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.

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.