Design of Pre-reading Asynchronous FIFO Based on Verilog
Main Article Content
Keywords
asynchronous FIFO, first-word fall-through, FIFO design
Abstract
With the rapid advancement of modern Very Large Scale Integration (VLSI), the increasing complexity of System-on-Chip (SoC) designs has made traditional single-clock domain synchronous architectures insufficient for meeting the escalating demands of high-performance computing and high-bandwidth communication. As a result, asynchronous FIFO has become increasingly prevalent for facilitating Clock Domain Crossing (CDC) data transfer, ensuring reliable communication between asynchronous interfaces. However, conventional asynchronous FIFOs suffer from inherent latency during the data transmission process, leading to a significant lag in data read-out, which ultimately compromises overall system efficiency. Based on Verilog HDL, this paper explores the optimization of standard asynchronous FIFO architectures. By reconfiguring the internal control logic, the design successfully incorporates First-Word Fall-Through (FWFT) functionality, effectively eliminating traditional read-to-output latency and minimizing data retrieval delays, thereby significantly enhancing transmission efficiency and throughput.
References
- [1] Chen, Z., et al. (2023). AI SoC design challenges in the foundation model era. In 2023 IEEE Custom Integrated Circuits Conference (CICC) (pp. 1–8). IEEE. https://doi.org/10.1109/CICC57935.2023.10121242
- [2] Verbitsky, D., Dobkin, R. R., Ginosar, R., et al. (2014). StarSync: An extendable standard-cell mesochronous synchronizer. Integration, the VLSI Journal, 47(2), 250–260. https://doi.org/10.1016/j.vlsi.2013.09.003
- [3] Furber, S. B., Galluppi, F., Temple, S., & Plana, L. A. (2014). The SpiNNaker project. Proceedings of the IEEE, 102(5), 652–665. https://doi.org/10.1109/JPROC.2014.2304638
- [4] Wang, Z. (2024). Research progress of asynchronous FIFO design. Science and Technology of Engineering, Chemistry and Environmental Protection, 1(6). https://doi.org/10.61173/kjgkj796
- [5] Talpes, E., et al. (2023). The microarchitecture of DOJO, Tesla’s exa-scale computer. IEEE Micro, 43(3), 31–39. https://doi.org/10.1109/MM.2023.3258906
- [6] Davies, M., et al. (2018). Loihi: A neuromorphic manycore processor with on-chip learning. IEEE Micro, 38(1), 82–99. https://doi.org/10.1109/MM.2018.112130359
- [7] Singh, T., et al. (2020). 2.1 Zen 2: The AMD 7nm energy-efficient high-performance x86 -64 microprocessor core. In 2020 IEEE International Solid-State Circuits Conference - (ISSCC) (pp. 42–44). IEEE. https://doi.org/10.1109/ISSCC19947.2020.9063113
- [8] Tammisetti, D., Jyothika, K., Rajesh, P. N. V., Devi, M. N., Reddy, K. M., & Raju, P. P. (2025). Design and verification of a parameterized asynchronous FIFO using Gray code synchronization. IJIRT, 12(9), 2926–2935.
- [9] Zhang, X. (2024). Optimizing data transfer across asynchronous clock domains: A comprehensive approach to asynchronous FIFO circuit design. Highlights in Science, Engineering and Technology, 87, 31–36. https://doi.org/10.54097/ab66rm52
- [10] Konstantinou, D., Psarras, A., Nicopoulos, C., & Dimitrakopoulos, G. (2020). The mesochronous dual- clock FIFO buffer. IEEE Transactions on Very Large Scale Integration (VLSI) Systems, 28(1), 302–306. https://doi.org/10.1109/TVLSI.2019.2946348
Article Sidebar
This work is licensed under a Creative Commons Attribution 4.0 International License.