公开(公告)号：US11082347B2

公开(公告)日：2021-08-03

申请号：US16277349

申请日：2019-02-15

申请人： Nvidia Corporation

发明人： Glenn Dearth ,  Nan Jiang ,  John Wortman ,  Alex Ishii ,  Mark Hummel ,  Rich Reeves

IPC分类号： H04L12/801 ,  H04L12/26 ,  H04L12/825

摘要： Multiple processors are often used in computing systems to solve very large, complex problems, such as those encountered in artificial intelligence. Such processors typically exchange data among each other via an interconnect fabric (such as, e.g., a group of network connections and switches) in solving such complex problems. The amount of data injected into the interconnect fabric by the processors can at times overwhelm the interconnect fabric preventing some of the processors from communicating with each other. To address this problem, techniques are disclosed to enable, for example, processors that are connected to an interconnect fabric to coordinate and control the amount of data injected so that the interconnect fabric does not get overwhelmed.

公开(公告)号：US20210067449A1

公开(公告)日：2021-03-04

申请号：US16553511

申请日：2019-08-28

申请人： Nvidia Corporation

发明人： Glenn Dearth ,  Mark Hummel ,  Jonathan Owen ,  Mike Osborn ,  John Wortman ,  Rich Reeves

IPC分类号： H04L12/801 ,  H04L12/947 ,  H04L12/743 ,  H04L7/00

摘要： An endpoint in a network may make posted or non-posted write requests to another endpoint in the network. For a non-posted write request, the target endpoint provides a response to the requesting endpoint indicating that the write request has been serviced. For a posted write request, the target endpoint does not provide such an acknowledgment. Hence, posted write requests have lower overhead, but they suffer from potential synchronization and resiliency issues. While non-posted write requests do not have those issues, they cause increased load on the network because such requests require the target endpoint to acknowledge each write request. Introduced herein is a network operation technique that uses non-posted transactions while maintaining a load overhead of the network as a manageable level. The introduced technique reduces the load overhead of the non-posted write requests by collapsing and reducing a number of the responses.

公开(公告)号：US11038800B2

公开(公告)日：2021-06-15

申请号：US16553511

申请日：2019-08-28

申请人： Nvidia Corporation

发明人： Glenn Dearth ,  Mark Hummel ,  Jonathan Owen ,  Mike Osborn ,  John Wortman ,  Rich Reeves

IPC分类号： H04L12/801 ,  H04L7/00 ,  H04L12/743 ,  H04L12/947 ,  G06F13/16 ,  G06F13/30 ,  G06F13/42

摘要： An endpoint in a network may make posted or non-posted write requests to another endpoint in the network. For a non-posted write request, the target endpoint provides a response to the requesting endpoint indicating that the write request has been serviced. For a posted write request, the target endpoint does not provide such an acknowledgment. Hence, posted write requests have lower overhead, but they suffer from potential synchronization and resiliency issues. While non-posted write requests do not have those issues, they cause increased load on the network because such requests require the target endpoint to acknowledge each write request. Introduced herein is a network operation technique that uses non-posted transactions while maintaining a load overhead of the network as a manageable level. The introduced technique reduces the load overhead of the non-posted write requests by collapsing and reducing a number of the responses.

公开(公告)号：US20190297018A1

公开(公告)日：2019-09-26

申请号：US16277349

申请日：2019-02-15

申请人： Nvidia Corporation

发明人： Glenn Dearth ,  Nan Jiang ,  John Wortman ,  Alex Ishii ,  Mark Hummel ,  Rich Reeves

IPC分类号： H04L12/801 ,  H04L12/825 ,  H04L12/26

摘要： Multiple processors are often used in computing systems to solve very large, complex problems, such as those encountered in artificial intelligence. Such processors typically exchange data among each other via an interconnect fabric (such as, e.g., a group of network connections and switches) in solving such complex problems. The amount of data injected into the interconnect fabric by the processors can at times overwhelm the interconnect fabric preventing some of the processors from communicating with each other. To address this problem, techniques are disclosed to enable, for example, processors that are connected to an interconnect fabric to coordinate and control the amount of data injected so that the interconnect fabric does not get overwhelmed.