paper-with-me

Papers

PhoneBit: Efficient GPU-Accelerated Binary Neural Network Inference Engine for Mobile Phones

2019-12-05 · Gang Chen, Shengyu He, Haitao Meng, Kai Huang

Over the last years, a great success of deep neural networks (DNNs) has been witnessed in computer vision and other fields. However, performance and power constraints make it still challenging to deploy DNNs on mobile devices due to their high computational complexity. Binary neural networks (BNNs) have been demonstrated as a promising solution to achieve this goal by using bit-wise operations to replace most arithmetic operations. Currently, existing GPU-accelerated implementations of BNNs are only tailored for desktop platforms. Due to architecture differences, mere porting of such implementations to mobile devices yields suboptimal performance or is impossible in some cases. In this paper, we propose PhoneBit, a GPU-accelerated BNN inference engine for Android-based mobile devices that fully exploits the computing power of BNNs on mobile GPUs. PhoneBit provides a set of operator-level optimizations including locality-friendly data layout, bit packing with vectorization and layers integration for efficient binary convolution. We also provide a detailed implementation and parallelization optimization for PhoneBit to optimally utilize the memory bandwidth and computing power of mobile GPUs. We evaluate PhoneBit with AlexNet, YOLOv2 Tiny and VGG16 with their binary version. Our experiment results show that PhoneBit can achieve significant speedup and energy efficiency compared with state-of-the-art frameworks for mobile devices.

📄 PDF Abstract BibTeX arXiv:1912.04050

Code (0)

등록된 구현이 없습니다.

Tasks

GPU

Methods 이 논문이 사용한 방법론

Ethereum Customer Service Number +1-833-534-1729 설명 없음
Average Pooling 설명 없음
Global Average Pooling Global Average Pooling is a pooling operation designed to replace fully connected layers in classical CNNs. The idea is to generate one feature map for each corresponding…
1x1 Convolution A 1 x 1 Convolution is a convolution with some special properties in that it can be used for dimensionality reduction,…
Batch Normalization 설명 없음
Convolution A convolution is a type of matrix operation, consisting of a kernel, a small matrix of weights, that slides over input data performing element-wise multiplication with the…
Darknet-19 설명 없음
Local Response Normalization Local Response Normalization is a normalization layer that implements the idea of lateral inhibition. Lateral inhibition is a concept in neurobiology that refers to the…

Similar Papers 제목 키워드 기반

BEANNA: A Binary-Enabled Architecture for Neural Network Acceleration

2021-08-04 · Caleb Terrill, Fred Chu

Modern hardware design trends have shifted towards specialized hardware acceleration for computationally intensive tasks like machine learning and computer vision. While these complex workloads can be accelerated by comm…

Binary-decomposed DCNN for accelerating computation and compressing model without retraining

2017-09-14 · Ryuji Kamiya, Takayoshi Yamashita, Mitsuru Ambai, Ikuro Sato 외

Recent trends show recognition accuracy increasing even more profoundly. Inference process of Deep Convolutional Neural Networks (DCNN) has a large number of parameters, requires a large amount of computation, and can be…

RSR-core: A High-Performance Engine for Low-Bit Matrix-Vector Multiplication

2026-03-29 · Mohsen Dehghankar, Abolfazl Asudeh arxiv

Matrix-vector multiplication is a fundamental building block in neural networks, vector databases, and large language models, particularly during inference. As a result, efficient matrix-vector multiplication engines dir…

Rapid Likelihood Free Inference of Compact Binary Coalescences using Accelerated Hardware

2024-07-26 · Deep Chatterjee, Ethan Marx, William Benoit, Ravi Kumar 외

We report a gravitational-wave parameter estimation algorithm, AMPLFI, based on likelihood-free inference using normalizing flows. The focus of AMPLFI is to perform real-time parameter estimation for candidates detected …

parameter estimation

MNN: A Universal and Efficient Inference Engine

2020-02-27 · Xiaotang Jiang, Huan Wang, Yiliu Chen, Ziqi Wu 외

Deploying deep learning models on mobile devices draws more and more attention recently. However, designing an efficient inference engine on devices is under the great challenges of model compatibility, device diversity,…

Deep LearningDiversityScheduling