MétaCan
Menu
Back to cohort
Record W4399282665 · doi:10.1109/access.2024.3409057

DNNSplit: Latency and Cost-Efficient Split Point Identification for Multi-Tier DNN Partitioning

2024· article· en· W4399282665 on OpenAlexaff
Paridhika Kayal, Alberto Leon‐Garcia

Bibliographic record

VenueIEEE Access · 2024
Typearticle
Languageen
FieldComputer Science
TopicAdvanced Neural Network Applications
Canadian institutionsUniversity of Toronto
Fundersnot available
KeywordsComputer scienceLatency (audio)ScalabilityInferenceComputational complexity theoryDeep neural networksArtificial neural networkParallel computingDistributed computingTheoretical computer scienceArtificial intelligenceAlgorithm

Abstract

fetched live from OpenAlex

Due to the high computational demands inherent in Deep Neural Network (DNN) executions, multi-tier environments have emerged as preferred platforms for DNN inference tasks. Previous research on partitioning strategies for DNN models typically involved leveraging all layers of the DNN to identify optimal splits aimed at reducing latency or cost. However, due to their computational complexity, these approaches face scalability issues, particularly with models containing hundreds of layers. The novelty of ourwork lies in uniquely identifying specific split points within variousDNNmodels that consistently lead to efficient latency or cost partitioning. Under the assumption that per unit computing cost decreases in higher tiers and that bandwidth is not free, we show that only these specific split points need to be considered to optimize latency or cost. Importantly, these split points are independent of different infrastructure configurations and bandwidth variations. The key contribution of our work is the significant reduction in the computational complexity of DNN partitioning, making our strategy applicable to models with a large number of layers. Introducing <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">DNNSplit</i> , an adaptive strategy, enables dynamic split decisions in varying conditions with the least complexity. Evaluated across nine DNN models varying in size and architecture, <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">DNNSplit</i> exhibits exceptional effectiveness in optimizing latency and cost. Even for a more substantial model containing 517 layers, it identifies only 5 points as potential split points, thereby reducing the partitioning complexity by more than 100x. This makes DNNSplit especially advantageous for managing larger models. <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">DNNSplit</i> also demonstrates significant improvements for multi-tier deployments compared to single-tier execution, including up to 15x latency speedup, 20x cost reduction, and 5x throughput enhancement.

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)0.000
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: none
GenreCandidate signal: Empirical · Consensus signal: none
Teacher disagreement score0.938
Threshold uncertainty score0.695

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 communication0.0010.001
Open science0.0010.000
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 head0.087
GPT teacher head0.380
Teacher spread0.293 · 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.

The models applied no category: nothing in the taxonomy fit this work.
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

Citations4
Published2024
Admission routes1
Has abstractyes

Explore more

Same venueIEEE AccessSame topicAdvanced Neural Network ApplicationsFrench-language works237,207