Enabling Portable and High-Performance SmartNIC Programs with Alkali
Jiaxin Lin, Zhiyuan Guo, Mihir Shah, Tao Ji, Yiying Zhang, Daehyeok Kim, Aditya Akella
Abstract
Trends indicate that emerging SmartNICs, either from different vendors or generations from the same vendor, exhibit substantial differences in hardware parallelism and memory interconnects. These variations make porting programs across NICs highly complex and time-consuming, requiring programmers to significantly refactor code for performance based on each target NIC's hardware characteristics.
We argue that an ideal SmartNIC compilation framework should allow developers to write target-independent programs, with the compiler automatically managing cross-NIC porting and performance optimization. We present such a framework, Alkali, that achieves this by (1) proposing a new intermediate representation for building flexible compiler infrastructure for multiple NIC targets and (2) developing a new iterative parallelism optimization algorithm that automatically ports and parallelizes the input programs based on the target NIC's hardware characteristics.
Experiments across a wide range of NIC applications demonstrate that Alkali enables developers to easily write portable, high-performance NIC programs. Our compiler optimization passes can automatically port these programs and make them run efficiently across all targets, achieving performance within 9.8% of hand-tuned expert implementations.
Ask about this paper
Your agent reads all of it.
Lune indexed this paper to the last equation, along with the top-tier papers that cite it. Ask a question and the answer quotes them.
Your agent calls
Luneget_paper_fulltext
Free to start. No credit card required.
Terminal
Install the CLIlune papers fulltext d833a2a2-060a-4803-93ad-af15b1531db2Cited by top-tier papers4
- NutCracker: A Compilation Framework for Hybrid DPU ArchitecturesYihan Yang, Haifeng Sun, Antoine Kaufmann, Jialin LiEuroSys 2026 · 2 citations
- Disdp: Disaggregating Compute, Network, and Storage for Model-Sharded Data-Parallel TrainingMo Sun, Zihan Yang, Changyue Liao, Yingtao Li et al.ISCA 2026 · 1 citation
- Efficient and Flexible Datapaths for Fine-Grained Rack-Scale Interconnects with Elastic QPChenxingyu Zhao, Yibo Wu, Hongtao Zhang, Jaehong Min et al.SIGCOMM 2026 · 1 citation
- VeriLucid: A Verification-aware Data-plane Programming LanguageJohn Sonchack, Pamela Zave, Jennifer RexfordSIGCOMM 2026
Builds on20
- SRNIC: A Scalable Architecture for RDMA NICsZilong Wang, Layong Luo, Qingsong Ning, Chaoliang Zeng et al.NSDI 2023 · 154 citations
- Sailfish: accelerating cloud-scale multi-tenant multi-service gateways with programmable switchesTian Pan, Nianbing Yu, Chenhao Jia, Jianwen Pi et al.SIGCOMM 2021 · 111 citations
- PANIC: A High-Performance Programmable NIC for Multi-tenant NetworksJiaxin Lin, Kiran Patel, Brent E. Stephens, Anirudh Sivaraman et al.OSDI 2020 · 104 citations
- Enabling Programmable Transport Protocols in High-Speed NICsMina Tahmasbi Arashloo, Alexey Lavrov, Manya Ghobadi, Jennifer Rexford et al.NSDI 2020 · 96 citations
- LineFS: Efficient SmartNIC Offload of a Distributed File System with Pipeline ParallelismJongyul Kim, Insu Jang, Waleed Reda, Jaeseong Im et al.SOSP 2021 · 83 citations
Related papers
- Unleashing SmartNIC Packet Processing Performance in P4Jiarong Xing, Yiming Qiu, Kuo-Feng Hsu, Songyuan Sui et al.SIGCOMM 2023 · 29 citations
- RpcNIC: Enabling Efficient Datacenter RPC Offloading on PCIe-attached SmartNICsJie Zhang, Hongjing Huang, Xuzheng Chen, Xiang Li et al.HPCA 2025 · 6 citations
- LogNIC: A High-Level Performance Model for SmartNICsZerui Guo, Jiaxin Lin, Yuebin Bai, Daehyeok Kim et al.MICRO 2023 · 17 citations
- Automated SmartNIC Offloading Insights for Network FunctionsYiming Qiu, Jiarong Xing, Kuo-Feng Hsu, Qiao Kang et al.SOSP 2021 · 37 citations
- STYX: Exploiting SmartNIC Capability to Reduce Datacenter Memory TaxHouxiang Ji, Mark Mansi, Yan Sun, Yifan Yuan et al.USENIX ATC 2023 · 22 citations
