Intel Corporation

Robert L Hinton

Stephan Jourdan

Alexandre J Farcy

Ilhyun Kim

Choon Wei Khor

Per H Hammarlund

Lihu Rappoport

Douglas M Carmean

Mark C Davis

Chen Koren

Morris Marden

Pierre Michaud

Boyd S Phelps

This disclosure includes tracking of in-use states of cache lines to improve throughput of pipelines and thus increase performance of processors. Access data for a number of sets of instructions stored in an instruction cache may be tracked using an in-use array in a first array until the data for one or more of those sets reach a threshold condition. A second array may then be used as the in-use array to track the sets of instructions after a micro-operation is inserted into the pipeline. When the micro-operation retires from the pipeline, the first array may be cleared. The process may repeat after the second array reaches the threshold condition. During the tracking, an in-use state for an instruction line may be detected by inspecting a corresponding bit in each of the arrays. Additional arrays may also be used to track the in-use state.

Multi-level tracking of in-use state of cache lines

This disclosure provides techniques and apparatuses to enable early, run-ahead handling of IC and ITLB misses by decoupling the ITLB and IC tag lookups from the IC data (instruction bytes) accesses, and making ITLB and IC tag lookups run ahead of the IC data accesses. This allows overlapping the ITLB and IC miss stall cycles with older instruction byte reads or older IC misses, resulting in fewer stalls than previous implementations and improved performance

Hiding instruction cache miss latency by running tag lookups ahead of the instruction accesses

Methods and apparatus for partitioning a microprocessor pipeline to support pipelined branch prediction and instruction fetching of multiple execution threads. A thread selection stage selects a thread from a plurality of execution threads. In one embodiment, storage in a branch prediction output queue is pre-allocated to a portion of the thread in one branch prediction stage in order to prevent stalling of subsequent stages in the branch prediction pipeline. In another embodiment, an instruction fetch stage fetches instructions at a fetch address corresponding to a portion of the selected thread. Another instruction fetch stage stores the instruction data in an instruction fetch output queue if enough storage is available. Otherwise, instruction fetch stages corresponding to the selected thread are invalidated and refetched to avoid stalling preceding stages in the instruction fetch pipeline, which may be fetching instructions of another thread.

Method and apparatus for partitioned pipelined execution of multiple execution threads

Systems and methods of managing threads provide for supporting a plurality of logical threads with a plurality of simultaneous physical threads in which the number of logical threads may be greater than or less than the number of physical threads. In one approach, each of the plurality of logical threads is maintained in one of a wait state, an active state, a drain state, and a stall state. A state machine and hardware sequencer can be used to transition the logical threads between states based on triggering events and whether or not an interruptible point has been encountered in the logical threads. The logical threads are scheduled on the physical threads to meet, for example, priority, performance or fairness goals. It is also possible to specify the resources that are available to each logical thread in order to meet these and other, goals. In one example, a single logical thread can speculatively use more than one physical thread, pending a selection of which physical thread should be committed.

Decoupling the number of logical threads from the number of simultaneous physical threads in a processor

In one embodiment, the present invention includes a method for determining if an entry corresponding to a prediction address is present in a first predictor, and overriding a prediction output from a second predictor corresponding to the prediction address if the entry is present in the first predictor. Other embodiments are described and claimed.

Overriding a static prediction with a level-two predictor

Method and apparatus for partitioned pipelined fetching of multiple execution threads

Growing community of inventors

Hillsboro, OR, United States of America

Robert L Hinton