Time Monday, April 24th
7:00 AM Registration (Dry Creek Foyer)
Breakfast (Russian River Valley Ballroom)
8:15 AM Welcome and Keynote (Dry Creek I & II)
Machine Learning for Performance and Power Modeling/Prediction [slides]
Lizy K. John, University of Texas at Austin
9:30 AM Break (Dry Creek Foyer)
10:00 AM Paper Session I: Resource Sharing (Dry Creek I & II)
Session Chair: Lizy K. John, University of Texas at Austin
Sharing the Instruction Cache Among Lean Cores on an Asymmetric CMP for HPC Applications
Ugljesa Milic, Barcelona Supercomputing Center, Universitat Politècnica de Catalunya, Alejandro Rico, ARM Inc, Paul Carpenter, Barcelona Supercomputing Center, and Alex Ramirez, Google
Performance Competitiveness of a Statically Compiled Language for Server-Side Web Applications
Yohei Ueda and Moriyoshi Ohara, IBM Research - Tokyo
Analyzing the Scalability of Managed Language Applications with Speedup Stacks [slides]
Jennifer B. Sartor, Ghent University and Vrije Universiteit Brussel, Kristof Du Bois, Intel, Stijn Eyerman, Intel, and Lieven Eeckhout, Ghent University
PMAL: Enabling Lightweight Adaptation of Legacy File Systems on Persistent Memory Systems
Hyunsub Song, Young Je Moon, Se Kwon Lee and Sam H. Noh, UNIST
Noon Lunch (Russian River Valley Ballroom)
1:30 PM Paper Session II: GPU Applications (Dry Creek I & II)
Session Chair: Wendy Elsasser, ARM
Chai: Collaborative Heterogeneous Applications for Integrated-architectures [slides]
Juan Gómez-Luna, Universidad de Córdoba, Izzat El Hajj, University of Illinois at Urbana-Champaign, Li-Wen Chang, University of Illinois at Urbana-Champaign, Victor Garcia-Flores, Barcelona Supercomputing Center, Simon Garcia de Gonzalo, University of Illinois at Urbana-Champaign, Thomas B. Jablin, University of Illinois at Urbana-Champaign, Antonio J. Peña, Barcelona Supercomputing Center, and Wen-Mei Hwu, University of Illinois at Urbana-Champaign
Performance Analysis of CNN Frameworks for GPUs [slides]
Heehoon Kim, Hyoungwook Nam, Wookeun Jung and Jaejin Lee, Seoul National University
GaaS Workload Characterization under NUMA Architecture for Virtualized GPU [slides]
Huixiang Chen, Meng Wang, Yang Hu, Mingcong Song and Tao Li, University of Florida
3:00 PM Break (Dry Creek Foyer)
3:30 PM Paper Session III: Statistical Techniques (Dry Creek I & II)
Session Chair: Lieven Eeckhout, Ghent University
Fast IPC Estimation for Performance Projections Using Proxy Suites and Decision Trees
Kanishka Lahiri and Subhash Kunnoth, AMD
Accurate Address Streams for LLC and Beyond (SLAB): A Methodology to Enable System Exploration
Reena Panda, Lizy John and Xinnian Zheng, University of Texas at Austin
Clone Morphing: Creating New Workload Behavior from Existing Applications
Yipeng Wang, Intel Labs, Amro Awad, Sandia National Laboratories, and Yan Solihin, North Carolina State University
Crossing the Architectural Barrier: Evaluating Representative Regions of Parallel HPC Applications [slides]
Alexandra Ferrerón, Universidad de Zaragoza, Radhika Jagtap, ARM Ltd., Sascha Bischoff, ARM Ltd., and Roxana Rusitoru, ARM Ltd.
5:30 PM Break (Dry Creek Foyer)
6:00 PM Poster Reception (Chalk Hill Room)
  • Characterization of GPGPU Workloads on a Commercial Multidimensional Heterogeneous Processor
    Matthew Watkins and Philip Bedoukian, Lafayette College
  • Service Capacity Measurement by Redlining with Live Production Traffic
    Susie Xia, Zhenyun Zhuang, Anant Rao, Haricharan Ramachandra, Yi Feng, and Ramya Pasumarti, LinkedIn Corp.
  • Predicting Memory Page Stability and its Application to Memory Deduplication and Live Migration
    Karim Elghamrawy, University of California-Santa Barbara, Fred Chong, University of Chicago, and Diana Franklin, University of Chicago
  • Analyzing OpenCL 2.0 Workloads Using a Heterogeneous CPU-GPU Simulator
    Li Wang1, Ren-Wei Tsai2, Shao-Chung Wang3, Kun-Chih Chen4, Po-Han Wang1, Hsiang-Yun Cheng5, Yi-Chung Lee1, Sheng-Jie Shu2, Chun-Chieh Yang3, Min-Yih Hsu3, Li-Chen Kan3, Chao-Lin Lee3, Tzu-Chieh Yu1, Rih-Ding Peng1, Chia-Lin Yang1, Yuan-Shin Hwang6, Jenq-Kuen Lee3, Shiao-Li Tsao2, and Ming Ouhyoung1
    1 National Taiwan University
    2 National Chiao Tung University
    3 National Tsing Hua University
    4 National Sun Yat-Sen University
    5 Academia Sinica
    6 National Taiwan University of Science and Technology
  • Microarchitecture Level Reliability Comparison of Modern GPU Designs: First Findings
    Alessandro Vallero, Politecnico di Torino, Sotiris Tselonis, University of Athens, Stefano Di Carlo, Politecnico di Torino, and Dimitris Gizopoulos, University of Athens
  • DARTS: Performance-Counter Driven Sampling Using Binary Translators
    Rajesh Kumar, Suchita Pati and Kanishka Lahiri, AMD India Pvt Ltd
  • Performance Analysis of Containerized Applications on Local and Remote Storage
    Qiumin Xu, University of Southern California, Manu Awasthi, Samsung, Krishna Malladi, Samsung, Janki Bhimani, Samsung, Jingpei Yang, Samsung, and Murali Annavaram, University of Southern California
  • A Taxonomy of Out-of-Order Instruction Commit
    Mehdi Alipour, Trevor E. Carlson and Stefanos Kaxiras, Uppsala University
  • PTAT: An Efficient and Precise Tool for Collecting Detailed TLB Miss Traces
    Jiutian Zhang, Yuhang Liu, Xiaojing Zhu, Yuan Ruan and Mingyu Chen, Institute Of Computing Technology, Chinese Academy of Sciences
  • Proxy Benchmarks for Emerging Workloads
    Reena Panda and Lizy John, University of Texas at Austin

Time Tuesday, April 25
7:15 AM Registration (Dry Creek Foyer)
Breakfast (Russian River Valley Ballroom)
8:15 AM Welcome and Best Paper Session (Paper Session IV)
Dry Creek I & II Session Chair: Bronis R. de Supinski, Lawrence Livermore National Laboratory
MaxSim: A Simulation Platform for Managed Applications [slides]
Andrey Rodchenko, Christos Kotselidis, Andy Nisbet, Antoniu Pop and Mikel Lujan, University of Manchester
dist-gem5: Distributed Simulation of Computer Clusters [slides]
Mohammad Alian, University of Illinois at Urbana-Champaign, Umur Darbaz, University of Illinois at Urbana-Champaign, Gabor Dozsa, ARM, Stephan Diestelhorst, ARM, Daehoon Kim, DGIST, and Nam Sung Kim, University of Illinois at Urbana-Champaign
Prefetching for Cloud Workloads: An Analysis Based on Address Patterns
Jiajun Wang, Reena Panda and Lizy John, University of Texas at Austin
10:00 AM Break (Dry Creek Foyer)
10:30 AM Paper Session V: Special-Purpose Simulators (Dry Creek I & II)
Session Chair: Michael Papamichael, Microsoft Research
Toolbox for Exploration of Energy-Efficient Event Processors for Human-Computer Interaction
Tayyar Rzayev, David Albonesi, Rajit Manohar, Francois Guimbretiere and Jaeyeon Kihm, Cornell University
HW/SW Co-designed Processors: Challenges, Design Choices and a Simulation Infrastructure for Evaluation [slides]
Rakesh Kumar, University of Edinburgh, Jose Cano, University of Edinburgh, Aleksandar Brankovic, Intel, Demos Pavlou, 11pets, Kyriakos Stavrou, 11pets, Enric Gibert, Pharmacelera, Alejandro Martinez, ARM, and Antonio Gonzalez, Universitat Politècnica de Catalunya
OpenSMART: Single-Cycle Multi-hop NoC Generator in BSV and Chisel [slides]
Hyoukjun Kwon and Tushar Krishna, Georgia Institute of Technology
Noon Lunch (Russian River Valley Ballroom)
1:30 PM Paper Session VI: Workloads and Benchmarks (Dry Creek I & II)
Session Chair: Sally McKee, Chalmers University of Technology
StressRight: Finding the Right Stress for Accurate In-development System Evaluation [slides]
Jaewon Lee, POSTECH, Hanhwi Jang, POSTECH, Jae-Eon Jo, POSTECH, Gyu-Hyeon Lee, POSTECH, and Jangwoo Kim, POSTECH and Seoul National University
SimBench: A Portable Benchmarking Methodology for Full-System Simulators [slides]
Harry Wagstaff, Bruno Bodin, Tom Spink and Bjoern Franke, University of Edinburgh
Treelogy: A Benchmark Suite for Tree Traversals [slides]
Nikhil Hegde, Jianqiao Liu, Kirshanthan Sundararajah and Milind Kulkarni, Purdue University
3:00 PM Break (Dry Creek Foyer)
3:30 PM Paper Session VII: GPU Modeling and Simulation (Dry Creek I & II)
Session Chair: Suzanne Rivoire, Sonoma State University
Evaluating and Mitigating Bandwidth Bottlenecks Across the Memory Hierarchy in GPUs
Saumay Dublish, Vijay Nagarajan and Nigel Topham, University of Edinburgh
SASSIFI: An Architecture-level Fault Injection Tool for GPU Application Resilience Evaluation [slides]
Siva Kumar Sastry Hari, Timothy Tsai, Mark Stephenson, Stephen W. Keckler and Joel Emer, NVIDIA
Exploring GPU Performance, Power and Energy-Efficiency Bounds with Cache-Aware Roofline Modeling [slides]
André Lopes, INESC-ID, IST, Universidade de Lisboa, Frederico Pratas, Imagination Technologies Limited, Leonel Sousa, INESC-ID, IST, Universidade de Lisboa, and Aleksandar Ilic, INESC-ID, IST, Universidade de Lisboa
Multi2Sim Kepler: A Detailed Architectural GPU Simulator [slides]
Xun Gong, Rafael Ubal and David Kaeli, Northeastern University
5:30 PM End of Conference