peer to peer
Recently Published Documents


TOTAL DOCUMENTS

11670
(FIVE YEARS 2299)

H-INDEX

114
(FIVE YEARS 22)

2022 ◽  
Vol 15 (2) ◽  
pp. 1-34
Author(s):  
Tobias Alonso ◽  
Lucian Petrica ◽  
Mario Ruiz ◽  
Jakoba Petri-Koenig ◽  
Yaman Umuroglu ◽  
...  

Customized compute acceleration in the datacenter is key to the wider roll-out of applications based on deep neural network (DNN) inference. In this article, we investigate how to maximize the performance and scalability of field-programmable gate array (FPGA)-based pipeline dataflow DNN inference accelerators (DFAs) automatically on computing infrastructures consisting of multi-die, network-connected FPGAs. We present Elastic-DF, a novel resource partitioning tool and associated FPGA runtime infrastructure that integrates with the DNN compiler FINN. Elastic-DF allocates FPGA resources to DNN layers and layers to individual FPGA dies to maximize the total performance of the multi-FPGA system. In the resulting Elastic-DF mapping, the accelerator may be instantiated multiple times, and each instance may be segmented across multiple FPGAs transparently, whereby the segments communicate peer-to-peer through 100 Gbps Ethernet FPGA infrastructure, without host involvement. When applied to ResNet-50, Elastic-DF provides a 44% latency decrease on Alveo U280. For MobileNetV1 on Alveo U200 and U280, Elastic-DF enables a 78% throughput increase, eliminating the performance difference between these cards and the larger Alveo U250. Elastic-DF also increases operating frequency in all our experiments, on average by over 20%. Elastic-DF therefore increases performance portability between different sizes of FPGA and increases the critical throughput per cost metric of datacenter inference.


2022 ◽  
Vol 102 ◽  
pp. 103140
Author(s):  
Yosef Alqayed ◽  
Pantea Foroudi ◽  
Kaouther Kooli ◽  
Mohammad M. Foroudi ◽  
Charles Dennis

2022 ◽  
Vol 10 (1) ◽  
pp. 100154
Author(s):  
Susanna Levantesi ◽  
Gabriella Piscopo
Keyword(s):  

Author(s):  
Shuai Xuanyue ◽  
Xiuli Wang ◽  
Xiong Wu ◽  
Yifei Wang ◽  
Zhenzi Song ◽  
...  

2022 ◽  
Vol 8 ◽  
pp. 59-66
Author(s):  
Xiaoyu Wang ◽  
Tao Xu ◽  
Yunfei Mu ◽  
Zibo Wang ◽  
Youjun Deng ◽  
...  

Sign in / Sign up

Export Citation Format

Share Document