Kyrylo Perelygin – NVIDIA Technical Blog News and tutorials for developers, data scientists, and IT admins 2023-06-12T21:16:47Z http://www.open-lab.net/blog/feed/ Kyrylo Perelygin <![CDATA[Improving GPU Utilization in Kubernetes]]> http://www.open-lab.net/blog/?p=49216 2022-06-16T20:42:13Z 2022-06-16T20:42:09Z For scalable data center performance, NVIDIA GPUs have become a must-have.  NVIDIA GPU parallel processing capabilities, supported by thousands of...]]>

For scalable data center performance, NVIDIA GPUs have become a must-have. NVIDIA GPU parallel processing capabilities, supported by thousands of computing cores, are essential to accelerating a wide variety of applications across different industries. The most compute-intensive applications across diverse industries use GPUs today: Different applications across this spectrum can…

Source

]]> 11 Kyrylo Perelygin <![CDATA[Cooperative Groups: Flexible CUDA Thread Programming]]> http://www.open-lab.net/blog/parallelforall/?p=8415 2023-06-12T21:16:47Z 2017-10-05T04:17:43Z In efficient parallel algorithms, threads cooperate and share data to perform collective computations. To share data, the threads must synchronize. The...]]>

In efficient parallel algorithms, threads cooperate and share data to perform collective computations. To share data, the threads must synchronize. The granularity of sharing varies from algorithm to algorithm, so thread synchronization should be flexible. Making synchronization an explicit part of the program ensures safety, maintainability, and modularity. CUDA 9 introduces Cooperative Groups…

Source

]]> 32 ���˳���97caoporen����