Coherence de-coupling buffer

US9558116B2 · US · B2

Patent metadata
FieldValue
Publication numberUS-9558116-B2
Application numberUS-201414295062-A
CountryUS
Kind codeB2
Filing dateJun 3, 2014
Priority dateApr 9, 2003
Publication dateJan 31, 2017
Grant dateJan 31, 2017

How to read this patent

A practical reading order for non-experts. Skip the full description unless you need deep technical detail.

  1. Title

    What the patent document calls the invention.

  2. Abstract

    A short plain-language summary of the technical disclosure.

  3. Assignees and inventors

    Who owns or filed the patent and who is credited as inventor.

  4. Key dates

    Filing, priority, publication, and grant dates set the timeline.

  5. First independent claim

    The legal scope of protection — read this for what is actually claimed.

  6. CPC / IPC classifications

    Technology tags used to group this patent with similar filings.

  7. Citations and related patents

    Prior art links and similar publications in this corpus.

Abstract

Official abstract text for this publication.

A coherence decoupling buffer. In accordance with a first embodiment, a coherence decoupling buffer is for storing tag information of cache lines evicted from a plurality of cache memories. A coherence decoupling buffer may be free of value information of the plurality of cache memories. A coherence decoupling buffer may also be combined with a coherence memory.

First claim

Opening claim text (preview).

What is claimed is: 1. An apparatus comprising: a local caching agent configured to communicate with a remote source; at least one local cache memory configured to store cache line tags and cache line data for the local caching agent; a coherence memory configured to store the cache line tags if the cache line tags are stored in the at least one local cache memory; and a coherence decoupling buffer coupled to the at least one local cache memory and the coherence memory and configured to store an evicted cache line tag of a cache line evicted from the at least one local cache memory in response to unavailability of space for a new cache line in the at least one local cache memory, wherein the coherence memory and the coherence decoupling buffer are configured to filter communications from the remote source to the local caching agent. 2. The apparatus of claim 1 , further comprising a main memory. 3. The apparatus of claim 2 , wherein the coherence memory is coupled to the main memory. 4. The apparatus of claim 1 , wherein the coherence memory is operable to respond to a remote snoop directed to a cache line of the at least one local cache memory, wherein the local caching agent comprises a processor, and wherein the remote snoop originates from the remote source. 5. The apparatus of claim 1 , wherein the coherence decoupling buffer is operable to respond to a remote snoop directed to an evicted cache line of the at least one local cache memory, wherein the local caching agent comprises a processor, and wherein the remote snoop originates from the remote source. 6. The apparatus of claim 1 , wherein the coherence memory is at a top of a caching hierarchy. 7. The apparatus of claim 1 , wherein the coherence decoupling buffer comprises a capacity that is of substantially less capacity than a total capacity of the at least one local cache memory. 8. An apparatus comprising: a local caching agent configured to communicate with a remote source; at least one local cache memory configured to store cache line tags and cache line data for the local caching agent; a coherence memory configured to store the cache line tags if the cache line tags are stored in the at least one local cache memory and configured to filter a remote snoop from the remote source to the local caching agent; and a coherence decoupling buffer coupled to the at least one local cache memory and the coherence memory and configured to store an evicted cache line tag of a cache line evicted from the at least one local cache memory in response to unavailability of space for a new cache line in the at least one local cache memory, wherein if the remote snoop is directed to the cache line evicted from the at least one local cache memory, the coherence decoupling buffer is configured to filter the remote snoop. 9. The apparatus of claim 8 , further comprising a main memory. 10. The apparatus of claim 9 , wherein the coherence memory is coupled to the main memory. 11. The apparatus of claim 8 , wherein the remote snoop comprises a read-only snoop, and wherein the local caching agent comprises a processor. 12. The apparatus of claim 8 , wherein the coherence memory and the coherence decoupling buffer increase cache performance. 13. The apparatus of claim 8 , wherein the coherence memory is at a top of a caching hierarchy. 14. The apparatus of claim 8 , wherein the coherence decoupling buffer comprises a capacity that is of substantially less capacity than a total capacity of the at least one local cache memory. 15. A method comprising: filtering a remote snoop from a remote source to a local caching agent by using a coherence memory configured to store cache line tags if the cache line tags are stored in at least one local cache memory for the local caching agent configured to communicate with the remote source; and if the remote snoop is directed to a cache line evicted from the at least one local cache memory, filtering the remote snoop by using a coherence decoupling buffer configured to store an evicted cache line tag of the cache line evicted from the at least one local cache memory in response to unavailability of space for a new cache line in the at least one local cache memory. 16. The method of claim 15 , wherein the coherence memory is coupled to a main memory. 17. The method of claim 15 , wherein the remote snoop is a read-only snoop, and wherein the local caching agent comprises a processor. 18. The method of claim 15 , wherein the coherence memory and the coherence decoupling buffer increase cache performance. 19. The method of claim 15 , wherein the coherence memory is at a top of a caching hierarchy. 20. The method of claim 15 , wherein the coherence decoupling buffer comprises a capacity that is of substantially less capacity than a total capacity of the at least one local cache memory.

Assignees

Inventors

Classifications

  • using directory methods · CPC title

  • Cache consistency protocols · CPC title

  • with a shared cache · CPC title

  • Correctness of operation, e.g. memory ordering · CPC title

  • using a bus scheme, e.g. with bus monitoring or watching means · CPC title

Patent family

Related publications grouped by family.

External sources

Frequently asked questions

Answers are generated from the same data shown on this page.

What does patent US9558116B2 cover?
A coherence decoupling buffer. In accordance with a first embodiment, a coherence decoupling buffer is for storing tag information of cache lines evicted from a plurality of cache memories. A coherence decoupling buffer may be free of value information of the plurality of cache memories. A coherence decoupling buffer may also be combined with a coherence memory.
Who is the assignee on this patent?
Intellectual Ventures Holding 81 Llc
What technology area does this patent fall under?
Primary CPC classification G06F12/0815. Mapped technology areas include Physics.
When was this patent published?
Publication date Tue Jan 31 2017 00:00:00 GMT+0000 (Coordinated Universal Time) (B2). Legal status and post-grant events are not shown on this page.
What related patents are in patentsdb?
We list 8 related publications on this page (citations in our corpus or others sharing the same primary CPC).