The convolution operation is a powerful tool which is widely used in many disciplines.Lately is has seen much use in the area of computer vision, particularly with convolutionalneural networks. For these use cases, convolutions need to be run repeatedly many timeswhich necessitates specialized hardware. Our work empirically investigates the efficiencyof some of the most prominent convolution methods used, such as the Fast FourierTransform and the Winograd method, and compares these to a baseline convolutionimplementation. These comparisons are made in both one and two dimensions, and forseveral different floating point data types.
| Identifer | oai:union.ndltd.org:UPSALLA1/oai:DiVA.org:kth-330781 |
| Date | January 2023 |
| Creators | Wallén Kiessling, Alexander, Svalstedt, Viktor |
| Publisher | KTH, Skolan för teknikvetenskap (SCI) |
| Source Sets | DiVA Archive at Upsalla University |
| Language | English |
| Detected Language | English |
| Type | Student thesis, info:eu-repo/semantics/bachelorThesis, text |
| Format | application/pdf |
| Rights | info:eu-repo/semantics/openAccess |
| Relation | TRITA-SCI-GRU ; 2023:130 |
Page generated in 0.0019 seconds