2015 · 27 citations · 16 references
ComputingComputer ScienceHigh-performance ComputingComputer GraphicsLow-power DesignReal-time SystemsGraphics Processing Unit ArchitectureGraphics Processing UnitsKernel ArchitectureKernel DesignPerformance TuningPower ManagementAuto-tuningEnergy ConsumptionGpu ArchitectureGpu Performance ProfilingGpu ProfilingKernel OptimizationKernel ProfilingMemory Bandwidth
Prompted by their very high computational capabilities and memory bandwidth, Graphics Processing Units (GPUs) are already widely used to accelerate the execution of many scientific applications. However, programmers are still required to have a very detailed knowledge of the GPU internal architecture when tuning the kernels, in order to improve either performance or energy-efficiency. Moreover, different GPU devices have different characteristics, moving a kernel to a different GPU typically requires re-tuning the kernel execution, in order to efficiently exploit the underlying hardware. The procedure proposed in this work is based on real-time kernel profiling and GPU monitoring and it automatically tunes parameters from several concurrent kernels to maximize the performance or minimize the energy consumption. Experimental results on NVIDIA GPU devices with up to 4 concurrent kernels show that the proposed solution achieves near optimal configurations. Furthermore, significant energy savings can be achieved by using the proposed energy-efficiency auto-tuning procedure.
16
Rodinia: A benchmark suite for heterogeneous computing
Shuai Che, Michael Boyer, Jiayuan Meng et al. · 2009 · 3K citations
Analyzing CUDA workloads using a detailed GPU simulator
Ali Bakhoda, George L. Yuan, Wilson Wai Lun Fung et al. · 2009 · 1.7K citations
Dark silicon and the end of multicore scaling
Hadi Esmaeilzadeh, Emily Blem, Renée St. Amant et al. · 2011 · 1.5K citations
Jingwen Leng, Tayler Hetherington, Ahmed ElTantawy et al. · 2013 · 498 citations
An integrated GPU power and performance model
Sunpyo Hong, Hyesoon Kim · 2010 · 477 citations