IP Library Granted Patent US 11,669,481
Granted Patent B2
US 11,669,481 · App. 17/559,002 · Granted Jun 6, 2023

Enabling sync header suppression latency optimization in the presence of retimers for serial interconnect

Inventors: Michelle Jen (Mountain View, CA); Debendra Das Sharma (Saratoga, CA); Bruce Tennant (Hillsboro, OR); Prahladachar Jayaprakash Bharadwaj (Bangalore, IN)
Assignee: Intel Corporation
G06F13/4068G06F1/3237G06F13/4291H04L69/161G06F13/385
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 11,669,481
App. No.
17/559,002
Granted
Jun 6, 2023
Kind
B2
Abstract

Methods and apparatuses associated with a secure stream protocol for a serial interconnect are disclosed herein. In embodiments, an apparatus comprises a transmitter and a receiver. The transmitter and receiver are configured to transmit and receive transaction layer data packets through a link, the transaction layer data packets including indicators associated with transmission of order set transmitted after a predetermined number of data blocks, when the transmission is during a header suppression mode. Additional features and other embodiments are also disclosed.

Claims (40)

1. An apparatus comprising:

a multi-protocol multiplexer to receive at least one of first information of a first interconnect protocol or second information of a second interconnect protocol, the multi-protocol multiplexer to direct the at least one of the first information or the second information to a physical layer; and

the physical layer coupled to the multi-protocol multiplexer, wherein the physical layer is to receive the first information of the first interconnect protocol and transmit a packet on a plurality of lanes of a serial interconnect, the packet comprising a protocol ID and payload information comprising a plurality of flits,

wherein the physical layer is to:

send the protocol ID in 8-bit chunks on two consecutive lanes of the plurality of lanes, wherein the protocol ID is to be sent prior to each of the plurality of flits;

send the plurality of flits on the plurality of lanes; and

send an ordered set after a predetermined number of data blocks, during a mode in which sync headers are suppressed.

2. The apparatus of claim 1 , wherein the plurality of lanes comprises 16 lanes.

3. The apparatus of claim 1 , wherein the physical layer is to send the ordered set after 340 data blocks.

4. The apparatus of claim 1 , wherein the physical layer is to send the ordered set comprising a SKP ordered set.

5. The apparatus of claim 1 , wherein the physical layer is to send the ordered set comprising a control SKP ordered set.

6. The apparatus of claim 1 , wherein the physical layer is to send the plurality of flits having a 528-bit flit width.

7. The apparatus of claim 1 , wherein the first interconnect protocol comprises a Peripheral Component Interconnect Express protocol and the second interconnect protocol comprises a memory protocol.

8. The apparatus of claim 1 , wherein the physical layer is to send an electrical idle ordered set when a data stream is to be exited.

9. A method comprising:

receiving, in a common physical layer (PHY) of an integrated circuit, from a multi-protocol multiplexer coupled to the common PHY, information of at least one of a first interconnect protocol or a second interconnect protocol;

sending the information in a packet, from the common PHY, to a destination component via a link, the packet comprising a protocol ID and payload information comprising a plurality of flits, wherein sending the information comprises:

sending the protocol ID in 8-bit chunks on two consecutive lanes of the plurality of lanes, prior to each of the plurality of flits;

sending the plurality of flits on the plurality of lanes; and

sending an ordered set after a predetermined number of data blocks, during a mode in which sync headers are suppressed.

10. The method of claim 9 , further comprising sending the ordered set after 340 data blocks.

11. The method of claim 9 , further comprising sending the ordered set comprising a SKP ordered set.

12. The method of claim 9 , further comprising sending the ordered set comprising a control SKP ordered set.

13. The method of claim 9 , further comprising sending the plurality of flits having a 528-bit flit width.

14. The method of claim 9 , further comprising sending an electrical idle ordered set when a data stream is to be exited.

15. A system comprising:

a central processing unit (CPU) having:

at least one core; and

a physical layer to receive first information of a first interconnect protocol and output a packet on a plurality of lanes of a link, the packet comprising a protocol ID and payload information comprising a plurality of flits,

wherein the physical layer is to:

send the protocol ID in 8-bit chunks on two consecutive lanes of the plurality of lanes, prior to each of the plurality of flits;

send the plurality of flits on the plurality of lanes; and

send an ordered set after a predetermined number of data blocks, during a mode in which sync headers are suppressed;

a retimer coupled to the CPU via the link; and

an accelerator coupled to the retimer.

16. The system of claim 15 , wherein the plurality of lanes comprises 16 lanes.

17. The system of claim 15 , wherein the physical layer is to send the ordered set after 340 data blocks.

18. The system of claim 15 , wherein the physical layer is to send the ordered set comprising a SKP ordered set.

19. The system of claim 15 , wherein the physical layer is to send the ordered set comprising a control SKP ordered set.

20. The system of claim 15 , wherein the physical layer is to send the plurality of flits having a 528-bit flit width.

Continuity (3)
Continuation 16554974 · Aug 29, 2019
Provisional Application 62815572 · Mar 8, 2019
Related Publication 20220114128A1 · Apr 14, 2022
Cited By (13)
US 12,418,429 US 12,422,981 US 12,430,271 US 12,436,885 US 12,476,832 US 12,541,477 US 12,541,480 US 12,556,417 US 12,561,266 US 12,561,270 US 12,572,491 US 12,650,944 US 12,664,117