University of Twente Student Theses
Evaluating Performance and Energy Efficiency of the Hybrid Memory Cube Technology
Brink, A.B. van den (2017) Evaluating Performance and Energy Efficiency of the Hybrid Memory Cube Technology.
PDF
7MB |
Abstract: | Embedded systems process fast and complex algorithms these days. Within these embedded systems, memory becomes a major part. Large (amount of bytes), small (in terms of area), fast and energy efficient memories are needed not only in battery operated devices but also in High Performance Computing systems to reduce the power consumption of the total system. Many systems implement their algorithm in software, usually implying a sequential execution. The more complex the algorithm, the more instructions are executed and therefore the execution time and power consumption increases accordingly. Parallel execution can be used to compensate for the increase in execution time introduced by the sequential software. For parallel execution of regular, structured algorithms, hardware solutions, like an FPGA, can be used. Only the physical boundaries of FPGAs limits the amount of parallelism. |
Item Type: | Essay (Master) |
Faculty: | EEMCS: Electrical Engineering, Mathematics and Computer Science |
Subject: | 53 electrotechnology |
Programme: | Embedded Systems MSc (60331) |
Link to this item: | https://purl.utwente.nl/essays/73126 |
Export this item as: | BibTeX EndNote HTML Citation Reference Manager |
Repository Staff Only: item control page