US 12,333,025 B2
Protected data accesses using remote copy operations
Ned Smith, Beaverton, OR (US); Kshitij A. Doshi, Tempe, AZ (US); Francesc Guim Bernat, Barcelona (ES); Kapil Sood, Washougal, WA (US); and Tarun Viswanathan, El Dorado Hills, CA (US)
Assigned to Intel Corporation, Santa Clara, CA (US)
Filed by Intel Corporation, Santa Clara, CA (US)
Filed on Sep. 19, 2023, as Appl. No. 18/370,137.
Application 18/370,137 is a continuation of application No. 16/845,885, filed on Apr. 10, 2020, granted, now 11,797,690.
Claims priority of provisional application 62/832,649, filed on Apr. 11, 2019.
Prior Publication US 2024/0111879 A1, Apr. 4, 2024
Int. Cl. G06F 21/60 (2013.01); G06F 15/173 (2006.01); H04L 9/32 (2006.01)
CPC G06F 21/602 (2013.01) [G06F 15/17331 (2013.01); H04L 9/3268 (2013.01)] 30 Claims
OG exemplary drawing
 
1. A cloud service provider system configurable to be used in association with multiple tenants, the cloud service provider system to be used in providing at least one service associated with at least one of the multiple tenants, the cloud service provider being configurable for use in association with at least one public cloud and/or at least one private cloud, the cloud service provider system comprising:
server hardware for use in executing at least one workload associated with the providing of the at least one service; and
multiple memory regions configurable to be associated with the multiple tenants, at least one of the multiple memory regions also to be associated with the at least one workload, the multiple tenants to be assigned access privileges with respect to the multiple memory regions;
wherein:
the server hardware is configurable for use in association with circuitry for use in processing at least one remote direct memory access (RDMA) request associated with the at least one of the multiple memory regions;
the at least one RDMA request is configurable to request at least one RDMA write access to and/or at least one RDMA read access from the at least one of the multiple memory regions;
the at least one RDMA write access is configurable to comprise data encryption for use in subsequent RDMA transmission to the at least one of the multiple memory regions;
the at least one RDMA read access is configurable to comprise RDMA reception of encrypted data from the at least one of the multiple memory regions for subsequent decryption;
the access privileges that are to be assigned to the multiple tenants with respect to the multiple memory regions are to be mutually different from each other, at least in part;
the at least one RDMA request is associated with at least one requesting tenant of the multiple tenants;
the processing comprises determining, based upon which of the access privileges is to be assigned to the at least one requesting tenant, whether to permit the at least one RDMA request;
the cloud service provider system comprises physical server resources;
the physical server resources:
comprise the server hardware; and
are configurable to comprise accelerator circuits that comprise graphics processing units (GPUs);
the cloud service provider system is configurable to dynamically allocate, based upon resource utilization trend data, resource utilization performance modeling data, and future resource utilization prediction data associated with the at least one workload, one or more portions of the physical server resources for use in association with the executing of the at least one workload;
the GPUs are configurable to implement one or more artificial intelligence models associated with machine learning and/or neural networks; and
the cloud service provider system is to execute virtual machines and/or containers that are configurable to be associated with the multiple tenants, multiple memory regions, and the at least one workload.