Revisiting Automatic Pipelining: Gate-level Forwarding and Speculation
Shuyao Cheng, Chongxiao Li, Zidong Du, Rui Zhang, Xing Hu, Xiaqing Li, Guanglin Xu, Yuanbo Wen, Qi Guo
2024Year
3Citations
Abstract
Pipelining is a widely applied micro-architectural performance optimization and requires non-trivial designs for better execution throughput. The key to pipeline throughput optimization is to resolve data hazards caused by read-after-write (RAW) dependencies, which are traditionally tackled by forwarding and speculation to avoid pipeline stalls. However, existing approaches are conducted based on high-level dataflow analysis, with potential loss of optimization opportunities for lack of analysis of the netlist structures.
Ask about this paper
Ask your agent about it.
Lune has read the top-tier papers around this one, so every answer names the papers it rests on.
Related papers
- Modular Hardware Design of Pipelined Circuits with HazardsMinseong Jang, Jungin Rhee, Woojin Lee, Shuangshuang Zhao et al.PLDI 2024 · 4 citations
- Sigma: Compiling Einstein Summations to Locality-Aware DataflowTian Zhao, Alexander Rucker, Kunle OlukotunASPLOS 2023 · 3 citations
- Avoiding Read Stalls on Flash StorageMijin An, In-Yeong Song, Yong Ho Song, Sang-Won LeeSIGMOD 2022 · 10 citations
- Pasta: A Cost-Based Optimizer for Generating Pipelining Schedules for Dataflow DAGsXiaozhen Liu, Yicong Huang, Xinyuan Lin, Avinash Kumar et al.SIGMOD 2025 · 1 citation
- Empower Programmable Pipeline for Advanced Stateful Packet ProcessingYong Feng, Zhikang Chen, Haoyu Song, Yinchao Zhang et al.NSDI 2024 · 8 citations
