Patents by Inventor German Rodriguez Herrera
German Rodriguez Herrera has filed for patents to protect the following inventions. This listing includes patent applications that are pending as well as patents that have already been granted by the United States Patent and Trademark Office (USPTO).
-
Patent number: 10911846Abstract: Various leaf switch modules including optical network interfaces, electrical network interfaces and packet processors are provided. Some of the leaf switch modules as described herein are adapted for upward transmission of signals from external client devices to an electrical fabric, and include O/E converters; other leaf switch modules are adapted for downward transmission of signals from an electrical fabric to external client devices, and include E/O converters. A third type of leaf switch as described herein is adapted for both upward and downward transmission of signals, and includes both types of converter. In addition to the leaf switch modules themselves, an optoelectronic switch containing a plurality of those leaf switches is also described.Type: GrantFiled: March 22, 2018Date of Patent: February 2, 2021Assignee: Rockley Photonics LimitedInventors: Nicholas Kucharewski, Cyriel Johan Agnes Minkenberg, German Rodriguez Herrera
-
Patent number: 10778814Abstract: A system and method for classifying packets according to packet header field values. Each of a set of subkey tables is searched for a respective packet header field value; each such search results in a value for a subkey. The subkeys are combined to form a decision key. A decision table is then searched for the decision key. The search of the decision table results in an action code and a reason code, one or both of which may be used to determine how to further process the packet.Type: GrantFiled: January 24, 2018Date of Patent: September 15, 2020Assignee: Rockley Photonics LimitedInventors: Chiang Yeh, German Rodriguez Herrera, Bhaskar Chowdhuri
-
Publication number: 20200037055Abstract: Various leaf switch modules including optical network interfaces, electrical network interfaces and packet processors are provided. Some of the leaf switch modules as described herein are adapted for upward transmission of signals from external client devices to an electrical fabric, and include O/E converters; other leaf switch modules are adapted for downward transmission of signals from an electrical fabric to external client devices, and include E/O converters. A third type of leaf switch as described herein is adapted for both upward and downward transmission of signals, and includes both types of converter. In addition to the leaf switch modules themselves, an optoelectronic switch containing a plurality of those leaf switches is also described.Type: ApplicationFiled: March 22, 2018Publication date: January 30, 2020Inventors: Nicholas KUCHAREWSKI, Cyriel Johan Agnes MINKENBERG, German RODRIGUEZ HERRERA
-
Patent number: 10284682Abstract: Disclosed herein is a system comprising a plurality of agents that desire access to a resource; a finite amount of an internal state; a processor that is configured to enforce an arbitration mechanism to translate a quota specification for the plurality of agents according to a set of rules comprising i) all classes of service that are serviceable are served according to the quota specification; ii) if an underserviced class is not serviceable, a serviceable class continues to be granted access to the one or more resources even if the granted access leads to an increase in the underservice of a non-serviceable class; iii) as soon as the underserviced class becomes serviceable, it will in priority recuperate its accumulated disadvantage until its quota specification is reached; and iv) the internal state is updated upon reaching boundary conditions.Type: GrantFiled: April 20, 2016Date of Patent: May 7, 2019Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATIONInventors: Wolfgang E. Denzel, Cyriel J. Minkenberg, Bogdan Prisacari, German Rodriguez Herrera
-
Patent number: 10042683Abstract: A method for all-to-all message exchange between program tasks including N>1 hierarchy levels ln, n=1 to N, in which a first level l1 includes a plurality of group tasks and each higher level l(n>1) includes at least one group of level l(n?1) groups to which that task belongs in respective hierarchy levels of the network topology; sending a message via the interconnection network to a respective destination task whose hierarchical identifier is determined; and using the hierarchical identifier to send the program task and the network topology, such that the resulting exchange pattern for the all-to-all message exchange exploits a hierarchical distance in the network topology in a desired manner.Type: GrantFiled: April 18, 2017Date of Patent: August 7, 2018Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATIONInventors: Cyriel J. Minkenberg, Bogdan Prisacari, German Rodriguez Herrera
-
Publication number: 20180213067Abstract: A system and method for classifying packets according to packet header field values. Each of a set of subkey tables is searched for a respective packet header field value; each such search results in a value for a subkey. The subkeys are combined to form a decision key. A decision table is then searched for the decision key. The search of the decision table results in an action code and a reason code, one or both of which may be used to determine how to further process the packet.Type: ApplicationFiled: January 24, 2018Publication date: July 26, 2018Inventors: Chiang Yeh, German Rodriguez Herrera, Bhaskar Chowdhuri
-
Publication number: 20170310788Abstract: Disclosed herein is a system comprising a plurality of agents that desire access to a resource; a finite amount of an internal state; a processor that is configured to enforce an arbitration mechanism to translate a quota specification for the plurality of agents according to a set of rules comprising i) all classes of service that are serviceable are served according to the quota specification; ii) if an underserviced class is not serviceable, a serviceable class continues to be granted access to the one or more resources even if the granted access leads to an increase in the underservice of a non-serviceable class; iii) as soon as the underserviced class becomes serviceable, it will in priority recuperate its accumulated disadvantage until its quota specification is reached; and iv) the internal state is updated upon reaching boundary conditions.Type: ApplicationFiled: April 20, 2016Publication date: October 26, 2017Inventors: Wolfgang E. Denzel, Cyriel J. Minkenberg, Bogdan Prisacari, German Rodriguez Herrera
-
Patent number: 9740542Abstract: A method for all-to-all message exchange between program tasks including N>1 hierarchy levels ln, n=1 to N, in which a first level l1 includes a plurality of group tasks and each higher level l(n>1) includes at least one group of level l(n?1) groups to which that task belongs in respective hierarchy levels of the network topology; sending a message via the interconnection network to a respective destination task whose hierarchical identifier is determined; and using the hierarchical identifier to send the program task and the network topology, such that the resulting exchange pattern for the all-to-all message exchange exploits a hierarchical distance in the network topology in a desired manner.Type: GrantFiled: April 18, 2016Date of Patent: August 22, 2017Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATIONInventors: Cyriel J. Minkenberg, Bogdan Prisacari, German Rodriguez Herrera
-
Publication number: 20170220398Abstract: A method for all-to-all message exchange between program tasks including N>1 hierarchy levels ln, n=1 to N, in which a first level l1 includes a plurality of group tasks and each higher level l(n>1) includes at least one group of level l(n?1) groups to which that task belongs in respective hierarchy levels of the network topology; sending a message via the interconnection network to a respective destination task whose hierarchical identifier is determined; and using the hierarchical identifier to send the program task and the network topology, such that the resulting exchange pattern for the all-to-all message exchange exploits a hierarchical distance in the network topology in a desired manner.Type: ApplicationFiled: April 18, 2017Publication date: August 3, 2017Inventors: Cyriel J. Minkenberg, Bogdan Prisacari, German Rodriguez Herrera
-
Patent number: 9720738Abstract: A computer-implemented method including: (i) receiving a computational task to be processed by the datacenter environment; (ii) receiving a set of computational task parameters, The computational task parameters specifying characteristics of the computational task to be processed; (iii) receiving a set of computing entity parameters, The computing entity parameters specifying characteristics of the computing entities; (iv) transmitting the computational task parameters and the computing entity parameters to a scheduling entity; and (v) selecting one or more computing entities of The plurality of computing entities for processing the computational task by the scheduling entity, based on various factors.Type: GrantFiled: April 9, 2015Date of Patent: August 1, 2017Assignee: International Business Machines CorporationInventors: Andreea S. Anghel, Bogdan Prisacari, German Rodriguez Herrera
-
Patent number: 9626322Abstract: A multiprocessor computer system includes a plurality of processor nodes and at least a three-tier hierarchical network interconnecting the processor nodes. The hierarchical network includes a plurality of routers interconnected such that each router is connected to a subset of the plurality of processor nodes; the plurality of routers are arranged in a hierarchy of n?3 tiers (T1, . . . , Tn); the plurality of routers are partitioned into disjoint groups at the first tier T1, the groups at tier Ti being partitioned into disjoint groups (of complete Ti groups) at the next tier Ti+1 and a top tier Tn including a single group containing all of the plurality of routers; and for all tiers 1?i?n, each tier-Ti?1 subgroup within a tier Ti group is connected by at least one link to all other tier-Ti?1 subgroups within the same tier Ti group.Type: GrantFiled: September 15, 2014Date of Patent: April 18, 2017Assignee: International Business Machines CorporationInventors: Baba L. Arimilli, Wolfgang Denzel, Philip Heidelberger, German Rodriguez Herrera, Christopher J. Johnson, Lonny Lambrecht, Cyriel Minkenberg, Bogdan Prisacari
-
Patent number: 9519605Abstract: A multiprocessor computer system includes a plurality of processor nodes and at least a three-tier hierarchical network interconnecting the processor nodes. The hierarchical network includes a plurality of routers interconnected such that each router is connected to a subset of the plurality of processor nodes; the plurality of routers are arranged in a hierarchy of n?3 tiers (T1, . . . , Tn); the plurality of routers are partitioned into disjoint groups at the first tier T1, the groups at tier Ti being partitioned into disjoint groups (of complete Ti groups) at the next tier Ti+1 and a top tier Tn including a single group containing all of the plurality of routers; and for all tiers 1?i?n, each tier-Ti?1 subgroup within a tier Ti group is connected by at least one link to all other tier-Ti?1 subgroups within the same tier Ti group.Type: GrantFiled: July 8, 2014Date of Patent: December 13, 2016Assignee: International Business Machines CorporationInventors: Baba L. Arimilli, Wolfgang Denzel, Philip Heidelberger, German Rodriguez Herrera, Christopher J. Johnson, Lonny Lambrecht, Cyriel Minkenberg, Bogdan Prisacari
-
Publication number: 20160299785Abstract: A computer-implemented method including: (i) receiving a computational task to be processed by the datacenter environment; (ii) receiving a set of computational task parameters, The computational task parameters specifying characteristics of the computational task to be processed; (iii) receiving a set of computing entity parameters, The computing entity parameters specifying characteristics of the computing entities; (iv) transmitting the computational task parameters and the computing entity parameters to a scheduling entity; and (v) selecting one or more computing entities of The plurality of computing entities for processing the computational task by the scheduling entity, based on various factors.Type: ApplicationFiled: April 9, 2015Publication date: October 13, 2016Inventors: Andreea S. Anghel, Bogdan Prisacari, German Rodriguez Herrera
-
Publication number: 20160239356Abstract: A method for all-to-all message exchange between program tasks including N>1 hierarchy levels ln, n=1 to N, in which a first level l1 includes a plurality of group tasks and each higher level l(n>1) includes at least one group of level l(n-1) groups to which that task belongs in respective hierarchy levels of the network topology; sending a message via the interconnection network to a respective destination task whose hierarchical identifier is determined; and using the hierarchical identifier to send the program task and the network topology, such that the resulting exchange pattern for the all-to-all message exchange exploits a hierarchical distance in the network topology in a desired manner.Type: ApplicationFiled: April 18, 2016Publication date: August 18, 2016Inventors: Cyriel J. Minkenberg, Bogdan Prisacari, German Rodriguez Herrera
-
Patent number: 9329914Abstract: A method for all-to-all message exchange between program tasks including N>1 hierarchy levels ln, n=1 to N, in which a first level l1 includes a plurality of group tasks and each higher level l(n>1) includes at least one group of level l(n?1) groups to which that task belongs in respective hierarchy levels of the network topology; sending a message via the interconnection network to a respective destination task whose hierarchical identifier is determined; and using the hierarchical identifier to send the program task and the network topology, such that the resulting exchange pattern for the all-to-all message exchange exploits a hierarchical distance in the network topology in a desired manner.Type: GrantFiled: February 12, 2014Date of Patent: May 3, 2016Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATIONInventors: Cyriel J Minkenberg, Bogdan Prisacari, German Rodriguez Herrera
-
Patent number: 9294385Abstract: Methods and apparatus are provided for routing data packets between source and destination switches in a fat tree network. For each packet, a route is selected having three or less routing phases such that the route follows a shortest path across the network between the source and destination switches. The data packet is transmitted from the source switch to the destination switch, via the route, on one of first and second virtual channels unless the route includes a predetermined one of a down-up turn and an up-down turn. If the route includes the predetermined one of a down-up turn and an up-down turn, the data packet is transmitted, via the route, on the first virtual channel up to the switch 1 at which the turn occurs and on the second virtual channel from that switch. This provides full-connectivity in fat tree networks with deadlock free operation.Type: GrantFiled: March 3, 2014Date of Patent: March 22, 2016Assignee: INTERNATIONAL BUSINESS MACHINES CORPORATIONInventors: Mircea Gusat, Cyriel J Minkenberg, German Rodriguez Herrera
-
Publication number: 20160012002Abstract: A multiprocessor computer system includes a plurality of processor nodes and at least a three-tier hierarchical network interconnecting the processor nodes. The hierarchical network includes a plurality of routers interconnected such that each router is connected to a subset of the plurality of processor nodes; the plurality of routers are arranged in a hierarchy of n?3 tiers (T1, . . . , Tn); the plurality of routers are partitioned into disjoint groups at the first tier T1, the groups at tier Ti being partitioned into disjoint groups (of complete Ti groups) at the next tier Ti+1 and a top tier Tn including a single group containing all of the plurality of routers; and for all tiers 1?i?n, each tier-Ti?1 subgroup within a tier Ti group is connected by at least one link to all other tier-Ti?1 subgroups within the same tier Ti group.Type: ApplicationFiled: September 15, 2014Publication date: January 14, 2016Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATIONInventors: BABA L. ARIMILLI, WOLFGANG DENZEL, PHILIP HEIDELBERGER, GERMAN RODRIGUEZ HERRERA, CHRISTOPHER J. JOHNSON, LONNY LAMBRECHT, CYRIEL MINKENBERG, BOGDAN PRISACARI
-
Publication number: 20160012004Abstract: A multiprocessor computer system includes a plurality of processor nodes and at least a three-tier hierarchical network interconnecting the processor nodes. The hierarchical network includes a plurality of routers interconnected such that each router is connected to a subset of the plurality of processor nodes; the plurality of routers are arranged in a hierarchy of n?3 tiers (T1, . . . , Tn); the plurality of routers are partitioned into disjoint groups at the first tier T1, the groups at tier Ti being partitioned into disjoint groups (of complete Ti groups) at the next tier Ti+1 and a top tier Tn including a single group containing all of the plurality of routers; and for all tiers 1?i?n, each tier-Ti?1 subgroup within a tier Ti group is connected by at least one link to all other tier-Ti?1 subgroups within the same tier Ti group.Type: ApplicationFiled: July 8, 2014Publication date: January 14, 2016Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATIONInventors: BABA L. ARIMILLI, WOLFGANG DENZEL, PHILIP HEIDELBERGER, GERMAN RODRIGUEZ HERRERA, CHRISTOPHER J. JOHNSON, LONNY LAMBRECHT, CYRIEL MINKENBERG, BOGDAN PRISACARI
-
Publication number: 20150249590Abstract: Methods and apparatus are provided for routing data packets between source and destination switches in a fat tree network. For each packet, a route is selected having three or less routing phases such that the route follows a shortest path across the network between the source and destination switches. The data packet is transmitted from the source switch to the destination switch, via the route, on one of first and second virtual channels unless the route includes a predetermined one of a down-up turn and an up-down turn. If the route includes the predetermined one of a down-up turn and an up-down turn, the data packet is transmitted, via the route, on the first virtual channel up to the switch 1 at which the turn occurs and on the second virtual channel from that switch. This provides full-connectivity in fat tree networks with deadlock free operation.Type: ApplicationFiled: March 3, 2014Publication date: September 3, 2015Applicant: International Business Machines CorporationInventors: Mircea Gusat, Cyriel J. Minkenberg, German Rodriguez Herrera
-
Publication number: 20140245324Abstract: A method for all-to-all message exchange between program tasks including N>1 hierarchy levels ln, n=1 to N, in which a first level l1 includes a plurality of group tasks and each higher level l(n>1) includes at least one group of level l(n?1) groups to which that task belongs in respective hierarchy levels of the network topology; sending a message via the interconnection network to a respective destination task whose hierarchical identifier is determined; and using the hierarchical identifier to send the program task and the network topology, such that the resulting exchange pattern for the all-to-all message exchange exploits a hierarchical distance in the network topology in a desired manner.Type: ApplicationFiled: February 12, 2014Publication date: August 28, 2014Applicant: INTERNATIONAL BUSINESS MACHINES CORPORATIONInventors: Cyriel J Minkenberg, Bogdan Prisacari, German Rodriguez Herrera