System and method for improving the page crossing performance of a data prefetcher

A computer-implemented method for prefetching data in a data processing system, the method comprising:

• generating a real address for a prior data stream;
• detecting whether the real address terminates at a page boundary of a first page;
• in response to detecting that the real address terminates at the page boundary of the first page, setting an aggressive profile flag;
• detecting a new data stream;
• and
• selecting an aggressive startup profile for the new data stream in response to setting the aggressive profile flag.

A computer program product stored on a computer operable media, the computer operable media containing instructions for execution by a computer, which, when executed by the computer, cause the computer to implement a method of improving page crossing performance, the method comprising:

• generating a plurality of page boundary values for a plurality of prior data streams, wherein each of the plurality of page boundary values indicate whether a corresponding data stream logically reached a page boundary;
• detecting a new data stream;
• in response to detecting the new data stream, analyzing the plurality of page boundary values, the analysis resulting in a historical page boundary percentage;
• comparing the historical page boundary percentage to a historical page boundary threshold;
• and
• selecting a prefetch startup profile for the new data stream based upon the comparison.

An information handling system comprising:

• one or more processors;
• a memory accessible by the processors;
• a register;
• one or more nonvolatile storage devices accessible by the processors;
• and
• a set of instructions stored in the memory, wherein one or more of the processors executes the set of instructions in order to perform actions of:
• generating a plurality of page boundary values for a plurality of prior data streams, wherein each of the plurality of page boundary values indicate whether a corresponding data stream logically reached a page boundary;
• detecting a new data stream;
• in response to detecting the new data stream, analyzing the plurality of page boundary values, the analysis resulting in a historical page boundary percentage;
• comparing the historical page boundary percentage to a historical page boundary threshold;
• and
• selecting a prefetch startup profile for the new data stream based upon the comparison.