Address translation technologies
US-2022261178-A1 · Aug 18, 2022 · US
US12579097B2 · US · B2
| Field | Value |
|---|---|
| Publication number | US-12579097-B2 |
| Application number | US-202419123006-A |
| Country | US |
| Kind code | B2 |
| Filing date | Feb 27, 2024 |
| Priority date | Jun 1, 2023 |
| Publication date | Mar 17, 2026 |
| Grant date | Mar 17, 2026 |
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.
The present disclosure provides a method for communication between nodes. The method includes: obtaining a list of field-programmable gate arrays; virtualizing the field-programmable gate arrays according to the list of field-programmable gate arrays to obtain a first source node and a first target node; obtaining an application descriptor between the first source node and the first target node, the application descriptor includes a memory address of the first source node and a memory address of the first target node; obtaining an identity document of the first source node according to the memory address, and obtaining an identity document of the first target node according to the memory address; and performing a communication action on the first source node and the first target node through a remote direct memory access module according to the identity document of the first source node and the identity document of the first target node.
Opening claim text (preview).
The invention claimed is: 1 . A method for communication between nodes, applied in a Kubernetes cluster management system, comprising: obtaining a list of field-programmable gate arrays; virtualizing the field-programmable gate arrays according to the list of field-programmable gate arrays to obtain a first source node and a first target node, wherein the first source node and the first target node are general purpose computing on graphics processing unit nodes; obtaining an application descriptor between the first source node and the first target node, wherein the application descriptor comprises a memory address of the first source node and a memory address of the first target node; obtaining an identity document of the first source node according to the memory address of the first source node, and obtaining an identity document of the first target node according to the memory address of the first target node; and performing a communication action on the first source node and the first target node through a remote direct memory access module according to the identity document of the first source node and the identity document of the first target node, wherein obtaining the identity document of the first source node according to the memory address of the first source node, and obtaining the identity document of the first target node according to the memory address of the first target node comprises: performing address resolution on the memory address of the first source node to obtain a local address of the first source node and the identity document of the first source node; and performing address resolution on the memory address of the first target node to obtain a local address of the first target node and the identity document of the first target node. 2 . The method according to claim 1 , wherein before obtaining the application descriptor between the first source node and the first target node, the method further comprises: allocating identity documents to a plurality of nodes, wherein the plurality of nodes comprise the first source node and the first target node; and performing unified memory address editing on the plurality of nodes according to an allocation order of the identity documents of the plurality of nodes. 3 . The method according to claim 2 , wherein the plurality of nodes are located in a cluster, and allocating identity documents to the plurality of nodes comprises: performing a cluster dynamic allocation action on the plurality of nodes to obtain identity documents corresponding to the cluster dynamic allocation action. 4 . The method according to claim 2 , wherein obtaining the application descriptor between the first source node and the first target node comprises: constructing an application description table of the plurality of nodes, wherein the application description table carries application descriptors among the plurality of nodes; and obtaining the application descriptor between the first source node and the first target node from the application description table according to a first input first output principle. 5 . The method according to claim 1 , wherein before performing address resolution on the memory address of the first source node to obtain the local address of the first source node and the identity document of the first source node, the method further comprises: generating mapping and demapping between memory addresses of the plurality of nodes with local addresses corresponding to the memory addresses. 6 . The method according to claim 1 , wherein performing the communication action on the first source node and the first target node through the remote direct memory access module according to the identity document of the first source node and the identity document of the first target node comprises: obtaining internet protocol address information of the first source node according to the identity document of the first source node; obtaining internet protocol address information of the first target node according to the identity document of the first target node; and performing the communication action on the first source node and the first target node based on a protocol preset in the remote direct memory access module according to the internet protocol address information of the first source node and the internet protocol address information of the first target node. 7 . The method according to claim 6 , wherein before obtaining internet protocol address information of the first source node according to the identity document of the first source node, the method further comprises: generating mapping between identity documents of the plurality of nodes with internet protocol address information corresponding to the identity documents. 8 . The method according to claim 6 , wherein the remote direct memory access module shares memory with graphics processing units corresponding to the general purpose computing on graphics processing unit nodes, and performing the communication action on the first source node and the first target node based on the protocol preset in the remote direct memory access module according to the internet protocol address information of the first source node and the internet protocol address information of the first target node comprises: performing a zero-copy action on the first source node and the first target node based on the protocol preset in the remote direct memory access module according to the internet protocol address information of the first source node and the internet protocol address information of the first target node. 9 . The method according to claim 8 , wherein the preset protocol comprises a transmission control protocol, and performing the zero-copy action on the first source node and the first target node based on the protocol preset in the remote direct memory access module according to the internet protocol address information of the first source node and the internet protocol address information of the first target node comprises: performing a memory read/write action on the first source node and the first target node based on the transmission control protocol preset in the remote direct memory access module according to the internet protocol address information of the first source node and the internet protocol address information of the first target node. 10 . The method according to claim 8 , wherein the preset protocol comprises a user datagram protocol, and performing the zero-copy action on the first source node and the first target node based on the protocol preset in the remote direct memory access module according to the internet protocol address information of the first source node and the internet protocol address information of the first target node comprises: performing a memory read/write action on the first source node and the first target node based on the user datagram protocol preset in the remote direct memory access module according to the internet protocol address information of the first source node and the internet protocol address information of the first target node. 11 . The method according to claim 6 , wherein the application descriptor further comprises a copy type, and performing the communication action on the first source node and the first target node based on the protocol preset in the remote direct memory access module according to the internet protocol address information of the first source node and the internet protocol address information of the first target node comprises: calling a communication mode preset in the remote direct memory access module according to the copy type; and performing the communication action on t
for distributed storage of data in networks, e.g. transport arrangements for network file system [NFS], storage area networks [SAN] or network attached storage [NAS] · CPC title
Network integration; Enabling network access in virtual machine instances · CPC title
Hypervisor-specific management and integration aspects · CPC title
Distributed shared memory [DSM], e.g. remote direct memory access [RDMA] · CPC title
in which an application is distributed across nodes in the network (software deployment G06F8/60; multiprogramming arrangements G06F9/46) · CPC title
Related publications grouped by family.
Answers are generated from the same data shown on this page.