The Parallella includes a low power dual core ARM A9 processor on a Zynq-7000 chip from Xilinx and runs several of the popular Linux distributions, including Ubuntu. The Zynq-7000 SoC also has a simple FPGA and DSPs.
The unique Epiphany co-processor chips consists of a scalable array of simple RISC processors programmable in bare metal C/C++ or in a parallel programming frameworks like OpenCL, MPI, and OpenMP. The mesh of independent cores are connected together with a fast on chip network within a distributed shared memory architecture.
In this master thesis, the student will write some simple multimedia workloads and optimize them for the Parallella system. The same multimedia workloads will also be written and optimized for GPUs using either the Nvidia CUDA framework or OpenCL. The students will then measure and compare power consumption on the two architectures and discuss the pros and cons of the different architectures.
- Knowledge outcome: Optimization, performance analysis, energy measurements, programming heterogeneous architectures
- Knowledge required: Low-level programming (C)