Array Processor
A supercomputer is a very powerful computer that includes architecture,
resources & components that gives a huge computing power to the
consumer. A supercomputer also contains a large number
of processors which performs millions or billions of computations each
second. So these computers can perform numerous tasks in a few
seconds. There are three types of supercomputers tightly connected cluster
computers that work together like a single unit. Commodity computers can
connect to low latency & high-bandwidth LANs and finally vector
processing computers which depend on an array processor or vectors. An
array processor is like a CPU that helps in performing mathematical
operations on various data elements. The most famous array processor is
the ILLIAC IV computer which is designed by the Burroughs Corporation.
This article discusses an overview of an array processor – working, types
& applications.
What is Array Processor?
A processor which is used to perform different computations on a huge
array of data is called an array processor. The other terms used for this
processor are vector processors or multiprocessors. This processor
performs only single instruction at a time on an array of data. These
processors work with huge data sets to execute computations. So, they are
mainly used for enhancing the performance of computers.
Array Processor Architecture
An array processor includes a number of ALUs (Arithmetic Logic Units)
which allows all the array elements to be processed together. Each ALU in
the processor is provided with local memory which is known as a
Processing Element or PE. The architecture of this processor is shown
below. By using this processor, a single instruction is issued through a
control unit & that instruction is simply applied to a number of data sets
simultaneously. By using a single instruction, a similar operation is
performed on an array of data which makes it suitable for vector
computations.
The array processing architecture is known as a 2-dimensional array or
matrix. This architecture is implemented by the two-dimensional processor.
In this processor, the CPU issues a single instruction & after that, it is
applied to a no. of data simultaneously. This architecture mainly depends
on the fact that all data sets work on similar instructions, however, if these
data sets are reliant on each other, it is not achievable to apply parallel
processing. Thus these processors contribute efficiently & enhance the
processing speed as compared to the whole instructions.
Working of Array Processor
An array processor has an architecture mainly designed for processing
arrays of numbers. This processor architecture contains a number of
processors that works simultaneously, each handling one array element, so
that a single operation is applied to all the array elements in parallel. To get
the same effect within a conventional processor, the operation should be
applied to every array element sequentially and much more slowly.
This processor is a self-contained unit connected to the main computer
through an internal bus or an I/O port. This processor increases the overall
speed of instruction processing. These processors operate asynchronously
from the host CPU to improve the overall system capacity. This processor
is a very powerful tool that handles troubles with a high level of parallelism.
Types of Array Processor
There are two types of array processor like; attached and SIMD which is
discussed below.
Attached Array Processor: The auxiliary processor like the attached
array processor is shown below. This processor is simply connected to a
computer for enhancing the performance of a machine within numerical
computational tasks. This processor is connected to the General Purpose
Computer through an I/O interface and a local memory interface where
both the memories like the main & the local are connected. This processor
achieves high performance through parallel processing by multiple
functional units.
SIMD Array Processor: SIMD (‘Single Instruction and Multiple Data
Stream’) processors are computers with several processing units which
operate in parallel. These processing units perform the same operation in
synchronizing under the supervision of the common control unit (CCU). The
SIMD processor includes a set of identical PEs (processing elements)
where each PES has a local memory.
This processor includes a master control unit and main memory. The
master control unit in the processor controls the operation of the processing
elements. And also, decodes the instruction & determines how the
instruction is executed. So, if the instruction is program control or scalar
then it is executed directly in the master control unit. Main memory is
mainly used to store the program while every processing unit uses
operands that are stored in its local memory.
Advantages
The advantages of an array processor include the following.
Array processors improve the whole instruction processing speed.
These processors run asynchronously from the host CPU the overall
capacity of the system is improved. These processors include their own
local memory that provides extra memory to systems. So this is an
important consideration for the systems through a limited address space
or physical memory.
These processors simply perform computations on a huge array of data.
These are extremely powerful tools that help in handling troubles with a
high amount of parallelism.
This processor includes a number of ALUs that permits all the array
elements to be processed simultaneously.
Generally, the I/O devices of this processor-array system are very
efficient in supplying the required data to the memory directly.
The main advantage of using this processor with a range of sensors is a
slighter footprint.
Applications
The applications of array processors include the following.
This processor is used in medical and astronomy applications.
These are very helpful in speech improvement.
These are used in sonar and radar systems.
These are applicable in anti-jamming, seismic exploration & wireless
communication.
This processor is connected to a general-purpose computer to improve
the computer’s performance within arithmetic computational tasks. So it
attains high performance through parallel processing by several
functional units.