Daniel Cederman

	Phone: +46 737-809013
	Room: 5126
	Email: cederman at chalmers.se

I'm a member of the DCS group, working with non-blocking synchronization for multi-core processors.
I'm currently involved in the european PEPPHER project.

Papers

Towards a Software Transactional Memory for Graphics Processors
Daniel Cederman, Philippas Tsigas, Muhammad Tayyab Chaudhry, In the Proceedings of the Eurographics Symposium on Parallel Graphics and Visualization 2010.

Supporting Lock-Free Composition of Concurrent Data Objects[pdf]
Daniel Cederman and Philippas Tsigas, In the Proceedings of the 7th ACM conference on Computing Frontiers (CF 10), pages: 53-62, ACM 2010.

On sorting and load balancing on GPUs [pdf]
Daniel Cederman and Philippas Tsigas, In the ACM SIGARCH Computer Architecture News, Vol. 36, No. 5, pages: 11-18, ACM press 2009.

GPU-Quicksort: A Practical Quicksort Algorithm for Graphics Processors[doi]
Daniel Cederman and Philippas Tsigas, In the ACM Journal of Experimental Algorithmics (JEA), Vol. 14, No. 4, ACM press 2009.

A Practical Quicksort Algorithm for Graphics Processors [pptx]
Daniel Cederman and Philippas Tsigas, In the Proceedings of the Annual European Symposium on Algorithms (ESA) 2008.

On Dynamic Load Balancing on Graphics Processors [pdf, pptx]
Daniel Cederman and Philippas Tsigas, In the Proceedings of the 11th Graphics Hardware (GH 2008), 2008.

A Practical Quicksort Algorithm for Graphics Processors [pdf]
Daniel Cederman and Philippas Tsigas, Technical Report 2008-01, Chalmers University of Technology, 2008.

Wait-free Queue Algorithms for the Real-time Java Specification [pdf]
Philippas Tsigas, Yi Zhang, Daniel Cederman, Tord Dellsén, Proceedings of the 12th Annual IEEE Real-Time and Embedded Technology and Applications Symposium (RTAS '06), pages 373-383, IEEE press.

Software

GPU Quicksort Library [link]
This sorting library gives programmers an easy way to increase sorting performance by harnessing the highly parallel computational power available in todays graphics cards. Sorting 16 million floating point numbers or integers take less than half a second!

Posters

Microsoft Research Summer School 2007 [pdf]

Supporting Lock-Free Composition of Concurrent Data Objects [doi]
Daniel Cederman and Philippas Tsigas, In the Proceedings of the 15th ACM SIGPLAN symposium on Principles and practice of parallel programming (PPoPP) 2010.