Reinventing Scheduling for Multicore Systems
High performance on multicore processors requires that schedulers be reinvented. Traditional schedulers focus on keeping execution units busy by assigning each core a thread to run. Schedulers ought to focus, however, on high utilization of on-chip memory, rather than of execution cores, to red...
| Main Authors: | , , |
|---|---|
| Other Authors: | |
| Format: | Article |
| Language: | en_US |
| Published: |
IEEE Computer Society Press
2011
|
| Online Access: | http://hdl.handle.net/1721.1/65870 https://orcid.org/0000-0001-7098-586X https://orcid.org/0000-0003-2700-9286 |
| Summary: | High performance on multicore processors requires that
schedulers be reinvented. Traditional schedulers focus
on keeping execution units busy by assigning each core
a thread to run. Schedulers ought to focus, however, on
high utilization of on-chip memory, rather than of execution
cores, to reduce the impact of expensive DRAM
and remote cache accesses. A challenge in achieving
good use of on-chip memory is that the memory is split
up among the cores in the form of many small caches.
This paper argues for a form of scheduling that assigns
each object and its operations to a specific core, moving
a thread among the cores as it uses different objects. |
|---|