2024 · 13 citations · 4 references
EngineeringComputer ScienceHigh-performance ComputingComputer ArchitectureHardware-software Co-designParallel ComputingData ParallelismGraphics Processing Unit ArchitectureHardware AccelerationMulticore Processor DesignParallel ArchitecturesParallel Computer ArchitectureArea EfficiencyMemory BandwidthMulticore ArchitecturesMulticore SystemsPower EfficiencyVector ProcessingVector Processing UnitsVector Processors
Vector processors have re-emerged in high-performance computing and flagship mobile SoC designs for their improved programmability, appealing power efficiency over multicore processors and area efficiency over GPUs [1]. For modern data-parallel tasks (ML, DSP, vision), vector processors can approach the efficiency of custom designs, while maintaining the flexibility of CPUs and GPUs. However, there are still limitations to the widespread adoption of vector architectures in general-purpose systems: the expensive on-chip data movement, the high off-chip memory bandwidth requirement and the Vector Register File (VRF) complexity.
4
Matheus Cavalcante, Fabian Schuiki, Florian Zaruba et al. · Archivio istituzionale della ricerca (Alma Mater Studiorum Università di Bologna) · 2020 · 131 citations · Full text