Afternoon Tutorial
DSM 2015 - Tutorial on Datacenter Simulation Methodologies
Day 2 -- March 30
- 8:00-8:15 Welcome (General, Program Chairs)
- 8:15-9:15 Keynote I: James C. Hoe, Hardware Acceleration Comes of Age
- 9:30-10:50 Session I: Best Paper Candidates, Session Chair: Jose Renau, UC Santa Cruz
- 9:30-9:50
- Critical-Path Candidates: Scalable Performance Modeling for MPI Workloads
J. Chen, R. Clapp
- 9:50-10:10
- DELPHI: A Framework for RTL-Based Architecture Design Evaluation Using DSENT Models
M. Papamichael, C. Cakir, C. Sun, O. Chen, J. Hoe, K. Mai, L. Peh, V. Stojanovic
- 10:10-10:30
- Where Does the Time Go? Characterizing Tail Latency in Memcached
G. Blake, A. Saidi
- 10:30-10:50
- Micro-Architecture Independent Analytical Processor Performance and Power Modeling
S. Van den Steen, S. De Pestel, M. Mechri, S. Eyerman, T. Carlson, L. Eeckhout, E. Hagersten, D. Black-Schaffer
- 11:15-11:55 Session II: Graphs, Session chair: Aaron Smith, Microsoft
- 11:15-11:35
- Graph processing platforms at scale: practices and experiences
S. Lim, S. Lee, G. Ganesh, T. Brown, S. Sukumar
- 11:35-11:55
- Graph-Matching-Based Simulation-Region Selection for Multiple Binaries
C. Yount, H. Patil, M. Islam, A. Srikanth
- 1:20-2:20 Session III: Sampling, Session chair: Stijn Eyerman, Ghent University
- 1:20-1:40
- A Modeling Framework for Reuse Distance-based Estimation of Cache Performance
X. Pan, B. Jonsson
- 1:40-2:00
- Multi-Program Benchmark Definition
A. Jacobvitz, A. Hilton, D. Sorin
- 2:00-2:20
- Precise Computer Performance Comparisons Via Statistical Resampling Methods
B. Li, S. Chen, L. Peng
- 2:45-3:45 Session IV: Operating Systems, Session chair: Geoffrey Blake, ARM
- 2:45-3:05
- PairMiner: mining for paired functions in kernel extensions
H. Liu, B. JiaJu, Y. Wang, S. Hu
- 3:05-3:25
- Self-monitoring Overhead of the Linux perf_event Performance Counter Interface
V. Weaver
- 3:25-3:45
- Hierarchical Cycle Accounting: A new method for application performance tuning
A. Nowak, D. Levinthal, W. Zwaenepoel
- 3:45-4:45 Session V: Insights, Session chair: Andrew Hilton, Duke University
- 3:45-4:05
- Revisiting Symbiotic Job Scheduling
S. Eyerman, P. Michaud, W. Rogiest
- 4:05-4:25
- Micro-Architecture Independent Branch Behavior Characterization
S. De Pestel, S. Eyerman, L. Eeckhout
- 4:25-4:45
- Non-Volatile Memory Host Controller Interfaces Performance Analysis in High-Performance I/O Systems
A. Awad, B. Kettering, Y. Solihin
- 5:00-7:00 Poster Session and Receptions
Day 3 -- March 31
- 8:00-9:00 Keynote II: Andreas Olofsson, What I Learned Building a Parallel Processor from Scratch
- 9:10-10:30 Session VI: Synthesizable and GPUs: Andrew Hilton, Duke University
- 9:10-9:30
- Nyami: Synthesizable GPU Architectural Model for General-Purpose and Graphics-Specific Workloads
J. Bush, P. Dexter, T. Miller, A. Carpenter
- 9:30-9:50
- DRAW: Investigating Benefits of Adaptive Fetch Group Size on GPU
M. Yoon, Y. Oh, S. Lee, S. Kim, D. Kim, W. Ro
- 9:50-10:10
- DNOC: An Accurate and Fast Virtual Channel and Deflection Routing Network-On-Chip Simulator
G. Oxman, S. Weiss
- 10:10-10:30
- Performance Evaluation of a DySER FPGA Prototype System Spanning the Compiler, Microarchitecture, and Hardware Implementation
C. Ho, V. Govindaraju, T. Nowatzki, R. Nagaraju, Z. Marzec, P. Agarwal, C. Frericks, R. Cofell, K. Sankaralingam
- 10:55-11:55 Session VII: Mobile, Session chair: Mark Hempstead, Drexel University
- 10:55-11:15
- Mosaic: Cross-Platform User-Interaction Record and Replay for the Fragmented Android Ecosystem
M. Halpern, Y. Zhu, R. Peri, V. Reddi
- 11:15-11:35
- A Study of Mobile Device Utilization
C. Gao, A. Gutierrez, M. Rajan, R. Dreslinski, T. Mudge, C. Wu
- 11:35-11:55
- Full-System Approach to Analyze the Impact of Next-Generation Mobile Flash Storage
R. de Jong, A. Hansson
- 1:20-2:40 Session VIII: Emulation/Simulation, Session chair: Benjamin C. Lee, Duke University
- 1:20-1:40
- QTrace: An Framework for Customizable Full System Instrumentation
X. Tong, A. Moshovos
- 1:40-2:00
- Pydgin: Generating Fast Instruction Set Simulators from Simple Architecture Descriptions with Meta-Tracing JIT Compilers
D. Lockhart, B. Ilbeyi, C. Batten
- 2:00-2:20
- Reciprocal Abstraction for Computer Architecture Co-Simulation
M. Moeng, R. Melhem, A. Jones
- 2:20-2:40
- SynchroTrace: Synchronization-aware Architecture-agnostic Traces for Light-Weight Multicore Simulation
S. Nilakantan, K. Sangaiah, A. More, G. Salvador, B. Taskin, M. Hempstead
- 3:05-4:45 Session IX: Real Hardware, Session chair: Vince Weaver, University of Maine
- 3:05-3:25
- Performance and Energy Evaluation of Data Prefetching on Intel Xeon Phi
D. Guttman, M. Kandemir, M. Arunachalam, V. Calina
- 3:25-3:45
- Emulating Cache Organizations on Real Hardware Using Performance Cloning
Y. Wang, Y. Solihin
- 3:45-4:05
- Prometheus: Scalable and Accurate Emulation of Task-Based Applications on Many-Core Systems
G. Kestor, R. Gioiosa, D. Chavarria
- 4:05-4:25
- Analyzing Communication Models for Distributed Thread-Collaborative Processors in Terms of Energy and Time
B. Klenk, L. Oden, H. Froening
- 4:25-4:45
- Characterization and analysis of a Web Search benchmark
Z. Hadjilambrou, M. Kleanthous, Y. Sazeides
- 4:45 Concluding Remarks, Best Paper Award