Systems and methods for load canceling in a processor that is connected to an external interconnect fabric

Patent metadata

Field	Value
Publication number	US-10884739-B2
Application number	US-201815989105-A
Country	US
Kind code	B2
Filing date	May 24, 2018
Priority date	Oct 11, 2012
Publication date	Jan 5, 2021
Grant date	Jan 5, 2021

Abstract

Systems and methods for load canceling in a processor that is connected to an external interconnect fabric are disclosed. As a part of a method for load canceling in a processor that is connected to an external bus, and responsive to a flush request and a corresponding cancellation of pending speculative loads from a load queue, a type of one or more of the pending speculative loads that are positioned in the instruction pipeline external to the processor, is converted from load to prefetch. Data corresponding to one or more of the pending speculative loads that are positioned in the instruction pipeline external to the processor is accessed and returned to cache as prefetch data. The prefetch data is retired in a cache location of the processor.

First claim

What is claimed is:

1. A method of handling data returned from a speculative load in a processor that is coupled to an external interconnect fabric, the method comprising:
receiving data returned for the speculative load after a flush request is processed by an instruction pipeline of the processor, where the speculative load is executing when the flush request is processed;
storing the data returned for the speculative load as prefetch data in a cache location; and
dropping a pending speculative load in the instruction pipeline executing at a stage of the instruction pipeline internal to the processor in response to the flush request.

2. A cache controller, comprising:
a data retiring component to receive data returned for a speculative load in an instruction pipeline of a processor after a flush request is processed by the instruction pipeline, where the speculative load is executing when the flush request is processed, and to store the data returned for the speculative load as prefetch data in a cache location; and
a converter coupled to the data retiring component, the converter to drop a pending speculative load in the instruction pipeline executing at a stage of the instruction pipeline internal to the processor in response to the flush request.

3. The cache controller of claim 2 , wherein the converter is further configured to convert the speculative load to a prefetch in response to the flush request where the speculative load is executing to access data external to the processor.

4. The cache controller of claim 2 , wherein the converter is further configured to drop any pending speculative loads that are executing at stages of the instruction pipeline internal to the processor, in response to the flush request.

5. A processor, comprising:
a set of execution units;
a load queue; and
a cache controller, the cache controller including,
a data retiring component to receive data returned for a speculative load in an instruction pipeline of a processor after a flush request is processed by the instruction pipeline, where the speculative load is executing when the flush request is processed, and to store the data returned for the speculative load as prefetch data in a cache location, and
a converter to drop a pending speculative load in the instruction pipeline executing at a stage of the instruction pipeline internal to the processor in response to the flush request.

6. The processor of claim 5 , wherein the converter is further configured to convert the speculative load to a prefetch in response to the flush request where the speculative load is executing to access data external to the processor.

7. The processor of claim 5 , wherein the converter is further configured to drop any pending speculative loads that are executing at stages of the instruction pipeline internal to the processor, in response to the flush request.

Assignees

• Intel Corp

Inventors

• Avudaiyappan Karthikeyan
• Abdallah Mohammad

Classifications

• G06F12/0215

  with look ahead addressing means · CPC title

• G06F2212/452

  Instruction code · CPC title

• G06F9/3842

  Speculative instruction execution · CPC title

• G06F12/0875

  with dedicated cache, e.g. instruction or stack · CPC title

• G06F12/0862

  with prefetch · CPC title