机译:KernelHive:基于工作流的新框架,用于使用具有CPU和GPU的集群和工作站进行多层高性能计算
Gdansk University of Technology Department of Computer Architecture Faculty of Electronics Telecommunications and Informatics Gdansk Poland;
Gdansk University of Technology Department of Computer Architecture Faculty of Electronics Telecommunications and Informatics Gdansk Poland;
Gdansk University of Technology Department of Computer Architecture Faculty of Electronics Telecommunications and Informatics Gdansk Poland;
Gdansk University of Technology Department of Computer Architecture Faculty of Electronics Telecommunications and Informatics Gdansk Poland;
high performance computing; GPGPU; cluster computing; multilevel parallelization; heterogeneous system; high level framework;
机译:使用GPU,多核CPU和混合CPU / GPU集群的加速高光谱图像递归分层分段
机译:大型GPU群集上用于长波辐射物理的CPU / GPU计算
机译:多核CPU中SSE和AYX指令的性能分析以及基于FDTD方案的GPU计算的固体和流体振动问题
机译:点亮:基于CPU / GPU集群的高性能海量数据计算框架
机译:异构CPU-GPU计算集群的分层调度和统一访问编程框架
机译:具有多核CPUGPU和MIC的系统上的应用程序性能分析和高效执行:以显微镜图像分析为例
机译:用于密码学中高性能计算的异构Gpu和Cpu集群