MétaCan
Menu
Back to cohort
Record W7133007753

Tackling Resource Utilization In Deep Neural Network Accelerators

2022· dissertation· W7133007753 on OpenAlexafffund
Iris Doriane Uwizeyimana

Bibliographic record

VenueTSpace · 2022
Typedissertation
Language
FieldComputer Science
TopicAdvanced Neural Network Applications
Canadian institutionsUniversity of Toronto
FundersUniversity of Toronto
KeywordsResource (disambiguation)Artificial neural networkGreedy algorithmBayesian probabilityBayesian networkResource allocationScheduling (production processes)
DOInot available

Abstract

fetched live from OpenAlex

Good resource utilization plays an important role in maximizing the performance of DNN accelerators. One method to maximize resource utilization is to divide accelerator resources into multiple sub-accelerators. However, there are a couple of design considerations that are essential to the production of efficient multi-accelerator systems. The number of sub-accelerators to use and the distribution of resources are among a few considerations that are important to the design of highly efficient multi- accelerator systems. We present DataflowBay, a framework that helps guide the design of multi-accelerator systems. DataflowBay implements a scheduler that extends the state-of-the-art to map DNN layers on multi-accelerators systems with an average energy-delay product improvement of ∼11.6%. DataflowBay also implements a Bayesian optimization module to automate the fine-grained mapping of DNN layers onto the sub-accelerators and a stochastic greedy search algorithm to decide what hardware resource distribution will lead to the best performance for each sub-accelerator.

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 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)0.001
metaresearch head score (Gemma)0.000
Version: codex-gemma-dda1882f352aValidation status: machine_predicted_unvalidated
Candidate categoriesMeta-epidemiology (narrow), Science and technology studies
Consensus categoriesnone
DomainCandidate signal: none · Consensus signal: none
Study designCandidate signal: Simulation or modeling · Consensus signal: Simulation or modeling
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.543
Threshold uncertainty score1.000

Codex and Gemma teacher scores by category

CategoryCodexGemma
Metaresearch0.0010.000
Meta-epidemiology (narrow)0.0010.001
Meta-epidemiology (broad)0.0010.000
Bibliometrics0.0000.006
Science and technology studies0.0010.000
Scholarly communication0.0000.001
Open science0.0030.001
Research integrity0.0000.002
Insufficient payload (model declined to judge)0.0010.000

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 head0.042
GPT teacher head0.354
Teacher spread0.312 · 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

Classification

machine, unvalidated

Machine predicted; a candidate call from one teacher head, not a consensus.

Study designSimulation or modeling
Domainnot available
GenreEmpirical

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".

Quick stats

Citations0
Published2022
Admission routes2
Has abstractyes

Explore more

Same venueTSpaceSame topicAdvanced Neural Network ApplicationsFrench-language works237,207