Master Thesis: FFT Instruction in DSP
Confirmed on the employer's own hiring board on Oct 28, 2026. First seen by Alion on Oct 20, 2026. Ericsson scores B on the Alion truth index.
Join our Team
About this opportunity
Fast Fourier Transform (FFT) processing is a fundamental building block in many digital communication and signal-processing systems. In a Single Instruction Multiple Data (SIMD) DSP, FFT performance depends on the selected algorithm, data layout, memory-access patterns, numerical representation, and the instructions available in the processor architecture.
In this thesis, you will investigate and compare different FFT algorithms and implementation strategies for a vector SIMD DSP. You will analyze performance, code size, memory behavior, numerical accuracy, and implementation complexity across different FFT variants and execution approaches.
A key objective is to identify opportunities to improve FFT execution through optimized use of the existing vector SIMD instruction set and, where beneficial, propose new hardware instructions. The project combines software optimization, primarily in assembler, with potential hardware/software co-design aspects. Depending on your interests, the thesis can focus more on low-level software development or processor architecture and instruction-set design.
The exact FFT variants, transform sizes, numerical formats, and evaluation criteria will be defined together with the supervisors based on the available DSP environment and thesis scope.
The thesis concludes with a written report and a presentation to Ericsson’s DSP and hardware teams.
What you will do
- Study FFT variants such as mixed-radix, split-radix, and other relevant approaches.
- Analyze and compare FFT implementation strategies for a vector SIMD DSP.
- Map FFT stages, twiddle-factor operations, permutations, and data movement to the existing vector SIMD instruction set.
- Implement and optimize FFT kernels primarily in assembler, utilizing existing processor instructions and built-in accelerators.
- Evaluate alternative data layouts, memory-access patterns, vectorization techniques, and instruction scheduling strategies.
- Benchmark implementations with respect to execution time, code size, memory traffic, numerical accuracy, and implementation complexity.
- Identify performance bottlenecks and limitations of the current instruction set.
- Propose and evaluate new hardware instructions or instruction-set extensions.
- Prototype or model promising instruction extensions and assess their impact on FFT performance.
- Recommend efficient hardware/software implementation strategies based on identified trade-offs.
The skills you bring
- Background in computer architecture, low-level programming, embedded systems, digital signal processing, or a related field.
- Strong interest in programming close to the hardware, including assembler programming, SIMD architectures, instruction scheduling, and performance optimization.
- Understanding of FFT algorithms, numerical methods, and signal-processing fundamentals.
- Interest in processor architecture, instruction-set design, hardware/software co-design, or hardware modelling.
- Analytical problem-solving skills and the ability to evaluate complex technical trade-offs.
- Curiosity about how algorithms, software implementations, and hardware architectures interact to influence system performance.
- Ability to work independently and communicate technical findings in both written and verbal form.
Why join Ericsson? At Ericsson, you´ll have an outstanding opportunity. The chance to use your skills and imagination to push the boundaries of what´s possible. To build solutions never seen before to some of the world’s toughest problems. You´ll be challenged, but you won’t be alone. You´ll be joining a team of diverse innovators, all driven to go beyond the status quo to craft what comes next.
What happens once you apply?Click Here to find all you need to know about what our typical hiring process looks like.Encouraging a diverse and inclusive organization is core to our values at Ericsson, that's why we champion it in everything we do. We truly believe that by collaborating with people with different experiences we drive innovation, which is essential for our future growth. We encourage people from all backgrounds to apply and realize their full potential as part of our Ericsson team. Ericsson is proud to be an Equal Opportunity Employer. learn more.
Primary country and city: Sweden (SE) || Stockholm
Req ID: 793104