发明名称 |
SELECTIVELY KILLING TRAPPED MULTI-PROCESS SERVICE CLIENTS SHARING THE SAME HARDWARE CONTEXT |
摘要 |
A method for handling parallel processing clients associated with a server in a GPU, the method comprising: receiving a failure indication for at least client running a thread in the GPU; determining threads in the GPU associated with the failing client; exiting threads in the GPU associated with the failing client; and continuing to execute remaining threads in the GPU for other clients running threads in the GPU. |
申请公布号 |
US2015206272(A1) |
申请公布日期 |
2015.07.23 |
申请号 |
US201414481802 |
申请日期 |
2014.09.09 |
申请人 |
NVIDIA Corporation |
发明人 |
PERELYGIN Kyrylo;KINI Vivek;VENKATARAMAN Vyas |
分类号 |
G06T1/20 |
主分类号 |
G06T1/20 |
代理机构 |
|
代理人 |
|
主权项 |
1. A method for handling parallel processing clients associated with a graphics processor, the method comprising:
receiving a failure indication for at least one client of a plurality of clients running threads in the graphics processor; determining threads in the graphics processor associated with the failing client; exiting threads in the graphics processor associated with the failing client; and continuing to execute remaining threads in the graphics processor for other clients of the plurality of clients running threads in the graphics processor. |
地址 |
Santa Clara CA US |