Equalization Time Configuration Method, Chip, and Communications System
US-2021073154-A1 · Mar 11, 2021 · US
US11921660B2 · US · B2
| Field | Value |
|---|---|
| Publication number | US-11921660-B2 |
| Application number | US-202217827271-A |
| Country | US |
| Kind code | B2 |
| Filing date | May 27, 2022 |
| Priority date | May 23, 2018 |
| Publication date | Mar 5, 2024 |
| Grant date | Mar 5, 2024 |
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.
An equalization time configuration method is applied to a processor system in which a Peripheral Component Interconnect Express (PCIe) bus or a Cache Coherent Interconnect for Accelerators (CCIX) bus is used. The equalization time configuration method includes determining a working physical layer (PHY) type of a master chip and a working PHY type of a slave chip, determining an equalization time of the slave chip in a fourth phase of equalization based on the working PHY type of the master chip, and determining an equalization time of the master chip in a third phase of the equalization based on the working PHY type of the slave chip.
Opening claim text (preview).
What is claimed is: 1. An equalization time configuration method comprising: obtaining a port number of a master chip and an identity of a slave chip; obtaining, based on the port number and the identity, a channel type of a channel between a port of the master chip and the slave chip, wherein the channel type is long reach (LR) or short reach (SR); obtaining a first physical layer (PHY) type supported by the master chip and a second PHY type supported by the slave chip; determining whether both the first PHY type and the second PHY type comprise the channel type; determining a first working PHY type of the master chip and a second working PHY type of the slave chip when both the first PHY type and the second PHY type comprise the channel type, wherein both the first working PHY type and the second working PHY type are the channel type; configuring a first equalization time of the master chip in a third phase of an equalization based on the second working PHY type; and configuring a second equalization time of the slave chip in a fourth phase of the equalization based on the first working PHY type. 2. The equalization time configuration method of claim 1 , further comprising: configuring a first equalization circuit of the slave chip based on the second working PHY type; determining, based on the first equalization circuit, a third equalization time required by the slave chip in the third phase; and configuring the first equalization time based on the third equalization time. 3. The equalization time configuration method of claim 1 , further comprising: configuring a second equalization circuit of the master chip based on the first working PHY type; determining, based on the second equalization circuit, a third equalization time required by the master chip in the fourth phase; and configuring the second equalization time based on the third equalization time. 4. The equalization time configuration method of claim 1 , wherein the first equalization time is T1 when the second working PHY type is the SR, wherein the first equalization time is T2 when the second working PHY type is the LR, and wherein T2 is greater than T1. 5. The equalization time configuration method of claim 1 , wherein the second equalization time is T3 when the first working PHY type is the SR, wherein the second equalization time is T4 when the first working PHY type is the LR, and wherein T4 is greater than T3. 6. The equalization time configuration method of claim 1 , further comprising: when both the first working PHY type and the second working PHY type are the LR: reading a third equalization time of the slave chip in the third phase; writing the third equalization time into the master chip to set the third equalization time as the first equalization time; reading a fourth equalization time of the master chip in the fourth phase; and writing the fourth equalization time into the slave chip to set the fourth equalization time as the second equalization time; and configuring both the first equalization time and the second equalization time as a default value when both the first working PHY type and the second working PHY type are the SR. 7. The equalization time configuration method of claim 1 , further comprising: when both the first working PHY type and the second working PHY type are SR: reading a third equalization time of the slave chip in the third phase; writing the third equalization time into the master chip to set the third equalization time as the first equalization time; reading a fourth equalization time of the master chip in the fourth phase; and writing the fourth equalization time into the slave chip to set the fourth equalization time as the second equalization time; and configuring both the first equalization time and the second equalization time as a default value when both the first working PHY type and the second working PHY type are the LR. 8. The equalization time configuration method of claim 1 , wherein the master chip and the slave chip are coupled to each other using a Peripheral Component Interconnect Express (PCIe) bus or a Cache Coherent Interconnect for Accelerators (CCIX) bus, wherein the master chip is a root complex or a switching chip, and wherein the slave chip is an endpoint device independent of the master chip. 9. The equalization time configuration method of claim 1 , further comprising obtaining the channel type based on a loss of the channel, wherein a first channel loss corresponding to the LR is greater than a second channel loss corresponding to the SR. 10. The equalization time configuration method of claim 1 , wherein the first PHY type supported by the master chip is based on a first channel loss that the master chip is able to drive, wherein the second PHY type supported by the slave chip is based on a second channel loss that the slave chip is able to drive, wherein the first channel loss is greater when the first PHY type is the LR than when the first PHY type is the SR, and wherein the second channel loss is greater when the second PHY type is the LR than when the second PHY type is the SR. 11. The equalization time configuration method of claim 1 , further comprising: storing the first PHY type in a first register of the master chip; and storing the second PHY type in a second register of the slave chip. 12. An equalization time configuration apparatus comprising: a transceiver configured to: receive a port number of a master chip and an identity of a slave chip; and receive a first physical layer (PHY) type supported by the master chip and a second PHY type supported by the slave chip; and a processor coupled to the transceiver and configured to: determine, based on the port number and the identity, a channel type of a channel between a port of the master chip and the slave chip, wherein the channel type is long reach (LR) or short reach (SR); determine whether both the first PHY type and the second PHY type comprise the channel type; determine a first working PHY type of the master chip and a second working PHY type of the slave chip when both the first PHY type and the second PHY type comprise the channel type, wherein both the first working PHY type and the second working PHY type are the channel type; configure a first equalization time of the master chip in a third phase of an equalization based on the second working PHY type; and configure a second equalization time of the slave chip in a fourth phase of the equalization based on the first working PHY type. 13. The equalization time configuration apparatus of claim 12 , wherein the processor is further configured to configure the first equalization time based on a third equalization time required by the slave chip in the third phase, wherein the third equalization time is based on a first equalization circuit of the slave chip, and wherein the first equalization circuit is based on the second working PHY type. 14. The equalization time configuration apparatus of claim 12 , wherein the processor is further configured to configure the second equalization time based on a third equalization time required by the master chip in the fourth phase, wherein the third equalization time is based on a second equalization circuit of the master chip, and wherein the second equalization circuit is based on the first working PHY type. 15. The equalization time configuration apparatus of claim 12 , wherein the processor is further configured to: configure both the first equalization time and the second equalization time as a default value when both the first working PHY type and the second working PHY t
with centralised access control · CPC title
using switching circuits, e.g. switching matrix, connection or expansion network (G06F13/4009 takes precedence) · CPC title
being an input/output bus, e.g. ISA bus, EISA bus, PCI bus, SCSI bus · CPC title
Version control (security arrangements therefor G06F21/57); Configuration management · CPC title
Drivers or receivers (G06F13/4086 takes precedence; for multistate logic circuits H03K19/0002) · CPC title
Related publications grouped by family.
Answers are generated from the same data shown on this page.