* All times are in Korea Standard Time (KST). ★ Best Paper Nominee.
| |
Characterizing State Space Model and Hybrid Language Model Performance with Long Context
Saptarshi Mitra (University of California, Irvine); Rachid Karami (University of California, Irvine); Haocheng Xu (University of California, Irvine); Sitao Huang (University of California, Irvine); Hyoukjun Kwon (University of California, Irvine)
|
GTPin: Enhancing Intel GPU Profiling With High-Level Binary Instrumentation
Konstantin Levit-Gurevich (Intel Corporation); Alex Skaletsky (Intel Corporation); Ortal Geller (Intel Corporation); Moshe Goren (Intel Corporation); Rawan Ziadat (Intel Corporation); Rami Burstein (Intel Corporation); Tal Oved (Intel Corporation)
|
| |
The xPU-athalon: Quantifying the Competition of AI Acceleration
Alicia Golden (Harvard University); Carole-Jean Wu (FAIR at Meta); Gu-Yeon Wei (Harvard University); David Brooks (Harvard University)
|
FlexNoC: Fast and Flexible Analysis for NoCs with Arbitrary Topologies and Hybrid Arbitration
Anuparna Ganguly (Indian Institute of Science); Rahul Tripathy (Indian Institute of Science); Tyson Loveless (Intel Corporation); Mohammad Majharul Islam (Intel Corporation); Sumit K. Mandal (Indian Institute of Science)
|
| |
HARMONI: Hierarchical ARchitecture MOdeling for LLMs with Near/In Memory Computing
Khyati Kiyawat (University of Virginia); Yasas Seneviratne (University of Virginia); Zhenxing Fan (University of Virginia); Morteza Baradaran (University of Virginia); Kevin Skadron (University of Virginia)
|
Towards System-2 AI: Workloads and Characterizations of Energy-Based Models
Hanchen Yang (Georgia Institute of Technology); Zishen Wan (Georgia Institute of Technology); Jiayi Qian (Georgia Institute of Technology); Jingtian Dang (Georgia Institute of Technology); Ziwei Li (Georgia Institute of Technology); Yilun Du (Harvard University); Tushar Krishna (Georgia Institute of Technology)
|
| |
TensorDynamic: Bridging Application- and Instruction-Level Fault Injection for DNN Tensor Core Execution
Yuxiao Jia (Georgia Institute of Technology); Euijun Chung (Georgia Institute of Technology); Huanzhi Pu (Georgia Institute of Technology); Ben Feinberg (Sandia National Laboratories); Hyesoon Kim (Georgia Institute of Technology)
|
It's Not the Storage: Exposing Linux Kernel Bottlenecks in Page Fault Handling with SSDs
Alireza Haddadi (Uppsala University); David Black-Schaffer (Uppsala University); Chang Hyun Park (Uppsala University)
|
| |
★ LLMServingSim 2.0: A Unified Simulator for Heterogeneous and Disaggregated LLM Serving Infrastructure
Jaehong Cho (KAIST); Hyunmin Choi (KAIST); Guseul Heo (KAIST); Jongse Park (KAIST)
|
(Recorded) Do Not Get Fooled: Use True Device Utilization on High-Performance Storage Devices
Ali Sedaghatgoo (Sharif University of Technology); Mohammadamin Ajdari (HPDS Research); Erfan Teymouri (Sharif University of Technology); Hossein Asadi (Sharif University of Technology)
|
| |
(Recorded) TaxBreak: Unmasking the Hidden Costs of LLM Inference Through Overhead Decomposition
Prabhu Vellaisamy (Carnegie Mellon University); Shreesh Tripathi (Carnegie Mellon University); Vignesh Natarajan (Carnegie Mellon University); Surya Santhan Thenarasu (Carnegie Mellon University); Shawn Blanton (Carnegie Mellon University); John Paul Shen (Carnegie Mellon University)
|
(Recorded) Characterization and Performance Analysis of Aging Effect on Enterprise HDDs
Ava Dezhban (Sharif University of Technology); Mohammadamin Ajdari (HPDS Research); Hossein Asadi (Sharif University of Technology)
|
| |
Understanding Simulated Architecture via gem5 Call-Stack Profiling
Johan Söderström (Université Grenoble Alpes, Inria); Rashid Aligholipour (Uppsala University); Yuan Yao (Uppsala University)
|
DyPNet-MSC: Dynamic Bandwidth Allocation in Photonic Network-on-Wafer GPU Architectures
Ziyue Zhang (Ghent University - imec); Hossein SeyyedAghaei (Ghent University); Benyamin Eslami; Xin Wang (Ghent University - imec); Gunther Roelkens (Ghent University - imec); Didier Colle (Ghent University - imec); Mario Pickavet (Ghent University - imec); Lieven Eeckhout (Ghent University)
|
| |
Multi-Level TDA for Heterogeneous Arm Processors Using a Standardized Telemetry Framework
Jumana Mundichipparakkal (Arm Ltd); Darin Greene (Arm Ltd); Joshua Randall (Arm Ltd); Michael Williams (Arm Ltd); Vincent Coubard (Arm Ltd); Rene De Jong (Arm Ltd)
|
A Heterogeneous Mapping of a Speech Neuroprosthesis Application
Iris Uwizeyimana (University of Toronto); Oscar Sun (University of Toronto); Natalie Enright Jerger (University of Toronto)
|
| |
Toward Reproducible and Standardized Computer Architecture Simulation with gem5
Kunal Pai (University of California, Davis); Harshil Patel (University of California, Davis); Erin Le (University of California, Davis); Noah Krim (University of California, Davis); Mahyar Samani (University of California, Davis); Bobby Bruce (University of California, Davis); Jason Lowe-Power (University of California, Davis)
|
UPSORT: Design and Analysis of Processing-in-Memory Sorting Algorithms using UPMEM
Ivan Vargas (Barcelona Supercomputing Center); Julian Pavon Rivera (Barcelona Supercomputing Center); Carlos Rojas Morales (Barcelona Supercomputing Center); Javier Chavez Rubio (Barcelona Supercomputing Center); Luis Alfonso Villa Vargas (National Polytechnic Institute of México); Marco Antonio Ramírez Salinas (National Polytechnic Institute of México); Adrian Cristal (Barcelona Supercomputing Center); Osman Sabri Unsal (Barcelona Supercomputing Center); Mateo Valero (Barcelona Supercomputing Center)
|
| |
Hibiscus: End-to-end Architectural Simulation Framework for Hybrid SFQ/CMOS-Memory Compute Systems
Ryan Marsala (Colorado School of Mines); Yerzhan Mustafa (University of Rochester); Prabhath Tangella (University of Virginia); Mohammad Sonji (University of Virginia); George Michelogiannakis (Lawrence Berkeley National Labs); Selcuk Kose (University of Rochester); Adwait Jog (University of Virginia); Mehmet Belviranli (Colorado School of Mines)
|
Scalable Assembler System: Optimizing Performance through Unified Data Structures and Procedure
Xinyu Pan (Central South University); Xi Li (Central South University); Jian Zhang (Central South University); Meiguang Zheng (Central South University)
|
| |
Cleaning up the Mess: Re-evaluating the Real-System Modeling Accuracy of Ramulator 2.0
Nisa Bostanci (ETH Zurich); Haocong Luo (ETH Zurich); Ataberk Olgun (ETH Zurich); Maria Makeenkova (ETH Zurich); Geraldo Francisco De Oliveira Junior (ETH Zurich); Abdullah Giray Yaglikci (CISPA); Onur Mutlu (ETH Zurich)
|
(Recorded) A Comprehensive Study of Performance Degradation for Diverse Intensive Workloads in RocksDB
Haoyu Gong (University of Minnesota, Twin Cities); Zhaokang Ke (University of Minnesota, Twin Cities); David H.C. Du (University of Minnesota)
|
| |
★ Compiler and System Optimizations for Gem5 Simulator
Haneul Park (UIUC); Siddharth Agarwal (UIUC); Pradyun Narkadamilli (UIUC); Kiung Jung (Yonsei University); Yongjun Park (Yonsei University); Ipoom Jeong (Yonsei University); Nam Sung Kim (UIUC)
|
(Recorded) CCPA: A Concurrent Content Processing Architecture for Hardware Firewalls
Shuangliang Chen (University of Illinois Urbana-Champaign); Saptadeep Pal (Etched.ai); Rakesh Kumar (University of Illinois Urbana-Champaign)
|
| 15:00 |
16:30 |
|
| 16:30 |
18:00 |
Session 3: Cryptographic, Security, and Reliability
Session Chair: Brandon Reagen (NYU)
Location: Ballroom 1&2
|
| |
Understanding the Performance Implications of Oblivious RAM (ORAM)
Biniyam Tiruye (University of Michigan); Sitota Mersha (University of Michigan); Kalab Assefa (University of Michigan); Samuel Owens (Lafayette College); Lauren Biernacki (Lafayette College); Todd Austin (University of Michigan)
|
| |
Theodosian: A Deep Dive into Memory-Centric FHE Acceleration
Wonseok Choi (Seoul National University); Hyunah Yu (Seoul National University); Jongmin Kim (Seoul National University); Hyesung Ji (Seoul National University); Jaiyoung Park (Seoul National University); Jung Ho Ahn (Seoul National University)
|
| |
★ An Empirical Study of LLM Serving in Confidential GPUs
Eunseong Park (Virginia Tech); Timo Thans (Virginia Tech); Vishnu Kumar Kalidasan (Virginia Tech); Qinghao Hu (MIT); Wenjie Xiong (Virginia Tech)
|
| |
Beyond Latency: A System-Level Characterization of MPC and FHE for PPML
Pengzhi Huang (Cornell University); Kiwan Maeng (Pennsylvania State University); Edward Suh (NVIDIA / Cornell University)
|
| |
CryptOracle: A Modular Framework to Characterize FHE
Cory Brynds (University of Central Florida); Parker McLeod (University of Central Florida); Lauren Caccamise (Purdue University); Asmita Pal (Advanced Micro Devices Inc.); Dewan Saiham (University of Central Florida); Sazadur Rahman (University of Central Florida); Joshua San Miguel (University of Wisconsin–Madison); Di Wu (University of Central Florida)
|
| |
FDPEmu: How to Separate Workloads for Better WAF on FDP SSDs
Nakyeong Kim (Dankook University); Kwanghee Lee (Dankook University); Bryan S. Kim (Syracuse University); Seehwan Yoo (Dankook University); Jaedong Lee (Dankook University); Jongmoo Choi (Dankook University)
|
| 18:00 |
18:30 |
Walk
|
| 18:30 |
20:00 |
|
|
| 07:30 |
08:30 |
Breakfast (provided)
|
| 08:30 |
09:30 |
|
|
|
Speaker: Myoungsoo Jung (KAIST, Panmnesia)
Session Chair: John Kim (KAIST)
Location: Ballroom 1&2
|
| 09:30 |
09:45 |
Break
|
| 09:45 |
11:15 |
Session 4: Microarchitecture
Session Chair: Won Woo Ro (Yonsei University)
Location: Ballroom 1&2
|
| |
FYI: A Foundational Counter Architecture for Building CPI Stacks on Out-of-Order Processors
Silvio Campelo de Santana (Norwegian University of Science and Technology (NTNU)); Lieven Eeckhout (Ghent University); Magnus Jahre (Norwegian University of Science and Technology (NTNU))
|
| |
Understanding BTB Tag Sizing
Roman Kaspar Brunner (Norwegian University of Science and Technology (NTNU)); Rakesh Kumar (Norwegian University of Science and Technology (NTNU))
|
| |
HOTP - High-conf Only Taken Predictor for Efficient Superscalar Multi-level Branch Predictor
Bhawandeep Singh (UC Santa Cruz); Jose Renau (UC Santa Cruz)
|
| |
Correct Wrong Path Simulation
Chrysanthos Pepi (Texas A&M University); Krishnam Tibrewala (Texas A&M University); Bhargav Reddy Godala (AheadComputing); Sankara Ramesh (University of California, San Diego); Paul Gratz (Texas A&M University); Daniel A. Jiménez (Texas A&M University); Alberto Ros (University of Murcia); Gilles Pokam (Intel)
|
| |
Pesto: Diagnosing Performance Pathologies in Out-of-Order Processors
Silvio Campelo de Santana (Norwegian University of Science and Technology (NTNU)); Joseph Rogers (Norwegian University of Science and Technology (NTNU)); Lieven Eeckhout (Ghent University); Magnus Jahre (Norwegian University of Science and Technology (NTNU))
|
| |
Characterizing Synonyms and TLB Invalidations for Virtually-Indexed Virtually-Tagged Caches
Sotiris Totomis (University of Crete & ICS-FORTH); Kallia Chronaki (FORTH-ICS); Vassilis Papaefstathiou (FORTH-ICS and University of Crete)
|
| 11:15 |
11:30 |
Coffee Break
|
| 11:30 |
13:00 |
Session 5: AI/ML 2
Session Chair: Yunho Oh (Korea University)
Location: Ballroom 1&2
|
| |
★ Hardware Generation and Exploration of Lookup Table-Based Accelerators for 1.58-bit LLM Inference
Joran Heldens (MICAS, KU Leuven); Robin Geens (MICAS, KU Leuven); Joren Dumoulin (MICAS, KU Leuven); Marian Verhelst (MICAS, KU Leuven)
|
| |
EnergAIzer: Fast and Accurate GPU Power Estimation Framework for AI Workloads
Kyungmi Lee (Massachusetts Institute of Technology); Zhiye Song (Massachusetts Institute of Technology); Eun Kyung Lee (IBM T. J. Watson Research Center); Xin Zhang (IBM T. J. Watson Research Center); Tamar Eilam (IBM T. J. Watson Research Center); Anantha P. Chandrakasan (Massachusetts Institute of Technology)
|
| |
Evaluating Cross-Architecture Performance Modeling of Distributed ML Workloads Using StableHLO
Jonas Svedas (Imec); Nathan Laubeuf (Imec); Ryan Harvey (Imec); Arjun Singh (Imec); Changhai Man (Georgia Institute of Technology); Abubakr Nada (Imec); Tushar Krishna (Georgia Institute of Technology); James Myers (Imec); Debjyoti Bhattacharjee (Imec)
|
| |
RACER: A Caching Layer based Optimization for Accelerating Reinforcement Learning Workloads
Kailash Gogineni (George Washington University); Yongsheng Mei (George Washington University); Karthikeya Gogineni (Independent); Peng Wei (George Washington University); Tian Lan (George Washington University); Guru Venkataramani (George Washington University)
|
| |
A Cluster-Based Sampling Scheme for High-Performance Graph Neural Networks
Surendra Kumar Raut (Indian Institute of Technology Bhilai); Kishan Tamboli (Indian Institute of Technology Bhilai); Vishwesh Jatala (Indian Institute of Technology Bhilai)
|
| |
HeadSkip: Characterizing and Accelerating `Small' Language Models on Edge CPUs
Ian Sartor (University of Toronto); Karthik Ganesan (University of Toronto); Anh Nguyen (Fujitsu Ltd.); Andreas Moshovos (University of Toronto)
|
| 13:00 |
14:00 |
Lunch (provided)
|
| 14:00 |
15:30 |
Session 6: Metrics, Benchmarks, and Efficiency
Session Chair: Tosiron Adegbija (University of Arizona)
Location: Ballroom 1&2
|
| |
ASI: A Unifying Metric to Assess and Improve Processor Microarchitecture Sustainability
Jaime Roelandts (Ghent University); Ajeya Naithani (TU Eindhoven); Lieven Eeckhout (Ghent University)
|
| |
Linearizability Alone Is Not Enough for Strict FIFO Semantics
Ryan Huard (University of Mississippi); Md Sabbir Polak (University of Mississippi); Joshua Jurgenson (University of Mississippi); David Troendle (University of Mississippi); Byunghyun Jang (University of Mississippi)
|
| |
eBeeMetrics: An eBPF-based Library Framework for Feedback-free Observability of QoS Metrics
Muntaka Ibnath (University of California, Riverside); Mohammadreza Rezvani (University of California, Riverside); Daniel Wong (University of California, Riverside)
|
| |
PLCG: Parametric Loop Code Generator for Loop Transformation Optimization Benchmarking
Yijie Zhi (Zhejiang University); Qingran Wu (Zhejiang University); Xiaoyang Han (Zhejiang University); Ming Cai (Zhejiang University)
|
| |
Reclaiming Energy: Quantifying the Energy Overheads of Garbage Collection on Mobile Devices
Kunal Sareen (Australian National University); Stephen M. Blackburn (Google and Australian National University)
|
| |
Exploring the Energy Storage and Voltage Control Unit Design Space in Battery-Less IoT
Lukas Liedtke (Norwegian University of Science and Technology (NTNU)); Espen Holsen (Norwegian University of Science and Technology (NTNU)); Per Gunnar Kjeldsberg (Norwegian University of Science and Technology (NTNU)); Frank Alexander Kraemer (Norwegian University of Science and Technology (NTNU)); Magnus Jahre (Norwegian University of Science and Technology (NTNU))
|
| 15:30 |
16:00 |
Coffee Break
|
| 16:00 |
17:30 |
Session 7: AI/ML 3
Session Chair: Ipoom Jeong (Yonsei University)
Location: Ballroom 1&2
|
| |
(Recorded) Situla: Studying the Interplay of Sparse Formats and CPU/GPU Libraries
Amirmahdi Namjoo (University of Maryland, College Park); Sanjali Yadav (University of Maryland, College Park); Helya Hosseini (University of Maryland, College Park); Bahar Asgari (University of Maryland, College Park)
|
| |
(Recorded) Characterization of Coherent Data Movement in Scaled-Out Shared Memory Systems
Maryam Babaie (University of California, Davis); Michael R. Miller (Rambus Inc.); Wendy Elsasser (Rambus Inc.); Steven C. Woo (Rambus Inc.); Jason Lowe-Power (University of California, Davis)
|
| |
Breaking the I/O Bottleneck: I/O Coordination Optimization for Efficient Large-Scale LLM Fine-Tuning
Ziyang Shen (Xiamen University); Hongchao Du (Mohamed bin Zayed University of Artificial Intelligence); Kaihuan Lin (Xiamen University); Dawei Wu (YEESTOR Microelectronics Co., Ltd); Yin Lin (YEESTOR Microelectronics Co., Ltd); Ting Luo (YEESTOR Microelectronics Co., Ltd); Qiao Li (Mohamed bin Zayed University of Artificial Intelligence); Chun Jason Xue (Mohamed bin Zayed University of Artificial Intelligence)
|
| |
Surrogates, Spikes, and Sparsity: Performance Analysis and Characterization of SNN Hyperparameters on Hardware
Ilkin Aliyev (University of Arizona); Jesus Lopez (University of Arizona); Tosiron Adegbija (University of Arizona)
|
| |
MINISA: Minimal Instruction Set Architecture for Next-gen Reconfigurable Inference Accelerator
Jianming Tong (Georgia Institute of Technology); Yujie Li (Georgia Institute of Technology); Devansh Jain (University of Illinois Urbana-Champaign); Charith Mendis (University of Illinois Urbana-Champaign); Tushar Krishna (Georgia Institute of Technology)
|
| |
Characterizing Machine Learning Force Fields as Emerging Molecular Dynamics Workloads on Graphics Processing Units
Udari De Alwis (imec); Benjamin Mayer (imec); Tom Ashby (imec); Maria Cecilia Barrera Moreno (imec); Timon Evenblij (imec); Joyjit Kundu (imec)
|
| 17:30 |
17:45 |
Awards announcement/Closing
|
This website is maintained by the ISPASS-2026 Committee.