Update: I recently joined Microsoft Research! More info to come.
I work at the intersection of systems and computer architecture. I explore how software and hardware can work together to make datacenter applications faster and more efficient.
I was formerly a grad student and then postdoc in the Sampa research group at UW CSE; I completed my Ph.D. in December 2014 under the supervision of Luis Ceze, Mark Oskin, and Simon Kahan. My thesis work was Grappa, a runtime system designed to improve the performance of data-intensive and irregular applications fon commodity clusters.
Latency-Tolerant Software Distributed Shared Memory. J. Nelson, B. Holt, B. Myers, P. Briggs, L. Ceze, S. Kahan, M. Oskin. Best paper at USENIX ATC, July 2015.
Comparing Runtime Systems with Exascale Ambitions Using the Parallel Research Kernels. R. Van der Wijngaart, A. Kayi, J. Hammond, T. Mattson, G. Jost, T. St. John, S. Sridharan, J. Abercrombie, J. Nelson. To appear in International Conference on Supercomputing (ISC), June 2016.
Scalable Adaptive Label Propagation in Grappa. G. Farnadi, Z. Mahdavifar, I. Keller, J. Nelson, A. Teredesai, M.-F. Moens, M. De Cock. Special Session on Intelligent Mining, IEEE Big Data 2015, October 2015.
Using the Parallel Research Kernels to Study PGAS Runtimes. R. Van der Wijngaart, S. Sridharan, A. Kayi, G. Jost, J. Hammond, T. Mattson, J. Nelson. International Conference on PGAS Programming Models (PGAS), September 2015.
A 10G NetFPGA Prototype for In-Network Aggregation. V. Lee, J. Nelson, M. Oskin, L. Ceze. Workshop on Architectural Research Prototyping (WARP w/ISCA), June 2015.
SNNAP: Approximate Computing on Programmable SoCs via Neural Acceleration. T. Moreau, M. Wyse, J. Nelson, A. Sampson, H. Esmaeilzadeh, L. Ceze, M. Oskin. In HPCA 2015.
Radish: Compiling Efficient Query Plans for Distributed Shared Memory. B. Myers, D. Halperin, J. Nelson, M. Oskin, B. Howe. UW CSE Tech Report 14-10-01, 2014.
Grappa: A Latency-Tolerant Runtime for Large-Scale Irregular Applications. J. Nelson, B. Holt, B. Myers, P. Briggs, L. Ceze, S. Kahan, M. Oskin. International Workshop on Rack-Scale Computing (WRSC w/EuroSys), April 2014.
Flat Combining Synchronized Global Data Structures. B. Holt, J. Nelson, B. Myers, P. Briggs, L. Ceze, S. Kahan, M. Oskin. 7th International Conference on PGAS Programming Models (PGAS), October 2013.
RCDC: A Relaxed Consistency Deterministic Computer. J. Devietti, J. Nelson, T. Bergan, L. Ceze, D. Grossman. In ASPLOS 2011.
Dynamic Concurrency Discovery for Very Large Windows of Execution. J. Nelson, L. Ceze. In PESPMA 2009.