Congratulations to group member Adel Ejjeh (lead author) and our co-authors Leon Medvinsky, Aaron Councilman, Hemang Nehra, Suraj Sharma, and Vikram Adve (University of Illinois at Urbana-Champaign), Luigi Nardi (Lund University and Stanford), and Eriko Nurvitadhi (Intel), for being shortlisted for Best Paper at the 33rd IEEE International Conference on Application-Specific Systems, Architectures and Processors (ASAP2022).
The paper, “HPVM2FPGA: Enabling True Hardware-Agnostic FPGA Programming”, presents a novel end-to-end compiler and auto-tuning system that can automatically tune hardware-agnostic programs for FPGAs. The paper shows that HPVM2FPGA can achieve up to 33×speedup compared to unoptimized baselines and can match the performance of HLS code for several key benchmarks.
The paper was also featured in the November 2022 issue of the IEEE VLSI Circuits & Systems Letter (from the IEEE Technical Committee on VLSI, TCVLSI), and can be found here.