The Commons

Back to Results

Patent Title: Superscalar instruction pipeline using alignment logic responsive to boundary identification logic for aligning and appending variable length instructions to instructions stored in cache

Assignee: IBM
Patent Number: US5625787
Issue Date: 04-29-1997
Application Number:
File Date:05-12-1995


Abstract: A mechanism which manages variable length instructions in cache is comprised of three cooperating elements designed to optimize self modifying code and anticipate next instructions for branch operand management. A content addressable memory (CAM) stores addresses of lines which have been accessed for instruction fetching. In a system having modifiable instruction stream (i.e., store to instruction stream), when the CAM matches, the system must retire certain instructions, flush instructions and then fetch the modified instruction stream. Boundary identification logic examines a field in each cache byte to determine the nature of the byte. This field is initially cleared at the time the cache line is loaded and filled with the line is fetched. An anticipation buffer designed to minimize the circuitry necessary for fetches across cache lines is loaded with sequentially anticipated prefetched instructions from the cache. These anticipated instructions can then be concatenated by a fetch aligner.

Notes:

Link to USPTO

IBM Pledge dated 1/11/2005