Apparatus and method for adaptively scheduling work on heterogeneous processing resources

A method comprising:

• scheduling a plurality of threads for execution on a plurality of logical processors in accordance with performance data associated with the plurality of threads, the plurality of logical processors including at least one logical processor of a first logical processor type and at least one logical processor of a second logical processor type, the first logical processor type associated with a first core type and the second logical processor type associated with a second core type;
• determining, based on the performance data, that a new thread should be executed on a logical processor of the first logical processor type, but all logical processors of the first logical processor type are busy;
• evaluating first and second performance values associated with execution of the new thread on the first or second logical processor types, respectively;
• evaluating third and fourth performance values associated with execution of a second thread on the first or second logical processor types, respectively;
• and
• determining whether to migrate the second thread from the logical processors of the first logical processor type to a logical processor of the second logical processor type based on the evaluating of the first and second performance values and the third and fourth performance values.

A machine-readable medium having program code stored thereon which, when executed by a machine, causes the machine to perform the operations of:

• scheduling a plurality of threads for execution on a plurality of logical processors in accordance with performance data associated with the plurality of threads, the plurality of logical processors including at least one logical processor of a first logical processor type and at least one logical processor of a second logical processor type, the first logical processor type associated with a first core type and the second logical processor type associated with a second core type;
• determining, based on the performance data, that a new thread should be executed on a logical processor of the first logical processor type, but all logical processors of the first logical processor type are busy;
• evaluating first and second performance values associated with execution of the new thread on the first or second logical processor types, respectively;
• evaluating third and fourth performance values associated with execution of a second thread on the first or second logical processor types, respectively;
• and
• determining whether to migrate the second thread from the logical processors of the first logical processor type to a logical processor of the second logical processor type based on the evaluating of the first and second performance values and the third and fourth performance values.