The demands on the signal processing in high-end sensor systems are rising rapidly. The systems are based on digital antenna arrays with thousands of antenna elements, and they operate using advanced adaptive signal processing algorithms. Since the processing typically is embedded, with the constraints that follow, high processing efficiency is important.
The competition on the future markets will require the ability to quickly innovate and develop new sensor functions. There is therefore also a focus put on efficient application development, i.e., engineering efficiency. This is emphasized by the fact that many sensor systems are low-volume products, where the development cost has a great impact on the total product cost. We want to find new application development methods and tools that improve the development of our high-
performance embedded applications.
Description of the master thesis
The workload of data-driven applications, such as sensor signal processing, is increasing exponentially. The applications will require diverse hardware computing architectures, where different components are specialized for different types of workloads. Examples are GPUs, AI accelerators and FPGAs. However, creating software that takes advantage of such diverse systems could be a challenge. Different languages and tools typically have to be used, and the possibility for code resuse is limited.
We want to model the applications in a unified way, without considering specific target processor architectures. This thesis investigates Intel oneAPI. It is an open standard for an application programming interface that is intended to be used across different processor architectures. The Intel DevCloud will be used as a sandbox to learn about oneAPI and the cross-architecture language DPC++. Available architectures include CPU Xeon, GPU Iris and FPGA Stratix.
A scalable multi-channel signal processing benchmark will be used as a use case. The benchmark includes workloads of different types.
The expected results include answers on:
- The main purposes and characteristics of the standard
- The level of maturity and adoption of the standard
- Intel oneAPI compared with similar standards. DPC++ compared with CUDA, OpenCL and other languages
- Execution and engineering efficiency
- Level of help in the choice of proper target architectures for specific workload types and sizes
- Possibility to create sustainable functions with performance that can improve with the general processor development
We are looking for 1-2 master degree students with an interest in:
- C/C++, CUDA, OpenCL
- Parallel computing
- Signal processing
You are at the end of your master’s degree in Computer engineering, Electrical engineering, or equivalent, and is eligible for your 30 HP degree project.
This position requires that you pass a security vetting based on the current regulations around/of security protection. For positions requiring security clearance additional obligations on citizenship may apply.
What you will be a part of
You will collaborate with experienced engineers and professionals in an environment that fosters career development and personal growth. You will be part of a unit working with Software design for radar systems.
Surveillance, a Business Area within Saab, is a world-leading supplier of systems for detection of threats and self-protection. Business Unit Radar Solutions is responsible for Radar in airborne-, surface- and naval systems.
If you aspire to help create and innovate whilst developing yourself in a challenging team setting, Saab may well have the perfect conditions for you to grow. We pride ourselves on a nurturing environment, where everyone is different yet we share the same goal – to help protect people.