公开(公告)号：US12107866B2

公开(公告)日：2024-10-01

申请号：US18211537

申请日：2023-06-19

申请人： Styra, Inc.

发明人： Timothy L. Hinrichs ,  Teemu Koponen ,  Torin Sandall

IPC分类号： G06F8/65 ,  G06F9/54 ,  G06F21/54 ,  H04L9/40 ,  H04L67/10 ,  G06F21/62

CPC分类号： H04L63/108 ,  G06F8/65 ,  G06F9/542 ,  G06F9/547 ,  H04L63/10 ,  H04L63/20 ,  H04L67/10 ,  G06F21/54 ,  G06F21/6281

摘要： Some embodiments provide a method for authorizing application programming interface (API) calls on a host computer in a local cluster of computers. The method is performed in some embodiments by an API-authorizing agent executing on the host computer in the local computer cluster. From a remote cluster of computers, the method receives (1) a set of API-authorizing policies to evaluate in order to determine whether API calls to an application executing on the host computer are authorized, and (2) a set of parameters needed for evaluating the policies. With the remote cluster of computers, the method registers for notifications regarding updates to the set of parameters. The method then receives notifications, from the remote cluster, regarding an update to the set of parameters, and modifies the set of parameters based on the update. In some embodiments, the notification includes the update, while in other embodiments the method directs the remote cluster to provide the update after receiving the notification regarding the update. In addition to the notifications, the method periodically polls the remote cluster to retrieve the set of parameters needed for the received set of policies, in order to supplement data received through the notifications.

公开(公告)号：US12093696B1

公开(公告)日：2024-09-17

申请号：US16537481

申请日：2019-08-09

申请人： Perceive Corporation

发明人： Kenneth Duong ,  Jung Ko ,  Steven L. Teig

IPC分类号： G06F9/38 ,  G06F15/80 ,  G06N3/063 ,  G06N5/046

CPC分类号： G06F9/3877 ,  G06F15/80 ,  G06N3/063 ,  G06N5/046

摘要： Some embodiments provide a neural network inference circuit (NNIC) for executing a neural network that includes multiple computation nodes at multiple layers. The NNIC includes multiple core circuits including memories for storing input values for the computation nodes. The NNIC includes a set of post-processing circuits for computing output values of the computation nodes. The output values for a first layer are for storage in the core circuits as input values for a second layer. The NNIC includes an output bus that connects the post-processing circuits to the core circuits. The output bus is for (i) receiving a set of output values from the post-processing circuits, (ii) transporting the output values of the set to the core circuits based on configuration data specifying a core circuit at which each of the output values is to be stored, and (iii) aligning the output values for storage in the core circuits.

公开(公告)号：US12061988B1

公开(公告)日：2024-08-13

申请号：US17089653

申请日：2020-11-04

申请人： Perceive Corporation

发明人： Eric A. Sather ,  Steven L. Teig

IPC分类号： G06N3/08 ,  G06N3/04 ,  G06N3/084

CPC分类号： G06N3/084 ,  G06N3/04

摘要： Some embodiments provide a method for training parameters of a network. The method receives a network with layers of nodes. Each node of a set of the layers computes an output value based on a set of input values and a set of trained weight values. A first layer of the network includes a first number of filters. The method replaces the first layer with a second layer having a second number of filters that is less than the first number and a third layer, following the second layer, having the first number of filters. Each weight value in the filters of the second and third layers is restricted to a set of allowed quantized weight values. A total number of weight values in the filters of the second and third layers is less than a total number of weight values in the filters of the first layer.

公开(公告)号：US12032567B1

公开(公告)日：2024-07-09

申请号：US18114191

申请日：2023-02-24

申请人： Styra, Inc.

发明人： Torin Sandall ,  Timothy L. Hinrichs

IPC分类号： G06F16/22 ,  G06F9/54 ,  G06F16/242 ,  G06F16/28

CPC分类号： G06F16/2445 ,  G06F9/547 ,  G06F16/2246 ,  G06F16/2272 ,  G06F16/288

摘要： Some embodiments of the invention provide a method for defining code-based policies. The method generates a policy-builder first view of a policy for display in a graphical user interface (GUI) by processing a syntax tree that is generated from a code second view of the policy. The method receives, through the policy-builder first view, a modification to a portion of the policy. To reflect the modification, the method updates a portion of the syntax tree that corresponds to the portion of the policy that is affected by the modification. Based on the updating of the syntax tree, the method updates the code second view by modifying a portion of the code second view that corresponds to the updated portion of the syntax tree.

公开(公告)号：US12001948B1

公开(公告)日：2024-06-04

申请号：US15836676

申请日：2017-12-08

申请人： Perceive Corporation

发明人： Steven L. Teig ,  Andrew C. Mihal

IPC分类号： G06N3/08 ,  G06N3/047 ,  G06N7/01 ,  G06N20/00

CPC分类号： G06N3/08 ,  G06N7/01 ,  G06N20/00 ,  G06N3/047

摘要： Some embodiments of the invention provide a machine-trained method that selects an output from a plurality of outputs by processing an input. The method uses layers of machine-trained processing nodes to process the input to produce a multi-dimensional codeword. The method generates a set of affinity scores with each affinity score identifying the proximity of the produced codeword to a codeword in a first set of previously defined codewords. The method compares the set of affinity scores generated for the produced codeword with sets of affinity scores previously generated for the first-set codewords that express the proximity of the first-set codewords to a second set of codewords. The method identifies the first-set codeword that has the affinity score set that best matches the affinity score set generated for the produced codeword. The method selects the associated output of the identified first-set codeword as the output of the network.

公开(公告)号：US11995533B1

公开(公告)日：2024-05-28

申请号：US16684128

申请日：2019-11-14

申请人： Perceive Corporation

发明人： Eric A. Sather ,  Steven L. Teig

IPC分类号： G06N3/063 ,  G06F17/16 ,  G06N3/084

CPC分类号： G06N3/063 ,  G06F17/16 ,  G06N3/084

摘要： Some embodiments provide a method for executing a layer of a neural network, for a circuit that restricts a number of weight values used per layer. The method applies a first set of weights to a set of inputs to generate a first set of results. The first set of weights are restricted to a first set of allowed values. For each of one or more additional sets of weights, the method applies the respective additional set of weights to the same set of inputs to generate a respective additional set of results. The respective additional set of weights is restricted to a respective additional set of allowed values that is related to the first set of allowed values and the other additional sets of allowed values. The method generates outputs for the particular layer by combining the first set of results with each respective additional set of results.

公开(公告)号：US11941511B1

公开(公告)日：2024-03-26

申请号：US17093296

申请日：2020-11-09

申请人： Perceive Corporation

发明人： Ryan J. Cassidy ,  Steven L. Teig

IPC分类号： G06N3/04 ,  G06N3/048 ,  G06N3/049 ,  G06N3/063

CPC分类号： G06N3/049 ,  G06N3/048 ,  G06N3/063

摘要： Some embodiments of the invention provide a method for implementing a temporal convolution network (TCN) that includes several layers of machine-trained processing nodes. While processing one set of inputs that is provided to the TCN at a particular time, some of the processing nodes of the TCN use intermediate values computed by the processing nodes for other sets of inputs that were provided to the TCN at earlier times. To speed up the operation of the TCN and improve its efficiency, the method of some embodiments stores intermediate values computed by the TCN processing nodes for earlier sets of TCN inputs, so that these values can later be used for processing later set of TCN inputs.

公开(公告)号：US11863376B2

公开(公告)日：2024-01-02

申请号：US17560153

申请日：2021-12-22

申请人： VMware, Inc.

发明人： Boon S. Ang ,  Wenyi Jiang ,  Guolin Yang ,  Jin Heo

IPC分类号： H04L41/0803 ,  G06F9/455

CPC分类号： H04L41/0803 ,  G06F9/45558 ,  G06F2009/45595

摘要： Some embodiments provide a method for a first smart NIC of multiple smart NICs of a host computer. Each of the smart NICs is for performing virtual networking operations for a set of data compute machines executing on the host computer. The method determines that the first smart NIC is elected to communicate with a network management and control system that configures the virtual networking operations. The method receives a set of configuration data for the virtual networking operations from the network management and control system. The method provides the received set of configuration data to the other smart NICs of the host computer.

公开(公告)号：US11863352B2

公开(公告)日：2024-01-02

申请号：US17185844

申请日：2021-02-25

申请人： VMware, Inc.

发明人： Jianjun Shen ,  Mark Johnson ,  Gaetano Borgione ,  Benjamin John Corrie ,  Derek Beard ,  Zach James Shepherd ,  Vinay Reddy

IPC分类号： H04L12/66 ,  H04L47/125 ,  H04L9/40 ,  H04L45/42 ,  H04L45/586 ,  H04L45/44

CPC分类号： H04L12/66 ,  H04L45/42 ,  H04L45/44 ,  H04L45/586 ,  H04L47/125 ,  H04L63/0272

摘要： Some embodiments of the invention provide a novel network architecture for deploying guest clusters (GCs) including workload machines for a tenant (or other entity) within an availability zone. The novel network architecture includes a virtual private cloud (VPC) deployed in the availability zone (AZ) that includes a centralized routing element that provides access to a gateway routing element of the AZ. In some embodiments, the centralized routing element provides a set of services for packets traversing a boundary of the VPC. The services, in some embodiments, include load balancing, firewall, quality of service (QoS) and may be stateful or stateless. Guest clusters are deployed within the VPC and use the centralized routing element of the VPC to access the gateway routing element of the AZ.

公开(公告)号：US11855959B2

公开(公告)日：2023-12-26

申请号：US17079461

申请日：2020-10-24

申请人： Nicira, Inc.

发明人： Uday Masurekar ,  Jayant Jain ,  Ronghua Zhang ,  Mani Kancherla ,  Minjal Agarwal

IPC分类号： H04L61/5014 ,  H04L41/12 ,  H04L61/5061 ,  H04L101/668

CPC分类号： H04L61/5014 ,  H04L41/12 ,  H04L61/5061 ,  H04L2101/668

摘要： Some embodiments provide a method for providing dynamic host configuration protocol (DHCP) services to different data compute nodes (e.g., virtual machines) that belong to different logical networks (e.g., for different tenants in a datacenter). In some embodiments, the method inserts a logical network identifier (LNI) value to each DHCP packet and forwards the packet to a DHCP server module for processing the DHCP request. Based on the LNI value, the DHCP server of some embodiments identifies the logical network from which the DHCP packet is received. The DHCP server then provides the requested DHCP service (e.g., assigning an IP address to a data compute node that has originated the DHCP packet, assigning a domain name, etc.) according to a DHCP service configuration for the identified logical network.