Q
Qin Zhao
Researcher at Massachusetts Institute of Technology
Publications - 15
Citations - 1178
Qin Zhao is an academic researcher from Massachusetts Institute of Technology. The author has contributed to research in topics: Cache & Shadow memory. The author has an hindex of 15, co-authored 15 publications receiving 1128 citations. Previous affiliations of Qin Zhao include Singapore–MIT alliance & National University of Singapore.
Papers
More filters
Proceedings ArticleDOI
PetaBricks: a language and compiler for algorithmic choice
TL;DR: PetaBricks is presented, a new implicitly parallel language and compiler where having multiple implementations of multiple algorithms to solve a problem is the natural way of programming and makes algorithmic choice a first class construct of the language.
Proceedings ArticleDOI
Practical memory checking with Dr. Memory
Derek Bruening,Qin Zhao +1 more
TL;DR: Dr. Memory is presented, a memory checking tool that operates on both Windows and Linux applications that handles the complex and not fully documented Windows environment, and avoids reporting false positive memory leaks that plague traditional leak locating algorithms.
Proceedings ArticleDOI
TaintTrace: Efficient Flow Tracing with Dynamic Binary Rewriting
TL;DR: This paper demonstrates that TaintTrace is effective in protecting against various attacks while maintaining a modest slowdown of 5.5 times, offering significant improvements over similar tools.
Proceedings ArticleDOI
Dynamic cache contention detection in multi-threaded applications
TL;DR: A novel approach is presented that efficiently analyzes interactions between threads to determine thread correlation and detect true and false sharing, and is able to improve the performance of some applications up to a factor of 12x and shed light on the obstacles that prevent their performance from scaling to many cores.
Proceedings ArticleDOI
Umbra: efficient and scalable memory shadowing
TL;DR: This paper presents an efficient and scalable memory shadowing framework called Umbra, which supports efficient mapping from application data to shadow metadata for both 32-bit and 64-bit applications and shows that shadow memory translation overhead can be reduced to just 133% on average.