Patent
1997-09-08
1998-11-17
Harrell, Robert B.
395376, 395381, 395390, 395582, G06F 940
Patent
active
058389407
ABSTRACT:
In a microprocessor, apparatus and method coordinate the fetch and issue of instructions by rotating multiple, fetched instructions into an issue order prior to issuance and dispatching selected of the issue ordered instructions. The rotate and dispatch block including a mixer for mixing newly fetched instructions with previously fetched and unissued instructions in physical memory order, a mix and rotate device for rotating the mixed instructions into issue order, an instruction latch for holding the issue ordered instructions prior to dispatch, and an unrotate device for rotating non-issued instructions from issue order to physical memory order prior to mixing with newly fetched instructions.
During the fetch cycle, multiple instructions are simultaneously fetched from storage in physical memory order and rotated into a PC-related issue order within the rotate and dispatch block. During the next clock cycle, selected ones of the previously fetched and rotated instructions enter the issue cycle, a new set of instructions are fetched in physical memory order, the previously fetched and rotated instructions which were not issued are rearranged into physical memory order and mixed in physical memory order with the newly fetched instructions, together all fetched and non-issued instructions are rotated into issue order prior to the next issue cycle, and so forth until all instructions have passed through the pipeline.
REFERENCES:
patent: 4654781 (1987-03-01), Schwartz et al.
patent: 4916652 (1990-04-01), Schwartz et al.
patent: 5127093 (1992-06-01), Moore, Jr. et al.
patent: 5247628 (1993-09-01), Grohoski
patent: 5295249 (1994-03-01), Blaner et al.
patent: 5497496 (1996-03-01), Ando
patent: 5519841 (1996-05-01), Sagar et al.
patent: 5519864 (1996-05-01), Martell et al.
patent: 5559975 (1996-09-01), Christie et al.
patent: 5564118 (1996-10-01), Steely, Jr. et al.
Kuga, Morihiro, Murakami, Kazuaki, & Tomita, Shinji, DSNS (Dynamically-hazard-resolved, Statically-code-scheduled, Nonuniform Superscalar): Yet Another Superscalar Processor Architecture, Computer Architecture News, vol. 19, No. 4, Jun., 1, 1991, pp. 14-25.
Sajjadian Farnad
Savkar Sunil
Shebanow Michael C.
Shen Gene W.
Fujitsu Limited
Harrell Robert B.
Najjar Saleh
LandOfFree
Method and apparatus for rotating active instructions in a paral does not yet have a rating. At this time, there are no reviews or comments for this patent.
If you have personal experience with Method and apparatus for rotating active instructions in a paral, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Method and apparatus for rotating active instructions in a paral will most certainly appreciate the feedback.
Profile ID: LFUS-PAI-O-895029