Ashok Kelur – NVIDIA Technical Blog News and tutorials for developers, data scientists, and IT admins 2023-02-13T17:45:44Z http://www.open-lab.net/blog/feed/ Ashok Kelur <![CDATA[Sharing CUDA Resources Through Interoperability with NvSciBuf and NvSciSync]]> http://www.open-lab.net/blog/?p=22340 2023-02-13T17:01:23Z 2020-12-10T17:02:38Z There is a growing need among embedded and HPC applications to share resources and control execution for pipelined workflows spanning multiple hardware engines...]]>

There is a growing need among embedded and HPC applications to share resources and control execution for pipelined workflows spanning multiple hardware engines and software applications. The following diagram gives an insight into the number of engines that can be supported on NVIDIA-embedded platforms. In addition to GPUs, this includes image processing units like image signal processors…

Source

]]> 6 Ashok Kelur <![CDATA[GPUDirect RDMA on NVIDIA Jetson AGX Xavier]]> http://www.open-lab.net/blog/?p=14675 2023-02-13T17:45:44Z 2019-06-11T13:00:25Z Remote Direct Memory Access (RDMA) allows computers to exchange data in memory without the involvement of a CPU. The benefits include low latency and high...]]>

Remote Direct Memory Access (RDMA) allows computers to exchange data in memory without the involvement of a CPU. The benefits include low latency and high bandwidth data exchange. GPUDirect RDMA extends the same philosophy to the GPU and the connected peripherals in Jetson AGX Xavier. GPUDirect RDMA enables a direct path for data exchange between the GPU-accessible memory (the CUDA memory) and a…

Source

]]> 1 ���˳���97caoporen����