A Data-Center FPGA Acceleration Platform for Convolutional Neural Networks.

In this paper, we develop an FPGA acceleration platform that leverages a unified framework architecture for general-purpose convolutional neural network (CNN) inference acceleration at a data center. ... For various non-convolution operators, a filter processing unit is designed for general-purpose filter-like/pointwise operators. ... INTRODUCTION Developing a hardware computing platform for convolutional neural network (CNN) based deep learning inference in a modern data center is a significant challenge [1] [2] . ...

<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/fpl.2019.00032">doi:10.1109/fpl.2019.00032</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/fpl/YuGWMWZMZMC19.html">dblp:conf/fpl/YuGWMWZMZMC19</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/l6jrzquumjfwnj7r46bjbymwk4">fatcat:l6jrzquumjfwnj7r46bjbymwk4</a> </span>

<span class="ui label basic blue small">Multiple Versions</span>

<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200904164406/https://arxiv.org/ftp/arxiv/papers/1909/1909.07973.pdf" title="fulltext PDF download [not primary version]" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <span style="color: #f43e3e;">✱</span> <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/20/9c/209c0b9b3410c6b3ba1f371e7b938a339466bc0d.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/fpl.2019.00032"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ieee.com </button> </a>

In this paper, we research neural networks which are involved in the acceleration on FPGA-based platforms. ... Then previous works on neural network acceleration are introduced following these topics. We summarize how to design a technical route for practical applications based on these strategies. ... Conclusions In this paper, we review resource-limited platforms and neural networks about acceleration. ...

<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3390/electronics10091025">doi:10.3390/electronics10091025</a> <a target="_blank" rel="external noopener" href="https://doaj.org/article/92e7eb4228a44c6387f846a1203529d0">doaj:92e7eb4228a44c6387f846a1203529d0</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/2xa7dv5hsjbczpvc4w6acdehwu">fatcat:2xa7dv5hsjbczpvc4w6acdehwu</a> </span>

<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210611171533/https://res.mdpi.com/d_attachment/electronics/electronics-10-01025/article_deploy/electronics-10-01025-v2.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/99/9d/999df34d012135868b1e191f8239ae2b1d6a8c2c.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3390/electronics10091025"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> mdpi.com </button> </a>

However, the diversity and large-scale data size have posed a significant challenge to construct a flexible and high-performance implementation of deep learning neural networks. ... Designing and implementing efficient, provably correct parallel neural network processing is challenging. ... The explosive volume of data makes the data centers quite power consuming. ...

<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1606.06234v1">arXiv:1606.06234v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/en7acoahonb7beqrnxv553g46e">fatcat:en7acoahonb7beqrnxv553g46e</a> </span>

<a target="_blank" rel="noopener" href="https://web.archive.org/web/20191027065219/https://arxiv.org/pdf/1606.06234v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/9c/5a/9c5af2226a48672c9d12cbd22f41b400717f5a21.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1606.06234v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

In this context, CERN openlab has a collaboration with the researchers at SHREC at the University of Florida and with Intel to accelerate the 3DGAN inferencing stage using FPGAs. ... A number of details of this work and preliminary results will be presented, specifically in terms of speedup, stimulating a discussion for future development. ... for FPGA acceleration FPGA Acceleration for DNN Inference  Experimental platforms  Dell EMC server: 2x Intel Xeon Gold 6130 CPU  Intel PAC: Arria 10 GX FPGA  Deep Learning Accelerator suite ...

<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.5281/zenodo.3599552">doi:10.5281/zenodo.3599552</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/utno2adxxfddbehed5al2fhtmy">fatcat:utno2adxxfddbehed5al2fhtmy</a> </span>

<span class="ui label basic orange small" title="Open Access">Open Access</span>

<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200214150707/https://zenodo.org/record/3599553/files/CHEP2019_490.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/e0/a9/e0a902a3702d1d6695a3c9daf0925a46dc59fc85.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.5281/zenodo.3599552"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> zenodo.org </button> </a>

Based on the application of convolutional neural network (CNN) in the field of image recognition and the characteristics of a large number of computing requirements, this paper designs an accelerator based ... The key parameters of the CNN training structure file and the selection of the appropriate excitation function ReLU (Rectifiedlinearunit) for training the convolutional neural network on the virtual machine ... The field-programmable gate Array (FPGA) has the characteristics of parallel processing data, and provides a research platform for the design of CNN accelerator [3] . ...

<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.12783/dtcse/iciti2018/29175">doi:10.12783/dtcse/iciti2018/29175</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/nm4ri4texfc23jz2shyvseqczm">fatcat:nm4ri4texfc23jz2shyvseqczm</a> </span>

<a target="_blank" rel="noopener" href="https://web.archive.org/web/20190426075642/http://dpi-proceedings.com/index.php/dtcse/article/download/29175/28184" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/81/50/81508619ebd087b8a12c6c3aa97f6d67bd18e262.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.12783/dtcse/iciti2018/29175"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> Publisher / doi.org </button> </a>

In the end, we prospect the development tendency of accelerator architectures in the future, hoping to provide a reference for computer architecture researchers. ... Among the typical heterogeneous architectures above, FPGA-based reconfigurable accelerators have two merits as follows: First, FPGA architecture contains a large number of reconfigurable circuits, which ... ISAAC [75] proposes a cross-switch simulation accelerator for convolutional neural networks. ...

<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1712.04771v1">arXiv:1712.04771v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/3lxv45qb4zaqpagtn3eghrmroe">fatcat:3lxv45qb4zaqpagtn3eghrmroe</a> </span>

<a target="_blank" rel="noopener" href="https://web.archive.org/web/20191021040107/https://arxiv.org/pdf/1712.04771v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/6f/53/6f537c85b5160a6375306f6eca1a3e8558e7dbd9.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/1712.04771v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Inference of convolutional neural networks is therefore usually done in centralized high-performance platforms. ... The convolutional neural network (CNN) is one of the most used deep learning models for image detection and classification, due to its high accuracy when compared to other machine learning algorithms. ... It is true that training is still a task for data centers but inference has many advantages if run at the edge platform. ...

<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3390/a12080154">doi:10.3390/a12080154</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/jbdak7eisbcjtj6ba5hlpvnq5y">fatcat:jbdak7eisbcjtj6ba5hlpvnq5y</a> </span>

<span class="ui label basic orange small" title="Directory of Open Access Journals">DOAJ</span> <span class="ui label basic orange small" title="Szcezepanski OA Journal List">Szczepanski</span>

<a target="_blank" rel="noopener" href="https://web.archive.org/web/20200209062111/https://res.mdpi.com/d_attachment/algorithms/algorithms-12-00154/article_deploy/algorithms-12-00154.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/d0/e1/d0e16ee1eeb9d102b63364108aaaaeb34bfa05dd.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3390/a12080154"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> mdpi.com </button> </a>

This paper presents an overview and review of embedded intelligence on FPGA with a focus on applications, platforms and challenges. ... There are four main classification and thematic descriptors which are reviewed and discussed in this paper for EI: (1) EI techniques including machine learning and neural networks, deep learning, expert ... Another research on independently recurrent neural networks (RNN) on FPGA based accelerator uses the Xilinx Zynq zc706 FPGA platform. ...

<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3390/electronics10080895">doi:10.3390/electronics10080895</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/igqk3n2kp5f4bmt6ho2qa3baau">fatcat:igqk3n2kp5f4bmt6ho2qa3baau</a> </span>

<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210428175312/https://res.mdpi.com/d_attachment/electronics/electronics-10-00895/article_deploy/electronics-10-00895.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/df/0c/df0cc7d9954cd68bb46a9c0d037486f7fdb0292f.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3390/electronics10080895"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> mdpi.com </button> </a>

In particular, we focus on acceleration of the inference of convolutional neural networks (CNNs) used for image recognition tasks. Given that there exist many different hardware architectures. ... In this article an overview of existing neural network hardware accelerators and acceleration methods is given. ... Therefore, TPU is a favorable solution for data centers. For power-critical embedded devices, ASICs or FPGAs is a feasible choice. ...

<span class="external-identifiers"> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2104.09252v1">arXiv:2104.09252v1</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/625wtuskhff3lbswhwmj7decni">fatcat:625wtuskhff3lbswhwmj7decni</a> </span>

<a target="_blank" rel="noopener" href="https://web.archive.org/web/20210515123129/https://arxiv.org/pdf/2104.09252v1.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/cc/aa/ccaace1c44e8bb5f6a2529e0c8bf4939c12a4063.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener" href="https://arxiv.org/abs/2104.09252v1" title="arxiv.org access"> <button class="ui compact blue labeled icon button serp-button"> <i class="file alternate outline icon"></i> arxiv.org </button> </a>

Convolutional Neural Networks (CNNs) have become some of the most influential innovations in the field of ML, and accelerating CNNs has become a very important task for a variety of applications including ... Prominent companies have introduced FPGA/GPU-based platforms for data centers. ...

<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/mdat.2017.2779981">doi:10.1109/mdat.2017.2779981</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/t27ltd5trzbunhsn5fy6v2lvya">fatcat:t27ltd5trzbunhsn5fy6v2lvya</a> </span>

<a target="_blank" rel="noopener" href="https://web.archive.org/web/20190430170809/http://repository.bilkent.edu.tr/bitstream/handle/11693/37989/Guest%20Editors%20%20Introduction%20Hardware%20Accelerators%20for%20Data%20Centers.pdf;jsessionid=B64B18564DE3AC42A12BCEF8444A595D?sequence=1" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/da/66/da6655b3a6dc14a9a6f67850f6ea2a46f56ea8ce.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/mdat.2017.2779981"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ieee.com </button> </a>

As a matter of fact, existing CPU and GPU platforms may not be the most efficient choices for the compute patterns of a wide range of applications. ... On the other hand, only a limited class of data-parallel applications can utilize the high throughputs provided by such architectures. ... TPU is aimed at accelerating the inference phase of different types of neural network applications, including multi-layer perceptrons (MLP), convolutional neural networks (CNN), and recurrent neural networks ...

<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/mdat.2017.2779742">doi:10.1109/mdat.2017.2779742</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/uf32ils7incthma5kju74wzwr4">fatcat:uf32ils7incthma5kju74wzwr4</a> </span>

<a target="_blank" rel="noopener" href="https://web.archive.org/web/20180723091308/http://repository.bilkent.edu.tr/bitstream/handle/11693/46939/MDAT2779742.pdf;jsessionid=EB55F560A22D1D088A43330A6301395E?sequence=1" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/35/39/353989bf35c48a861decc2a9e0f512165efbd34d.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1109/mdat.2017.2779742"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> ieee.com </button> </a>

Convolutional neural network (CNN) has been widely employed for image recognition because it can achieve high accuracy by emulating behavior of optic nerves in living creatures. ... As a case study, we implement a CNN accelerator on a VC707 FPGA board and compare it to previous approaches. ... INTRODUCTION Convolutional neural network (CNN), a well-known deep learning architecture extended from artificial neural network, has been extensively adopted in various applications, which include video ...

<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1145/2684746.2689060">doi:10.1145/2684746.2689060</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/fpga/ZhangLSGXC15.html">dblp:conf/fpga/ZhangLSGXC15</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/2iq7kld26vcjnl32evdzb6l3qi">fatcat:2iq7kld26vcjnl32evdzb6l3qi</a> </span>

<a target="_blank" rel="noopener" href="https://web.archive.org/web/20150812175550/http://cadlab.cs.ucla.edu/~cong/slides/fpga2015_chen.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/2f/fc/2ffc74bec88d8762a613256589891ff323123e99.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1145/2684746.2689060"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> acm.org </button> </a>

The accelerator can handle network layers of different scales through parameter configuration and maximizes bandwidth and achieves full pipelined by using a data stream interface and ping-pong on-chip ... The Convolutional Neural Network (CNN) has been used in many fields and has achieved remarkable results, such as image classification, face detection, and speech recognition. ... Acknowledgments: The authors would like to thank the Editor and the anonymous reviewers for their valuable comments and suggestions. ...

<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3390/electronics8030281">doi:10.3390/electronics8030281</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/mx4esrhr7zhmpfjd6gtbdsc3x4">fatcat:mx4esrhr7zhmpfjd6gtbdsc3x4</a> </span>

<a target="_blank" rel="noopener" href="https://web.archive.org/web/20190504004839/https://res.mdpi.com/electronics/electronics-08-00281/article_deploy/electronics-08-00281.pdf?filename=&attachment=1" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/18/52/18527fcf8924aabacaf4bbb9132966a7b471fe25.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.3390/electronics8030281"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="unlock alternate icon" style="background-color: #fb971f;"></i> mdpi.com </button> </a>

Due to the exponential increase in network traffic in the data centers, thousands of servers interconnected with high bandwidth switches are required. ... This paper looks at FPGAs as reconfigurable accelerators for the cloud computing presents the main hardware accelerators that have been presented in various widely used cloud computing applications such ... Moreover they, Accelerated the training of deep convolutional neural networks by using the SPARK run time environment in a data center. ...

<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1145/3284557.3284563">doi:10.1145/3284557.3284563</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/chmip5oxmjcdnmjde2g52fxg4i">fatcat:chmip5oxmjcdnmjde2g52fxg4i</a> </span>

<a target="_blank" rel="noopener" href="https://web.archive.org/web/20201104164237/http://nectar.northampton.ac.uk/13418/1/Mohammedali_etal_ACM_2018_A_Study_of_Reconfigurable_Accelerators_for_Cloud_Computing.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/88/81/88818bb305cdc2b0a9a39d39b6839a3d11551e21.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1145/3284557.3284563"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> acm.org </button> </a>

These accelerators were validated on a multi-FPGA platform and significant performance enhancement and power efficiencies were demonstrated when compared to CMP and GPU platforms. ... This paper presents the design and evaluation of hardware accelerators for extracting visual features for universal recognition. ... Other works [19, 22] have proposed an architecture for image processing using Convolutional Neural Networks, CNN. ...

<span class="external-identifiers"> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1145/2228360.2228465">doi:10.1145/2228360.2228465</a> <a target="_blank" rel="external noopener" href="https://dblp.org/rec/conf/dac/Al-MaashriDCCXNC12.html">dblp:conf/dac/Al-MaashriDCCXNC12</a> <a target="_blank" rel="external noopener" href="https://fatcat.wiki/release/m7qdz2k225arnmkplthvoedcwu">fatcat:m7qdz2k225arnmkplthvoedcwu</a> </span>

<a target="_blank" rel="noopener" href="https://web.archive.org/web/20170519080709/http://www.public.asu.edu:80/~chaitali/confpapers/neuromorphic_dac12.pdf" title="fulltext PDF download" data-goatcounter-click="serp-fulltext" data-goatcounter-title="serp-fulltext"> <button class="ui simple right pointing dropdown compact black labeled icon button serp-button"> <i class="icon ia-icon"></i> Web Archive [PDF] <div class="menu fulltext-thumbnail"> <img src="https://blobs.fatcat.wiki/thumbnail/pdf/29/fc/29fc8380eccdd1b4e2f8d9dd8faac6a2c3906230.180px.jpg" alt="fulltext thumbnail" loading="lazy"> </div> </button> </a> <a target="_blank" rel="external noopener noreferrer" href="https://doi.org/10.1145/2228360.2228465"> <button class="ui left aligned compact blue labeled icon button serp-button"> <i class="external alternate icon"></i> acm.org </button> </a>

A Data-Center FPGA Acceleration Platform for Convolutional Neural Networks

Preserved Fulltext

Accelerating Neural Network Inference on FPGA-Based Platforms—A Survey

Preserved Fulltext

CNNLab: a Novel Parallel Framework for Neural Networks using GPU and FPGA-a Practical Study with Trade-off Analysis [article]

Preserved Fulltext

3D Generative Adversarial Networks inference implementation on FPGAs

Preserved Fulltext

Design of Image Recognition Accelerator Based on FPGA

Preserved Fulltext

Reconfigurable Hardware Accelerators: Opportunities, Trends, and Challenges [article]

Preserved Fulltext

A Survey of Convolutional Neural Networks on Edge with Reconfigurable Computing

Preserved Fulltext

Embedded Intelligence on FPGA: Survey, Applications and Challenges

Preserved Fulltext

Learning on Hardware: A Tutorial on Neural Network Accelerators and Co-Processors [article]

Preserved Fulltext

Guest Editors' Introduction: Hardware Accelerators for Data Centers

Preserved Fulltext

Emerging Accelerator Platforms for Data Centers

Preserved Fulltext

Optimizing FPGA-based Accelerator Design for Deep Convolutional Neural Networks

Preserved Fulltext

An FPGA-Based CNN Accelerator Integrating Depthwise Separable Convolution

Preserved Fulltext

A Study of Reconfigurable Accelerators for Cloud Computing

Preserved Fulltext

Accelerating neuromorphic vision algorithms for recognition

Preserved Fulltext