公开(公告)号：US20210312271A1

公开(公告)日：2021-10-07

申请号：US16837385

申请日：2020-04-01

Applicant: VMware, Inc.

Inventor： Tiejun Chen ,  Hong Yue ,  Yinghua Chen ,  Yuxin Kou ,  Shreekanta Das

IPC: G06N3/063 ,  G06F13/38 ,  G06F9/38 ,  H04L12/26 ,  H04L12/751

Abstract: Disclosed are various examples of providing AI accelerator access as a service at the edge. In some embodiments an artificial intelligence (AI) accelerator device identifier is transmitted to register an AI accelerator with the AI broker service. An AI processing request for the AI accelerator is received from a networked computing device. A bus redirect of the AI accelerator to the networked device is enabled. An AI workload is performed controlled by the networked device through the bus redirect.

公开(公告)号：US20230205557A1

公开(公告)日：2023-06-29

申请号：US17668285

申请日：2022-02-09

Applicant: VMware, Inc.

Inventor： Yanchao Zhang ,  Lin Lv ,  Yang Liu ,  Yuxin Kou

IPC: G06F9/451

CPC classification number: G06F9/452

Abstract: Techniques are described for redirecting GPU capability from a client device to the virtual desktop. The virtual desktop client includes a GPU controller deployed on the client computing device, which is capable of virtualizing the local GPU of the client device and exposing it to the virtual desktop. The virtual desktop agent operating on the host server includes a GPU consumer, which is capable of accepting machine learning (ML) or artificial intelligence (AI) workloads on the virtual desktop and offload these workloads to the GPU controller on the client computing device. When the GPU consumer detects the ML workload task on the virtual desktop, it transmits the ML workload task over the network to the GPU controller on the client computing device, which processes the ML workload task using the GPU of the client computing device and sends the results of the processing to the GPU consumer.