IEEE Circuits and Systems Magazine - Q1 2021 - 8

Emerging Technologies
Energy (J/op)
-12
5

ntum

Qua
al

Optic

Cost (US$/Gate)

-13.8

y
gicall
Biolo ed
ir
Insp

-15.6
RSFQ

-5

-17.4
S
Si CMO

-10

Plastic

-19.2

-15
-20

NEMS

-21

Molecular

-15
Sw
itc
hin -10
gT
im
e

(s)

-5
0 -10

-8

-4
-6
Size (m)

-2

-22.8

-24.6

Figure 1. Emerging technologies and CMOS speed, size, cost, and switching energy (scales are logarithmic) [7].

for example, quantum computing. While it is challenging to build general purpose computing engines based
on these technologies, they are much faster on certain
specific tasks. A last example is the integrated optical
technology, which is based on having small optical cavities that change their properties to either store or emit
photons-a zero or a one. It is a challenging approach,
both from the fan-out and cost point of view. As will
be seen, computing-in-the-network circuits can be designed with integrated photonics switches.
These emergent technologies will become more and
more relevant as the end of the CMOS era approaches [8]. Nevertheless, for the time being, there is no
technology better than CMOS, as it provides a good
balance between energy consumption, cost, speed
and scalability, as shown in Fig. 1. Yet, better solutions
can be identified in Fig. 1 along every individual axis.
However, to design and implement processing systems
based on these new technologies and devices, different
solutions have to be found at various levels: from the
circuits to the data representation and architectures,
as depicted in Fig. 2. For the conventional scaled CMOS
technology, the layers have been quite well established,
and the characteristics were successfully explored from
the material layer, silicon, up to the topmost layer, mul8

IEEE CIRCUITS AND SYSTEMS MAGAZINE

ticore architectures. Moreover, the conventional binary
system has been dominant at the data representation
layer. However, when considering emergent technologies or new architectures for designing these systems,
data representation must also be reconsidered to properly adapt each system to the features of both the bottom and top layers. Data representation and the related
computer arithmetic are the motivation behind this
survey, which looks beyond the CMOS technology and
conventional systems.
B. Structure of the Survey
This survey analyzes the confluence of emergent technologies, nonconventional computer arithmetic, innovative computing paradigms and new applications. Similar to a jigsaw puzzle, although these pieces exist by
themselves, it is only by connecting them in the right
way that the whole picture can be derived and, in this
particular case, the way to design efficient systems
can be determined. Fig. 3 depicts the tight interconnections and dependencies of all these aspects in a matrix
representation. In addition, this figure shows how these
very important topics are addressed in this paper, highlighting the fact that nonconventional arithmetic exposes the characteristics of the underlying technology to
FIRST QUARTER 2021

IEEE Circuits and Systems Magazine - Q1 2021

Table of Contents for the Digital Edition of IEEE Circuits and Systems Magazine - Q1 2021