April 1 (Sunday) |
8:30 Breakfast
*Tutorials
-The
Sniper Multi-Core Simulator
(Half-day, Morning) -Functional Modeling of Heterogeneous Systems Using AMD SimNow (Half-day, Morning) -Detailed Pin! Binary Instrumentation Engine (Half-day, Afternoon) *Workshop -FastPath 2012 Workshop on Performance Modeling and Analysis of Workload Optimized Systems (Half-day, Afternoon)
|
April 2 (Monday) |
8:30 Breakfast 8:45 - 9:00 Welcome by General and Program Chairs 9:00 -10:00 Keynote I Systems management in the age of cloud 10:30 -12:10 Session 1 12:10 - 1:45 Lunch 1:45 - 3:00 Session 2 3:30 - 4:45 Session 3 4:45 - 5:15 Poster Highlights 5:00 - 6:30 Reception & |
April 3 (Tuesday) |
8:30 Breakfast 9:00 - 10:00 Keynote II Parallelism, Heterogeneity, Communication: Emerging Challenges for Performance Analysis 10:30 -12:10 Session 4 12:10 - 1:45 Lunch 1:45 - 3:00 Session 5 3:30 - 4:45 Session 6 4:45 - Concluding Remarks, Best Paper Award |
8:30 Breakfast
*Tutorials
-The
Sniper Multi-Core Simulator
(Half-day, Morning)
-Functional Modeling of Heterogeneous Systems Using AMD SimNow (Half-day, Morning) AMD
-Detailed Pin! Binary Instrumentation Engine (Half-day, Afternoon) Intel
*Workshop
-FastPath 2012 Workshop on Performance Modeling and Analysis of Workload Optimized Systems (Half-day, Afternoon) IBM
8:30 Breakfast
8:45 - 9:00 Welcome (by the general and program chairs)
9:00 - 10:00 Keynote I Systems management in the age of cloud, Dr. Mazda Marvasti (VMware)
(Session Chair: Vijayalakshmi Srinivasan, IBM T.J.Watson Research Center)
10:30 - 12:10 Session 1: Best Paper Candidates
(Session Chair: Trey Cain, IBM Research)
Stargazer: Automated Regression-Based GPU Design Space Exploration
Wenhao Jia (Princeton University)
Kelly A. Shaw (University of Richmond)
Margaret Martonosi (Princeton University)
A Mechanistic Performance Model for Superscalar In-Order Processors
Maximilien Breughe (Ghent University)
Stijn Eyerman (Ghent University)
Lieven Eeckhout (Ghent University)
An LTE Uplink Receiver PHY Benchmark and Subframe-Based Power Management
Magnus Sjander (Chalmers Univ. of Technology)
Sally A. McKee (Chalmers Univ. of Technology)
Peter Brauer (Ericsson AB)
David Engdal (Ericsson AB)
Andras Vajda (Ericsson AB)
BigHouse: A simulation infrastructure for data center systems
[Best Paper Award]
David Meisner (University of Michigan)
Junjie Wu (University of Michigan)
Thomas F. Wenisch (University of Michigan)
12:10 - 1:45 Lunch
(Session Chair: Vijay Janapa Reddi, University of Texas at Austin)
A Lightweight Hybrid Hardware/Software Approach for Object-Relative Memory
Profiling
Licheng chen (ICT, CAS)
Zehan Cui (ICT, CAS)
Yungang Bao (ICT, CAS)
Mingyu Chen (ICT, CAS)
Yongbing Huang (ICT, CAS)
Guangming Tan (ICT, CAS)
Lynx: A Dynamic Instrumentation System for
Data-Parallel
Applications on GPGPU Architectures
Naila Farooqui (Georgia Institute of Technology)
Andrew Kerr (Georgia Institute of Technology)
Greg Eisenhauer (Georgia Institute of Technology)
Karsten Schwan (Georgia Institute of Technology)
Sudhakar Yalamanchili (Georgia Institute of Technology)
An FPGA-based Multi-Core Platform for Testing and Analysis of Architectural
Techniques
Will Simoneau (University of Rhode Island)
Resit Sendag (University of Rhode Island)
3:30 - 4:45 Session 3: Characterization and Optimizations for Emerging Architectures
(Session Chair: Lieven Eeckhout, Ghent University)
Comparing the Power and Performance of Intel’s SCC to State-of-the-Art CPUs and
GPUs
Ehsan Totoni (University of Illinois at Urbana-Champaign)
Babak Behzad (University of Illinois at Urbana-Champaign)
Swapnil Ghike (University of Illinois at Urbana-Champaign)
Josep Torrellas (University of Illinois at Urbana-Champaign)
Characterizing and Evaluating a Key-Value Store Applications on
Heterogeneous CPU-GPU Systems
Tayler H. Hetherington (University of British Columbia)
Timothy G. Rogers (University of British Columbia)
Lisa Hsu (AMD)
Mike O'Connor (AMD)
Tor M. Aamodt (University of British Columbia)
Selective Commitment and Selective Margin: Techniques to Minimize Cost in an
IaaS Cloud
Yu-Ju Hong (Purdue University)
Jiachen Xue (Purdue University)
Mithuna Thottethodi (Purdue University)
4:45 - 5:15 Poster Highlights
(Session Chair: Trey Cain, IBM Research)
5:15 - 6:30 Reception and Poster Session
Exploiting Temporal Locality in Network Traffic Using Commodity Multi-cores
Govind Shenoy (Universitat Politecnica De Catalunya (UPC))
Jordi Tubella (Universitat Politecnica De Catalunya (UPC))
Antonio Gonzalez (Intel Research Barcelona and UPC)
Power and Performance Analysis of Network Traffic Prediction Techniques
Muhammad Faisal Iqbal (UT Austin)
Lizy John (UT Austin)
A Cycle-Level SIMT-GPU Simulation Framework
Po-Han Wang (Dept. of CSIE, National Taiwan University)
Yu-Jung Cheng (GINM, National Taiwan University)
Chien-Wei Lo (Dept. of CSIE, National Taiwan University)
Chia-Lin Yang (Dept. of CSIE, National Taiwan University)
Bandwidth Bandit: Understanding Memory Contention
David Eklov (Uppsala University)
Nikos Nikoleris (Uppsala University)
David Black-Schaffer (Uppsala University)
Erik Hagersten (Uppsala University)
Performance Modeling and Characterization of Large Last Level Caches
Parijat Dube (IBM)
Michael Tsao (IBM)
Li Zhang (IBM)
Alan Bivens (IBM)
SLA-Guided Energy Savings for Enterprise Servers
Vlasia Anagnostopoulou (UC Santa Barbara)
Martin Dimirtov (Intel Corporation)
Doshi Kshitij (Intel Corporation)
Understanding the Communication Characteristics in HBase: What are the
Fundamental Bottlenecks?
Md. Wasi-ur-Rahman (The Ohio State University)
Jian Huang (The Ohio State University)
Jithin Jose (The Ohio State University)
Xiangyong Ouyang (The Ohio State University)
Hao Wang (The Ohio State University)
Nusrat S. Islam (The Ohio State University)
Hari Subramoni (The Ohio State University)
Chet Murthy (IBM T.J. Watson Research Center)
Dhabaleswar K. Panda (The Ohio State University)
8:30 Breakfast
9:00 - 10:00 Keynote II Parallelism, Heterogeneity, Communication: Emerging Challenges for Performance Analysis, Prof. Margaret Martonosi, Princeton University
(Session Chair: Rajeev Balasubramonian, University Of Utah)
10:30 - 12:10 Session 4: Performance Analysis of Multi-Threading
(Session Chair: Abhishek Bhattacharya, Rutgers University)
Data Sharing in Multi-Threaded Applications and its Impact on Chip Design
Anil Krishna (NCSU, IBM)
Ahmad Samih (NCSU)
Yan Solihin (NCSU)
Using Utility Prediction Models to Dynamically Choose Program Thread Counts
Ryan W. Moore (University of Pittsburgh)
Bruce R. Childers (University of Pittsburgh)
Speedup Stacks: Identifying Scaling Bottlenecks in Multi-Threaded
Applications
Stijn Eyerman (Ghent University)
Kristof Du Bois (Ghent University)
Lieven Eeckhout (Ghent University)
Performance Analysis of Thread Mappings with a Holistic View of the Hardware
Resources
Wei Wang (University of Virginia)
Tanima Dey (University of Virginia)
Jason Mars (University of Virginia)
Lingjia Tang (University of Virginia)
Jack Davidson (University of Virginia)
Mary Lou Soffa (University of Virginia)
12:10 - 1:45 Lunch
1:45 - 3:00 Session 5: Modeling and Simulation Methodology
(Session Chair: Kelly Shaw, University of Richmond)
A Single-Pass Cache Simulation Methodology for Two-level Unified Caches
Wei Zang (University of Florida)
Ann Gordon-Ross (University of Florida)
Fast and Cycle-Accurate Modeling of a Multicore Processor
Asif Khan (MIT)
Muralidaran Vijayaraghavan (MIT)
Silas Boyd-Wickizer (MIT)
Arvind (MIT)
FPGA Modeling of Diverse Superscalar Processors
Brandon H. Dwiel (North Carolina State University)
Niket K. Choudhary (North Carolina State University)
Eric Rotenberg (North Carolina State University)
3:30 - 4:45 Session 6: Application Characterization and Acceleration
(Session Chair: Peter Sweeney, IBM Research)
Evaluating FPGA-acceleration for Real-time Unstructured Search
Sai Chalamalasetti (UMass Lowell)
Martin Margala (UMass Lowell)
Wim Vandervauwhede (University of Glasgow)
Mitch Wright (Hewlett Packard)
Parthasarathy Ranganathan (Hewlett Packard Labs)
Combined Profiling: Practical Collection of Feedback Information for Code
Optimization
Paul Berube (University of Alberta)
Jose Nelson Amaral (University of Alberta)
Architectural Characterization and Similarity Analysis of Sunspider and
Google’s V8 Javascript Benchmarks
Devesh Tiwari (North Carolina State University)
Yan Solihin (North Carolina State University)
4:45 - Concluding Remarks, Best Paper Award
Keynote
I:
Systems management in the age of cloud
Bio:
Mazda Marvasti is currently the Chief
Architect for Analytics at VMware Corporation, the leader in virtualization and
cloud enablement software. He arrived at VMware via the acquisition of his
company Integrien which he was the co-founder and CTO from 2002 to 2010. He led
the development of Integrien’s flagship product Alive that used patented
statistical algorithms to proactively determine application performance issues.
Prior to Integrien Mazda was the CTO of LowerMyBills.com (acquired by Experian
for $380M) where he build the initial team and launched the service to millions
of daily users. A decade of experience at The Aerospace Corporation, Ford Motor
Company and General Motors Research round out his 20 years of Engineering and IT
experience. Mazda holds a Masters degree from University of Michigan and a
Ph.D. from Georgia Tech in Aerospace Engineering and holds multiple patents on
large scale data analysis.
Abstract: With the growing demand for cloud computing and the
need for elastic environments comes new challenges in systems manageability.
The abstraction of physical from application to the end-user computing and
the need to expand and contract capacity on demand has introduced a new
paradigm for systems and application management. Transiency of performance
counters and the inability to get appropriate sample sizes renders
traditional frequency based statistical analysis techniques ineffective.
This talk will look into current research at VMware regarding these topics
and the general trends in systems management in the age of the hybrid cloud.
Parallelism, Heterogeneity, Communication: Emerging Challenges for Performance Analysis
Bio:
Margaret Martonosi is Professor of Computer
Science at Princeton University, where she has been on the faculty since 1994.
Martonosi’s research interests are in computer architecture and the
hardware-software interface, particularly focusing on power-efficient systems
and mobile computing. Her group developed the Wattch power modeling tool, the
first architecture level power modeling infrastructure for superscalar
processors. In mobile computing and sensor networks, Martonosi led the Princeton
ZebraNet project, including two real-world deployments of tracking collars on
zebras in Kenya. Her current research studies power and performance tradeoffs in
mobile and parallel systems at all scales.
Martonosi is a Fellow of IEEE
and ACM. In 2010, she received Princeton University’s Graduate Mentoring Award.
She holds an affiliated faculty appointment in Princeton EE, and from 2005-2007,
she served as Associate Dean for Academic Affairs for the Princeton University
School of Engineering and Applied Science.
Abstract:
The quick evolution in computing platforms represents
an ongoing cat-and-mouse game with the techniques we can build to measure
and analyze them. Where performance used to be the dominant metric to
measure, current tools and techniques must also accurately estimate power,
error resiliency, and other attributes. Furthermore, the trajectory towards
extensive, dynamic, and heterogeneous parallelism make such estimates both
more important and more difficult to achieve. This talk will discuss
measurement trends and opportunities in two particular domains---for mobile
computing, and for heterogeneous parallelism---as examples of the broadening
challenges and opportunities for the field overall.