Publications & Talks
Publications
Souradip Ghosh, Yufei Shi, Brandon Lucia, Nathan Beckmann. “Ripple: Asynchronous Programming for Spatial Dataflow Architectures.” 46th ACM SIGPLAN Conference on Programming Language Design and Implementation. (PLDI ‘25). Paper.
Souradip Ghosh, Graham Gobieski, Tom Jackson, Keyi Zhang, Brandon Lucia, Nathan Beckmann, Tony Nowatzki. “NUPEA: Optimizing Critical Loads on Spatial Dataflow Architectures via Non-Uniform Processing-Element Access.” 52nd ACM/IEEE International Symposium on Computer Architecture. (ISCA ‘25). Paper.
Nikhil Agarwal, Mitchell Fream, Souradip Ghosh, Brian C. Schwedock, Nathan Beckmann. “The TYR Dataflow Architecture: Improving Locality by Taming Parallelism.” 57th ACM/IEEE International Symposium on Microarchitecture. (MICRO ‘24). Paper.
Nikhil Agarwal, Mitchell Fream, Souradip Ghosh, Brian C. Schwedock, Nathan Beckmann. “UDIR: Towards a Unified Compiler Framework for Reconfigurable Dataflow Architectures.” IEEE Computer Architecture Letters. (CAL ‘24). Paper.
Nikhil Agarwal, Mitchell Fream, Souradip Ghosh, Brian C. Schwedock, Nathan Beckmann. “UDIR: Towards a Unified Compiler Framework for Reconfigurable Dataflow Architectures.” 2nd Workshop on Democratizing Domain-Specific Accelerators. (WDDSA ‘23). Paper.
Nathan Serafin, Souradip Ghosh, Harsh Desai, Nathan Beckmann, Brandon Lucia. “Pipestitch: An Energy-Minimal Dataflow Architecture With Lightweight Threads.” 56th ACM/IEEE International Symposium on Microarchitecture. (MICRO ‘23). Paper.
Graham Gobieski, Souradip Ghosh, Marijn Heule, Todd C. Mowry, Tony Nowatzki, Nathan Beckmann, Brandon Lucia. “RipTide: A Programmable, Energy-Minimal Dataflow Compiler and Architecture.” 55th ACM/IEEE International Symposium on Microarchitecture. (MICRO ‘22). Paper.
Peter Dinda, Nick Wanninger, Jiacheng Ma, Alex Bernat, Charles Bernat, Souradip Ghosh, Christopher Kraemer, Yehya Elmasry. “FPVM: Towards a Floating Point Virtual Machine.” 31st International ACM Symposium on High-Performance Parallel and Distributed Computing. (HPDC ‘22). Paper.
Vito Kortbeek, Souradip Ghosh, Josiah Hester, Simone Campanoni, Przemysław Pawełczak. “WARio: Efficient Code Generation for Intermittent Computing.” 43rd ACM SIGPLAN Conference on Programming Language Design and Implementation. (PLDI ‘22). Paper.
Brian Suchy, Souradip Ghosh, Drew Kersnar, Siyuan Chai, Zhen Huang, Aaron Nelson, Michael Cuevas, Gaurav Chaudhary, Alex Bernat, Nikos Hardavellas, Simone Campanoni, Peter Dinda. “CARAT CAKE: Replacing Paging via Compiler/Kernel Cooperation.” 27th International Conference on Architectural Support for Programming Languages and Operating Systems. (ASPLOS ‘22). Paper.
Angelo Matni, Enrico Armenio Deiana, Yian Su, Lukas Gross, Souradip Ghosh, Sotiris Apostolakis, Ziyang Xu, Zujun Tan, Ishita Chaturvedi, Brian Homerding, Tommy McMichen, David I. August, Simone Campanoni. “NOELLE Offers Empowering LLVM Extensions.” 20th International Conference on Code Generation and Optimization. (CGO ‘22). Paper.
Souradip Ghosh, Michael Cuevas, Simone Campanoni, Peter Dinda. “Compiler-Based Timing For Extremely Fine-Grain Preemptive Parallelism.” Proceedings of the ACM/IEEE International Conference on High Performance Computing, Networking, Storage and Analysis (Supercomputing). (SC ‘20). Paper.
Talks and Presentations
“NUPEA: Optimizing Critical Loads on Spatial Dataflow Architectures via Non-Uniform Processing-Element Access.” ISCA, June ‘25. Tokyo, Japan. Slides.
“Ripple: Asynchronous Programming for Spatial Dataflow Architectures.” PLDI, June ‘25. Seoul, South Korea. Slides.
“Ripple: Asynchronous Programming for Spatial Dataflow Architectures.” DOE CSGF Program Review, July ‘24. Washington, D.C.
“Ripple: Asynchronous Programming for Energy-Minimal Edge Devices.” DOE CSGF Program Review, July ‘23. Washington, D.C.
“RipTide: A Programmable, Energy-Minimal Dataflow Compiler and Architecture.” SRC Artificial Intelligence/Hardware (AIHW) Annual Review, August ‘22. San Diego, CA. Poster. Slides. Recording.
“RipTide: A Programmable, Energy-Minimal Dataflow Compiler and Architecture.” DOE CSGF Program Review, July ‘22. Arlington, VA. Poster.
“Compiler-Based Timing For Extremely Fine-Grain Preemptive Parallelism” SC, November ‘20. Virtual. Slides. Video.