Master thesis: Coarse-grained reconfigurable arrays (CGRA)
Ericsson ABNy
Sammanfattning
This master's thesis opportunity focuses on coarse-grained reconfigurable arrays (CGRAs) within Ericsson's 6G testbed program in Stockholm, Sweden. The role involves hands-on experience with a pre-commercial CGRA device, implementing baseband kernels and AI workloads, and investigating programming models and architecture characteristics. Candidates will collaborate on shaping research questions based on their experiences with the technology.Det här erbjuder vi
Opportunity to work with cutting-edge technology in a collaborative environment.Access to a pre-commercial CGRA device and tools for hands-on experience.Engagement in a diverse and inclusive team culture.
Ansök senast: Öppet tillsvidare
Publicerad: 2026-09-28
Beskrivning
Join our Team
About this opportunity:
Are you curious about what comes after the CPU? This master's thesis explores coarse-grained reconfigurable arrays (CGRAs), a class of processors where the program is not a sequence of instructions, but a computational graph mapped spatially onto a fabric of compute elements. CGRAs promise high-power efficiency and rapid reconfiguration, which makes them a highly interesting candidate both for the real-time signal processing at the heart of tomorrow's cellular networks and for the AI workloads increasingly embedded in them.
The work is carried out within our 6G testbed program, where we build cellular network prototypes for future standards and evaluate alternative compute platforms for real-time, high-performance computation. You will get hands-on access to a pre-commercial CGRA device with accompanying tools and be among the first to find out what this architecture is really like to program, integrate, and run baseband and AI workloads on. Since the technology is new, the exact research question will be shaped together with you once you have first-hand experience with the architecture and its tools.
What you will do:
• Implement classic baseband kernels and / or AI workloads on the CGRA and verify them against bit-exact reference models
• Investigate the programming model: how a computational-graph target changes development, debugging, testing, and CI compared to a CPU
• Investigate the CPU-CGRA boundary: shared memory, pointer passing, and asynchronous offload primitives
• Characterize the architecture: how DSP and AI kernels map onto the fabric, reconfiguration cost, timing determinism, and power and performance versus a CPU/GPU baseline
The skills you bring:
• Proficiency in C/C++ for embedded systems and comfort with linear algebra
• Interest in computer architecture, compilers, or digital hardware; no prior CGRA knowledge is expected
• Curiosity about signal processing, wireless systems, and machine learning inference; prior experience in these areas is a plus but not required
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: 791381
About this opportunity:
Are you curious about what comes after the CPU? This master's thesis explores coarse-grained reconfigurable arrays (CGRAs), a class of processors where the program is not a sequence of instructions, but a computational graph mapped spatially onto a fabric of compute elements. CGRAs promise high-power efficiency and rapid reconfiguration, which makes them a highly interesting candidate both for the real-time signal processing at the heart of tomorrow's cellular networks and for the AI workloads increasingly embedded in them.
The work is carried out within our 6G testbed program, where we build cellular network prototypes for future standards and evaluate alternative compute platforms for real-time, high-performance computation. You will get hands-on access to a pre-commercial CGRA device with accompanying tools and be among the first to find out what this architecture is really like to program, integrate, and run baseband and AI workloads on. Since the technology is new, the exact research question will be shaped together with you once you have first-hand experience with the architecture and its tools.
What you will do:
• Implement classic baseband kernels and / or AI workloads on the CGRA and verify them against bit-exact reference models
• Investigate the programming model: how a computational-graph target changes development, debugging, testing, and CI compared to a CPU
• Investigate the CPU-CGRA boundary: shared memory, pointer passing, and asynchronous offload primitives
• Characterize the architecture: how DSP and AI kernels map onto the fabric, reconfiguration cost, timing determinism, and power and performance versus a CPU/GPU baseline
The skills you bring:
• Proficiency in C/C++ for embedded systems and comfort with linear algebra
• Interest in computer architecture, compilers, or digital hardware; no prior CGRA knowledge is expected
• Curiosity about signal processing, wireless systems, and machine learning inference; prior experience in these areas is a plus but not required
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: 791381
Ansök till tjänsten
Master thesis: Coarse-grained reconfigurable arrays (CGRA)
Ny
OM FÖRETAGET
Ericsson AB
