Module-per-Object: a Human-Driven Methodology for C++-based High-Level\n Synthesis Design
Bibliographic record
Abstract
High-Level Synthesis (HLS) brings FPGAs to audiences previously unfamiliar to\nhardware design. However, achieving the highest Quality-of-Results (QoR) with\nHLS is still unattainable for most programmers. This requires detailed\nknowledge of FPGA architecture and hardware design in order to produce\nFPGA-friendly codes. Moreover, these codes are normally in conflict with best\ncoding practices, which favor code reuse, modularity, and conciseness.\n To overcome these limitations, we propose Module-per-Object (MpO), a\nhuman-driven HLS design methodology intended for both hardware designers and\nsoftware developers with limited FPGA expertise. MpO exploits modern C++ to\nraise the abstraction level while improving QoR, code readability and\nmodularity. To guide HLS designers, we present the five characteristics of MpO\nclasses. Each characteristic exploits the power of HLS-supported modern C++\nfeatures to build C++-based hardware modules. These characteristics lead to\nhigh-quality software descriptions and efficient hardware generation. We also\npresent a use case of MpO, where we use C++ as the intermediate language for\nFPGA-targeted code generation from P4, a packet processing domain specific\nlanguage. The MpO methodology is evaluated using three design experiments: a\npacket parser, a flow-based traffic manager, and a digital up-converter. Based\non experiments, we show that MpO can be comparable to hand-written VHDL code\nwhile keeping a high abstraction level, human-readable coding style and\nmodularity. Compared to traditional C-based HLS design, MpO leads to more\nefficient circuit generation, both in terms of performance and resource\nutilization. Also, the MpO approach notably improves software quality,\naugmenting parametrization while eliminating the incidence of code duplication.\n
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.002 | 0.000 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.005 | 0.002 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
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 teacher head, 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".