Theme

Language

Global EN
Sweden ENSV
India EN

Master Thesis: FFT Instruction in DSP

Technology, Data & Digital · Software & Web Development · Embedded Systems · Software Engineering

In short

This Master Thesis project investigates Fast Fourier Transform (FFT) algorithms and implementation strategies for a vector SIMD DSP. You will analyze performance, optimize code in assembler, and potentially propose new hardware instructions, combining software optimization with hardware/software co-design aspects.

Responsibilities

  • 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.

Requirements

  • 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.

Benefits

  • Outstanding opportunity to use your skills and imagination to push the boundaries of what's possible.
  • Opportunity to build solutions never seen before to some of the world's toughest problems.
  • Will be challenged, but not alone.
  • Joining a team of diverse innovators.
  • Opportunity to go beyond the status quo to craft what comes next.

Skills

AssemblerFFT algorithmsDSPSIMDComputer architectureEmbedded systemsSignal processingHardware modeling
#FFT#DSP#SIMD#Assembler#Thesis#Master Thesis#Computer Architecture#Signal Processing#Embedded Systems
Ericsson Logo

About Ericsson

Pioneering technology for connecting billions of people worldwide

Our purpose \nTo create connections that make the unimaginable possible.\n\nOur vision\nA world where limitless connectivity improves lives, redefines business and pioneers a sustainable future.\n\nOur values\nPerseverance, professionalism, respect and integrity.\n\nThe future is a place for purpose & vision – ours are clear, and we invite partners, customers and consumers to join us in our journey. \n\nFor a brighter future. For all. Let's #ImaginePossible

Ericsson Logo

Company

Ericsson

Job Posted

3 days ago

Employment Type

Internship

Work mode

On Site

Experience Level

Entry

Locations

Stockholm, Sweden

Qualification

Master

Applicants

Be an early applicant