - Hailong Liu 0007
  - Jinrong Jiang
  - Yi Zhang 0127
  - Pengfei Lin 0004
  - Tianyi Wang
  - Pengfei Wang
  - Weipeng Zheng
  - Jingwei Xie
  - Jiakang Zhang
  - Zilu Liu
  - Xiaoyu Jin
  - Jilin Wei
  - Qixin Chang
  - Qingxia Lin
  - Yanzhi Zhou
  - Weiguo Liu
  - Wei Xue 0003
  - Yiwen Li
  - Haohuan Fu
  - Yue Yu 0001
  - Xuebin Chi
  - Lixin Wu
  reason: "Integrates AI acceleration into a kilometer-scale climate model to reach year-scale simulation throughput, showing how ML–physics hybrid approaches can redefine climate modeling at supercomputer scale."

- title: 'Uno: A One-Stop Solution for Inter- and Intra-Data Center Congestion Control and Reliable Connectivity'
  authors:
  - Tommaso Bonato
  - Sepehr Abdous
  - Abdul Kabbani
  - Ahmad Ghalayini
  - Nadeen Gebara
  - Terry Lam
  - Anup Agarwal
  - Tiancheng Chen
  - Zhuolong Yu
  - Konstantin Taranov
  - Mahmoud Elhaddad
  - Daniele De Sensi
  - Soudeh Ghorbani
  - Torsten Hoefler
  reason: "Proposes a unified congestion control and reliable transport architecture spanning intra- and inter-datacenter links, with strong throughput and latency results relevant to AI and HPC clusters."

- title: 'SDR-RDMA: Software-Defined Reliability Architecture for Planetary Scale RDMA Communication'
  authors:
  - Mikhail Khalilov
  - Siyuan Shen
  - Marcin Chrapek
  - Tiancheng Chen
  - Kenji Nakano
  - Nicola Mazzoletti
  - Peter-Jan Gootzen
  - Salvatore Di Girolamo
  - Rami Nudelman
  - Gil Bloch
  - Jithin Jose
  - Abdul Kabbani
  - Sreevatsa Anantharamu
  - Jie Zhang
  - Konstantin Taranov
  - Zhuolong Yu
  - Scott Moe
  - Mahmoud Elhaddad
  - Torsten Hoefler
  reason: "Introduces software-defined reliability for RDMA at global scale, decoupling reliability policies from hardware to dramatically improve fault tolerance and reconfigurability in large-scale HPC networks."

- title: 'Bine Trees: Enhancing Collective Operations by Optimizing Communication Locality'
  authors:
  - Daniele De Sensi
  - Saverio Pasqualoni
  - Lorenzo Piarulli
  - Tommaso Bonato
  - Seydou Ba
  - Matteo Turisini
  - Jens Domke
  - Torsten Hoefler
  reason: "Presents bine tree topologies for MPI collective operations that exploit communication locality, yielding significant latency and bandwidth improvements over standard binomial trees on modern HPC interconnects."

- title: 'STELLAR: Storage Tuning Engine Leveraging LLM Autonomous Reasoning for High Performance Parallel File Systems'
  authors:
  - Chris Egersdoerfer
  - Philip H. Carns
  - Shane Snyder
  - Robert Ross
  - Dong Dai 0001
  reason: "Demonstrates that an LLM-driven autonomous reasoning engine can tune parallel file system parameters as effectively as expert hand-tuning, opening a new direction for self-optimizing HPC storage."

- title: 'Phoenix: A Refactored I/O Stack for GPU Direct Storage without Phony Buffers'
  authors:
  - Jianqin Yan
  - Shi Qiu 0012
  - Yina Lv
  - Yifan Hu
  - Hao Chen
  - Zhirong Shen
  - Xin Yao
  - Renhai Chen
  - Jiwu Shu
  - Gong Zhang 0001
  - Yiming Zhang 0003
  reason: "Redesigns the GPU direct storage I/O stack to eliminate staging buffers, achieving large bandwidth gains for GPU-to-SSD transfers critical to LLM training and scientific data workflows."

- title: Breaking the System Noise Barrier at Exascale
  authors:
  - Edgar A. León
  - Joseph Glenski
  - Mark J. Stock
  - Kim H. McMahon
  - William Loewe
  - Clark Snyder
  - Larry Kaplan
  - Srinath Vadlamani
  - Timothy I. Mattox
  - Trent D'Hooge
  - Brian Behlendorf
  - Nathan Hanford
  - Ramesh Pankajakshan
  - Matthew L. Leininger
  reason: "Provides a rigorous characterization and mitigation of OS and hardware noise at exascale, demonstrating measurable improvements in collective communication performance on a real production system."

- title: 'Story of Two GPUs: Characterizing the Resilience of Hopper H100 and Ampere A100 GPUs'
  authors:
  - Shengkun Cui
  - Archit Patke
  - Hung Nguyen
  - Aditya Ranjan
  - Ziheng Chen 0006
  - Phuong Cao
  - Gregory H. Bauer
  - Brett M. Bode
  - Catello Di Martino
  - Saurabh Jha
  - Chandra Narayanaswami
  - Daby Sow
  - Zbigniew T. Kalbarczyk
  - Ravishankar K. Iyer
  reason: "Delivers the first detailed side-by-side hardware fault-injection study of H100 and A100 GPUs, revealing how architecture changes in Hopper alter error propagation and resilience for HPC and AI workloads."

- title: Exploring and Mitigating Failure Behavior of Large Language Model Training Workloads in HPC Systems
  authors:
  - Pengfei Yu 0002
  - Jingjing Gu
  - Hao Han
  - Dazhong Shen
  - Bao Wen
  - Yang Liu 0390
  reason: "Characterizes real-world failure modes of large-scale LLM training on HPC clusters and proposes targeted mitigation strategies, providing essential reliability insights for AI infrastructure operators."

- title: 'XaaS Containers: Performance-Portable Representation With Source and IR Containers'
  authors:
  - Marcin Copik
  - Eiman Alnuaimi
  - Alok Kamatar
  - Valérie Hayot-Sasson
  - Alberto Madonna
  - Todd Gamblin
  - Kyle Chard
  - Ian T. Foster
  - Torsten Hoefler
  reason: "Proposes source- and IR-level HPC containers that enable performance portability across heterogeneous architectures without recompilation, addressing a key deployment challenge for reproducible HPC software."

- title: 'cMPI: Using CXL Memory Sharing for MPI One-Sided and Two-Sided Inter-Node Communications'
  authors:
  - Xi Wang 0027
  - Bin Ma
  - Jongryool Kim
  - Byungil Koh
  - Hoshik Kim
  - Dong Li 0001
  reason: "Exploits CXL memory semantics to implement MPI communication primitives with dramatically reduced software overhead, demonstrating a promising path for memory-centric supercomputer interconnects."

- title: 'X-MoE: Enabling Scalable Training for Emerging Mixture-of-Experts Architectures on HPC Platforms'
  authors:
  - Yueming Yuan
  - Ahan Gupta
  - Jianping Li
  - Sajal Dash
  - Feiyi Wang
  - Minjia Zhang
  reason: "Addresses the communication and load-balance bottlenecks of sparse Mixture-of-Experts training at scale, achieving efficient utilization of large GPU clusters for next-generation LLM workloads."

- title: Benchmark-driven Models for Energy Analysis and Attribution of GPU-Accelerated Supercomputing
  authors:
  - Oscar Antepara
  - Zhengji Zhao
  - Brian Austin
  - Nan Ding 0006
  - Leonid Oliker
  - Nicholas J. Wright
  - Samuel Williams 0001
  reason: "Develops fine-grained benchmark-driven energy models for GPU supercomputers that attribute power consumption to individual components and workloads, enabling principled energy optimization at the facility level."