I am a Postdoctoral Research Associate at Rice University, working with Dr. Vivek Sarkar. The main focus of my research is high performance software design for GPUs. Due to the heterogeneous nature of my research, I have had experience in related areas including microarchitecture, compiler optimizations and software libraries, mostly for GPUs. Currently at Rice, we are looking at challenges regarding efficient GPU utilization for machine learning purposes. I interned at AMD Research in Sunnyvale, CA during the Spring of 2016. I received my PhD in Computer Science from University of California Riverside under supervision of Dr. Rajiv Gupta, and my B.Sc. in Electrical Engineering from Sharif University of Technology in Tehran, Iran.




Publications

MAPL 2017      Dyna: Toward a self-optimizing declarative language for machine learning applications
Tim Vieira, Matthew Francis-Landau, Nathaniel Wesley Filardo, Farzad Khorasani, and Jason Eisner.
In Proceedings of the First ACM SIGPLAN Workshop on Machine Learning and Programming Languages, 10 pages, June 2017.
ICS 2016     
CuMAS: Data Transfer Aware Multi-Application Scheduling for Shared GPUs
M. Belviranli, F. Khorasani, L.N. Bhuyan, and R. Gupta.
ACM 30th International Conference on Supercomputing, pages 1-12, June 2016.
IPDPS 2016   
Eliminating Intra-warp Load Imbalance in Irregular Nested Patterns via Collaborative Task Engagement   [ Slides ]
F. Khorasani, B. Rowe, R. Gupta, and L.N. Bhuyan.
The 30th IEEE International Parallel and Distributed Processing Symposium, pages 524-533, May 2016.
MICRO 2015   
Efficient Warp Execution in Presence of Divergence with Collaborative Context Collection   [ Slides ]
F. Khorasani, R. Gupta, and L.N. Bhuyan.
The 48th Annual IEEE/ACM International Symposium on Microarchitecture, pages 204-215, December 2015.
PACT 2015    
Scalable SIMD-Efficient Graph Processing on GPUs   [ Slides ] [ Code ]
F. Khorasani, R. Gupta, and L.N. Bhuyan.
The 24th International Conference on Parallel Architectures and Compilation Techniques, pages 39-50, October 2015.
PACT 2015    
Stadium Hashing: Scalable and Flexible Hashing on GPUs   [ Slides ]
F. Khorasani, M.E. Belviranli, R. Gupta, and L.N. Bhuyan.
The 24th International Conference on Parallel Architectures and Compilation Techniques, pages 63-74, October 2015.
HPDC 2014    
CuSha: Vertex-Centric Graph Processing on GPUs   [ Slides ] [ Code ]
F. Khorasani, K. Vora, R. Gupta, and L.N. Bhuyan.
The 23rd International ACM Symposium on High Performance Parallel and Distributed Computing, pages 239-251, June 2014.
LCPC 2014    
LightPlay: Efficient Replay with GPUs
M. Feng, F. Khorasani, R. Gupta, and L.N. Bhuyan.
The 27th International Workshop on Languages and Compilers for Parallel Computing, September 2014.