Master Thesis: Digital Compute-in-Memory Accelerator for Radio Access Network Workloads
Join our Team
About this opportunity:
Radio access networks (RAN) require high-throughput, low-latency, and energy-efficient processing. By performing selected operations close to where data are stored, digital compute-in-memory (CIM) may reduce data movement, exploit parallelism, and improve throughput and energy efficiency while maintaining digitally controlled numerical precision.
However, area, peripheral-circuit overhead, coefficient updates, partial-sum accumulation, control complexity, and potentially low memory utilisation may offset these benefits. This thesis will study the underlying trade-offs by comparing digital CIM with a conventional accelerator for a selected RAN workload.
The project will design and evaluate a digital CIM architecture and determine whether it offers a measurable advantage over a conventional accelerator. The evaluation will provide a quantitative comparison using consistent assumptions for precision, workload, throughput, bandwidth, and implementation technology.
The work is expected to start in January or February 2027 and is proposed for one or two students for a duration of six months. The location is Ericsson Research in Stockholm (Kista), Sweden. Please submit your application in English as soon as possible, as candidate selection is ongoing.
What you will do:
Select a representative RAN workload and reference algorithm, define performance, precision, and signal-quality requirements, and model a conventional MAC, vector, or systolic accelerator as the baseline.
Design a parameterised digital CIM architecture with dataflows for complex-valued linear algebra.
Develop a functional model and, where feasible, an RTL or FPGA prototype using software modelling, RTL simulation, FPGA measurements, and technology-based estimation.
Compare the architectures in terms of throughput, latency, area, energy, and resource utilisation.
Assess scalability, quantisation effects, and output accuracy across different antenna counts.
Identify the conditions under which the benefits of digital CIM justify its additional overheads.
Develop reproducible evaluations and critically compare alternative architectures.
The skills you bring:
You are pursuing a Master's degree in Electrical Engineering, Computer Engineering, Embedded Systems, Wireless Communications, Computer Architecture, VLSI or Digital Integrated-Circuit Design, Signal Processing, or a related field.
You are comfortable working across algorithm, system-architecture, and hardware-modelling levels.
You have an interest in digital signal processing and wireless communication systems.
You have strong analytical and problem-solving skills.
You have good technical writing and communication skills.
The following knowledge or experience is considered a plus:
FPGA or RTL design using Verilog or SystemVerilog.
Python, MATLAB, or comparable modelling environments.
Fixed-point arithmetic, quantisation, and numerical-accuracy analysis.
CIM architectures, computer architecture, and dataflow optimisation.
Hardware acceleration, energy modelling, and performance evaluation.
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: 791039