Core Research Lab

The core research group studies the interaction of software and modern compute hardware, with an emphasis on improving application performance on multicore systems. The group's work ranges from application architectures, hardware-tuned support libraries, and application performance tuning tools to operating systems support and novel microarchitectures.

Proving Conflict Serializability for Full Invalidation
Justin E. Gottschlich, Jeremy G. Siek, and Manish Vachharajani
Proceedings of the 2nd Workshop on the Theory of Transactional Memory (WTTM) , September 2010.

Power-Efficient Variation-Aware Photonic On-Chip Network Management
Moustafa Mohamed, Zheng Li, Xi Chen, Li Shang, Alan Mickelson, Manish Vachharajani, and Yihe Sun
The ACM Internatioal Symposium on Low Power Electronics and Design (ISLPED), August 2010.
Nominated For Best Paper Award

An Efficient Software Transactional Memory Using Commit-Time Invalidation [abstract] (PDF)
Justin E. Gottschlich, Manish Vachharajani, and Jeremy G. Siek
Proceedings of the 2010 ACM/IEEE International Symposium on Code Generation and Optimization (CGO'10) , April 2010.
Accept Rate: 39% (29/74).
Best Presentation Award

Large Program Trace Analysis and Compression with ZDDs [abstract] (PDF)
Graham D. Price and Manish Vachharajani
Proceedings of the 2010 ACM/IEEE International Symposium on Code Generation and Optimization (CGO'10) , April 2010.
Accept Rate: 39% (29/74).

Multi-core Acceleration of Chemical Kinetics for Simulation and Prediction [abstract]
John C. Linford, John Michalakes, Manish Vachharajani, and Adrian Sandu
Proceedings of the International Conference on High Performance Computing, Networking, Storage, and Analysis (SC), November 2009.
Accept Rate: 22% (59/261).


Home Upcoming and Recent Events October 27, 2008 See Graham D. Price present our work on Visualizing Potential Parallelism in Sequential Programs at PACT-08. August 27, 2008 See Manish Vachharajani and John Michalakes host a Research Round Table on Weather Modeling on GPUs at nvision 2008. April 14, 2008 See John Michalakes present our work on GPU acceleration of numerical weather prediction at LSPP (co-located with IPDPS) February 20-23, 2008 See John Giacomoni present our work on high-speed multicore communication at PPoPP Tuesday, December 3, 2007 See John Giacomoni present our work on high-performance networking at ANCS Publications Active Projects Software Support for Fine-Grain TLP ParaMeter Weather Modeling with GPGPUs Faculty Members Manish Vachharajani Student Members John Giacomoni John Michalakes Graham Price External Links of Interest Computer Engineering Systems Research Lab Dept. of Computer Science Dept. of Electrical & Computer Engineering Computer Architecture Conferences Operating System Conferences OS Design for CMP wiki		The core research group studies the interaction of software and modern compute hardware, with an emphasis on improving application performance on multicore systems. The group's work ranges from application architectures, hardware-tuned support libraries, and application performance tuning tools to operating systems support and novel microarchitectures. Recent Publications Proving Conflict Serializability for Full Invalidation Justin E. Gottschlich, Jeremy G. Siek, and Manish Vachharajani Proceedings of the 2nd Workshop on the Theory of Transactional Memory (WTTM) , September 2010. Power-Efficient Variation-Aware Photonic On-Chip Network Management Moustafa Mohamed, Zheng Li, Xi Chen, Li Shang, Alan Mickelson, Manish Vachharajani, and Yihe Sun The ACM Internatioal Symposium on Low Power Electronics and Design (ISLPED), August 2010. Nominated For Best Paper Award An Efficient Software Transactional Memory Using Commit-Time Invalidation [abstract] (PDF) Justin E. Gottschlich, Manish Vachharajani, and Jeremy G. Siek Proceedings of the 2010 ACM/IEEE International Symposium on Code Generation and Optimization (CGO'10) , April 2010. Accept Rate: 39% (29/74). Best Presentation Award Large Program Trace Analysis and Compression with ZDDs [abstract] (PDF) Graham D. Price and Manish Vachharajani Proceedings of the 2010 ACM/IEEE International Symposium on Code Generation and Optimization (CGO'10) , April 2010. Accept Rate: 39% (29/74). Multi-core Acceleration of Chemical Kinetics for Simulation and Prediction [abstract] John C. Linford, John Michalakes, Manish Vachharajani, and Adrian Sandu Proceedings of the International Conference on High Performance Computing, Networking, Storage, and Analysis (SC), November 2009. Accept Rate: 22% (59/261). All Publications