WACAS 2014: Program
March 2, 2014
7:45am–9:00: Breakfast (provided)
9:00–9:15: Introduction
9:15–10:00: Full Papers
Session 1: Programming Paradigms (Chair: Luis Ceze)
- Improving Coverage and Reliability in Approximate Computing Using Application-Specific, Light-Weight Checks
(slides)
Beayna Grigorian and Glenn Reinman (University of California, Los Angeles) - Parallel Streaming Computation on Error-Prone Processors
(slides)
Yavuz Yetim, Margaret Martonosi, and Sharad Malik (Princeton University) - Synthesis of Randomized Accuracy-Aware Map-Fold Programs
Sasa Misailovic and Martin Rinard (MIT)
10:00–10:30: Morning break (refreshments provided)
10:30–12:00: Full Papers
Session 2: Programming and Frameworks (Chair: Ben Ransford)
- iACT: A Software-Hardware Framework for Understanding the Scope of
Approximate Computing
(slides)
Asit K. Mishra, Rajkishore Barik, and Somnath Paul (Intel) - Profiling and Autotuning for Energy-Aware Approximate Programming
(slides)
Michael F. Ringenburg, Adrian Sampson, Luis Ceze, and Dan Grossman (University of Washington) - Expectation-Oriented Framework for Automating Approximate Programming
(slides)
Jongse Park, Kangqi Ni, Xin Zhang, Hadi Esmaeilzadeh, and Mayur Naik (Georgia Institute of Technology)
Session 3: Hardware Approximation Mechanisms (Chair: Venkatesh Akella)
- Exploring a Brink-of-Failure Memory Controller to Design an Approximate
Memory System
Meysam Taassori (University of Utah), Niladrish Chatterjee (NVIDIA), Ali Shafiee (University of Utah), and Rajeev Balasubramonian (University of Utah) - Load Value Approximation: Approaching the Ideal Memory Access Latency
(slides)
Joshua San Miguel and Natalie Enright Jerger (University of Toronto) - Toward General-Purpose Code Acceleration with Analog Computation
(slides)
Amir Yazdanbakhsh (Georgia Institute of Technology), Renee St. Amant (The University of Texas at Austin), Bradley Thwaites (Georgia Institute of Technology), Jongse Park (Georgia Institute of Technology), Hadi Esmaeilzadeh (Georgia Institute of Technology), Arjang Hassibi (The University of Texas at Austin), Luis Ceze (University of Washington), and Doug Burger (The University of Texas at Austin)
12:00pm–1:30: Lunch (Provided!)
1:30–3:00: Full Papers, Position Papers and Short Papers
Session 4: Hardware Design (Chair: Natalie Enright Jerger)
- Methodical Approximate Hardware Design and Reuse
(slides)
Amir Yazdanbakhsh, Bradley Thwaites, Jongse Park, and Hadi Esmaeilzadeh (Georgia Institute of Technology) - Automated High-Level Synthesis of Low Power/Area Approximate Computing
Circuits
Kumud Nepal, Yueting Li, R. Iris Bahar, and Sherief Reda (Brown University)
Session 5: Short Position Papers (Chair: Hadi Esmaeilzadeh)
- Reliable Computation on Unreliable Hardware: Can We Have Our Digital Cake
and Eat It?
Vladimir Kiriansky and Saman Amarasinghe (MIT CSAIL) - Context-Aware Adaptive Approximation
Lakshminarayana Renganarayana, Vijayalakshmi Srinivasan, Ravi Nair, and Daniel Prener (IBM T.J. Watson Research Center) - Refreshing Thoughts on DRAM: Power Saving vs. Data Integrity
Amir Rahmati, Matthew Hicks, Daniel Holcomb, and Kevin Fu (University of Michigan) - Revisiting Stochastic Computation: Approximate Estimation of Machine
Learning Kernels
Suyog Gupta and Kailash Gopalakrishnan (IBM Research)
Session 6: Short Notes (Chair: Karin Strauss)
- Approximate Semantics for Wirelessly Networked Applications
(slides)
Benjamin Ransford, Adrian Sampson, and Luis Ceze (University of Washington) - CPU-GPU Collaboration for Output Quality Monitoring
Mehrzad Samadi and Scott Mahlke (University of Michigan) - Tuning Approximate Computations with Constraint-Based Type Inference
Brett Boston, Adrian Sampson, Dan Grossman, and Luis Ceze (University of Washington) - QBF-Based Synthesis of Optimal Word-Splitting in Approximate Multi-Level
Storage Cells
Daniel E. Holcomb and Kevin Fu (University of Michigan)
3:00–3:30: Afternoon break (refreshments provided)
3:30–5:00: Panel on Open Questions/Challenges in Approximate Computing