Write a Blog >>
LCTES 2018
co-located with PLDI 2018
Tue 19 Jun 2018 16:25 - 16:40 at Discovery AB - WIP paper session

Deep Neural Networks (DNNs) are the algorithm of choice for image processing applications. DNNs present highly parallel workloads that lead to the emergence of custom hardware accelerators. Deep Learning (DL) models specialized in different tasks require a programmable custom hardware and a compiler/mapper to efficiently translate different DNNs into an efficient dataflow in the accelerator. The goal of this paper is to present a compiler for running DNNs on Snowflake, which is a programmable hardware accelerator that targets DNNs. The compiler correctly generates instructions for various DL models: AlexNet, VGG, ResNet and LightCNN9. Snowflake, with a varying number of processing units, was implemented on FPGA to measure the compiler and Snowflake performance properties upon scaling up. The system achieves 70 frames/s and 4.5 GB/s of off-chip memory bandwidth for AlexNet without linear layers on Xilinx’s Zynq-SoC XC7Z045 FPGA.

Tue 19 Jun

Displayed time zone: Eastern Time (US & Canada) change

16:10 - 17:25
WIP paper sessionLCTES 2018 at Discovery AB
16:25
15m
Short-paper
WIP: Deep Neural Networks compiler for a trace-based accelerator
LCTES 2018
Andre Xian Ming Chang FWDNXT and Purdue, Aliasger Zaidy FWDNXT and Purdue, Lukasz Burzawa FWDNXT and Purdue, Eugenio Culurciello FWDNXT and Purdue
16:40
15m
Short-paper
WIP: Statically Relating Program Properties for Efficient Verification
LCTES 2018
Bharti Chimdyalwar Tata Consultancy Services, Priyanka Darke Tata Consultancy Services
16:55
15m
Short-paper
WIP: Transparent Standby for Low-Power, Resource-Constrained Embedded Systems: A Programming Language-Based Approach
LCTES 2018
Francisco Sant'Anna Rio de Janeiro State University, Alexandre Sztajnberg Rio de Janeiro State University, Noemi Rodriguez PUC-Rio, Ana Lúcia de Moura
17:10
15m
Short-paper
WIP: An open-source realtime computational platform
LCTES 2018
Pavan Mehrotra Stanford University, Sabar Dasgupta Stanford University, Samantha Robertson Stanford University, Paul Nuyujukian Stanford University
Link to publication DOI Pre-print Media Attached