发明名称 |
SCHEDULING AND DISPATCH OF GPGPU WORKLOADS |
摘要 |
A method and system are described herein for an optimization technique on two aspects of thread scheduling and dispatch when the driver is allowed to pick the scheduling attributes. The present techniques rely on an enhanced GPGPU Walker hardware command and one dimensional local identification generation to maximize thread residency. |
申请公布号 |
US2015187040(A1) |
申请公布日期 |
2015.07.02 |
申请号 |
US201314142681 |
申请日期 |
2013.12.27 |
申请人 |
Rao Jayanth N.;Mrozek Michal |
发明人 |
Rao Jayanth N.;Mrozek Michal |
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 scheduling and dispatching workloads, comprising:
selecting a local work group size of a graphics processing unit workload; and dispatching threads of the graphics processing unit workload by splitting a graphics processing unit walker command. |
地址 |
Folsom CA US |