Techniques for resonant rotary clocking for die-to-die communication
US-2024429865-A1 · Dec 26, 2024 · US
US9547497B2 · US · B2
| Field | Value |
|---|---|
| Publication number | US-9547497-B2 |
| Application number | US-201314129663-A |
| Country | US |
| Kind code | B2 |
| Filing date | Sep 27, 2013 |
| Priority date | Sep 27, 2013 |
| Publication date | Jan 17, 2017 |
| Grant date | Jan 17, 2017 |
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.
Technologies for facilitating inter-system-on-a-chip (SoC) communication include a first SoC, a second SoC, and a dedicated manageability controller network. The first SoC includes a first main processor, a first manageability controller, and a memory dedicated to the first manageability controller and having manageability controller firmware stored thereon. The first manageability controller is different from the first main processor and to control functions of the first SoC. The second SoC is different from the first SoC and includes a second main processor and a second manageability control, which is different from the second main processor and to control functions of the second SoC. The second SoC is to access the manageability controller firmware of the memory of the first SoC over the dedicated manageability network.
Opening claim text (preview).
The invention claimed is: 1. A system-on-a-chip (SoC) cluster to facilitate inter-SoC communication, the SoC cluster comprising: a first SoC including (i) a first main processor, (ii) a first manageability controller, different from the first main processor, to control functions of the first SoC, and (iii) a memory dedicated to the first manageability controller and having manageability controller firmware stored thereon; a second SoC, different from the first SoC, including (i) a second main processor and (ii) a second manageability controller, different from the second main processor, to control functions of the second SoC; and a dedicated manageability controller network, wherein the second SoC is to access the manageability controller firmware of the memory of the first SoC over the dedicated manageability controller network. 2. The SoC cluster of claim 1 , wherein the first manageability controller comprises a first microcontroller and the second manageability controller comprises a second microcontroller. 3. The SoC cluster of claim 1 , wherein the memory dedicated to the first manageability controller comprises a static random-access memory (SRAM). 4. The SoC cluster of claim 1 , wherein the dedicated manageability controller network comprises a fabric-to-fabric interface. 5. The SoC cluster of claim 1 , wherein the second SoC includes a memory dedicated to the second manageability controller and having a first manageability controller firmware section stored thereon; and wherein the memory dedicated to the first manageability controller and accessible by the second SoC has a second manageability controller firmware section stored thereon, wherein the first manageability controller firmware section and the second manageability controller firmware section are separate portions of a manageability controller firmware to be executed by the second manageability controller. 6. The SoC cluster of claim 5 , wherein the memory dedicated to the second manageability controller includes a data structure that identifies a memory location of each section of a plurality of sections of the manageability controller firmware to be executed by the second manageability controller. 7. The SoC cluster of claim 1 , wherein the second manageability controller is to access the manageability controller firmware of the memory of the first SoC over the dedicated manageability controller network. 8. The SoC cluster of claim 1 , wherein the memory of the first SoC includes (i) a first manageability controller firmware section to be executed by the first manageability controller to control functions of the first SoC and (ii) a second manageability controller firmware section to be retrieved and executed by the second manageability controller to control functions of the second SoC. 9. The SoC cluster of claim 8 , wherein the first manageability controller firmware section includes all manageability controller firmware required for the first manageability controller to control functions of the first SoC; and wherein second manageability controller firmware section includes only a portion of manageability controller firmware required for the second manageability controller to control functions of the second SoC. 10. One or more non-transitory machine-readable storage media comprising a plurality of instructions stored thereon that, in response to execution by a first system-on-a-chip (SoC) within a SoC cluster of a computing device, cause a manageability controller of the first SoC to: determine a memory location of a manageability controller firmware section; and communicate with a second SoC of the SoC cluster over a dedicated manageability controller network to retrieve the manageability controller firmware section from a memory of the second SoC in response to determining the memory location is located on the memory of the second SoC, wherein the memory of the second SoC is dedicated to a manageability controller of the second SoC. 11. The one or more non-transitory machine-readable storage media of claim 10 , wherein to determine the memory location of the manageability controller firmware section comprises to query a data structure stored on a memory of the first SoC. 12. The one or more non-transitory machine-readable storage media of claim 10 , wherein the plurality of instructions further cause the manageability controller of the first SoC to load the retrieved manageability controller firmware section in response to communication with the second SoC. 13. The one or more non-transitory machine-readable storage media of claim 10 , wherein the plurality of instructions further cause the manageability controller of the first SoC to load the manageability controller firmware section from a memory of the first SoC in response to the determined memory location being within the memory of the first SoC. 14. The one or more non-transitory machine-readable storage media of claim 10 , wherein to communicate with the second SoC to retrieve the manageability controller firmware section comprises to retrieve a high feature firmware section; and wherein the high feature firmware section is to be loaded by the manageability controller of the first SoC with at least one other high feature firmware section as a global high feature manageability controller firmware, and wherein the global high feature manageability controller firmware requires more memory for storage than available in memory on the first SoC. 15. The one or more non-transitory machine-readable storage media of claim 10 , wherein to communicate with the second SoC over a dedicated manageability controller network comprises to communicate with the second SoC over a fabric-to-fabric interface. 16. The one or more non-transitory machine-readable storage media of claim 15 , wherein the plurality of instructions further cause the manageability controller of the first SoC to communicate with a memory external to the SoC cluster over an input-output subsystem to retrieve the manageability controller firmware section in response to a determination that the manageability controller firmware section is not stored on a memory of a SoC within the SoC cluster, wherein the input-output subsystem is different from the dedicated manageability controller network. 17. A method of sharing hardware resources between a first system-on-a-chip (SoC) and a second SoC within a SoC cluster, the method comprising: determining, by a manageability controller of the first SoC, a memory location of a manageability controller firmware section; communicating, by the manageability controller of the first SoC, with the second SoC over a dedicated manageability controller network to retrieve the manageability controller firmware section from a memory of the second SoC in response to determining the memory location is located on the memory of the second SoC, wherein the memory of the second SoC is dedicated to a manageability controller of the second SoC. 18. The method of claim 17 , wherein determining the memory location of the manageability controller firmware section comprises querying a data structure stored on a memory of the first SoC. 19. The method of claim 17 , further comprising loading, by the manageability controller of the first SoC, the retrieved manageability controller firmware section in response to communicating with the second SoC. 20. The method of claim 17 , further comprising loading, by the manageability controller of the first SoC, the manageability controller firmware section from a memory of th
System on chip, i.e. computer system on a single chip; System in package, i.e. computer system on one or more chips in a single package · CPC title
Bootstrapping (security arrangements therefor G06F21/57) · CPC title
Related publications grouped by family.
Answers are generated from the same data shown on this page.