University of Twente Student Theses


TrackScorer : Skyrmion Logic-In-Memory Accelerator for Document Ranking

Noorlander, M.S. (2024) TrackScorer : Skyrmion Logic-In-Memory Accelerator for Document Ranking.

[img] PDF
Abstract:Skyrmion racetrack memories have shown to have lower leakage power and higher density compared to traditional memories like DRAM/SRAM. The cost of these memories comes with the penalty of time to shift data to an access port. Logic-In-Memory can be used to perform operations on data in memory without first transferring the data to a CPU. In this paper, the popular document ranking algorithm Quickscorer is mapped onto Skyrmion racetrack memory to use the advantages of this new memory technology. This mapping uses a Logic-In-Memory accelerator to improve performance on Skyrmion racetrack memories. The results show a decrease in the number of read and write operations that are performed, and in some cases show a decrease in the time spent shifting during the document ranking process.
Item Type:Essay (Master)
Faculty:EEMCS: Electrical Engineering, Mathematics and Computer Science
Subject:53 electrotechnology, 54 computer science
Programme:Embedded Systems MSc (60331)
Link to this item:
Export this item as:BibTeX
HTML Citation
Reference Manager


Repository Staff Only: item control page