MétaCan
Menu
Back to cohort
Record W3163263218 · doi:10.1109/icfpt51103.2020.00036

StateReveal: Enabling Checkpointing of FPGA Designs with Buried State

2020· article· en· W3163263218 on OpenAlex

Why this work is in the frame

A frame that forgets how it found something cannot be audited. These are the routes that admitted this work.

affAt least one author lists a Canadian institution in the pinned OpenAlex snapshot.
fundA Canadian funder is recorded on the work.

Bibliographic record

Venuenot available
Typearticle
Languageen
FieldEngineering
TopicRadiation Effects in Electronics
Canadian institutionsUniversity of Toronto
FundersNatural Sciences and Engineering Research Council of Canada
KeywordsComputer scienceField-programmable gate arrayDebuggingBlock (permutation group theory)Overhead (engineering)Embedded systemState (computer science)ObservabilityLogic blockFinite-state machineControllabilityComputer hardwarePlace and routeDigital signal processingParallel computingOperating systemAlgorithm

Abstract

fetched live from OpenAlex

The ability to save and restore the entire state of an FPGA design is essential for hardware checkpointing, which enables live migration, fault recovery, and novel debugging flows. However, hard blocks such as block RAMs and DSP blocks have state elements that cannot be saved or restored using conventional checkpointing techniques such as readback. This results in an incomplete checkpoint, thereby preventing checkpointing of most FPGA designs. In this paper, we propose general techniques that allow a complete checkpoint to be captured and loaded even when a design contains inaccessible state elements. The proposed techniques include using multi-cycle capture and inserting capture registers that add observability and controllability of this buried state. Moreover, we present StateReveal, a tool that detects the presence of inaccessible state elements in a design and automatically inserts the required capture registers. This enables checkpointing of designs that contain fully registered block RAMs and pipelined DSP blocks, which was not previously feasible. We verify the ability to capture and load a complete checkpoint on several designs using an enhanced checkpointing framework that supports multi-cycle capture. StateReveal currently supports Xilinx FPGAs, and the added circuitry has a low timing overhead of 5% and an acceptable area overhead that averages 19 LUTs and 35 registers per hard block.

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.

Full frame distilled prediction

Teacher imitation

Not 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.

metaresearch head score (Codex)0.000
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesnone
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: Simulation or modeling
GenreCandidate signal: Empirical · Consensus signal: Empirical
Teacher disagreement score0.385
Threshold uncertainty score0.407

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0000.000
Meta-epidemiology (narrow)0.0000.000
Meta-epidemiology (broad)0.0000.000
Bibliometrics0.0000.000
Science and technology studies0.0000.000
Scholarly communication0.0000.000
Open science0.0000.000
Research integrity0.0000.000
Insufficient payload (model declined to judge)0.0000.000

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.

Opus teacher head0.015
GPT teacher head0.203
Teacher spread0.188 · how far apart the two teachers sit on this one work
Validation statusscore_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from it

Quick stats

Citations10
Published2020
Admission routes2
Has abstractyes

Explore more

Same topicRadiation Effects in ElectronicsFrench-language works237,207