Customizing function behavior based on cache and scheduling parameters of a memory argument

An article of manufacture embodied as a computer program product comprising:

• non-transitory computer readable storage device;
• and
• program code on the computer readable storage device that when executed by a processor, provides functions comprising:
• populating a first memory object in a global memory with a first plurality of work items;
• populating a second memory object in the global memory with a second plurality of work items, wherein the second memory object does not share a common address space with the first memory object;
• copying a first portion of the first memory object to a node memory;
• receiving a plurality of attributes associated with the first memory object and the second memory object;
• determining a first data size from at least a first attribute of the plurality of attributes that is associated with the first memory object;
• partitioning a memory store of a first processor core of a plurality of processor cores into a plurality of partitions based on the plurality of attributes, wherein each partition stores a plurality of cache lines;
• and
• copying, based on the first data size, a first work item from the first portion of the first memory object to a first partition of the plurality of partitions of the memory store of the first processor core.

A data processing system, comprising:

• a processor;
• a global memory coupled to the processor;
• a node memory coupled to the global memory;
• a first node that includes a plurality of processing cores coupled to the node memory;
• and
• program code that when executed by the processor enables the data processing system to:
• populate a first memory object in the global memory with a first plurality of work items;
• populate a second memory object in the global memory with a second plurality of work items, wherein the second memory object does not share a common address space with the first memory object;
• copy a first portion of the first memory object to the node memory;
• receive a plurality of attributes associated with the first memory object and the second memory object;
• determine a first data size from at least a first attribute of the plurality of attributes that is associated with the first memory object;
• partition a memory store of a first processor core of a plurality of processor cores into a plurality of partitions based on the plurality of attributes, wherein each partition stores a plurality of cache lines;
• and
• copy, based on the first data size, a first work item from the first portion of the first memory object to a first partition of the plurality of partitions of the memory store of the first processor core.