Packet transmission scheduling
US-2023061794-A1 · Mar 2, 2023 · US
US12132802B2 · US · B2
| Field | Value |
|---|---|
| Publication number | US-12132802-B2 |
| Application number | US-202117553387-A |
| Country | US |
| Kind code | B2 |
| Filing date | Dec 16, 2021 |
| Priority date | Sep 1, 2021 |
| Publication date | Oct 29, 2024 |
| Grant date | Oct 29, 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 application specific integrated circuit (ASIC) is provided for reliable transport of packets. The network interface card may include a reliable transport accelerator (RTA). The RTA may include a cache lookup database. The RTA may be configured to determine, from a received data packet, a connection identifier and query the cache lookup database for a cache entry corresponding to a connection context having the connection identifier. In response to the query, the RTA may receive a cache hit or a cache miss.
Opening claim text (preview).
The invention claimed is: 1. An application specific integrated circuit (ASIC) of a network interface card, including: a reliable transport accelerator (RTA) including a cache lookup database, wherein the RTA is configured to: determine, from a received data packet, a connection identifier; query the cache lookup database for a cache entry corresponding to a connection context having the connection identifier; and receive, in response to the query, a cache hit or a cache miss, wherein: the network interface card includes off-chip memory storing one or more connection contexts associated with one or more connection identifiers, the off-chip memory is positioned on the network interface card and connected to the ASIC, and the RTA communicates with the off-chip memory via a network-on-chip (NOC). 2. The ASIC of claim 1 , wherein the ASIC further includes on-chip memory storing one or more connection contexts associated with one or more connection identifiers. 3. The ASIC of claim 2 , wherein a cache miss indicates that the connection context having the connection identifier is not stored in the cache lookup database. 4. The ASIC of claim 3 , wherein, after receiving a cache miss, the RTA retrieves the connection context from the on-chip memory or the off-chip memory. 5. The ASIC of claim 4 , wherein the RTA stores the connection context in the on-chip memory or the off-chip memory based on a predefined user configuration. 6. The ASIC of claim 1 , wherein a cache hit indicates that the connection context having the connection identifier is stored in the cache lookup database. 7. The ASIC of claim 6 , further including a cache policy stored by the cache lookup database, wherein the cache policy defines when one or more connection contexts are evicted from the cache lookup database. 8. The ASIC of claim 7 , wherein evicted connection contexts are moved to on-chip or off-chip memory. 9. The ASIC of claim 1 further comprising an upper-layer protocol accelerator (ULP) and a packet process pipeline accelerator. 10. The ASIC of claim 1 , wherein the RTA further includes a context flush interface, and the RTA is further configured to: dynamically fetch and update connection context at run-time; and update, using the context flush interface, the context connections stored in the cache lookup database. 11. The ASIC of claim 1 , wherein: the RTA further includes a reliable transport protocol partitioned into at least two layers, and the at least two layers of protocols include a solicitation layer configured to end-point admission control and a sliding window layer configured for end-to-end reliable delivery and congestion control. 12. The ASIC of claim 1 , wherein the RTA communicates with the off-chip memory for managing connection contexts with the off-chip memory. 13. A method for managing connection contexts, the method including: determining, by a reliable transport accelerator (RTA) including a cache lookup database, a connection identifier for a received data packet; querying, by the RTA, the cache lookup database for a cache entry corresponding to a connection context having the connection identifier; and receiving, from the cache lookup database, in response to the query, a cache hit or a cache miss, wherein: the RTA communicates with off-chip memory via a network-on-chip (NOC), the off-chip memory stores one or more connection contexts associated with one or more connection identifiers, the off-chip memory is positioned on a network interface card and connected to an application specific integrated circuit (ASIC) of the network interface card. 14. The method of claim 13 , wherein a cache miss indicates that the connection context having the connection identifier is not stored in the cache lookup database. 15. The method of claim 14 , wherein, after receiving a cache miss, the RTA retrieves the connection context from on-chip memory or off-chip memory. 16. The method of claim 15 , wherein the RTA stores the connection context in the on-chip memory or the off-chip memory based on a predefined user configuration. 17. The method of claim 13 , wherein a cache hit indicates that the connection context having the connection identifier is stored in the cache lookup database. 18. The method of claim 13 , wherein the RTA further includes a cache policy stored by the cache lookup database, wherein the cache policy defines when one or more connection contexts are evicted from the cache lookup database. 19. The method of claim 18 , wherein evicted connection contexts are moved to on-chip or off-chip memory. 20. The method of claim 19 , wherein the on-chip memory is located on an ASIC with the RTA.
in the transport layer [OSI layer 4] (H04L69/16 takes precedence) · CPC title
Pipelined operation · CPC title
Database cache management · CPC title
Centralised controller, i.e. arbitration or scheduling · CPC title
Storing data temporarily at an intermediate stage, e.g. caching · CPC title
Related publications grouped by family.
Answers are generated from the same data shown on this page.