Coogee - HPCA 2026

VenueInternational Convention Centre Sydney

Room nameCoogee

Floor3

Room numberC3.3

Capacity144

Room InformationNo extra information available

Program

This program is tentative and subject to change.

Time Zone

The program is currently displayed in (GMT+11:00) Hobart.

Use conference time zone: (GMT+11:00) HobartSelect other time zone

The GMT offsets shown reflect the offsets at the moment of the conference.

Time Band

By setting a time band, the program will dim events that are outside this time window. This is useful for (virtual) conferences with a continuous program (with repeated sessions).
The time band will also limit the events that are included in the personal iCalendar subscription service.

Display full programSpecify a time band

Save

You're viewing the program in a time zone which is different from your device's time zone change time zone

Sat 31 Jan
Displayed time zone: Hobart change

08:45 - 10:30	Opening and Keynote TalkCC Main Conference at Coogee Chair(s): Uday Bondhugula Indian Institute of Science

08:45 15m Day opening		Opening note from program chairs CC Main Conference Uday Bondhugula Indian Institute of Science
09:00 90m Keynote		Building Compilers for AI Accelerators: Lessons from Real Hardware CC Main Conference K: Nicholas Smith Tenstorrent

11:00 - 12:45	OptimizationsCC Main Conference at Coogee Chair(s): Martin Kong The Ohio State University

11:00 26m Talk		GraalMHC: ML-Based Method-Hotness Classification for Binary-Size Reduction in Optimizing Compilers CC Main Conference Milan Cugurovic Oracle and University of Belgrade, Aleksandar Prokopec Oracle Labs, Boris Spasojevic Oracle Labs, Zurich, Switzerland, Vojin Jovanovic Oracle Labs, Milena Vujosevic Janicic University of Belgrade and Oracle
11:26 26m Talk		It’s about Time - Temporal Abstractions for Asynchronous GPU Tensor Computations CC Main Conference Bastian Hagedorn NVIDIA, Vinod Grover NVIDIA
11:52 26m Talk		Optimizing Sparse Tensor Compilation for Sparse Output CC Main Conference Shideh Hashemian University of Edinburgh, Michael F. P. O'Boyle University of Edinburgh, Amir Shaikhha University of Edinburgh
12:18 26m Talk		RIFS: Run-time Invariant Function Specialization CC Main Conference Saba Jamilan University of California, Santa Cruz, Snehasish Kumar Google LLC, Heiner Litz UC Santa Cruz

13:45 - 15:30	Optimizations for safety and moreCC Main Conference at Coogee

13:45 26m Talk		DiTOX: Fault Detection and Localization in the ONNX Optimizer CC Main Conference Nikolaos Louloudakis The University of Edinburgh, Ajitha Rajan The University of Edinburgh
14:11 26m Talk		SSMR: Statically Detecting Speculation Safe Memory Regions to Mitigate Transient Execution Attacks CC Main Conference Ange-Thierry Ishimwe University of Colorado Boulder, Sam Mcdiarmid-sterling University of Colorado Boulder, Zack McKevitt University of Colorado Boulder, Tamara Silbergleit Lehman University of Colorado Boulder
14:37 26m Talk		CHEHAB: Automatic Compiler Code Optimization for Fully Homomorphic Encryption CC Main Conference Riyadh Baghdadi New York University Abu Dhabi, Abdessamed Seddiki New York University Abu Dhabi and Ecole Superieure d'Informatique, Arab Mohammed New York University Abu Dhabi and Ecole Superieure d'Informatique, Zakaria Hebbal Ecole nationale Supérieure d'Informatique, Aimad Chabounia Ecole Superieure d'Informatique; New York University Abu Dhabi, Eduardo Chielle New York University Abu Dhabi, Michail Maniatakos New York University Abu Dhabi, MENACER Djamel Eddine Ecole Superieure d'Informatique, Karima Benatchba Ecole Nationale Supérieure d'Informatique, Challal Yacine University of Doha for Science and Technology
15:03 26m Talk		Parallel and Customizable Equality Saturation CC Main Conference Jonathan Van der Cruysse McGill University, Abd-El-Aziz Zayed McGill University, Mai Jacob Peng McGill University, Christophe Dubach McGill University

16:00 - 17:45	Code generation and tuningCC Main Conference at Coogee Chair(s): Ari Rasch University of Muenster

16:00 26m Talk		Accelerating Sparse Algebra with Program Synthesis CC Main Conference José Wesley De Souza Magalhães University of Edinburgh, Shideh Hashemian University of Edinburgh, Alexander Brauckmann University of Edinburgh, Jackson Woodruff University of Edinburgh, Elizabeth Polgreen University of Edinburgh, Michael F. P. O'Boyle University of Edinburgh
16:26 26m Talk		Schedgehammer: Auto-Tuning Compiler Optimizations Beyond Numerical Parameters CC Main Conference Johannes Lenfers University of Münster, Martin Lücke AMD, Sven Spehr University of Münster, Justus Dieckmann University of Münster, Johannes Jansen University of Münster, Sergei Gorlatch University of Muenster
16:52 26m Talk		TinyGen: Portable and Compact Code Generation for Tiny Machine Learning CC Main Conference Gaeun Ko Kyung Hee University, Seonyeong Heo Kyung Hee University
17:18 26m Talk		CPerfSmith - A Randomized C Program Generator for Performance-Oriented Compiler Testing CC Main Conference Boda Yashwanth Indian institute of Technology Roorkee, Chunduri Abhijit Indian institute of Technology Roorkee, Ruchi Kumari Indian institute of Technology Roorkee, Awanish Pandey IIT Roorkee

Sun 1 Feb
Displayed time zone: Hobart change

08:45 - 10:30	Panel + ToolsCC Main Conference at Coogee Chair(s): Martin Kong Brookhaven National Laboratory

08:45 20m Talk		Inside VOLT: Designing of an Open-Source GPU Compiler (Tool) CC Main Conference Shinnung Jeong Georgia Institute of Technology, Chihyo Ahn Georgia Tech, Huanzhi Pu Georgia Institute of Technology, Jisheng Zhao Georgia Institute of Technology, Hyesoon Kim Georgia Institute of Technology, Blaise Tine University of California, Los Angeles
09:05 20m Talk		Nsight Python: A Python-First Profiling Toolkit for Seamless GPU Kernel Analysis (Tool) CC Main Conference Bastian Hagedorn NVIDIA, Alexander Collins NVIDIA, Tony Mongkolsmai NVIDIA, Vinod Grover NVIDIA
09:30 60m Panel		Panel: The role of compilers in the era of AI chips and programming frameworks CC Main Conference A: Ayal Zaks Mobileye, P: Albert Cohen Google DeepMind, P: Nicholas Smith Tenstorrent, P: Uday Bondhugula Indian Institute of Science

11:00 - 12:45	AnalysisCC Main Conference at Coogee

11:00 26m Talk		HORIZON: Estimating Alias Analysis Precision Bounds and Their Impact on Performance CC Main Conference Khushboo Chitre IIIT Delhi, Piyus Kedia IIIT Delhi, Rahul Purandare University of Nebraska-Lincoln
11:26 26m Talk		Type Deduction Analysis: Reconstructing Transparent Pointer Types in LLVM-IR CC Main Conference Niccolò Nicolosi Politecnico di Milano, Gabriele Magnani Politecnico di Milano, Emilio Corigliano Politecnico di Milano, Davide Baroffio Politecnico di Milano, Federico Reghenzani Politecnico di Milano, Giovanni Agosta Politecnico di Milano, Italy
11:52 26m Talk		Compact Representation and Interleaved Solving for Scalable Constraint-Based Points-to Analysis CC Main Conference Ramya Kasaraneni IIT Madras, V Krishna Nandivada IIT Madras
12:18 26m Talk		Practical MHP Analysis for Java CC Main Conference Samuel Moses IIT Madras, V Krishna Nandivada IIT Madras

Mon 2 Feb
Displayed time zone: Hobart change

09:50 - 11:10	Best Paper CandidatesMain Conference at Coogee

09:50 20m Talk		Focus: A Streaming Concentration Architecture for Efficient Vision-Language Models Main Conference Chiyue Wei Duke University, Cong Guo Duke University, Junyao Zhang Duke University, Haoxuan Shan Duke University, Yifan Xu Duke University, Ziyue Zhang Duke University, Yudong Liu Duke University, Qinsi Wang Duke University, Changchun Zhou Duke University, Hai "Helen" Li Duke University, Yiran Chen Duke University
10:10 20m Talk		LoCaLUT: Harnessing Capacity–Computation Tradeoffs for LUT-Based Inference in DRAM-PIM Main Conference Junguk Hong Seoul National University, Changmin Shin Seoul National University, Sukjin Kim Seoul National University, Si Ung Noh Seoul National University, Taehee Kwon Seoul National University, Seongyeon Park Seoul National University, Hanjun Kim Yonsei University, Youngsok Kim Yonsei University, Jinho Lee Seoul National University
10:30 20m Talk		RPU - A Reasoning Processing Unit Main Conference Matthew Adiletta Harvard University, David Brooks Harvard University, Gu-Yeon Wei Harvard University
10:50 20m Talk		PinDrop: Breaking the Silence on SDCs in a Large-Scale Fleet Main Conference Peter W. Deutsch Massachusetts Institute of Technology/Meta, Harish D. Dixit Meta, Gautham Vunnam Meta, Carl Moran Meta, Eleanor Ozer Meta, Sriram Sankar Meta

11:30 - 12:50	Near-Data Processing and StorageMain Conference at Coogee

11:30 20m Talk		PIMphony: Overcoming Bandwidth and Capacity Inefficiency in PIM-based Long-Context LLM Inference System Main Conference hyucksung kwon Hanyang University, Kyungmo Koo Hanyang University, Janghyeon Kim Hanyang University, Woongkyu Lee Hanyang University, Minjae Lee Hanyang University, Gyeonggeun Jung KAIST, Hyungdeok Lee Solution Advanced Technology, SK hynix, Yousub Jung Solution Advanced Technology, SK hynix, Jaehan Park Solution Advanced Technology, SK hynix, Yosub Song Solution Advanced Technology, SK hynix, Byeongsu Yang Solution Advanced Technology, SK hynix, Haerang Choi Solution Advanced Technology, SK hynix, Guhyun Kim Solution Advanced Technology, SK hynix, Jongsoon Won Solution Advanced Technology, SK hynix, Woojae Shin Solution Advanced Technology, SK hynix, Changhyun Kim Solution Advanced Technology, SK hynix, Shin Gyeongcheol Solution Advanced Technology, SK hynix, Yongkee Kwon Tenstorrent, Ilkon Kim Solution Advanced Technology, SK hynix, Euicheol Lim SK hynix, John Kim KAIST, Jungwook Choi Hanyang University
11:50 20m Talk		Adaptive Draft Sequence Length: Enhancing Speculative Decoding Throughput on PIM-Enabled Systems Main Conference Runze Wang Huazhong University of Science and Technology, Qinggang Wang Huazhong University of Science and Technology, Haifeng Liu Huazhong University of Science and Technology, Long Zheng Huazhong University of Science and Technology, XIAOFEI LIAO Huazhong University of Science and Technology, Hai Jin Huazhong University of Science and Technology, Jingling Xue University of New South Wales
12:10 20m Talk		Conduit: Programmer-Transparent Near-Data Processing Using Multiple Compute-Capable Resources in SSDs Main Conference Rakesh Nadig ETH Zurich, Vamanan Arulchelvan ETH Zurich, Mayank Kabra ETH Zurich, Harshita Gupta ETH Zurich, Rahul Bera ETH Zurich, Nika Mansouri Ghiasi ETH Zurich, Nanditha Rao ETH Zurich, Qingcai Jiang ETH Zurich, Andreas Kosmas Kakolyris ETH Zurich, Yu Liang ETH Zurich, Mohammad Sadrosadati ETH Zürich, Onur Mutlu ETH Zurich
12:30 20m Talk		Inter-Die Interconnection Networks for Reducing Peak Current Overlaps in Next-Generation NAND Systems Main Conference Jinwoo Park KAIST, John Kim KAIST

14:10 - 15:30	LLM Inference Serving SystemsMain Conference at Coogee

14:10 20m Talk		Towards Resource-Efficient Serverless LLM Inference with SLINFER Main Conference Chuhao Xu Shanghai Jiao Tong University, Zijun Li Shanghai Jiao Tong University, Quan Chen Shanghai Jiao Tong University, China, Han Zhao Shanghai Jiao Tong University, Xueyan Tang Nanyang Technological University, Minyi Guo Shanghai Jiao Tong University
14:30 20m Talk		ELORA: Efficient LoRA and KV Cache Management for Multi-LoRA LLM Serving Main Conference Jiuchen Shi Shanghai Jiao Tong University & The Hong Kong Polytechnic University, Hang Zhang Shanghai Jiao Tong University, Yixiao Wang Shanghai Jiao Tong University, Quan Chen Shanghai Jiao Tong University, China, Yizhou Shan Huawei Cloud, Kaihua Fu Hong Kong University of Science and Technology, Wei Wang Hong Kong University of Science and Technology, Minyi Guo Shanghai Jiao Tong University
14:50 20m Talk		PASCAL: A Phase-Aware Scheduling Algorithm for Serving Reasoning-based Large Language Models Main Conference Eunyeong Cho KAIST, Jehyeon Bang KAIST, Ranggi Hwang KAIST, Minsoo Rhu KAIST
15:10 20m Talk		The Cost of Dynamic Reasoning: Demystifying AI Agents and Test-Time Scaling from an AI Infrastructure Perspective Main Conference Jiin Kim KAIST, Byeongjun Shin KAIST, Jinha Chung KAIST, Minsoo Rhu KAIST

15:50 - 17:10	Efficient LLM Inference TechniquesMain Conference at Coogee

15:50 20m Talk		PADE: A Predictor-Free Sparse Attention Accelerator via Unified Execution and Stage Fusion Main Conference Huizheng Wang Tsinghua University, Hongbin Wang Tsinghua University, Zichuan Wang Tsinghua University, Zhiheng Yue Tsinghua University, Yang Wang Tsinghua University, Chao Li Shanghai Jiao Tong University, Yang Hu Tsinghua University, Shouyi Yin Tsinghua University
16:10 20m Talk		AQPIM: Breaking the PIM Capacity Wall for LLMs with In-Memory Activation Quantization Main Conference Kosuke Matsushima Institute of Science Tokyo, Yasuyuki Okoshi Institute of Science Tokyo, Masato Motomura Institute of Science Tokyo, Daichi Fujiki Institute of Science Tokyo
16:30 20m Talk		BitDecoding: Unlocking Tensor Cores for Long-Context LLMs with Low-Bit KV Cache Main Conference Dayou Du University of Edinburgh, Shijie Cao Microsoft Research, Jianyi Cheng University of Edinburgh, UK, Luo Mai University of Edinburgh, Ting Cao Institute for AI Industry Research (AIR), Tsinghua University, Mao Yang Microsoft Research
16:50 20m Talk		GyRot: Leveraging Hidden Synergy between Rotation and Fine-grained Group Quantization for Low-bit LLM Inference Main Conference Sangjin Kim KAIST, Yuseon Choi KAIST, Byeongcheol Kim KAIST, Jungjun Oh KAIST, Hoi-Jun Yoo KAIST

17:30 - 19:00	Business MeetingMain Conference at Coogee

17:30 90m Meeting		Business Meeting Main Conference

Tue 3 Feb
Displayed time zone: Hobart change

09:50 - 11:10	Wafer-Scale Systems for Large ModelsMain Conference at Coogee

09:50 20m Talk		WATOS: Efficient LLM Training Strategies and Architecture Co-exploration for Wafer-scale Chip Main Conference Huizheng Wang Tsinghua University, Zichuan Wang Tsinghua University, Hongbin Wang Tsinghua University, Jingxiang Hou Tsinghua University, Taiquan Wei Tsinghua University, Chao Li Shanghai Jiao Tong University, Yang Hu Tsinghua University, Shouyi Yin Tsinghua University
10:10 20m Talk		FACE: Fully PD Overlapped Scheduling and Multi-Level Architecture Co-Exploration on Wafer Main Conference Zheng Xu Tsinghua University, Dehao Kong Tsinghua University, Jiaxin Liu Tsinghua University, Dingcheng Jiang Tsinghua University, Xu Dai Shanghai Artificial Intelligence Laboratory, Jinyi Deng Tsinghua University, Yang Hu Tsinghua University, Shouyi Yin Tsinghua University
10:30 20m Talk		TEMP: A Memory Efficient Physical-aware Tensor Partition-Mapping Framework on Wafer-scale Chips Main Conference Huizheng Wang Tsinghua University, Taiquan Wei Tsinghua University, Zichuan Wang Tsinghua University, Dingcheng Jiang Tsinghua University, Qize Yang Tsinghua University, Jiaxin Liu Tsinghua University, Jingxiang Hou Tsinghua University, Chao Li Shanghai Jiao Tong University, Jinyi Deng Tsinghua University, Yang Hu Tsinghua University, Shouyi Yin Tsinghua University
10:50 20m Talk		MoEntwine: Unleashing the Potential of Wafer-scale Chips for Large-scale Expert Parallel Inference Main Conference Xinru Tang Tsinghua University, Jingxiang Hou Tsinghua University, Dingcheng Jiang Tsinghua University, Taiquan Wei Tsinghua University, Jiaxin Liu Tsinghua University, Jinyi Deng Tsinghua University, Huizheng Wang Tsinghua University, Qize Yang Tsinghua University, Haoran Shang Tsinghua University, Chao Li Shanghai Jiao Tong University, Yang Hu Tsinghua University, Shouyi Yin Tsinghua University

11:30 - 12:50	Visual and Multimodal AccelerationMain Conference at Coogee

11:30 20m Talk		V-Rex: Real-Time Streaming Video LLM Acceleration via Dynamic KV Cache Retrieval Main Conference Donghyuk Kim KAIST, Sejeong Yang KAIST, Wonjin Shin KAIST, Joo-Young Kim KAIST
11:50 20m Talk		SFD: Towards Segment Fusion Dataflow for Spatial Accelerators Main Conference Fuyu Wang Sun Yat-sen University, Minghua Shen Sun Yat-sen University, Yufei Ding UCSD, Nong Xiao National University of Defense Technology & Sun Yat-sen University, Yutong Lu Sun Yat-sen University
12:10 20m Talk		VAR-Turbo: Unlocking the Potential of Visual Autoregressive Models through Dual Redundancy Main Conference Xujiang Xiang The Hong Kong University of Science and Technology, Fengbin Tu The Hong Kong University of Science and Technology
12:30 20m Talk		GauPHP: An Accelerator for 3D Gaussian Splatting Training with Gaussian-Pixel Hybrid Parallelism Main Conference Rui Wen Institute of Computing Technology, Chinese Academy of Sciences, Zhifei Yue University of Science and Technology of China, Tianbo Liu University of Science and Technology of China, Xinkai Song Institute of Computing Technology, Chinese Academy of Sciences, Jin Li Institute of Computing Technology, Chinese Academy of Sciences, Di Huang Chinese Academy of Sciences, Institute of Computing Technology, Jiaming Guo Institute of Computing Technology, Chinese Academy of Sciences, Xing Hu Institute of Computing Technology, Chinese Academy of Sciences, zidong du Institute of Computing Technology, Chinese Academy of Sciences, Qi Guo Chinese Academy of Sciences, Tianshi Chen Cambricon Technologies

14:10 - 15:30	LLM Systems and Microarchitecture ToolsMain Conference at Coogee

14:10 20m Talk		LILo: Harnessing the On-chip Accelerators in Intel CPUs for Compressed LLM Inference Acceleration Main Conference Hyungyo Kim UIUC, Qirong Xia UIUC, Jinghan Huang UIUC, Nachuan Wang UIUC, Jung Ho Ahn Seoul National University, Younjoo Lee Seoul National University, Wajdi K Feghali Intel, Ren Wang Intel Labs, Nam Sung Kim UIUC
14:30 20m Talk		ReThermal: Co-Design of Thermal-Aware Static and Dynamic Scheduling for LLM Training on Liquid-Cooled Wafer-Scale Chips Main Conference Chengran Li Tsinghua University, Huizheng Wang Tsinghua University, Jiaxin Liu Tsinghua University, Jingyao Liu Tsinghua University, Zhiheng Yue Tsinghua University, Xia Li Shanghai AI Lab, Shenfei Jiang Shanghai AI Lab, Jinyi Deng Tsinghua University, Yang Hu Tsinghua University, Shouyi Yin Tsinghua University
14:50 20m Talk		TraceRTL: Agile Performance Evaluation for Microarchitecture Exploration Main Conference Zifei Zhang SKLP, Institute of Computing Technology, Chinese Academy of Sciences; University of Chinese Academy of Sciences, Yinan Xu SKLP, Institute of Computing Technology, Chinese Academy of Sciences; University of Chinese Academy of Sciences, Sa Wang SKLP, Institute of Computing Technology, Chinese Academy of Sciences; University of Chinese Academy of Sciences, Dan Tang SKLP, Institute of Computing Technology, Chinese Academy of Sciences; Beijing Institute of Open Source Chip, Yungang Bao State Key Lab of Processors, Institute of Computing Technology, CAS; University of Chinese Academy of Sciences
15:10 20m Talk		Nugget: Portable Program Snippets Main Conference Zhantong Qiu University of California, Davis, Mahyar Samani University of California, Davis, Jason Lowe-Power University of California, Davis & Google

15:50 - 17:10	Distributed and Multi-GPU TrainingMain Conference at Coogee

15:50 20m Talk		Compression-Aware Gradient Splitting for Collective Communications in Distributed Training Main Conference Pranati Majhi Texas A&M University, Sabuj Laskar Texas A&M University, Abdullah Muzahid Texas A & M University, Eun Jung Kim
16:10 20m Talk		SCALE: Tackling Communication Bottlenecks in Confidential Multi-GPU ML Main Conference Joongun Park Georgia Tech, Yongqin Wang University of Southern California, Huan Xu Georgia Institute of Technology, Hanjiang Wu Georgia Institute of Technology, Mengyuan Li USC, Tushar Krishna Georgia Institute of Technology
16:30 20m Talk		AutoHAAP: Automated Heterogeneity-Aware Asymmetric Partitioning for LLM Training Main Conference Yuanyuan Wang Zhejiang Lab, Nana Tang Zhejiang Lab, Yuyang Wang Zhejiang Lab, Shu Pan Zhejiang Lab, Dingding Yu Zhejiang Lab, Zeyue Wang Zhejiang Lab, Mou Sun Zhejiang Lab, Kejie Fu Zhejiang Lab, Fangyu Wang Zhejiang Lab, Yunchuan Chen Zhejiang Lab, Ning Sun Zhejiang Lab, Fei Yang Zhejiang Lab
16:50 20m Talk		Towards Compute-Aware In-Switch Computing for LLMs Tensor-Parallelism on Multi-GPU Systems Main Conference Chen Zhang Shanghai Jiao Tong University, Qijun Zhang Shanghai Jiao Tong University, Zhuoshan Zhou Shanghai Jiao Tong University, Yijia Diao Shanghai Jiao Tong University, Haibo Wang Huawei, Zhe Zhou Huawei, Zhipeng Tu Huawei, Zhiyao Li Huawei, Guangyu Sun Peking University, Zhuoran Song Shanghai Jiao Tong University, Zhigang Ji Shanghai Jiao Tong University, Jingwen Leng Shanghai Jiao Tong University, Minyi Guo Shanghai Jiao Tong University

17:15 - 18:15	Industry TrackIndustry Track at Coogee

17:15 20m Industry talk		Enterprise Class On-Chip Accelerator Integration Industry Track Deanna Berger IBM, Alper Buyuktosunoglu IBM Research, Craig Walters IBM, Robert Sonnelitter IBM, Hailey Nicholson IBM, Ashraf ElSharif IBM, Yamil Rivera IBM, Avery Francois IBM, Cedric Lichtenau IBM, Jason Kohl IBM
17:35 20m Industry talk		Characterizing Cloud-Native LLM Inference at ByteDance and Exposing Optimization Challenges and Opportunities for Future AI Accelerators Industry Track Jingwei Cai ByteDance Seed, Dehao Kong , Huang Hantao ByteDance Seed, Zishan Jiang ByteDance Seed, Zixuan Ma ByteDance Seed, Qingyu Guo ByteDance Seed, Zhenxing Zhang ByteDance Seed, Guiming Shi Tsinghua University, Mingyu Gao Tsinghua University, Kaisheng Ma Tsinghua University, Minghui Yu ByteDance Seed
17:55 20m Industry talk		eGPU: Production-Scale Elastic Sharing over 10,000 GPUs Industry Track Xiaochuan Tang Alibaba Group, Hao Qi , Jianbo Dong Alibaba Group, Yinghao Yu Alibaba Group, Zhennan Xue Alibaba Group, Zhengyu Zhang Alibaba Group, Daocheng Ying Alibaba Group, Zheng Cao Alibaba Group, Xiaoyi Lu UC Merced

Wed 4 Feb
Displayed time zone: Hobart change

09:50 - 11:10	Graph Neural Networks and Retrieval SystemsMain Conference at Coogee

09:50 20m Talk		VeloxGNN: Accelerating Out-of-Core based GNN Training with Low Data Migration and High Accuracy via Delayed Gradient Propagation Main Conference Yi Li University of Texas at Dallas, Tsun-Yu Yang Center for Computational Evolutionary Intelligence, Electrical & Computer Engineering, Duke University, Zhaoyan Shen Shandong University, Ming-Chang Yang The Chinese University of Hong Kong (CUHK), Bingzhe Li University of Texas at Dallas
10:10 20m Talk		AutoGNN: End-to-End Hardware-Driven Graph Preprocessing for Enhanced GNN Performance Main Conference Seungkwan Kang KAIST, Seungjun Lee KAIST, Donghyun Gouk Panmnesia, Miryeong Kwon Panmnesia, Hyunkyu Choi Panmnesia, Junhyeok Jang Panmnesia, Sangwon Lee Panmnesia, Huiwon Choi KAIST, Jie Zhang Peking University, Wonil Choi Hanyang University, Mahmut Taylan Kandemir Pennsylvania State University, Myoungsoo Jung KAIST
10:30 20m Talk		Scaling Graph Neural Network Training via Geometric Optimization Main Conference Fangzhou Ye University of Central Florida, Lingxiang Yin University of Central Florida, Hao Zheng University of Central Florida
10:50 20m Talk		VectorLiteRAG: Latency-Aware and Fine-Grained Resource Partitioning for Efficient RAG Main Conference Junkyum Kim Georgia Institute of Technology, Divya Mahajan Georgia Institute of Technology

11:30 - 12:50	Efficient Serving and Resource ManagementMain Conference at Coogee

11:30 20m Talk		Near-Zero-Overhead Freshness for Recommendation Systems via Inference-Side Model Updates Main Conference Wenjun Yu Hong Kong Baptist University, Sitian Chen Hong Kong Baptist University, Amelie Chi Zhou Hong Kong Baptist University, Cheng Chen ByteDance, China
11:50 20m Talk		AccelFlow: Orchestrating an On-Package Ensemble of Fine-Grained Accelerators for Microservices Main Conference Jovan Stojkovic University of Illinois at Urbana-Champaign, Abraham Farrell University of Illinois Urbana-Champaign, Zhangxiaowen Gong Intel, Christopher J. Hughes Intel, Josep Torrellas University of Illinois at Urbana-Champaign
12:10 20m Talk		SpotCC: Facilitating Coded Computation for Prediction Serving Systems on Spot Instances Main Conference Lin Wang , Yuchong Hu Huazhong University of Science and Technology, Ziling Duan Huazhong University of Science and Technology, Mingqi Li Huazhong University of Science and Technology, Chenxuan Yao Huazhong University of Science and Technology, feifanliu Huazhong University of Science and Technology, Xiaolu Li Huazhong University of Science and Technology, Leihua Qin Huazhong University of Science and Technology, Dan Feng Huazhong University of Science and Technology, China
12:30 20m Talk		LowCarb: Carbon-Aware Scheduling of Serverless Functions Main Conference Rohan Basu Roy University of Utah, Devesh Tiwari Northeastern University

Sat 31 Jan
Displayed time zone: Hobart change


Room	8:00						30						9:00						30						10:00						30						11:00						30						12:00						30						13:00						30						14:00						30						15:00						30						16:00						30						17:00						30
Coogee										CC Main Conference Opening and Keynote Talk																											CC Main Conference Optimizations																																	CC Main Conference Optimizations for safety and more																											CC Main Conference Code generation and tuning

Sun 1 Feb
Displayed time zone: Hobart change


Room	8:00						30						9:00						30						10:00						30						11:00						30						12:00						30
Coogee										CC Main Conference Panel + Tools																											CC Main Conference Analysis

Mon 2 Feb
Displayed time zone: Hobart change


Room	9:00						30						10:00						30						11:00						30						12:00						30						13:00						30						14:00						30						15:00						30						16:00						30						17:00						30						18:00						30
Coogee											Main Conference Best Paper Candidates																				Main Conference Near-Data Processing and Storage																																Main Conference LLM Inference Serving Systems																				Main Conference Efficient LLM Inference Techniques																				Main Conference Business Meeting

Tue 3 Feb
Displayed time zone: Hobart change


Room	9:00						30						10:00						30						11:00						30						12:00						30						13:00						30						14:00						30						15:00						30						16:00						30						17:00						30						18:00						30
Coogee											Main Conference Wafer-Scale Systems for Large Models																				Main Conference Visual and Multimodal Acceleration																																Main Conference LLM Systems and Microarchitecture Tools																				Main Conference Distributed and Multi-GPU Training																	Industry Track Industry Track

Wed 4 Feb
Displayed time zone: Hobart change


Room	9:00						30						10:00						30						11:00						30						12:00						30
Coogee											Main Conference Graph Neural Networks and Retrieval Systems																				Main Conference Efficient Serving and Resource Management

Sat 31 Jan
Displayed time zone: Hobart change


Room	8:00			15			30			45			9:00			15			30			45			10:00			15			30			45			11:00			15			30			45			12:00			15			30			45			13:00			15			30			45			14:00			15			30			45			15:00			15			30			45			16:00			15			30			45			17:00			15			30			45
Coogee										CC Main Conference Opening note from program chairs 08:45 - 09:00			CC Main Conference Building Compilers for AI Accelerators: Lessons from Real Hardware 09:00 - 10:30																								CC Main Conference GraalMHC: ML-Based Method-Hotness Classification for Binary-Size Reduct ... 11:00 - 11:26					CC Main Conference It’s about Time - Temporal Abstractions for Asynchronous GPU Tensor Com ... 11:26 - 11:52					CC Main Conference Optimizing Sparse Tensor Compilation for Sparse Output 11:52 - 12:18						CC Main Conference RIFS: Run-time Invariant Function Specialization 12:18 - 12:45																	CC Main Conference DiTOX: Fault Detection and Localization in the ONNX Optimizer 13:45 - 14:11					CC Main Conference SSMR: Statically Detecting Speculation Safe Memory Regions to Mitigate ... 14:11 - 14:37					CC Main Conference CHEHAB: Automatic Compiler Code Optimization for Fully Homomorphic Encr ... 14:37 - 15:03						CC Main Conference Parallel and Customizable Equality Saturation 15:03 - 15:30											CC Main Conference Accelerating Sparse Algebra with Program Synthesis 16:00 - 16:26					CC Main Conference Schedgehammer: Auto-Tuning Compiler Optimizations Beyond Numerical Para ... 16:26 - 16:52					CC Main Conference TinyGen: Portable and Compact Code Generation for Tiny Machine Learning 16:52 - 17:18						CC Main Conference CPerfSmith - A Randomized C Program Generator for Performance-Oriented ... 17:18 - 17:45

Sun 1 Feb
Displayed time zone: Hobart change


Room	8:00			15			30			45			9:00			15			30			45			10:00			15			30			45			11:00			15			30			45			12:00			15			30			45
Coogee										CC Main Conference Inside VOLT: Designing of an Open-Source GPU Compiler (Tool) 08:45 - 09:05				CC Main Conference Nsight Python: A Python-First Profiling Toolkit for Seamless GPU Kernel ... 09:05 - 09:25					CC Main Conference Panel: The role of compilers in the era of AI chips and programming fra ... 09:30 - 10:30																		CC Main Conference HORIZON: Estimating Alias Analysis Precision Bounds and Their Impact on ... 11:00 - 11:26					CC Main Conference Type Deduction Analysis: Reconstructing Transparent Pointer Types in LL ... 11:26 - 11:52					CC Main Conference Compact Representation and Interleaved Solving for Scalable Constraint- ... 11:52 - 12:18						CC Main Conference Practical MHP Analysis for Java 12:18 - 12:45

Mon 2 Feb
Displayed time zone: Hobart change


Room	9:00			15			30			45			10:00			15			30			45			11:00			15			30			45			12:00			15			30			45			13:00			15			30			45			14:00			15			30			45			15:00			15			30			45			16:00			15			30			45			17:00			15			30			45			18:00			15			30			45
Coogee											HPCA Main Conference Focus: A Streaming Concentration Architecture for Efficient Vision-Lang ... 09:50 - 10:10				HPCA Main Conference LoCaLUT: Harnessing Capacity–Computation Tradeoffs for LUT-Based Infere ... 10:10 - 10:30				HPCA Main Conference RPU - A Reasoning Processing Unit 10:30 - 10:50				HPCA Main Conference PinDrop: Breaking the Silence on SDCs in a Large-Scale Fleet 10:50 - 11:10								HPCA Main Conference PIMphony: Overcoming Bandwidth and Capacity Inefficiency in PIM-based L ... 11:30 - 11:50				HPCA Main Conference Adaptive Draft Sequence Length: Enhancing Speculative Decoding Throughp ... 11:50 - 12:10				HPCA Main Conference Conduit: Programmer-Transparent Near-Data Processing Using Multiple Com ... 12:10 - 12:30				HPCA Main Conference Inter-Die Interconnection Networks for Reducing Peak Current Overlaps i ... 12:30 - 12:50																				HPCA Main Conference Towards Resource-Efficient Serverless LLM Inference with SLINFER 14:10 - 14:30				HPCA Main Conference ELORA: Efficient LoRA and KV Cache Management for Multi-LoRA LLM Serving 14:30 - 14:50				HPCA Main Conference PASCAL: A Phase-Aware Scheduling Algorithm for Serving Reasoning-based ... 14:50 - 15:10				HPCA Main Conference The Cost of Dynamic Reasoning: Demystifying AI Agents and Test-Time Sca ... 15:10 - 15:30								HPCA Main Conference PADE: A Predictor-Free Sparse Attention Accelerator via Unified Executi ... 15:50 - 16:10				HPCA Main Conference AQPIM: Breaking the PIM Capacity Wall for LLMs with In-Memory Activatio ... 16:10 - 16:30				HPCA Main Conference BitDecoding: Unlocking Tensor Cores for Long-Context LLMs with Low-Bit ... 16:30 - 16:50				HPCA Main Conference GyRot: Leveraging Hidden Synergy between Rotation and Fine-grained Grou ... 16:50 - 17:10								HPCA Main Conference Business Meeting 17:30 - 19:00

Tue 3 Feb
Displayed time zone: Hobart change


Room	9:00			15			30			45			10:00			15			30			45			11:00			15			30			45			12:00			15			30			45			13:00			15			30			45			14:00			15			30			45			15:00			15			30			45			16:00			15			30			45			17:00			15			30			45			18:00			15			30			45
Coogee											HPCA Main Conference WATOS: Efficient LLM Training Strategies and Architecture Co-exploratio ... 09:50 - 10:10				HPCA Main Conference FACE: Fully PD Overlapped Scheduling and Multi-Level Architecture Co-Ex ... 10:10 - 10:30				HPCA Main Conference TEMP: A Memory Efficient Physical-aware Tensor Partition-Mapping Framew ... 10:30 - 10:50				HPCA Main Conference MoEntwine: Unleashing the Potential of Wafer-scale Chips for Large-scal ... 10:50 - 11:10								HPCA Main Conference V-Rex: Real-Time Streaming Video LLM Acceleration via Dynamic KV Cache ... 11:30 - 11:50				HPCA Main Conference SFD: Towards Segment Fusion Dataflow for Spatial Accelerators 11:50 - 12:10				HPCA Main Conference VAR-Turbo: Unlocking the Potential of Visual Autoregressive Models thro ... 12:10 - 12:30				HPCA Main Conference GauPHP: An Accelerator for 3D Gaussian Splatting Training with Gaussian ... 12:30 - 12:50																				HPCA Main Conference LILo: Harnessing the On-chip Accelerators in Intel CPUs for Compressed ... 14:10 - 14:30				HPCA Main Conference ReThermal: Co-Design of Thermal-Aware Static and Dynamic Scheduling for ... 14:30 - 14:50				HPCA Main Conference TraceRTL: Agile Performance Evaluation for Microarchitecture Exploration 14:50 - 15:10				HPCA Main Conference Nugget: Portable Program Snippets 15:10 - 15:30								HPCA Main Conference Compression-Aware Gradient Splitting for Collective Communications in D ... 15:50 - 16:10				HPCA Main Conference SCALE: Tackling Communication Bottlenecks in Confidential Multi-GPU ML 16:10 - 16:30				HPCA Main Conference AutoHAAP: Automated Heterogeneity-Aware Asymmetric Partitioning for LLM ... 16:30 - 16:50				HPCA Main Conference Towards Compute-Aware In-Switch Computing for LLMs Tensor-Parallelism o ... 16:50 - 17:10					HPCA Industry Track Enterprise Class On-Chip Accelerator Integration 17:15 - 17:35				HPCA Industry Track Characterizing Cloud-Native LLM Inference at ByteDance and Exposing Opt ... 17:35 - 17:55				HPCA Industry Track eGPU: Production-Scale Elastic Sharing over 10,000 GPUs 17:55 - 18:15

Wed 4 Feb
Displayed time zone: Hobart change


Room	9:00			15			30			45			10:00			15			30			45			11:00			15			30			45			12:00			15			30			45
Coogee											HPCA Main Conference VeloxGNN: Accelerating Out-of-Core based GNN Training with Low Data Mig ... 09:50 - 10:10				HPCA Main Conference AutoGNN: End-to-End Hardware-Driven Graph Preprocessing for Enhanced GN ... 10:10 - 10:30				HPCA Main Conference Scaling Graph Neural Network Training via Geometric Optimization 10:30 - 10:50				HPCA Main Conference VectorLiteRAG: Latency-Aware and Fine-Grained Resource Partitioning for ... 10:50 - 11:10								HPCA Main Conference Near-Zero-Overhead Freshness for Recommendation Systems via Inference-S ... 11:30 - 11:50				HPCA Main Conference AccelFlow: Orchestrating an On-Package Ensemble of Fine-Grained Acceler ... 11:50 - 12:10				HPCA Main Conference SpotCC: Facilitating Coded Computation for Prediction Serving Systems o ... 12:10 - 12:30				HPCA Main Conference LowCarb: Carbon-Aware Scheduling of Serverless Functions 12:30 - 12:50

Room information: Coogee

This program is tentative and subject to change.

Sat 31 Jan
Displayed time zone: Hobart change

Sun 1 Feb
Displayed time zone: Hobart change

Mon 2 Feb
Displayed time zone: Hobart change

Tue 3 Feb
Displayed time zone: Hobart change

Wed 4 Feb
Displayed time zone: Hobart change

Sat 31 Jan
Displayed time zone: Hobart change

CC Main Conference

CC Main Conference

CC Main Conference

CC Main Conference

Sun 1 Feb
Displayed time zone: Hobart change

CC Main Conference

CC Main Conference

Mon 2 Feb
Displayed time zone: Hobart change

Main Conference

Main Conference

Main Conference

Main Conference

Main Conference

Tue 3 Feb
Displayed time zone: Hobart change

Main Conference

Main Conference

Main Conference

Main Conference

Industry Track

Wed 4 Feb
Displayed time zone: Hobart change

Main Conference

Main Conference

Sat 31 Jan
Displayed time zone: Hobart change

Sun 1 Feb
Displayed time zone: Hobart change

Mon 2 Feb
Displayed time zone: Hobart change

Tue 3 Feb
Displayed time zone: Hobart change

Wed 4 Feb
Displayed time zone: Hobart change

Tracks

HPCA/CGO/PPoPP/CC 2026

Co-hosted Conferences

Room information: Coogee

This program is tentative and subject to change.

Program Display Configuration

Sat 31 JanDisplayed time zone: Hobart change

Sun 1 FebDisplayed time zone: Hobart change

Mon 2 FebDisplayed time zone: Hobart change

Tue 3 FebDisplayed time zone: Hobart change

Wed 4 FebDisplayed time zone: Hobart change

Sat 31 JanDisplayed time zone: Hobart change

CC Main Conference

CC Main Conference

CC Main Conference

CC Main Conference

Sun 1 FebDisplayed time zone: Hobart change

CC Main Conference

CC Main Conference

Mon 2 FebDisplayed time zone: Hobart change

Main Conference

Main Conference

Main Conference

Main Conference

Main Conference

Tue 3 FebDisplayed time zone: Hobart change

Main Conference

Main Conference

Main Conference

Main Conference

Industry Track

Wed 4 FebDisplayed time zone: Hobart change

Main Conference

Main Conference

Sat 31 JanDisplayed time zone: Hobart change

Sun 1 FebDisplayed time zone: Hobart change

Mon 2 FebDisplayed time zone: Hobart change

Tue 3 FebDisplayed time zone: Hobart change

Wed 4 FebDisplayed time zone: Hobart change

Sat 31 Jan
Displayed time zone: Hobart change

Sun 1 Feb
Displayed time zone: Hobart change

Mon 2 Feb
Displayed time zone: Hobart change

Tue 3 Feb
Displayed time zone: Hobart change

Wed 4 Feb
Displayed time zone: Hobart change

Sat 31 Jan
Displayed time zone: Hobart change

Sun 1 Feb
Displayed time zone: Hobart change

Mon 2 Feb
Displayed time zone: Hobart change

Tue 3 Feb
Displayed time zone: Hobart change

Wed 4 Feb
Displayed time zone: Hobart change

Sat 31 Jan
Displayed time zone: Hobart change

Sun 1 Feb
Displayed time zone: Hobart change

Mon 2 Feb
Displayed time zone: Hobart change

Tue 3 Feb
Displayed time zone: Hobart change

Wed 4 Feb
Displayed time zone: Hobart change