Image processing using unaligned memory load instructions

摘要

Pixel values of an image are loaded into main memory and cache of a computer system. Two different instructions are used to load pixel values of the image from the cache to a set of registers in a processor of the system. A first one is used when loading an operand (containing pixel values) that is aligned with a cache line boundary of the cache. A second instruction is to be used when loading an operand (containing pixel values) that is not aligned with the cache line boundary. The second instruction can execute a cache line split without a significant performance penalty relative to execution of the first instruction. Other embodiments are also described and claimed.