Automated Bitstream-Level Cost-Reliability Design-Space Exploration for SRAM-Based FPGAs
Bibliographic record
Abstract
Triple Modular Redundancy (TMR) is a common approach to mitigate the effects of Single-Event Upsets (SEUs) in SRAM-based Field-Programmable Gate Arrays (FPGAs), where these faults may cause changes in the configuration of logic or interconnect resources. Partial TMR aims at balancing SEU mitigation with redundancy costs. This work introduces a Design-Space Exploration (DSE) approach that automatically generates and evaluates cost-reliability-optimized, Pareto-optimal partial TMR configurations of modules in a hierarchical design. The approach is evaluated using a proof-of-concept implementation for AMD’s 7 Series FPGAs and five case-study designs, including the NEORV32 RISC-V CPU. Multiple fitness assignment variants – based on static bitstream analysis, (statistical) fault injection results, and a combined approach –-are compared regarding effectiveness and runtime. Comparing the hypervolumes of the generated Pareto fronts of the final generation and a randomly generated starting generation, the approach improves cost-effectiveness of the generated TMR solutions by 17%–52%, delivering an attractive benefit-cost-ratio. The presented approach effectively generates a diverse set of TMR solutions across a wide cost-reliability range, allowing the designer to choose a variant that best fulfills the application’s, mission’s, or mission phase’s cost-reliability requirements.
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 | 0.002 |
| 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 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.002 | 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 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".