Main Conference

List of Accepted Papers

1. Benchmarking 3D Gaussian Splatting Rendering
Saichand Samudrala (Texas A&M University), Sushant Kondguli (Meta), Paul Gratz (Texas A&M University)

2. Evaluation of MindPalace for Chip Design Tradeoffs on Function-as-a-Service
Kaifeng Xu (Princeton University), Georgios Tziantzioulis (Princeton University), David Wentzlaff (Princeton University)

3. An Analytical Cost Model for Fast Evaluation of Multiple Compute-Engine CNN Accelerators
Fareed Qararyah (Chalmers University of Technology), Mohammad Ali Maleki (Chalmers University of Technology), Pedro Trancoso (Chalmers University of Technology)

4. FinGraV: Methodology for Fine-Grain GPU Power Visibility and Insights
Varsha Singhania (AMD Research and Advanced Development), Shaizeen Aga (AMD Research and Advanced Development), Mohamed Assem Ibrahim (AMD Research and Advanced Development)

5. Hierarchical Traversal Stack Design Using Shared Memory for GPU Ray Tracing
Eunsoo Jung (Ewha Womans University), Eunbi Jeong (Ewha Womans University), Gunjae Koo (Korea University), Yunho Oh (Korea University), Myung Kuk Yoon (Ewha Womans University)

6. PowerSensor3: A Fast and Accurate Open Source Power Measurement Tool
Steven van der Vlugt (ASTRON), Leon Oostrum (Netherlands eScience Center), Gijs Schoonderbeek (ASTRON), Ben van Werkhoven (Leiden University, Netherlands eScience Center), Bram Veenboer (ASTRON), Krijn Doekemeijer (Vrije Universiteit Amsterdam), John Romein (ASTRON)

7. MeMo: Enhancing Representative Sampling via Mechanistic Micro-Model Signatures
Chenji Han (State Key Lab of Processors, Institute of Computing Technology, CAS; University of Chinese Academy of Sciences), Huai Xu (State Key Lab of Processors, Institute of Computing Technology, CAS; University of Chinese Academy of Sciences), Guangyao Guo (State Key Lab of Processors, Institute of Computing Technology, CAS; University of Chinese Academy of Sciences), Yuxuan Wu (Loongson Lab), Fuxin Zhang (Institute of Computing Technology, Chinese Academy of Sciences)

8. ConCCL: Optimizing ML Concurrent Computation and Communication with GPU DMA Engines
Anirudha Agrawal (AMD Research & Advanced Development), Shaizeen Aga (AMD Research & Advanced Development), Suchita Pati (AMD Research & Advanced Development), Mahzabeen Islam (AMD Research & Advanced Development)

9. Concurrent PIM and Load/Store Servicing in PIM-Enabled Memory
Sudhanshu Gupta (University of Rochester), Niti Madan (AMD Research), Sooraj Puthoor (AMD Research), Nuwan Jayasena (AMD Research), Sandhya Dwarkadas (University of Virginia)

10. Dissecting Performance Overheads of Confidential Computing on GPU-based Systems
Yang Yang (University of Virginia), Mohammad Sonji (University of Virginia), Adwait Jog (University of Virginia)

11. Luthier: A Dynamic Binary Instrumentation Framework Targeting AMD GPUs
Matin Raayai Ardakani (Northeastern University), Andrew Nguyen (Northeastern University), Ivan Rosales (Northeastern University), Daoxuan Xu (William & Mary), Yuwei Sun (New York University), Yifan Sun (William & Mary), David Kaeli (Northeastern University), Norm Rubin (Northeastern University)

12. COCOSSim: A Cycle-Accurate Simulator for Heterogeneous Systolic Array Architectures
Mansi Choudhary (Duke University), Chris Kjellqvist (Duke University), Jiaao Ma (Duke University), Lisa Wu Wills (Duke University)

13. ADOR: A Design Exploration Framework for LLM Serving with Enhanced Latency and Throughput
Junsoo Kim (HyperAccel), Hunjong Lee (HyperAccel), Geonwoo Ko (KAIST), Gyubin Choi (HyperAccel), Seri Ham (KAIST), Seongmin Hong (HyperAccel), Joo-Young Kim (HyperAccel)

14. Beethoven: A Heterogeneous Multi-Core Accelerator System Composer
Chris Kjellqvist (Duke University), Brendan Peercy (Duke University), Alvin R. Lebeck (Duke), Lisa Wu Wills (Duke University)

15. Performance Analysis of GEMM Workloads on the AMD Versal Platform
Kaustubh Manohar Mhatre (Arizona State University), Venkata Guru Prasanth Mulleti (Arizona State University), Curt John Bansil (Arizona State University), Endri Taka (The University of Texas at Austin), Aman Arora (Arizona State University)

16. Exploring Constrained Dataflow Accelerators for Real-Time Multi-Task Multi-Model ML Workloads
Jamin Seo (Georgia Institute of Technology), Jianming Tong (Georgia Institute of Technology), Hyoukjun Kwon (University of California, Irvine), Tushar Krishna (Georgia Tech)

17. COSMOS: An LLC Contention Slowdown Model for Heterogeneous Multi-core Systems
Yongju Lee (Yonsei University), Jaewon Kwon (Yonsei University), Cheolhwan Kim (Yonsei University), Enhyeok Jang (Yonsei University), Jiwon Lee (Yonsei University), hyunwuk lee (Yonsei University), Won Woo Ro (Yonsei University)

18. Intel® In-Memory Analytics Accelerator: Performance Characterization and Guidelines
Jaeyoung Kang (University of Illinois Urbana-Champaign), Qirong Xia (University of Illinois Urbana-Champaign), Ipoom Jeong (Yonsei University), Yongjoo Park (University of Illinois Urbana-Champaign), Nam Sung Kim (University of Illinois Urbana-Champaign)

19. Generative AI in Embodied Systems: System-Level Analysis of Performance, Efficiency and Scalability
Zishen Wan (Georgia Tech), Jiayi Qian (Georgia Tech), Yuhang Du (University of Minnesota, Twin Cities), Jason Jabbour (Harvard University), Yilun Du (Harvard University), Yang Zhao (University of Minnesota, Twin Cities), Arijit Raychowdhury (Georgia Tech), Tushar Krishna (Georgia Tech), Vijay Janapa Reddi (Harvard University)

20. SCALE-SIM v3: A modular cycle-accurate systolic accelerator simulator for end-to-end system analysis
Ritik Raj (Georgia Institute of Technology), Sarbartha Banerjee (Department of Electrical & Computer Engineering, University of Texas at Austin), Nikhil Chandra Boopalam Srinivas (Georgia Institute of Technology), Zishen Wan (Georgia Institute of Technology), Jianming Tong (Georgia Institute of Technology), Ananda Samajdar (IBM), Tushar Krishna (Georgia Institute of Technology)

21. Beyond the Numbers: Measuring Android Performance Through User Perception
Jaeheon Lee (POSTECH), Juhyung Park (DGIST), Seonggyun Oh (DGIST), Jinhyung Koo (POSTECH), Sungjin Lee (POSTECH)

22. SAGA: A Surrogate Assisted Genetic Algorithm for Fast CPU Power Virus Generation
Panteleimonas Chatzimiltis (University of Cyprus), Georgia Antoniou (University of Cyprus), Haris Volos (University of Cyprus), Yiannakis Sazeides (University of Cyprus)

23. Understanding the Performance Horizon of the Latest ML Workloads with NonGEMM Workloads
Rachid Karami (University of California, Irvine), Sheng-Chun Kao (Google), Hyoukjun Kwon (University of California, Irvine)

List of Accepted Papers with Shepherd

24. La Superba: Leveraging a Self-Comparison Method to Understand the Performance Benefits of Sparse Accelerator Optimizations
Nebil Ozer (University of Maryland: College Park), Gregory Kollmer (Rain AI), Ramyad Hadidi (Rain AI), Bahar Asgari (University of Maryland, College Park)

25. Identifying Important Data Transformations for Synthesizing Effective Lossless Compressors
Noushin Azami (Texas State University), Martin Burtscher (Texas State University)

26. Characterizing and Optimizing LLM Inference Workloads on CPU-GPU Coupled Architectures
Prabhu Vellaisamy (Carnegie Mellon University), Thomas Labonte (Samsung Semiconductor), Sourav Chakraborty (Samsung Semiconductor), Matt Turner (Hewlett Packard Enterprise), Samantika Sury (Hewlett Packard Enterprise), John Paul Shen (Carnegie Mellon University)

27. RayFlex: An Open-Source RTL Implementation of the Hardware Ray Tracer Datapath
Fangjia Shen (Purdue University), Aaron Barnes (Purdue University), Anusuya Nallathambi (Purdue University), Timothy G. Rogers (Purdue University)

28. Use Equal-Work or Equal-Time Speedup, Not Geomean Speedup
Lieven Eeckhout (Ghent University)




This website is maintained by the ISPASS-2025 Committee.

Contact Sander De Pestel if you have any questions or comments on this website.