后天习得
发表于 2025-3-30 08:54:22
http://reply.papertrans.cn/89/8818/881800/881800_51.png
CRUE
发表于 2025-3-30 16:07:06
Julian Martin Kunkel,Thomas Ludwig,Hans Werner MeuUp to date results.Fast track conference proceedings.State of the art research
GOUGE
发表于 2025-3-30 16:57:24
Lecture Notes in Computer Sciencehttp://image.papertrans.cn/t/image/881800.jpg
BRUNT
发表于 2025-3-30 22:33:21
http://reply.papertrans.cn/89/8818/881800/881800_54.png
Pathogen
发表于 2025-3-31 01:47:48
591 TFLOPS Multi-trillion Particles Simulation on SuperMUC,on to make use of Hyperthreading. Finally we present results for weak and strong scaling experiments on up to 146016 Cores of SuperMUC at the Leibniz Supercomputing Centre, achieving a speed-up of 133k times which corresponds to an absolute performance of 591.2 TFLOPS.
reception
发表于 2025-3-31 08:06:57
Heterogeneous Programming and Optimization of Gyrokinetic Toroidal Code and Large-Scale PerformanceIA M2050 GPUs to Intel Xeon X5670 CPUs. Strong and weak scaling studies have been performed using actual production simulation parameters, providing insights into GTC’s scalability and bottlenecks on large GPU supercomputers.
neoplasm
发表于 2025-3-31 10:49:11
Improving Performance Portability in OpenCL Programs,We further demonstrate that proper tuning could improve the OpenCL portable performance from the current 15% to a potential 67% of the state-of-the-art performance on the Ivy Bridge CPU. Finally, we evaluate the current OpenCL programming model, and propose a list of extensions that improve performance portability.
evince
发表于 2025-3-31 13:38:54
0302-9743 gorithms; accelerators; performance analysis and optimization; library development; administration and management of supercomputers; energy efficiency; parallel I/O; grid and cloud.978-3-642-38749-4978-3-642-38750-0Series ISSN 0302-9743 Series E-ISSN 1611-3349
管理员
发表于 2025-3-31 20:47:41
http://reply.papertrans.cn/89/8818/881800/881800_59.png
蛰伏
发表于 2025-3-31 22:32:02
http://reply.papertrans.cn/89/8818/881800/881800_60.png