Mitigation of Single Event Effects (SEEs) Through TMR Implementation in Multi-Core Processors with LLM-Assisted Assembly Code Generation
Bibliographic record
Abstract
Radiation can disrupt semiconductor devices, creating significant challenges for safety-critical computing. This work investigates multi-threaded Triple Modular Redundancy (TMR) as a mitigation strategy for radiation-induced soft errors in multi-core processors. The research has two primary objectives: (1) Develop and integrate a multi-threaded TMR approach tailored for a multicore processor, OpenPiton, leveraging its architectural features to enhance error detection and correction capabilities. (2) Leverage Large Language Models (LLMs) to automatically generate application-specific SPARCV9 assembly programs, for applications including Fibonacci Series (FS), Matrix Multiplication (MxM), 2D Image Convolution, and sequences with read-after-write (RAW) hazards. For evaluation, faults are injected systematically in the general-purpose register and the Error Correction Code (ECC) of a general-purpose register in one core, two cores, and three random cores and processor behavior with TMR protection is evaluated against the processor behavior without TMR protection. The proposed methodology demonstrates significant improvements of 13.5 % for the Fibonacci Series (FS), 20.4 % for Matrix Multiplication (MxM),$\text{1 3. 4 1 \%}$for RAW Hazards Sequence, and 9.35% for 2D Convolution of Images benchmarks, respectively. This is achieved with minimal time overhead, ranging from 5 % to 11 %, with no additional area overhead.
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 | 0.000 | 0.001 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.001 | 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".