16523

Caffeine: Towards Uniformed Representation and Acceleration for Deep Convolutional Neural Networks

Chen Zhang, Zhenman Fang, Peipei Zhou, Peichen Pan, Jason Cong
Center for Energy-Efficient Computing and Applications, Peking University, Beijing, China
IEEE/ACM International Conference on Computer-Aided Design (ICCAD 2016), 2016

@article{zhang2016caffeine,

   title={Caffeine: Towards Uniformed Representation and Acceleration for Deep Convolutional Neural Networks},

   author={Zhang, Chen and Fang, Zhenman and Zhou, Peipei and Pan, Peichen and Cong, Jason},

   year={2016}

}

Download Download (PDF)   View View   Source Source   

343

views

With the recent advancement of multilayer convolutional neural networks (CNN), deep learning has achieved amazing success in many areas, especially in visual content understanding and classification. To improve the performance and energy-efficiency of the computation-demanding CNN, the FPGA-based acceleration emerges as one of the most attractive alternatives. In this paper we design and implement Caffeine, a hardware/software co-designed library to efficiently accelerate the entire CNN on FPGAs. First, we propose a uniformed convolutional matrixmultiplication representation for both computation-intensive convolutional layers and communication-intensive fully connected (FCN) layers. Second, we design Caffeine with the goal to maximize the underlying FPGA computing and bandwidth resource utilization, with a key focus on the bandwidth optimization by the memory access reorganization not studied in prior work. Moreover, we implement Caffeine in the portable high-level synthesis and provide various hardware/software definable parameters for user configurations. Finally, we also integrate Caffeine into the industry-standard software deep learning framework Caffe. We evaluate Caffeine and its integration with Caffe by implementing VGG16 and AlexNet network on multiple FPGA platforms. Caffeine achieves a peak performance of 365 GOPS on Xilinx KU060 FPGA and 636 GOPS on Virtex7 690t FPGA. This is the best published result to our best knowledge. We achieve more than 100x speedup on FCN layers over previous FPGA accelerators. An endto-end evaluation with Caffe integration shows up to 7.3x and 43.5x performance and energy gains over Caffe on a 12-core Xeon server, and 1.5x better energy-efficiency over the GPU implementation on a medium-sized FPGA (KU060). Performance projections to a system with a high-end FPGA (Virtex7 690t) shows even higher gains.
VN:F [1.9.22_1171]
Rating: 2.0/5 (2 votes cast)
Caffeine: Towards Uniformed Representation and Acceleration for Deep Convolutional Neural Networks, 2.0 out of 5 based on 2 ratings

* * *

* * *

TwitterAPIExchange Object
(
    [oauth_access_token:TwitterAPIExchange:private] => 301967669-yDz6MrfyJFFsH1DVvrw5Xb9phx2d0DSOFuLehBGh
    [oauth_access_token_secret:TwitterAPIExchange:private] => o29ji3VLVmB6jASMqY8G7QZDCrdFmoTvCDNNUlb7s
    [consumer_key:TwitterAPIExchange:private] => TdQb63pho0ak9VevwMWpEgXAE
    [consumer_secret:TwitterAPIExchange:private] => Uq4rWz7nUnH1y6ab6uQ9xMk0KLcDrmckneEMdlq6G5E0jlQCFx
    [postfields:TwitterAPIExchange:private] => 
    [getfield:TwitterAPIExchange:private] => ?cursor=-1&screen_name=hgpu&skip_status=true&include_user_entities=false
    [oauth:protected] => Array
        (
            [oauth_consumer_key] => TdQb63pho0ak9VevwMWpEgXAE
            [oauth_nonce] => 1481241937
            [oauth_signature_method] => HMAC-SHA1
            [oauth_token] => 301967669-yDz6MrfyJFFsH1DVvrw5Xb9phx2d0DSOFuLehBGh
            [oauth_timestamp] => 1481241937
            [oauth_version] => 1.0
            [cursor] => -1
            [screen_name] => hgpu
            [skip_status] => true
            [include_user_entities] => false
            [oauth_signature] => s4n/nRGy6tX4bN5z0kxU5//cuGg=
        )

    [url] => https://api.twitter.com/1.1/users/show.json
)
Follow us on Facebook
Follow us on Twitter

HGPU group

2081 peoples are following HGPU @twitter

HGPU group © 2010-2016 hgpu.org

All rights belong to the respective authors

Contact us: