System, apparatus and method for prefetching physical pages in a processor
US-2022197808-A1 · Jun 23, 2022 · US
US12282428B2 · US · B2
| Field | Value |
|---|---|
| Publication number | US-12282428-B2 |
| Application number | US-202117564141-A |
| Country | US |
| Kind code | B2 |
| Filing date | Dec 28, 2021 |
| Priority date | Dec 28, 2021 |
| Publication date | Apr 22, 2025 |
| Grant date | Apr 22, 2025 |
A practical reading order for non-experts. Skip the full description unless you need deep technical detail.
What the patent document calls the invention.
A short plain-language summary of the technical disclosure.
Who owns or filed the patent and who is credited as inventor.
Filing, priority, publication, and grant dates set the timeline.
The legal scope of protection — read this for what is actually claimed.
Technology tags used to group this patent with similar filings.
Prior art links and similar publications in this corpus.
Official abstract text for this publication.
In response to generating one or more speculative prefetch requests for a last-level cache, a processor determines prefetch analytics for the generated speculative prefetch requests and compares the determined prefetch analytics of the speculative prefetch requests to selection thresholds. In response to a speculative prefetch request meeting or exceeding a selection threshold, the processor selects the speculative prefetch request for issuance to a memory-side cache controller. When one or more system conditions meet one or more condition thresholds, the processor issues the selected speculative prefetch request to the memory-side cache controller. The memory-side cache controller then retrieves the data indicated in the selected speculative prefetch request from a memory and stores it in a memory-side cache in the data fabric coupled to the last-level cache.
Opening claim text (preview).
What is claimed is: 1. A method for speculative prefetching into a cache in a data fabric, comprising: selectively issuing, by a processing device to a cache controller of a cache in a data fabric, a speculative prefetch request for a last-level cache (LLC) based on the speculative prefetch request meeting a selection threshold; and based on receiving a prefetch fill data based on the speculative prefetch request for the LLC, filling at least a portion of the cache in the data fabric with the prefetch fill data. 2. The method of claim 1 , further comprising: in response to a cache miss in the LLC, retrieving the prefetch fill data from the cache in the data fabric. 3. The method of claim 1 , further comprising: determining a prefetch analytic based on the speculative prefetch request; and comparing the prefetch analytic to the selection threshold to determine whether the speculative prefetch request meets the selection threshold. 4. The method of claim 3 , wherein the prefetch analytic comprises a confidence of the speculative prefetch request and the selection threshold comprises a predetermined confidence. 5. The method of claim 3 , wherein the prefetch analytic comprises an access type of the speculative prefetch request and the selection threshold comprises a predetermined access type. 6. The method of claim 3 , further comprising: selectively issuing the speculative prefetch request based on the comparison of the prefetch analytic to the selection threshold indicating that the speculative prefetch meets the selection threshold. 7. The method of claim 1 , wherein the speculative prefetch request is issued in response to a fill buffer associated with the LLC being full. 8. The method of claim 1 , further comprising: downgrading a speculative prefetch request for a higher-level cache to produce the speculative prefetch request for the LLC. 9. A system comprising: a last-level cache (LLC) coupled to a cache in a data fabric; and a processor coupled to the LLC and cache in the data fabric, the processor configured to: selectively issue, to a cache controller of the cache in the data fabric, a speculative prefetch request for the LLC based on the speculative prefetch request meeting a selection threshold; and based on receiving a prefetch fill data based on the speculative prefetch request for the LLC, fill at least at least a portion of the cache in the data fabric with the prefetch fill data. 10. The system of claim 9 , wherein the processor is further configured to: in response to a cache miss in the LLC, retrieve the prefetch fill data from the cache in the data fabric. 11. The system of claim 9 , wherein the processor is further configured to: determine a prefetch analytic based on the speculative prefetch request; and compare the prefetch analytic to the selection threshold to determine whether the speculative prefetch request meets the selection threshold. 12. The system of claim 11 , wherein the prefetch analytic comprises a data type of the speculative prefetch request and the selection threshold comprises a predetermined data type. 13. The system of claim 11 , wherein the prefetch analytic comprises an initiator of the speculative prefetch request and the selection threshold comprises a predetermined initiator. 14. The system of claim 11 , wherein the processor is further configured to: selectively issue the speculative prefetch request based on the comparison of the prefetch analytic to the selection threshold indicating that the speculative prefetch request meets the selection threshold. 15. The system of claim 9 , wherein the processor is further configured to issue the speculative prefetch request in response to a queue associated with the LLC being full. 16. The system of claim 9 , wherein the processor is further configured to: downgrade a speculative prefetch request for a higher-level cache to produce the speculative prefetch request for the LLC. 17. A method for speculative prefetching into a cache in a data fabric, comprising: selectively issuing, by a processing device coupled to a last-level cache (LLC) and a cache in a data fabric, a speculative prefetch request for the LLC to a cache controller of the cache in the data fabric based on a prefetch analytic of the speculative prefetch request meeting a selection threshold; and based on receiving a prefetch fill data based on the speculative prefetch request for the LLC, filling at least a portion of the cache in the data fabric with the prefetch fill data. 18. The method of claim 17 , wherein selectively issuing the speculative prefetch request comprises: comparing the prefetch analytic to a selection threshold; and selectively issuing the speculative prefetch request based on the comparison indicating that the prefetch analytic meets the selection threshold. 19. The method of claim 17 , further comprising: in response to a cache miss in the LLC, retrieving the prefetch fill data from the cache in the data fabric. 20. The method of claim 17 , wherein the prefetch analytic comprises a confidence of the speculative prefetch request and the selection threshold comprises a predetermined confidence.
Speculative instruction execution · CPC title
Prefetch instructions; cache control instructions · CPC title
Hit rate improvement · CPC title
with multilevel cache hierarchies · CPC title
Operand prefetching (cache prefetching G06F12/0862) · CPC title
Related publications grouped by family.
Answers are generated from the same data shown on this page.