Computer Architecture and System Programming

This document is for Coventry University students for their own use in completing their
assessed work for this module and should not be passed to third parties or posted on any
website. Any infringements of this rule should be reported to
[email protected].
Faculty of Engineering, Environment and Computing
7090CEM Computer Architecture and System
Programming
Resit/Deferral Assignment Brief 2022/23

Module Title: Computer Architecture and
System Programming
Individual Cohort
2223_MAYSEP
(Resit)
Module Code:
7090CEM
Coursework Title
Coursework
Hand out date:
w/c 31/10/2022
Lecturer
Dr Dianabasi Nkantah
Due date: 6pm 28th
November 2022
Estimated Time (hrs): 50 hours
Word Limit*:
2000
Coursework type: Assignment % of Module Mark
66.67%
Submission arrangement online via Aula: Submission link on Aula
File types and method of recording:
‘.pdf’, ‘.docx’, ‘.doc’
Mark and Feedback date: 13th December 2022
Mark and Feedback method: Feedback file via Aula

 

Module Learning Outcomes Assessed:
1. Evaluate alternative systems software and machine performance features in order to select
appropriate tools for technical and operational requirements.
2. Critically review a wide range of system architecture for applications and user requirements whilst
considering the constraints of performance, cost, security and usability.
3. Examine different architectural styles to determine the suitable applications and measure their
effectiveness in meeting performance and other critical requirements.
4. Demonstrate the ability to design and implement a computer system based on parallel architecture
solutions.
5. Discuss the advance of technology and trends to meet the increasing demands of new application
requirements.
Task and Mark distribution:
Conduct a literature review on Domain-specific Architectures (DSAs). These are currently used in industry
to achieve high computing performance in an efficient manner. Your literature review should include a
discussion of a typical structure of DSAs, and their design issues. The review should also consider typical
architectural features used to enhance the energy-efficiency, dependability, performance, security, and
cost of DSAs, as well as typical application domains of DSAs. The review should include a discussion on
how various parallelism techniques are exploited in DSAs. The trend of development of DSAs and a
comparison of DSA accelerators with standard CPUs and GPUs should also be discussed.
Discuss the design features of an instruction set that could be used in a DSA system. This should include
a discussion of the challenges faced in the choice of instruction sets for such systems.
You are expected to use peer-reviewed literature sources.

This document is for Coventry University students for their own use in completing their
assessed work for this module and should not be passed to third parties or posted on any
website. Any infringements of this rule should be reported to
[email protected].

Assignment Deliverables
o Literature Review [75 marks]
o Discussion of the design features of an Instruction Set [15 marks]
Report Presentation will be assessed [10 marks]
Notes:
1. You are expected to use the
APA referencing format. For support and advice on how this
students can contact
Centre for Academic Writing (CAW).
2. Please notify your registry course support team and module leader for disability support.
3. Any student requiring an extension or deferral should follow the university process as outlined
here.
4. The University cannot take responsibility for any coursework lost or corrupted on disks, laptops
or personal computer. Students should therefore regularly back-up any work and are advised to
save it on the University system.
5. If there are technical or performance issues that prevent students submitting coursework
through the online coursework submission system on the day of a coursework deadline, an
appropriate extension to the coursework submission deadline will be agreed. This extension
will normally be 24 hours or the next working day if the deadline falls on a Friday or over the
weekend period. This will be communicated via email and as an Aula announcement.
6. Assignments that are more than 10% over the word limit will result in a deduction of 10% of
the mark i.e. a mark of 60% will lead to a reduction of 6% to 54%. The word limit includes
quotations, but excludes the bibliography, reference list and tables.

A report (not more than 2000 words) should be submitted online (via Aula). The report should
include:
Mark allocation guidelines to students

0-39 40-49 50-59 60-69 70+ 80+
Work mainly
incomplete
and /or
weaknesses in
most areas
Most elements
completed;
weaknesses
outweigh
strengths
Most elements
are strong,
minor
weaknesses
Strengths in all
elements
Most work
exceeds the
standard
expected
All work
substantially
exceeds the
standard
expected

This document is for Coventry University students for their own use in completing their assessed work for this module and should not be passed to third
parties or posted on any website. Any infringements of this rule should be reported to
[email protected].
Marking Rubric

GRADE Literature Review on Warehouse-scale Computers Discussion of Design Features of
Instruction Set Architecture
Presentation
Distinction
90-100
Exceptional in-depth critical analysis of the different aspects of design of DSAs. Appropriate recommendations made
towards the achievement of better DSA system design/performance.
Typical structure of DSAs have been excellently described.
Outstanding discussion on the design trade-offs with a focus on energy-efficiency, dependability, performance,
security, and cost.
Discussion covers typical application domains of DSAs.
Outstanding discussion on how various parallelism techniques are exploited in DSAs, with good examples.
Outstanding discussion on the trend of development of DSAs, with insightful prediction of the future trend of DSAs.
Outstanding comparison of DSA accelerators with standard CPUs and GPUs.
Use of a wide range of relevant and up-to-date peer-reviewed, journal/conference articles in research.
Well referenced report, with in-text citations.
Report may be strongly considered for publication.
Excellent detailed discussion of the
design features of the chosen
Instruction Set.
Discussion focuses on operation
repertoire, data types, instruction
format, registers and addressing
modes.
The challenges faced in the choice of
instruction sets for DSA systems have
been excellently and elaborately
discussed.
Recommendations made on suitable
application domains for the ISA.
Exceptional presentation
with cover page, table of
content, and page
numbers.
Tables and figures are
properly labelled.
Exceptional
communication and
expression expressed
throughout the report.
Distinction
80-89
Outstanding in-depth critical analysis of the different aspects of design of DSAs. Appropriate recommendations made
towards the achievement of better DSA system design/performance.
Typical structure of DSAs have been excellently described.
Excellent discussion on the design trade-offs with a focus on energy-efficiency, dependability, performance, security,
and cost.
Discussion covers typical application domains of DSAs.
Excellent discussion on how various parallelism techniques are exploited in DSAs, with good examples.
Excellent discussion on the trend of development of DSAs, with insightful prediction of the future trend of DSAs.
Excellent comparison of DSA accelerators with standard CPUs and GPUs.
Use of a wide range of relevant and up-to-date peer-reviewed, journal/conference articles in research.
Well referenced report, with in-text citations.
With some amendment, report may be considered for publication.
Very good, detailed comparison of the
design features of the chosen
Instruction Set.
Discussion focuses on operation
repertoire, data types, instruction
format, registers and addressing
modes.
The challenges faced in the choice of
instruction sets for DSA systems have
been very well discussed.
Recommendations made on suitable
application domains for the ISA.
Outstanding presentation
with cover page, table of
content, and page
numbers.
Tables and figures are
properly labelled.
Outstanding
communication and
expression expressed
throughout the report.
Distinction
70-79
Excellent in-depth critical analysis of the different aspects of design of DSAs. Recommendations made towards the
achievement of better DSA system design/performance.
Typical structure of DSAs have been excellently described.
Very good discussion on the design trade-offs with a focus on energy-efficiency, dependability, performance,
security, and cost.
Discussion covers typical application domains of DSAs.
Very good discussion on how various parallelism techniques are exploited in DSAs, with good examples.
Very good discussion on the trend of development of DSAs, with insightful prediction of the future trend of DSAs.
Very good comparison of DSA accelerators with standard CPUs and GPUs.
Use of relevant and up-to-date peer-reviewed, journal/conference articles in research.
Well referenced report, with in-text citations.
Good, detailed discussion of the
design features of the chosen
Instruction Sets.
Discussion focuses on operation
repertoire, data types, instruction
format, registers and addressing
modes.
The challenges faced in the choice of
instruction sets for DSA systems have
been well discussed.
Recommendations made on suitable
application domains for the ISA.
Excellent presentation with
cover page, table of
content, and page
numbers.
Tables and figures are
properly labelled.
Excellent communication
and expression expressed
throughout the report.

This document is for Coventry University students for their own use in completing their assessed work for this module and should not be passed to third
parties or posted on any website. Any infringements of this rule should be reported to
[email protected].

Merit
60-69
Very good critical analysis of the different aspects of design of DSAs, with recommendations.
Typical structure of DSAs have been very well described.
Good discussion on the design trade-offs with a focus on energy-efficiency, dependability, performance, security,
and cost.
Discussion covers typical application domains of DSAs.
Good discussion on how various parallelism techniques are exploited in DSAs, with examples.
Good discussion on the trend of development of DSAs, with an attempt at predicting the future trend of DSAs.
Good comparison of DSA accelerators with standard CPUs and GPUs.
Use of relevant peer-reviewed, journal/conference articles in research.
Well referenced report, with in-text citations.
Good discussion of the design
features of the chosen Instruction Set.
Discussion focuses on some of
operation repertoire, data types,
instruction format, registers and
addressing modes.
The challenges faced in the choice of
instruction sets for DSA systems have
been discussed.
Recommendations made on suitable
application domains for the ISA.
Very good presentation
with cover page, table of
content, and page
numbers.
Tables and figures may
not be properly labelled.
Very good communication
and expression expressed
throughout the report.
Pass
50-59
Good critical analysis of the different aspects of design of DSAs.
Typical structure of DSAs have been described.
Discussion on the design trade-offs with a focus on some of energy-efficiency, dependability, performance, security,
or cost.
Discussion covers typical application domains of DSAs.
Attempt at discussing how parallelism techniques are exploited in WSCs.
Discussion on the trend of development of DSAs.
Good attempt at comparing DSA accelerators with standard CPUs and GPUs.
Use of peer-reviewed, journal/conference articles in research.
Well referenced report, with in-text citations.
Discussion of the design features of
the chosen Instruction Set.
Discussion focuses on some of
operation repertoire, data types,
instruction format, registers and
addressing modes.
An attempt has been made at
discussing the challenges faced in the
choice of instruction sets for DSA
systems.
Good presentation with
only one of the following
missing: cover page, table
of content, and page
numbers.
Tables and figures may
not be properly labelled.
Pass
40-49
Fairly good analysis of the different aspects of design of DSAs.
Typical structure of DSAs have been outlined.
Attempt at discussing the design trade-offs with a focus on any of energy-efficiency, dependability, performance,
security, or cost.
Attempt at discussing the trend of development of DSAs.
Referenced report.
Fairly good attempt at discussing
design features the chosen Instruction
Set.
Attempt to base discussion on one or
two of operation repertoire, data types,
instruction format, registers and
addressing modes.
Fairly good presentation
with some of the following
missing: cover page, table
of content, and page
numbers.
Tables and figures may
not be properly labelled.
Fail
<40
Very little or no evidence of research work. Little to no attempt made at discussing
the chosen instruction set.
No attempt made at a
decent presentation.
Late
submission
0 0 0
Marks
Awarded

This document is for Coventry University students for their own use in completing their
assessed work for this module and should not be passed to third parties or posted on any
website. Any infringements of this rule should be reported to
[email protected].