TY - GEN
T1 - CYNQ
T2 - 31st IEEE International Conference on Electronics, Circuits and Systems, ICECS 2024
AU - Leon-Vega, Luis G.
AU - Avila-Torres, Diego
AU - Leon-Vega, Indra
AU - Castro-Godinez, Jorge
N1 - Publisher Copyright:
© 2024 IEEE.
PY - 2024
Y1 - 2024
N2 - FPGAs for hardware acceleration face several issues in their adoption by the emerging AI embedded software commu-nity, mainly due to the difficulty of getting started in the field. To address these issues, FPGA vendors have tried to simplify and combine workflows to make them user-friendly. This has also impacted the runtime libraries used on Linux to allow user space applications to interact with FPGA programmable logic. However, this approach can result in suboptimal results, given the added overhead in single-purpose applications in an attempt to generalise the runtime libraries. This work presents CYNQ Runtime Library, a simplistic and API-agnostic C/C++ runtime library with the ease of PYNQ and the efficiency of C++ and XRT. In comparison to most popular runtime libraries for AMD FPGAs, our work outperforms PYNQ and XRT with more than 5.34 × speedup in execution latency and more than 1.20 × in large workloads than XRT, which poses a better scenario for high-performance single-purpose applications.
AB - FPGAs for hardware acceleration face several issues in their adoption by the emerging AI embedded software commu-nity, mainly due to the difficulty of getting started in the field. To address these issues, FPGA vendors have tried to simplify and combine workflows to make them user-friendly. This has also impacted the runtime libraries used on Linux to allow user space applications to interact with FPGA programmable logic. However, this approach can result in suboptimal results, given the added overhead in single-purpose applications in an attempt to generalise the runtime libraries. This work presents CYNQ Runtime Library, a simplistic and API-agnostic C/C++ runtime library with the ease of PYNQ and the efficiency of C++ and XRT. In comparison to most popular runtime libraries for AMD FPGAs, our work outperforms PYNQ and XRT with more than 5.34 × speedup in execution latency and more than 1.20 × in large workloads than XRT, which poses a better scenario for high-performance single-purpose applications.
KW - Cloud Computing
KW - Edge Computing
KW - Field Programmable Gate Arrays
KW - Hardware Acceleration
KW - High Performance Computing
UR - https://www.scopus.com/pages/publications/85217615925
U2 - 10.1109/ICECS61496.2024.10848808
DO - 10.1109/ICECS61496.2024.10848808
M3 - Contribución a la conferencia
AN - SCOPUS:85217615925
T3 - Proceedings of the IEEE International Conference on Electronics, Circuits, and Systems
BT - 2024 31st IEEE International Conference on Electronics, Circuits and Systems, ICECS 2024
PB - Institute of Electrical and Electronics Engineers Inc.
Y2 - 18 November 2024 through 20 November 2024
ER -