P4THLS: A Templated HLS Framework to Automate Efficient Mapping of P4 Data-Plane Applications to FPGAs
Bibliographic record
Abstract
The rising demand for high-bandwidth, low-latency network processing has led to a significant shift towards programmable data planes. The P4 language enables network operators to define packet processing pipelines flexibly. However, efficiently deploying P4-defined applications onto Field-Programmable Gate Arrays (FPGAs) remains a complex task due to the low-level hardware design requirements. This paper introduces P4THLS, a templated high-level synthesis framework that converts P4 data-plane applications into synthesizable C++ code for FPGA deployment. Key contributions include an automatic design process, a templated data structure and bus width, and unified memory management techniques. The proposed P4THLS architecture is evaluated through experiments, showing significant improvements in throughput, latency, and resource utilization over existing FPGA-based packet processing methods. The experiments demonstrate that P4THLS achieves up to 143.3 Gbps throughput with a 512-bit bus and 76.5 Gbps with a 256-bit bus, supports match-action tables with up to 64K entries, and sustains sub-50-cycle processing latency at 250 MHz, with end-to-end latencies of around 8 μs.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.001 |
| Bibliometrics | 0.001 | 0.000 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.000 | 0.001 |
| Insufficient payload (model declined to judge) | 0.006 | 0.002 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".