02. hams - fpgas because
TRANSCRIPT
1
HAMS project
Chiara [email protected]
Guido [email protected]
2. FPGAs BECAUSE…March, 17th 2016
NECST Lab, Politecnico di Milano
Credits: Shahriar Emil from the Noun Project
2
The problem
If only MATLAB
simulations could
take less time…
https://thenounproject.com/
3
The solution
If only MATLAB
simulations could
take less time…
https://thenounproject.com/
HARDWARE
ACCELERATION of
MATLAB
SIMULATIONS
4
Hardware devices
GPUs(Graphic Processing
Units)
ASICs(Application SpecificIntegrated Circuits)
FPGAs(Field Programmable
Gate Arrays)
5
Features
Speedup vs GPPs
Power requirements
Flexibility
Cost of the device
6
Speedup (vs GPP[*]
)
GPUs High speedup
ASICs Best possible
FPGAs High speedup
[*]
General Purpose Processor
7
Power requirements
GPUs High speedup Hundreds of watts
(Tesla K40 by Nvidia max 235W)
ASICs Highest possible Lowest possible
FPGAs High speedup Tens of watts
(Virtex7-VC707 by Xilinx abt 15W)
8
Flexibility
GPUs High speedup Hundreds of watts Programmable
ASICs Highest possible Lowest possible Application-specific
FPGAs High speedup Tens of watts Programmable
9
Costs
GPUs High speedup Hundreds of watts Programmable About 3000$ each
(Tesla K40 by Nvidia)
ASICs Highest possible Lowest possible Application-specific Too high if few
circuits required
FPGAs High speedup Tens of watts Programmable About 3500$ each
(Virtex7 VC707 by Xilinx)
10
The choice
GPUs High speedup Hundreds of watts Programmable About 3000$ each
ASICs Highest possible Lowest possible Application-specific Too high if few
circuits required
FPGAs High speedup Tens of watts Programmable About 3500$ each
11
The choice
GPUs High speedup Hundreds of watts Programmable About 3000$ each
ASICs Highest possible Lowest possible Application-specific Too high if few
circuits required
FPGAs High speedup Tens of watts Programmable About 3500$ each
12
The choice
GPUs High speedup Hundreds of watts Programmable About 3000$ each
ASICs Highest possible Lowest possible Application-specific Too high if few
circuits required
FPGAs High speedup Tens of watts Programmable About 3500$ each
13
The choice
GPUs High speedup Hundreds of watts Programmable About 3000$ each
FPGAs High speedup Tens of watts Programmable About 3500$ each
14
The choice
GPUs High speedup Hundreds of watts Programmable About 3000$ each
FPGAs High speedup Tens of watts Programmable About 3500$ each
15
The choice
FPGAs High speedup Tens of watts Programmable About 3500$ each
MATRIX INVERSION
16
First case study
• Intense computation
• Useful in different applications(e.g. fluid dynamics lumped parameters model)
reusability
MATRIX INVERSION
17
First case study
So… FPGAs!
- High speedup vs GPPs
- Low power requirements
- Programmable
- Affordable costs
ANY QUESTIONS? HAMSprojectContact us!
You can find us…
www.facebook.com/hams.project
https://twitter.com/HAMS_project
http://www.slideshare.net/HAMSproject
https://vimeo.com/necstxohw16
https://www.youtube.com/channel/UCaovqRpUc7D_Uf2WJHL0rvA