| 摘要 |
A method, apparatus and program product for decreasing overall time for performing a system/device boot-up or initial program load (IPL). The system/device IPL code is organized into a plurality of portions, including a first portion and second portion. The first portion contains code to configure system memory, and is initially copied into the system's L2 cache. This first portion also provides initial control of cache inhibit and cache enable by way of software control. This first portion is executed from a non-volatile memory device to configure system memory and enable instruction caching by way of software control. The cache-enabling code is strategically located at a memory page boundary such that the system/device hardware will disable instruction prefetching in an adjoining page just past this cache enabling software code. After the system memory is configured by the initial portion of the IPL code, the second portion of the IPL code is copied into memory through the L2 cache and executed from memory with cache enabled to allow both normal and speculative instruction prefetching, thus improving overall system performance during system IPL.
|
