Tackling Resource Utilization In Deep Neural Network Accelerators
Bibliographic record
Abstract
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 imitationNot 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.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.000 |
| Bibliometrics | 0.000 | 0.006 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.003 | 0.001 |
| Research integrity | 0.000 | 0.002 |
| 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 teacher head, 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".