2018 International SoC Design Conference (ISOCC) 2018
DOI: 10.1109/isocc.2018.8649950
|View full text |Cite
|
Sign up to set email alerts
|

System Level Power Reduction for YOLO2 Sub-modules for Object Detection of Future Autonomous Vehicles

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...
2

Citation Types

0
0
0
2

Year Published

2021
2021
2024
2024

Publication Types

Select...
3
2

Relationship

0
5

Authors

Journals

citations
Cited by 5 publications
(3 citation statements)
references
References 2 publications
0
0
0
2
Order By: Relevance
“…Each manufacturer provides the CAD tools and development platforms for the implementation process and reconfigurable components and parts on the FPGA (e.g., Vivado from Xilinx, Quartus Prime from Intel, and PYNQ). However, due to the closed platform feature of the Xilinx FPGA products, in the High Level of Synthesis (HLS) design flow as shown in Figure 1, the Vivado HLS system can verify the functionality of the C/C++/System C code and convert the code to the register-transfer level (RTL) code for the FPGA hardware operation and optimization [7], [23], [35], however, once the RTL code is generated by Vivado HLS Tool, the code is no longer readable or modifiable. On the other hand, the platform-based design flow can import the VHDL/Verilog code to set as customized IP blocks so that we can easily modify the hardware design at the RT level or gate level and intuitively configure the data flow for Processing System (PS) and Programmable Logic (PL) through the Vivado IP Integrator.…”
Section: Introductionmentioning
confidence: 99%
“…Each manufacturer provides the CAD tools and development platforms for the implementation process and reconfigurable components and parts on the FPGA (e.g., Vivado from Xilinx, Quartus Prime from Intel, and PYNQ). However, due to the closed platform feature of the Xilinx FPGA products, in the High Level of Synthesis (HLS) design flow as shown in Figure 1, the Vivado HLS system can verify the functionality of the C/C++/System C code and convert the code to the register-transfer level (RTL) code for the FPGA hardware operation and optimization [7], [23], [35], however, once the RTL code is generated by Vivado HLS Tool, the code is no longer readable or modifiable. On the other hand, the platform-based design flow can import the VHDL/Verilog code to set as customized IP blocks so that we can easily modify the hardware design at the RT level or gate level and intuitively configure the data flow for Processing System (PS) and Programmable Logic (PL) through the Vivado IP Integrator.…”
Section: Introductionmentioning
confidence: 99%
“…Além disso, sistemas de computac ¸ão distribuída têm sido explorados para distribuir a carga de trabalho e acelerar a inferência em escala [Imani et al 2020, Guo et al 2017, Coutinho et al 2019]. Otimizac ¸ões de compilador, como a eliminac ¸ão de expressões comuns, também podem ser aplicadas para melhorar o desempenho [Kim et al 2018].…”
Section: Introduc ¸ãOunclassified
“…As abordagens de aceleração baseadas em algoritmo incluem processamento paralelo (paralelismo de dados e modelo), compressão de modelo (remoção de pesos e quantização de valores de peso e ativação), exploração de esparsidade (esparsidade em nível de valor e em nível de bit) e redução de modelo por meio de aproximação [7], [8], [9], [10], [11], [12], [13], [14], [15]. As abordagens de aceleração baseadas em sistema incluem sistemas de memória de alta largura de banda para minimização do tempo de acesso, aceleradores de hardware (ASIC e FPGA), sistemas de computação distribuída [16], [17], [18] e otimizações de compilador, como eliminação de expressões comuns [19].…”
unclassified