Intel Corporation

Atiq A Bajwa

Andrew F Glew

Glenn J Hinton

Michael A Fetterman

Robert P Colwell

David B Papworth

Kris G Konigsfeld

Jeffrey M Abramson

Sunil R Shenoy

Mark S Myers

Robert C Duzett

Warren R Morrow

M Vittal Kini

William C Alexander, Iii

Kent Mason

A mechanism and method for renaming flags within a register alias table ('RAT') to increase processor parallelism and also providing and using flag masks associated with individual instructions. In order to reduce the amount of data dependencies between instructions that are concurrently processed, the flags used by these instructions are renamed. In general, a RAT unit provides register renaming to provide a larger physical register set than would ordinarily be available within a given macroarchitecture's logical register set (such as the Intel architecture or PowerPC or Alpha designs, for instance) to eliminate false data dependencies between instructions that reduce overall superscalar processing performance for the microprocessor. The renamed flag registers contain several flag bits and various flag bits may be updated or read by different instructions. Also, static and dynamic flag masks are associated with particular instructions and indicate which flags are capable of being updated by a particular instruction and also indicate which flags are actually updated by the instruction. Static flag masks are used in flag renaming and dynamic flag masks are used at retirement. The invention also discovers cases in which a flag register is required that is a superset of the previously renamed flag register portion.

Flag renaming and flag masks within register alias table

A simplified method and apparatus for handling the change of instruction control flow in a microprocessor is provided. Rather than attempting to implement a change in the instruction flow immediately, the processor first recognizes that flow is to be redirected from a predicted instruction flow to a correct instruction flow according to a flow control indicator. The flow control indicator may be attached to instructions flowing down the pipeline or inserted as a separate instruction in the pipeline. The pipeline is cleared of state created by instructions that do not follow the correct instruction flow, i.e., instructions that were erroneously fetched after the instruction causing the change in flow. The change in flow as indicated by the flow control indicator is implemented later in the pipeline.

Method and apparatus for changing flow of control in a processor

Method and apparatus for predicting, clearing and redirecting

A method is provided for recovering the effective address of memory instructions in an out-of-order microprocessor for use by an exception handler upon the occurrence of one of an exception and a systems management interrupt. The microprocessor comprises at least one execution unit for executing a plurality of instructions out-of-order and a re-order buffer having storage locations for buffering result data produced from the execution of the plurality of instructions. Each instruction is associated with a location designator to identify a unique storage location within the re-order buffer in which the result data for an executed instruction is written. The microprocessor further comprises a memory order buffer having storage locations for buffering memory instructions waiting for access to memory for execution, these storage locations also being identified by corresponding location designators. According to this embodiment of the microprocessor, the effective address of memory instructions can be reconstructed by utilizing the location designators of the ROB (Reorder Buffer) to find the corresponding storage location in the MOB (Memory Order Buffer) at which place the linear address for the instruction may be found. By associating both the retirement and exception information of the memory instructions stored within the storage locations of the re-order buffer with the corresponding memory instructions and information stored within the memory order buffer, the linear address of either the youngest, valid, retiring memory uop or the oldest, valid, excepted memory uop can be selected, written to memory and subsequently used to reconstruct the effective address of the memory instruction for use by an exception handler.

Method and apparatus for saving the effective address of floating point

The waveform of a strobe type signal (70) is specified by two bit strings (72, 74) stored in the RAM (20), one bit string (72) denoting when the strobe is to be reset and the other (74) denoting when the strobe is to be set. The bit positions in the bit strings correspond with clock cycles (76) taken for a DRAM memory access. The bit positions are written by means of addressable registers (71) corresponding to rows (e.g. 80-87) of the RAM. A one bit in the set bit string (72) causes the signal (70) to be asserted in the corresponding clock cycle of the request. A one bit in the reset bit string causes the signal (70) to be de-asserted in the corresponding clock cycle of the request. The set and reset times are fine-tuned to a fraction of a cycle by providing a multi-bit fractional cycle index field (78) to accompany each bit string. If a two bit quarter cycle index (QCI) field is used, the boundaries of the quarter cycles are numbered from 0 to 3. 0 coincides with the first quarter cycle after the leading edge of a clock cycle and 3 coincides with the clock cycle boundary. The one bit in the set or reset bit string denotes the cycle in which a transition is to take place, while the quarter cycle index field encoding denotes the precise quarter of the cycle in which the transition takes place.

Programmable memory array control signals

Growing community of inventors

Portland, OR, United States of America

Atiq A Bajwa