Controlling transitions of devices between normal state and quiescent state
US-10621128-B2 · Apr 14, 2020 · US
US11340671B2 · US · B2
| Field | Value |
|---|---|
| Publication number | US-11340671-B2 |
| Application number | US-201916368443-A |
| Country | US |
| Kind code | B2 |
| Filing date | Mar 28, 2019 |
| Priority date | Mar 30, 2018 |
| Publication date | May 24, 2022 |
| Grant date | May 24, 2022 |
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.
A system for consistently implementing reset and power management of IP agents on a System on a Chip (SoC). When IP agents undergo a reset, an individual negotiation takes placed between an interconnect and each IP agent over a link. Each IP agent can emerge from reset at its own time schedule, independently of the timing of the other IP agents. The interconnect may be configured as a proxy for any IP agent that is inoperable, including prior to reset, when in a power-down mode, or malfunctioning.
Opening claim text (preview).
What is claimed is: 1. A System on a Chip (SoC), comprising: an interconnect for handling transactional traffic between a plurality of IP agents on the SoC, the interconnect comprising a port, the plurality of IP agents including a first IP agent configured to initiate a wake-up sequence to enable the first IP agent to resume normal operation, the wake-up sequence involving: the first IP agent sending a wake-up communication over a link to the interconnect in response to a wake-up trigger event, while the first IP agent is in an inoperable state and the link is in a quiescent state; the interconnect waiting for the wake-up communication from the first IP agent that is in the inoperable state; and the interconnect notifying a system controller when the wake-up communication is received by forwarding the wake-up communication to the system controller a power manager arranged to place the first IP agent into the inoperable state by performing at least one of: shutting off a clock associated with the first IP agent; or reducing a power supply to the first IP agent; a quiescent manager arranged to place the link in the quiescent state by: (a) instructing the first IP agent to stop generating transactions; (b) waiting for outstanding transactions to complete and placing the link in the quiescent state responsive to determining that transactions generated by the first IP agent are complete; and (c) causing the first IP agent to initiate a sequence to enter the inoperable state. 2. The SoC of claim 1 , further comprising configuring the interconnect to act as a proxy on behalf of the first IP agent when in the inoperable state, the interconnect acting as the proxy after the interconnect drains transactions that the first IP agent has already issued by one or more of: preventing new transactions from being initiated; or waiting for outstanding transactions to complete. 3. The SoC of claim 2 , wherein the interconnect acts as the proxy on behalf of the first IP agent by: disallowing further transactions from being generated by the first IP agent; ascertaining if a source sends a transaction to the first IP agent while in the inoperable state; and responding to transactions targeted for the first IP agent. 4. The SoC of claim 3 , wherein the interconnect responds to transactions targeted for the first IP agent by sending an exception message over the interconnect to the source notifying the source of: a condition of the first IP agent, including at least one of: the first IP agent not being available; or the first IP agent being in a lower power mode; or an occurrence of an error associated with the first IP agent. 5. The SoC of claim 1 , wherein the wake-up trigger event includes one or more of the following: (a) the first IP agent receiving a communication from a source external to the SoC; (b) a predetermined time period has expired; (c) when instructed by the system controller; or (d) a valid transaction targeting the first IP agent in the inoperable state. 6. The SoC of claim 1 , wherein the wake-up sequence further involves: the system controller sending a wake-up command to the first IP agent that is in the inoperable state in response to receiving the wake-up communication forwarded by the interconnect; and the first IP agent initiating its own wake-up sequence in response to receiving the wake-up command from the system controller. 7. The SoC of claim 1 , wherein the system controller determines the trigger condition is met when at least one of the following is detected: a reduced battery-power supply of a battery-powered device that includes the SoC; an overheated condition of the SoC; a malfunction of the first IP agent; or an indication the first IP agent is not being used. 8. The SoC of claim 1 , wherein the power supply to the first IP agent is reduced to: maintain state information; or refrain from maintaining state information. 9. A System on a Chip (SoC), comprising: an interconnect for handling transactional traffic between a plurality of shared resources on the SoC, the plurality of shared resources directly connected to the interconnect at one or more ports; a link connecting a shared resource of the plurality of shared resources to the interconnect, the shared resource configured to initiate a wake-up sequence when in an inoperable state in response to a wake-up trigger event, the wake-up sequence arranged to enable the shared resource to resume normal operation and involves: the shared resource sending a wake-up communication over the link to the interconnect in response to the wake-up trigger event, while the shared resource is in the inoperable state and the link is in a quiescent state; the interconnect waiting for the wake-up communication from the shared resource that is in the inoperable state; and the interconnect notifying a system controller when the wake-up communication is received by forwarding the wake-up communication to the system controller; a power manager arranged to place the shared resource into the inoperable state responsive to the system controller determining a trigger condition is met; and a quiescent manager arranged to place the link in the quiescent state by: (a) instructing the shared resource to stop processing transactions; (b) waiting for outstanding transactions to complete and placing the link in the quiescent state responsive to determining outstanding transactions being processed by the shared resource are complete; and (c) causing the shared resource to initiate a sequence to enter the inoperable state. 10. The SoC of claim 9 , further comprising configuring the interconnect as a proxy on behalf of the shared resource when in the inoperable state, the interconnect acting as the proxy after the interconnect drains transactions that the shared resource has already issued by one or more of: preventing new transactions from being initiated; and waiting for outstanding transactions to complete. 11. The SoC of claim 10 , wherein the interconnect acts as the proxy on behalf of the shared resource by: disallowing further transactions from being generated by the shared resource; ascertaining if a source sends a transaction to the shared resource while in the inoperable state; and responding to transactions targeted for the shared resource by sending an exception message over the interconnect to the source. 12. The SoC of claim 9 , wherein the wake-up trigger event includes one of the following: (a) the shared resource receiving a communication from a source external to the SoC; (b) a predetermined time period has expired; (c) when instructed by the system controller; or (d) a valid transaction targeting the shared resource in the inoperable state. 13. The SoC of claim 9 , wherein the wake-up sequence further involves: the system controller sending a wake-up command to the shared resource that is in the inoperable state in response to receiving the wake-up communication forwarded by the interconnect; and the shared resource initiating its own wake-up sequence in response to receiving the wake-up command from the system controller. 14. The SoC of claim 9 , wherein the shared resource is one of the following, including a switch on the interconnect; an IP agent; or a component on the interconnect. 15. The SoC of claim 9 , wherein the system controller determines the trigger condition is met when at least one of the following is detected: a reduced battery-power supply of a battery-powered device that includes the SoC; an overheated condition of the SoC; a malfunction of the shared
Reducing energy consumption in communication networks · CPC title
Power saving in microcontroller unit · CPC title
Saving, restoring, recovering or retrying · CPC title
Secret sharing or secret splitting, e.g. threshold schemes · CPC title
by lowering clock frequency · CPC title
Related publications grouped by family.
Answers are generated from the same data shown on this page.