ACM Transactions on Reconfigurable Technology and Systems · 2015 · 26 citations · 22 references
EngineeringComputer EngineeringComputer ScienceComputer ArchitectureField-programmable Gate ArraysLow-power DesignAccelerator ArchitectureField-programmable Gate Array ArchitectureFpga ArchitectureGraphics Processing UnitsHardware AccelerationPower OptimizationAcceleratorsApplication-specific Accelerator DesignArchitectural ExplorationComplexityEnergy ConsumptionEnergy-efficient Hardware AccelerationField-programmable Gate Array AcceleratorsField-programmable Gate Arrays (Fpgas)
The increasing usage of hardware accelerators such as Field-Programmable Gate Arrays (FPGAs) and Graphics Processing Units (GPUs) has significantly increased application design complexity. Such complexity results from a larger design space created by numerous combinations of accelerators, algorithms, and hw/sw partitions. Exploration of this increased design space is critical due to widely varying performance and energy consumption for each accelerator when used for different application domains and different use cases. To address this problem, numerous studies have evaluated specific applications across different architectures. In this article, we analyze an important domain of applications, referred to as sliding-window applications , implemented on FPGAs, GPUs, and multicore CPUs. For each device, we present optimization strategies and analyze use cases where each device is most effective. The results show that, for large input sizes, FPGAs can achieve speedups of up to 5.6× and 58× compared to GPUs and multicore CPUs, respectively, while also using up to an order of magnitude less energy. For small input sizes and applications with frequency-domain algorithms, GPUs generally provide the best performance and energy.
22
The Design and Implementation of FFTW3
Matteo Frigo, Steven G. Johnson · Proceedings of the IEEE · 2005 · 5.2K citations
Scalable Parallel Programming with CUDA
John Nickolls, Ian Buck, Michael Garland et al. · Queue · 2008 · 1.6K citations · Full text
John D. Owens, Michael Houston, David Luebke et al. · Proceedings of the IEEE · 2008 · 1.4K citations