|
doi: 10.3850/978-3-9815370-4-8_1136
Memrisor Based Computation-in-Memory Architecture for Data-Intensive Applications
Said Hamdioui1,a, Lei Xie1,b, Anh Nguyen Hai Anh1,c, Mottaqiallah Taouil1,d, Koen Bertels1,e, Henk Corporaal2,f, Hailong Jiao2,g, Francky Catthoor3,h, Dirk Wouters3, Linn Eike4 and Jan van Lunteren5
1Computer Engineering, Delft University of Technology, Delft, The Netherlands.
as_said_hamdioui@tudelft.nl
bl_lei_xie@tudelft.nl
ca_anh_nguyen_hai_anh@tudelft.nl
dm_mottaqiallah_taouil@tudelft.nl
ek_koen_bertels@tudelft.nl
2Electronic Systems group Eindhoven University of Technology, Eindhoven, The Netherlands.
fh.corporaal@tue.nl
gH.Jiao@tue.nl
3IMEC, Kapeldreef 75, Leuven, Belgium.
hcatthoor@imec.be
4RWTH Aachen University, Aachen, Germany.
linn@IWE.RWTH-Aachen.de
5IBM Research Laboratory, Zurich, Switzerland.
jvl@zurich.ibm.com
ABSTRACT
One of the most critical challenges for today’s and
future data-intensive and big-data problems is data storage and
analysis. This paper first highlights some challenges of the new
born Big Data paradigm and shows that the increase of the data
size has already surpassed the capabilities of today’s computation
architectures suffering from the limited bandwidth,
programmability overhead, energy inefficiency, and limited
scalability. Thereafter, the paper introduces a new memristorbased
architecture for data-intensive applications. The potential
of such an architecture in solving data-intensive problems is
illustrated by showing its capability to increase the computation
efficiency, solving the communication bottleneck, reducing the
leakage currents, etc. Finally, the paper discusses why memristor
technology is very suitable for the realization of such an
architecture; using memristors to implement dual functions
(storage and logic) is illustrated.
Full Text (PDF)
|