paper-with-me

Papers

ED-Batch: Efficient Automatic Batching of Dynamic Neural Networks via Learned Finite State Machines

2023-02-08 · Siyuan Chen, Pratik Fegade, Tianqi Chen, Phillip B. Gibbons, Todd C. Mowry

Batching has a fundamental influence on the efficiency of deep neural network (DNN) execution. However, for dynamic DNNs, efficient batching is particularly challenging as the dataflow graph varies per input instance. As a result, state-of-the-art frameworks use heuristics that result in suboptimal batching decisions. Further, batching puts strict restrictions on memory adjacency and can lead to high data movement costs. In this paper, we provide an approach for batching dynamic DNNs based on finite state machines, which enables the automatic discovery of batching policies specialized for each DNN via reinforcement learning. Moreover, we find that memory planning that is aware of the batching policy can save significant data movement overheads, which is automated by a PQ tree-based algorithm we introduce. Experimental results show that our framework speeds up state-of-the-art frameworks by on average 1.15x, 1.39x, and 2.45x for chain-based, tree-based, and lattice-based DNNs across CPU and GPU.

📄 PDF Abstract BibTeX arXiv:2302.03851

Code (0)

등록된 구현이 없습니다.

Tasks

CPUDynamic neural networksGPU

Methods 이 논문이 사용한 방법론

AWARE We propose to theoretically and empirically examine the effect of incorporating weighting schemes into walk-aggregating GNNs. To this end, we propose a simple, interpretable, and…

Similar Papers 제목 키워드 기반

ACRoBat: Optimizing Auto-batching of Dynamic Deep Learning at Compile Time

2023-05-17 · Pratik Fegade, Tianqi Chen, Phillip B. Gibbons, Todd C. Mowry

Dynamic control flow is an important technique often used to design expressive and efficient deep learning computations for applications such as text parsing, machine translation, exiting early out of deep models and so …

Code GenerationDeep LearningGPUMachine Translation+1

An Automatic Operation Batching Strategy for the Backward Propagation of Neural Networks Having Dynamic Computation Graphs

2019-05-01 · ICLR 2019 5 · Yuchen Qiao, Kenjiro Taura

Organizing the same operations in the computation graph of a neural network into batches is one of the important methods to improve the speed of training deep learning models and applications since it helps to execute op…

On-the-fly Operation Batching in Dynamic Computation Graphs

2017-05-22 · NeurIPS 2017 12 · Graham Neubig, Yoav Goldberg, Chris Dyer

Dynamic neural network toolkits such as PyTorch, DyNet, and Chainer offer more flexibility for implementing models that cope with data of varying dimensions and structure, relative to toolkits that operate on statically …

SMDP-Based Dynamic Batching for Efficient Inference on GPU-Based Platforms

2023-01-30 · Yaodan Xu, Jingzhou Sun, Sheng Zhou, Zhisheng Niu

In up-to-date machine learning (ML) applications on cloud or edge computing platforms, batching is an important technique for providing efficient and economical services at scale. In particular, parallel computing resour…

Edge-computingGPU

Quantifying the mini-batching error in Bayesian inference for Adaptive Langevin dynamics

2021-05-21 · Inass Sekkat, Gabriel Stoltz

Bayesian inference allows to obtain useful information on the parameters of models, either in computational statistics or more recently in the context of Bayesian Neural Networks. The computational cost of usual Monte Ca…

Bayesian InferenceFriction