Write Locality and Optimization for Persistent Memory
Dong Chen (University of Rochester), Chencheng Ye (University of Rochester), Chen Ding (University of Rochester)
Replacement Policies for Heterogeneous Memories
Jacob Brock (University of Rochester), Chencheng Ye (University of Rochester), Chen Ding (University of Rochester)
Yun (Eric) Liang
Peking University
Enabling Effective Optimization Techniques for Heterogeneous System
Abstract: Heterogeneous systems couple CPUs with Programmable Gate Array. In this talk, I will first present the on-chip storage and multitasking optimization techniques for GPUs. The proposed techniques leverage on compile-time and run-time techniques to improve the cache performance, register utilization, pipeline utilization and overall performance. For the second half of the talk, I will present performance modeling and optimization techniques for FPGAs based on OpenCL programming model.
Bio: Yun (Eric) Liang is currently an assistant professor in School of EECS at Peking University, China. Before joining Peking University, he was a Research Scientist in University of Illinois at Champaign Urbana. He received the B.S degree from Tongji University, Shanghai, and the Ph.D degree in computer science from National University Singapore. He has published more than 40 research papers in the top conferences and journals on compilation, computer architecture, and embedded system including MICRO, HPCA, ISCA, DAC, CGO, ICCAD, FPGA, FCCM, etc. His work has received the Best Paper Award of FCCM 2011 and Best Paper Award nominations from ASPDAC 2016, DAC 2012, FPT 2011, and CODES+ISSS 2008.
Abstract:
With the end of Dennard scaling, software must become more parallel to exploit microprocessors that offer more, instead of faster, execution contexts. General-purpose languages and systems provide the shared-memory abstraction, which is powerful and easy to understand — but achieving both correctness and scalability is notoriously hard. A fundamental problem is that shared-memory languages and systems provide weak or undefined behavior for all parallel programs that are not perfectly synchronized.
This talk motivates the necessity of putting languages and systems on a solid foundation by providing strong end-to-end memory consistency models. I’ll describe our ongoing software- and architecture-based approaches for providing strong memory consistency. An important element of our solutions is that providing strong consistency enables us to rethink the design of other system features such as cache coherence. Overall, our work suggests that practical strong consistency is achievable and that it offers benefits that have not previously been realized.
Bio:
Michael Bond is an associate professor at Ohio State University. He did his Ph.D. and a postdoc at UT Austin, advised by Kathryn McKinley. In collaboration with his Ph.D. students and others, Mike’s research addresses the challenges of achieving reliable and scalable parallel systems. His work has received an OOPSLA Distinguished Paper Award, OOPSLA Distinguished Artifact Award, and ACM SIGPLAN Outstanding Dissertation Award.
In an anonymous submission using
\documentclass[10pt]{sig-alternate}
The style file will insist on a large empty space around the paper title. To use the space for paper text, instead of
\begin{document} \title{ A great paper from Rochester } \author{double-blind} \maketitle
Use the following
\twocolumn[{\begin{figure}[H] \setlength{\linewidth}{\textwidth} \setlength{\hsize}{\textwidth} \centering {\LARGE \bf A great paper from Rochester } \bigskip \bigskip \end{figure}}]
Then start the paper text as usual.
Rochester Programming Systems Reseach 