An Adaptive Markov Model for the Timing Analysis of Probabilistic Caches
Bibliographic record
Abstract
Accurate timing prediction for real-time embedded software execution is becoming a problem due to the increasing complexity of computer architecture, and the presence of mixed-criticality workloads. Probabilistic caches were proposed to set bounds to Worst Case Execution Time (WCET) estimates and help designers improve real-time embedded system resource use. Static Probabilistic Timing Analysis (SPTA) for probabilistic caches is nevertheless difficult to perform, because cache accesses depend on execution history, and the computational complexity of SPTA makes it intractable for calculation as the number of accesses increases. In this paper, we explore and improve SPTA for caches with evict-on-miss random replacement policy using a state space modeling technique. A nonhomogeneous Markov model is employed for single-path programs in discrete-time finite state space representation. To make this Markov model tractable, we limit the number of states and use an adaptive method for state modification. Experiments show that compared to the state-of-the-art methodology, the proposed adaptive Markov chain approach provides better results at the occurrence probability of 10 −15 : in terms of accuracy, the state-of-the-art SPTA results are more conservative, by 11% more on average. In terms of computation time, our approach is not significantly different from the state-of-the-art SPTA.
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 | 0.004 |
| 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 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.003 | 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".