Publications

(2025). ARIES: An Agile MLIR-Based Compilation Flow for Reconfigurable Devices with AI Engines(FPGA 2025 Best Paper Candidate). Proceedings of the 2025 ACM/SIGDA International Symposium on Field Programmable Gate Arrays, FPGA 2025, Feb. 28 - March 3, Monterey, CA, US. Full Paper Accepted! https://dl.acm.org/doi/10.1145/3706628.3708870.

Cite PDF Code

(2024). Amortizing Embodied Carbon Across Generations (Best Viewpoint Paper in IGSC 2024). Proceedings of the IEEE 15th International Green and Sustainable Computing Conference, IGSC 2024.

Cite Slides IEEE

(2024). EQ-ViT: Algorithm-Hardware Co-Design for End-to-End Acceleration of Real-Time Vision Transformer Inference on Versal ACAP Architecture. International Conference on Hardware/Software Codesign and System Synthesis (CODES+ISSS) in conjunction with (ESWEEK), RALEIGH, NC, USA, Sept. 29-Oct. 4, 2024. Also appears as part of the ESWEEK-TCAD Special Issue, IEEE Transactions on Computer-Aided Design of Integrated Circuits and Systems (IEEE TCAD).

Slides

(2024). CHARM 2.0: Composing Heterogeneous Accelerators for Deep Learning on Versal ACAP Architecture. ACM Transactions on Reconfigurable Technology and Systems.

Cite PDF

(2024). SSR: Spatial Sequential Hybrid Architecture for Latency Throughput Tradeoff in Transformer Acceleration. Proceedings of the 2024 ACM/SIGDA International Symposium on Field Programmable Gate Arrays, FPGA 2024, March 3 - March 5, Monterey, CA, US. Full Paper Accepted! https://doi.org/10.1145/3626202.3637569.

Cite PDF Code

(2024). Challenges and Opportunities to Enable Large-Scale Computing via Heterogeneous Chiplets. Proceedings of the 28th Asia and South Pacific Design Automation Conference, ASPDAC 2024, Incheon Songdo Convensia, South Korea! https://doi.org/10.1109/ASP-DAC58780.2024.10473961.

Cite IEEE arXiv

(2023). High Performance, Low Power Matrix Multiply Design on ACAP: from Architecture, Design Challenges and DSE Perspectives. Proceedings of the 60th ACM/IEEE Design Automation Conference, San Francisco, California, USA, (DAC ’23), July 9–13, 2023, San Francisco, CA, USA..

PDF Cite Code

(2023). AIM: Accelerating Arbitrary-precision Integer Multiplication on Heterogeneous Reconfigurable Computing Platform Versal ACAP. Proceedings of the 42nd IEEE/ACM International Conference on Computer-Aided Design, ICCAD 2023, October 29, 2023 - November 2, 2022, San Francisco, CA, USA..

Cite Code

(2022). CHARM: Composing Heterogeneous AcceleRators for Matrix Multiply on Versal ACAP Architecture. Proceedings of the 2023 ACM/SIGDA International Symposium on Field Programmable Gate Arrays (FPGA ’23), February 12–14, 2023, Monterey, CA, USA. ACM, New York, NY, USA, 12 pages..

PDF Cite Code