Proposal for a high-performance computer system for a company in a specific application area

Module Learning Outcomes Assessed:

1. Identify and describe a range of architectural features and their operation using a recognised set of terms for machine description.

2. Apply an understanding of the influences and constraints which affect the capability and performance of computer systems (and in particular the requirements placed on the hardware by operating systems and the needs of error control and maintenance) to analyse trade-offs and make design decisions which maximise system performance.

4. Use an awareness of the interaction between specialised architectures and particular application areas to make appropriate selections of computer structures to offer high performance computing, taking into account performance, cost and availability.

5. Apply knowledge of parallel programming models to the use of one such model in designing programs for a real or abstract parallel machine.

A company in one of the application areas listed below needs to replace their computing infrastructure. The company requires a high-performance computer system to cater for their business needs.

• Weather forecasting

• Natural Language Processing

• Image Processing

• Data centre

• Modelling and Simulation

• Materials and Manufacturing Industries

• Any other application area discussed with the module leader Propose a complete and working computer system for the company. This proposal should include a breakdown of the main components of the system.

Justify the main components of the proposed system considering their performance, cost, and availability. You should provide parts identification for all componentsused. Discuss the parallel processing techniques used in enhancing the performance of these components, including any instruction-level parallelism, data level parallelism and thread-level parallelism concepts used. Indicate details of the Instruction Set Architecture used in this system.

Discuss the benchmark suite that would be suitable for measuring the performance of the system, compared to similar systems.

• A report should be submitted online (via CUMoodle). The report should include:

o An assembly language code for the implementation of a basic algorithm

• Each student will be asked oral questions over 10 minutes to enable them to demonstrate ownership and understanding of work submitted. [10 marks]

• Report Presentation will be assessed

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.

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 a CUMoodle announcement