Dependency checking and forwarding of variable width operands

References Cited

U.S. Patent Documents

Foreign Patent Documents

Other References

• Instruction Reorganization For A Variable-Length Pipelined Microprocessor by Seth Abraham et al, 1988, IEEE, pp. 96-101.

  Brian Case, "AMD Unveils First Superscaler 29K Core", Microprocessor Report, Oct. 24, 1994, pp. 23-26.

  Michael Slater, "AMD's K5 Designed to Outrun Pentium", Microprocessor Report, Oct. 24, 1994, pp. 1, 6-11.

  Toyohiko Yoshida, et al., "The Approach to Multiple Instruction Execution in the GMICRO/400 Processor", .COPYRGT.1991, pp. 185.195.

  R. M. Tomasulo, "An Efficient Algorithm for Exploiting Multiple Arithmetic Units", Part 2 Regions of Computer Space, Section 3 Concurrency: Single Processor System, IBM Journal. vol. 11, Jan. 1967, pp, 293-305.

  U. S. patent application Serial No. 08/145,902 filed Oct. 29, 1993 entitled "Speculative Instruction Queue and Method Therefor Particularly Suitable for Variable Byte-Length Instructions"--David B. Witt, Attorney Docket M-2279 US.

  U.S. patent application Serial No. 08/145,9065 filed Oct. 29, 1993 entitled "Pre-Decoded Instruction Cache and Method Therefor Particularly Suitable for Variable Byte-Length Instructions"--David B. Witt and Michael D. Goddard, Attorney Docket M-2278 US.

  U.S. patent application Serial No. 08/146,376 filed Oct. 29, 1993 entitled "High Performance Load/Store Functional Unit and Data Cache"--William M. Johnson, David B. Witt, and Murali Chinnakonda, Attorney Docket M-2281 US.

  U.S. patent application Serial No. 08/146,382 filed Oct. 29, 1993 entitled "High Performance Superscalar Microprocessor"--David B. Witt and William M. Johnson, Attorney Docket M-2518 US.

  U.S. patent application Serial No. 08/146,383 filed Oct. 29, 1993 entitled "Superscalar Instruction Decoder"--David B. Witt and Michael d. Goddard, Attorney Docket M-2280 US.

  U.S. patent application Serial No. 08/233,563 filed Apr. 26, 1994 entitled "Mixed Integer/Floating Point Core"--Scott A. White, Michael D. Goddard, and William M. Johnson, Attorney Docket M-2518-1P US.

  U.S. patent application Application Serial No. 08/233,568 filed Apr. 26, 1994 entitled "A Range Finding Circuit Using Circular Carry Lookahead"--Scott A. White, Attorney Docket M-2657 US.

Primary Examiner: Coleman; Eric
Attorney, Agent or Firm: Skjerven, Morrill, MacPherson, Franklin & Friel

Abstract

A pipelined or superscalar processor (10) that executes operations utilizing operand data of variable bit widths improves parallel performance by partitioning a fixed bit width operand (200) into several partial operand fields (215, 216 and 217), and checking for data dependencies, tagging and forwarding data in these fields independently of one another. An instruction decoder (18) concurrently dispatches multiple ROPs to various functional units (20, 21, 22 and 80). Conflicts which arise with respect to register resources are resolved through register renaming. However, implementation of register renaming is difficult when register structures are overlapping. The present invention supports independent dependency checking, tagging and forwarding of partial bit fields of a register operand which, in combination, allow renaming of registers. Therefore, the variable width register operand structure greatly assists the processor to resolve data dependencies. Operands are tagged by a reorder buffer (26) and supplied with data when it becomes available without regard for the type of data. This method of dependency resolution supports parallel performance of operations and provides a substantial improvement in overall speed of processing. Thus, the processor promotes parallel processing of operations that act upon overlapping data structures which otherwise resist parallel handling.

31 Claims, 17 Drawing Figures

Last Updated : Sun Mar 9 23:27:03 EST 2008