practical implementation of Embedded Automaton is realized by using a matured
high-level behavioral synthesis tool called CyberWorkBench (CWB) [6–8], which
can handle high level programming language like ANSI-C and SystemC. It is
discussed that although MCUs are suitable for many IoT applications, FPGAs and
DRPs using atomic switches and high-level behavioral synthesis technology are
powerful alternatives for embedded system design.
We discuss a suitable processor element architecture to exploit atomic switches. It
is an extension of Flexible Reliability Reconfigurable Array (FRRA) [3, 4], and we
call it Generic Processor element (GPE) architecture. The necessity of employing
non-stored program architecture is deduced from considerations of the characteristics of processors required for embedded system applications. The requirements for
high speed response and low power consumption are essential factors that call for
non-stored program architecture—a liberation from the performance bottleneck of
stored program architecture. The GPE architecture includes the higher design levels
of hierarchy that accommodate functions of higher abstraction like dependability in
addition to processor elements (PEs) design in the bottom level of design hierarchy
that realizes the same high speed and low power consumption as FPGA does.
2 Design Requirements for Edge Computing of IoT
Applications in Space
The Internet of Things (IoT) has been envisioned as a fundamental infrastructure that
will bring about useful information and knowledge resulting in efficiency and
growth in industry and improved comfort and safety in human life. Everything is
to be connected through Machine to Machine (M2M) network anytime and anywhere to realize the IoT framework. Wide range of information is collected and
accumulated in a system using embedded processors as shown in Fig. 1, which will
result in accumulating, sharing and using various kinds of know-how and social
knowledge [1].
Sensors, networks, information technology (IT), and robotics are distinguished as
key technology elements to make IoT a practical knowledge framework. IoT can be
used for supporting so-called lifeline as energy supply, water works, traffic control,
logistics, broadcasting, and telecommunication. Namely, IoT is used for constructing
social infrastructures such as roads, airports, railways, power plants, factories, etc.
Dependability is a mandatory requirement for social infrastructures, and we discuss
the dependability requirement through the consideration about space systems
applications.
This chapter exemplifies the IoT in space systems and highlights the requirements
for embedded processors used in sensor nodes for IoT applications. Space systems,
such as artificial satellites, are identified as sensor nodes and communication relay
nodes among IoT applications. However, the node size and complexity might be
different from those of nodes for environment monitoring, traffic monitoring, home
Atomic Switch FPGA: Application for IoT Sensing Systems in Space
35
high-level behavioral synthesis tool called CyberWorkBench (CWB) [6–8], which
can handle high level programming language like ANSI-C and SystemC. It is
discussed that although MCUs are suitable for many IoT applications, FPGAs and
DRPs using atomic switches and high-level behavioral synthesis technology are
powerful alternatives for embedded system design.
We discuss a suitable processor element architecture to exploit atomic switches. It
is an extension of Flexible Reliability Reconfigurable Array (FRRA) [3, 4], and we
call it Generic Processor element (GPE) architecture. The necessity of employing
non-stored program architecture is deduced from considerations of the characteristics of processors required for embedded system applications. The requirements for
high speed response and low power consumption are essential factors that call for
non-stored program architecture—a liberation from the performance bottleneck of
stored program architecture. The GPE architecture includes the higher design levels
of hierarchy that accommodate functions of higher abstraction like dependability in
addition to processor elements (PEs) design in the bottom level of design hierarchy
that realizes the same high speed and low power consumption as FPGA does.
2 Design Requirements for Edge Computing of IoT
Applications in Space
The Internet of Things (IoT) has been envisioned as a fundamental infrastructure that
will bring about useful information and knowledge resulting in efficiency and
growth in industry and improved comfort and safety in human life. Everything is
to be connected through Machine to Machine (M2M) network anytime and anywhere to realize the IoT framework. Wide range of information is collected and
accumulated in a system using embedded processors as shown in Fig. 1, which will
result in accumulating, sharing and using various kinds of know-how and social
knowledge [1].
Sensors, networks, information technology (IT), and robotics are distinguished as
key technology elements to make IoT a practical knowledge framework. IoT can be
used for supporting so-called lifeline as energy supply, water works, traffic control,
logistics, broadcasting, and telecommunication. Namely, IoT is used for constructing
social infrastructures such as roads, airports, railways, power plants, factories, etc.
Dependability is a mandatory requirement for social infrastructures, and we discuss
the dependability requirement through the consideration about space systems
applications.
This chapter exemplifies the IoT in space systems and highlights the requirements
for embedded processors used in sensor nodes for IoT applications. Space systems,
such as artificial satellites, are identified as sensor nodes and communication relay
nodes among IoT applications. However, the node size and complexity might be
different from those of nodes for environment monitoring, traffic monitoring, home
Atomic Switch FPGA: Application for IoT Sensing Systems in Space
35