A system for processing gather and scatter instructions can implement a front-end subsystem, a back-end subsystem, or both. The front-end subsystem includes a prediction unit configured to determine a predicted quantity of coalesced memory access operations required by an instruction. A decode unit converts the instruction into a plurality of access operations based on the predicted quantity, and transmits the plurality of access operations and an indication of the predicted quantity to an issue queue. The back-end subsystem includes a load-store unit that receives a plurality of access operations corresponding to an instruction, determines a subset of the plurality of access operations that can be coalesced, and forms a coalesced memory access operation from the subset. A queue stores multiple memory addresses for a given load-store entry to provide for execution of coalesced memory accesses.
Systems and methods are provided for performing routing in a switch network or fabric. Switches can be configured in a hierarchical topology having a plurality of groups, where switches in a group are connected to one another, and groups are connected to other groups. Routing can be performed by maintaining per-group group load information. A packet can be routed between at least two groups using the per-group group load information to effect a set of routing decisions. The set of routing decisions can be biased towards or away one or more paths.
A switch is provided, which can receive a data communication at an edge of a network. The network may be made up of a plurality of switches. The switch may generate a flow channel based upon an identified source and destination for the data communication. The data communication can be routed across the plurality of switches based on minimizing a number of hops between a subset of the plurality of switches and in accordance with the flow channel.
H04L 12/721 - Procédures de routage, p.ex. routage par le chemin le plus court, routage par la source, routage à état de lien ou routage par vecteur de distance
H04L 12/733 - Sélection d’un chemin de longueur minimum ou de nombre de sauts minimum
H04L 12/937 - Commande de la commutation, p.ex. arbitrage
H04L 12/935 - Interfaces de commutation, p.ex. détails de port
Systems and methods are provided for efficiently routing data through a network having a plurality of switches configured in a fat-tree topology, including: receiving a data transmission comprising a plurality of packets at an edge port of the network, and routing the data transmission through the network with routing decisions based upon a routing table, wherein the routing table includes entries to effect routing decisions based upon a destination based hash function.
Systems and methods of routing a data communication across a network having a plurality switches are provided by monitoring the operation of the plurality of global links to determine which of the plurality of global links provide working paths. A routing table indicative of a status for the plurality of links is maintained, where the routing table provides weighting for each of the working paths. When routing, a link using a weighted pseudo-random selection from the choices available in the routing table is selected. Routing along one of the working paths commensurate with the selected link is performed, and the weighting is updated based upon the operation of the plurality of links.
A switch equipped with a self-managing reduction engine is provided. During operation, the reduction engine can use a timeout mechanism to manage itself in different latency-induced or error scenarios. As a result, the network can facilitate an efficient and scalable environment for high performance computing.
A network interface controller (NIC) capable of facilitating fine-grain flow control (FGFC) is provided. The NIC can be equipped with a network interface, an FGFC logic block, and a traffic management logic block. During operation, the network interface can determine that a control frame from a switch is associated with FGFC. The network interface can then identify a data flow indicated in the control frame for applying the FGFC. The FGFC logic block can insert information from the control frame into an entry of a data structure stored in the NIC. The traffic management logic block can identify the entry in the data structure based on one or more fields of a packet belonging to the flow. Subsequently, the traffic management logic block can determine whether the packet is allowed to be forwarded based on the information in the entry.
A network interface controller (NIC) capable of efficient command management is provided. The NIC can be equipped with a host interface, an arbitration logic block, and a command management logic block. During operation, the host interface can couple the NIC to a host device. The arbitration logic block can select a command queue of the host device for obtaining a command. The command management logic block can determine whether an internal buffer associated with the command queue includes a command. If the internal buffer includes the command, the command management logic block can obtain the command from the internal buffer. On the other hand, if the internal buffer is empty, the command management logic block can obtain the command from the command queue via the host interface.
A data-driven intelligent networking system that can facilitate tracing of data flow packets is provided. The system add tracer packets to data flow packets arriving at an ingress point of the network. As the tracer packets progress through network in-band with the data flow packets, the system can copy, at each switch, trace data into pre-defined fields in the tracer packets. When the data flow packets arrive at an egress point of the network the system can separate the trace data from the data flow packet for analysis. Based on the analysis of the trace data, the system can adopt one or more policies to mitigate the impact of congestion on time-sensitive applications.
A network interface controller (NIC) capable of facilitating efficient management of idempotent operations is provided. The NIC can be equipped with a network interface and an operation management logic block. During operation, the network interface can receive a request for an operation from a remote device. The operation management logic block can determine whether the request for an idempotent operation. If the request is for an idempotent operation, the operation management logic block can execute the operation to generate an outcome and generate a response comprising the outcome for responding to the request.
H04L 12/861 - Mise en mémoire tampon de paquets ou mise en file d’attente; Ordonnancement de file d’attente
G06F 15/173 - Communication entre processeurs utilisant un réseau d'interconnexion, p. ex. matriciel, de réarrangement, pyramidal, en étoile ou ramifié
11.
SYSTEM AND METHOD FOR FACILITATING EFFICIENT HOST MEMORY ACCESS FROM A NETWORK INTERFACE CONTROLLER (NIC)
A network interface controller (NIC) capable of efficient memory access is provided. The NIC can be equipped with an operation logic block, a signaling logic block, and a tracking logic block. The operation logic block can maintain an operation group associated with packets requesting an operation on a memory segment of a host device of the NIC. The signaling logic block can determine whether a packet associated with the operation group has arrived at or departed from the NIC. Furthermore, the tracking logic block can determine that a request for releasing the memory segment has been issued. The tracking logic block can then determine whether at least one packet associated with the operation group is under processing in the NIC. If no packet associated with the operation group is under processing in the NIC, tracking logic block can notify the host device that the memory segment can be released.
A switch equipped with a reduction engine capable of being dynamically allocated in a network is provided. During operation, the reduction engine can be dynamically armed based on a multicast frame. As a result, the network can facilitate an efficient and scalable environment for high performance computing.
H04L 12/911 - Contrôle d’admission au réseau et allocation de ressources, p.ex. allocation de bande passante ou renégociation en cours de communication
H04L 12/931 - Architecture de matrice de commutation
H04L 12/801 - Commande de flux ou commande de congestion
H04L 12/927 - Allocation de ressources en fonction du type de trafic, qualité de service ou priorité
H04L 12/741 - Traitement de l'adressage d’en-tête pour le routage, p.ex. table de correspondance
H04L 29/12 - Dispositions, appareils, circuits ou systèmes non couverts par un seul des groupes caractérisés par le terminal de données
13.
SYSTEM AND METHOD FOR FACILITATING GLOBAL FAIRNESS IN A NETWORK
A data-driven intelligent networking system that can facilitate global fairness is provided. The system can maintain state information of individual packet flows, which can be set up or released dynamically based on injected data. Each flow can be provided with a flow-specific input queue upon arriving at a switch. Packets of a respective flow are acknowledged after reaching the egress point of the network, and the acknowledgement packets are sent back to the ingress point of the flow along the same data path. As a result, each switch can obtain state information of each flow and enforce global fairness on a per-flow basis.
Data-driven intelligent networking systems and methods are provided. The system can accommodate dynamic traffic with fast, effective per-flow credit-based flow control. The system can maintain state information of individual packet flows, which can be set up or released dynamically based on injected data. Each flow can be provided with a flow-specific input queue upon arriving at a switch. Packets of a respective flow can be acknowledged after reaching the egress point of the network, and the acknowledgement packets can be sent back to the ingress point of the flow along the same data path. As a result, each switch can obtain state information of each flow and perform flow control on a per-flow basis.
Data-driven intelligent networking systems and methods are provided. The system can accommodate dynamic traffic with fast, effective flow control of individual applications and traffic flows in conjunction with an end host. The system can maintain state information of individual packet flows, which can be set up or released dynamically based on injected data. Each flow can be provided with a flow-specific input queue upon arriving at a switch. Packets of a respective flow can be acknowledged after reaching the egress point of the network, and the acknowledgement packets can be sent back to the ingress point of the flow along the same data path. As a result, an ingress edge switch can perform fine grain flow control of individual sources of the flows residing on an end host.
A network interface controller (NIC) capable of facilitating efficient memory address translation is provided. The NIC can be equipped with a host interface, a cache, and an address translation unit (ATU). During operation, the ATU can determine an operating mode. The operating mode can indicate whether the ATU is to perform a memory address translation at the NIC. The ATU can then determine whether a memory address indicated in the memory access request is available in the cache. If the memory address is not available in the cache, the ATU can perform an operation on the memory address based on the operating mode.
G06F 12/1045 - Traduction d'adresses utilisant des moyens de traduction d’adresse associatifs ou pseudo-associatifs, p. ex. un répertoire de pages actives [TLB] associée à une mémoire cache de données
G06F 12/0862 - Adressage d’un niveau de mémoire dans lequel l’accès aux données ou aux blocs de données désirés nécessite des moyens d’adressage associatif, p. ex. mémoires cache avec pré-lecture
G06F 12/0888 - Adressage d’un niveau de mémoire dans lequel l’accès aux données ou aux blocs de données désirés nécessite des moyens d’adressage associatif, p. ex. mémoires cache utilisant la mémorisation cache sélective, p. ex. la purge du cache
H04L 12/861 - Mise en mémoire tampon de paquets ou mise en file d’attente; Ordonnancement de file d’attente
Systems and methods are provided for managing multicast data transmission in a network having a plurality of switches arranged in a Dragonfly network topology, including: receiving a multicast transmission at an edge port of a switch and identifying the transmission as a network multicast transmission; creating an entry in a multicast table within the switch; routing the multicast transmission across the network to a plurality of destinations via a plurality of links, wherein at each of the links the multicast table is referenced to determine to which ports the multicast transmission should be forwarded; and changing, when necessary, the virtual channel used by each copy of the multicast transmission as the copy progresses through the network.
A network interface controller (NIC) capable of efficient packet injection into an output buffer is provided. The NIC can be equipped with an output buffer, a plurality of injectors, a prioritization logic block, and a selection logic block. The plurality of injectors can share the output buffer. The prioritization logic block can determine a priority associated with a respective injector based on a high watermark and a low watermark associated with the injector. The selection logic block can then determine, from the plurality of injectors, a subset of injectors associated with a buffer class and determine whether the subset of injectors includes a high- priority injector. Upon identifying a high-priority injector in the subset of injectors, the selection logic block can select the high-priority injector for injecting a packet in the output buffer.
Data-driven intelligent networking systems and methods are provided. The system can accommodate dynamic traffic while applying injection limits to different traffic classes at an ingress edge port. The system can maintain state information of individual packet flows, which can be set up or released dynamically based on injected data. Each flow can be provided with a flow-specific input queue upon arriving at a switch. Packets of a respective flow can be acknowledged after reaching the egress point of the network, and the acknowledgement packets can be sent back to the ingress point of the flow along the same data path. Furthermore, an edge switch can dynamically allocate the ingress port bandwidth among the traffic classes that are active at a given moment.
H04L 12/935 - Interfaces de commutation, p.ex. détails de port
H04L 12/825 - Commande adaptative, à la source ou aux nœuds intermédiaires, sur réception d'avis de congestion, p.ex. X-on X-off
H04L 12/801 - Commande de flux ou commande de congestion
H04L 12/851 - Actions liées au type de trafic, p.ex. qualité de service ou priorité
H04L 12/911 - Contrôle d’admission au réseau et allocation de ressources, p.ex. allocation de bande passante ou renégociation en cours de communication
H04L 12/947 - Procédés d’adressage dans un dispositif, p.ex. utilisant des identifiants ou étiquettes internes pour routage dans un commutateur
H04L 12/931 - Architecture de matrice de commutation
Systems and methods are described for providing per traffic class routing of data within a network. A network switch has the capability to classify traffic data based on High Performance Computing (HPC) related characteristics. Traffic classes are defined based on aspects of HPC, such as routing, ordering, redirection, quiesce, HPC protocol configuration, and telemetry. A switch can receive packets at an ingress port of a switch fabric, and determine traffic classifications for the packets. The traffic classification is selected from a group of defined traffic classes. Then, the switch can generate a fabric specific flag for the at least one packet that indicates the determined traffic classification, where the fabric specific flag is used for routing packets based on their assigned traffic classification. Examples of traffic classes include: low latency class; dedicated access class; bulk data class; best efforts class; and scavenger class.
H04L 12/851 - Actions liées au type de trafic, p.ex. qualité de service ou priorité
H04L 12/721 - Procédures de routage, p.ex. routage par le chemin le plus court, routage par la source, routage à état de lien ou routage par vecteur de distance
Systems and methods are provided for "on the fly" routing of data transmissions in the presence of errors. Switches can establish flow channels corresponding to flows in the network. In response to encountering a critical error on a network link along a transmission path, a switch can generate an error acknowledgement. The switch can transmit the error acknowledgements to ingress ports upstream from the network link via the plurality of flow channels. By transmitting the error acknowledgement, it indicates that the network link where the critical error was encountered is a failed link to ingress ports upstream from the failed link. Subsequently, each ingress port upstream from the failed link can dynamically update the path of the plurality of flows that are upstream from the failed link such that the plurality of flows that are upstream from the failed link are routed in a manner that avoids the failed link.
H04L 12/703 - Prévention ou récupération du défaut de routage, p.ex. reroutage, redondance de route "virtual router redundancy protocol" [VRRP] ou "hot standby router protocol" [HSRP]
H04L 12/721 - Procédures de routage, p.ex. routage par le chemin le plus court, routage par la source, routage à état de lien ou routage par vecteur de distance
H04L 12/741 - Traitement de l'adressage d’en-tête pour le routage, p.ex. table de correspondance
H04L 12/801 - Commande de flux ou commande de congestion
H04L 12/935 - Interfaces de commutation, p.ex. détails de port
H04L 12/939 - Dispositions pour la commutation redondante, p.ex. utilisant des plans de commutation parallèles
22.
ALGORITHMS FOR USE OF LOAD INFORMATION FROM NEIGHBORING NODES IN ADAPTIVE ROUTING
Systems and methods are provided for passing data amongst a plurality of switches having a plurality of links attached between the plurality of switches. At a switch, a plurality of load signals are received from a plurality of neighboring switches. Each of the plurality of load signals are made up of a set of values indicative of a load at each of the plurality of neighboring switches providing the load signal. Each value within the set of values provides an indication for each link of the plurality of links attached thereto as to whether the link is busy or quiet. Based upon the plurality of load signals, an output link for routing a received packet is selected, and the received packet is routed via the selected output link.
H04L 12/937 - Commande de la commutation, p.ex. arbitrage
H04L 12/935 - Interfaces de commutation, p.ex. détails de port
H04L 12/803 - Commande de flux ou commande de congestion Équilibrage de charge, p.ex. répartition du trafic entre multiples liens
H04L 12/721 - Procédures de routage, p.ex. routage par le chemin le plus court, routage par la source, routage à état de lien ou routage par vecteur de distance
H04L 12/26 - Dispositions de surveillance; Dispositions de test
23.
DRAGONFLY ROUTING WITH INCOMPLETE GROUP CONNECTIVITY
Systems and methods are provided for managing a data communication within a multi-level network having a plurality of switches organized as groups, with each group coupled to all other groups via global links, including: at each switch within the network, maintaining a global fault table identifying the links which lead only to faulty global paths, and when the data communication is received at a port of a switch, determine a destination for the data communication and, route the communication across the network using the global fault table to avoid selecting a port within the switch that would result in the communication arriving at a point in the network where its only path forward is across a global link that is faulty; wherein the global fault table is used for both a global minimal routing methodology and a global non-minimal routing methodology.
Methods and systems are provided to facilitate network egress fairness between applications. At an egress port of a network, an arbitrator can provide fairness-based traffic shaping to data associated with applications. The desired fairness-based traffic shaping can be provided based on bandwidth, traffic classes, or other parameters. Consequently, the egress link's bandwidth can be allocated with fairness among the applications.
Systems and methods for dynamic buffer management in switches that facilitate a data-driven intelligent networking system are provided. The system can accommodate dynamic traffic with fast, effective congestion control while providing efficient use of internal input buffer space.
One embodiment provides a network interface controller (NIC). The NIC can include a storage device, a network interface, a hardware list-processing engine (LPE), and a message state table (MST) logic block. The storage device can store an MST. The network interface can couple the NIC to a network. The LPE can perform message matching on a first packet of a message received via the network interface. The MST logic block can store results of the message matching in the MST and receive a request to read the results of the message matching from the MST if the NIC receives a second packet associated with the message.
H04L 12/863 - Ordonnancement de file d’attente, p.ex. ordonnancement circulaire
H04L 12/861 - Mise en mémoire tampon de paquets ou mise en file d’attente; Ordonnancement de file d’attente
G06F 15/173 - Communication entre processeurs utilisant un réseau d'interconnexion, p. ex. matriciel, de réarrangement, pyramidal, en étoile ou ramifié
27.
SYSTEM AND METHOD FOR FACILITATING EFFICIENT UTILIZATION OF AN OUTPUT BUFFER IN A NETWORK INTERFACE CONTROLLER (NIC)
A network interface controller (NIC) capable of efficiently utilizing an output buffer is provided. The NIC can be equipped with an output buffer, a host interface, an injector logic block, and an allocation logic block. The output buffer can include a plurality of cells, each of which can be a unit of storage in the output buffer. If the host interface receives a command from a host device, the injector logic block can generate a packet based on the command. The allocation logic block can then determine whether the packet is a multi-cell packet. If the packet is a multi-cell packet, the allocation logic block can determine a virtual index for the packet. The allocation logic block can then store, in an entry in a data structure, the virtual index, and a set of physical indices of cells storing the packet.
A network interface controller (NIC) capable of on-demand paging is provided. The NIC can be equipped with a host interface, an operation logic block, and an address logic block. The host interface can couple the NIC to a host device. The operation logic block can obtain from a remote device, a request for an operation based on a virtual memory address. The address logic block can obtain, from the operation logic block, a request for an address translation for the virtual memory address and issue an address translation request to the host device via the host interface. If the address translation is unsuccessful, the address logic block can send a page request to a processor of the host device via the host interface. The address logic block can then determine that a page has been allocated in response to the page request and reissue the address translation request.
G06F 12/1009 - Traduction d'adresses avec tables de pages, p. ex. structures de table de page
G06F 12/1045 - Traduction d'adresses utilisant des moyens de traduction d’adresse associatifs ou pseudo-associatifs, p. ex. un répertoire de pages actives [TLB] associée à une mémoire cache de données
G06F 13/16 - Gestion de demandes d'interconnexion ou de transfert pour l'accès au bus de mémoire
G06F 13/24 - Gestion de demandes d'interconnexion ou de transfert pour l'accès au bus d'entrée/sortie utilisant l'interruption
G06F 13/28 - Gestion de demandes d'interconnexion ou de transfert pour l'accès au bus d'entrée/sortie utilisant le transfert par rafale, p. ex. acces direct à la mémoire, vol de cycle
29.
SYSTEM AND METHOD FOR FACILITATING HYBRID MESSAGE MATCHING IN A NETWORK INTERFACE CONTROLLER (NIC)
A network interface controller (NIC) capable of hybrid message matching is provided. The NIC can be equipped with a host interface, a hardware endpoint, and an endpoint management logic block. The host interface can couple the NIC to a host device. The hardware endpoint can facilitate a point of communication for an application running on the host device. The endpoint management logic block can maintain a list for storing a message associated with an endpoint represented by the hardware endpoint. The endpoint management logic block can then determine whether the utilization of the list is higher than a threshold. If the utilization is higher than the threshold, the endpoint management logic block can set a state of the endpoint to indicate that the endpoint is software managed. The NIC thus can transfer the control of the endpoint from the hardware endpoint to a software process of the host device.
H04L 12/835 - Adaptation du débit de flux actifs utilisant des informations sur la capacité de mémoire tampon aux points d’extrémité ou aux nœuds de transit
H04L 12/801 - Commande de flux ou commande de congestion
H04L 12/861 - Mise en mémoire tampon de paquets ou mise en file d’attente; Ordonnancement de file d’attente
H04L 12/851 - Actions liées au type de trafic, p.ex. qualité de service ou priorité
30.
SYSTEM AND METHOD FOR FACILITATING EFFICIENT EVENT NOTIFICATION MANAGEMENT FOR A NETWORK INTERFACE CONTROLLER (NIC)
A network interface controller (NIC) capable of efficient event management is provided. The NIC can be equipped with a host interface, a first memory device, and an event management module. During operation, the host interface can couple the NIC to a host device. The event management module can identify an event associated with an event queue stored in a second memory device of the host device. The event management module can insert, into a buffer, an event notification associated with the event. The buffer can be associated with the event queue and stored in the first memory device. If the buffer has met a release criterion, the event management module can insert, via the host interface, the aggregated event notifications into the event queue.
Data-driven intelligent networking systems and methods are provided. The system can accommodate dynamic traffic with fast, effective endpoint congestion detection and control. The system can maintain state information of individual packet flows, which can be set up or released dynamically based on injected data. Each flow can be provided with a flow-specific input queue upon arriving at a switch. Packets of a respective flow can be acknowledged after reaching the egress point of the network, and the acknowledgement packets can be sent back to the ingress point of the flow along the same data path. As a result, each switch can obtain state information of each flow and perform flow control on a per-flow basis.
A network interface controller (NIC) capable of facilitating efficient data request management is provided. The NIC can be equipped with a command queue, a message chopping unit (MCU), and a traffic management logic block. During operation, the command queue can store a command issued via a host interface. The MCU can then determine a type of the command and a length of a response of the command. If the command is a data request, the traffic management logic block can determine whether the length of the response is within a threshold. If the length exceeds the threshold, the traffic management logic block can pace the command such that the response is within the threshold.
G06F 3/06 - Entrée numérique à partir de, ou sortie numérique vers des supports d'enregistrement
G06F 13/16 - Gestion de demandes d'interconnexion ou de transfert pour l'accès au bus de mémoire
G06F 13/28 - Gestion de demandes d'interconnexion ou de transfert pour l'accès au bus d'entrée/sortie utilisant le transfert par rafale, p. ex. acces direct à la mémoire, vol de cycle
A network interface controller (NIC) capable of efficient operation management for host accelerators is provided. The NIC can be equipped with a host interface and triggering logic block. During operation, the host interface can couple the NIC to a host device. The triggering logic block can obtain, via the host interface from the host device, an operation associated with an accelerator of the host device. The triggering logic block can determine whether a triggering condition has been satisfied for the operation based on an indicator received from the accelerator. If the triggering condition has been satisfied, the triggering logic block can obtain a piece of data generated from the accelerator from a memory location and execute the operation using the piece of data.
G06F 13/10 - Commande par programme pour dispositifs périphériques
G06F 13/28 - Gestion de demandes d'interconnexion ou de transfert pour l'accès au bus d'entrée/sortie utilisant le transfert par rafale, p. ex. acces direct à la mémoire, vol de cycle
H04L 12/861 - Mise en mémoire tampon de paquets ou mise en file d’attente; Ordonnancement de file d’attente
34.
SYSTEM AND METHOD FOR FACILITATING DATA-DRIVEN INTELLIGENT NETWORK
Data-driven intelligent networking systems and methods are provided. The system can accommodate dynamic traffic with fast, effective congestion control. The system can maintain state information of individual packet flows, which can be set up or released dynamically based on injected data. Each flow can be provided with a flow-specific input queue upon arriving at a switch. Packets of a respective flow can be acknowledged after reaching the egress point of the network, and the acknowledgement packets can be sent back to the ingress point of the flow along the same data path. As a result, each switch can obtain state information of each flow and perform flow control on a per-flow basis.
H04L 12/851 - Actions liées au type de trafic, p.ex. qualité de service ou priorité
H04L 12/721 - Procédures de routage, p.ex. routage par le chemin le plus court, routage par la source, routage à état de lien ou routage par vecteur de distance
H04L 12/743 - Traitement de l'adressage d’en-tête pour le routage, p.ex. table de correspondance par des techniques de hachage
H04L 12/863 - Ordonnancement de file d’attente, p.ex. ordonnancement circulaire
H04L 12/931 - Architecture de matrice de commutation
H04L 12/935 - Interfaces de commutation, p.ex. détails de port
35.
SYSTEM AND METHOD FOR FACILITATING EFFICIENT PACKET FORWARDING IN A NETWORK INTERFACE CONTROLLER (NIC)
A network interface controller (NIC) capable of efficient packet forwarding is provided. The NIC can be equipped with a host interface, a packet generation logic block, and a forwarding logic block. During operation, the packet generation logic block can obtain, via the host interface, a message from the host device and for a remote device. The packet generation logic block may generate a plurality of packets for the remote device from the message. The forwarding logic block can then send a first subset of packets of the plurality of packets based on ordered delivery. If a first condition is met, the forwarding logic block can send a second subset of packets of the plurality of packets based on unordered delivery. Furthermore, if a second condition is met, the forwarding logic block can send a third subset of packets of the plurality of packets based on ordered delivery.
A switch architecture for a data-driven intelligent networking system is provided. The system can accommodate dynamic traffic with fast, effective congestion control. The system can maintain state information of individual packet flows, which can be set up or released dynamically based on injected data. Each flow can be provided with a flow-specific input queue upon arriving at a switch. Packets of a respective flow are acknowledged after reaching the egress point of the network, and the acknowledgement packets are sent back to the ingress point of the flow along the same data path. As a result, each switch can obtain state information of each flow and perform flow control on a per-flow basis.
A switch capable of on-the-fly reduction in a network is provided. The switch is equipped with a reduction engine that can be dynamically configured to perform on-the-fly reduction. As a result, the network can facilitate an efficient and scalable environment for high performance computing.
H04L 12/931 - Architecture de matrice de commutation
H04L 12/933 - Cœur de commutateur, p.ex. barres croisées, mémoire partagée ou support partagé
H04L 12/911 - Contrôle d’admission au réseau et allocation de ressources, p.ex. allocation de bande passante ou renégociation en cours de communication
H04L 12/861 - Mise en mémoire tampon de paquets ou mise en file d’attente; Ordonnancement de file d’attente
38.
SYSTEM AND METHOD FOR FACILITATING EFFICIENT LOAD BALANCING IN A NETWORK INTERFACE CONTROLLER (NIC)
A network interface controller (NIC) capable of efficient load balancing among the hardware engines is provided. The NIC can be equipped with a plurality of ordering control units (OCUs), a queue, a selection logic block, and an allocation logic block. The selection logic block can determine, from the plurality of OCUs, an OCU for a command from the queue, which can store one or more commands. The allocation logic block can then determine a selection setting for the OCU, select an egress queue for the command based on the selection setting, and send the command to the egress queue.
System and methods are described for providing adaptive routing in the presence of persistent flows. Switches in a fabric have the capability to establish flow channels. Switches can adaptively route flows, while monitoring transmission characteristics of the flows channels to identify whether any flows are experiencing congestion towards a destination. In response to detecting congestion, it can be further determined whether the flow is related to a source of congestion, or alternative the flow is a victim of congestion. Flows that are a source of congestion have their routing constrained to prevent congestion from propagating For example, new packets of a flow that is a source of congestion may be forced to only take the path of the data transmission that detected said congestion (preventing congestion from spreading). Alternatively, victims of congestion do not have their routing constrained, and packets can take any path as permitted by adaptive routing.
H04L 12/721 - Procédures de routage, p.ex. routage par le chemin le plus court, routage par la source, routage à état de lien ou routage par vecteur de distance
H04L 12/801 - Commande de flux ou commande de congestion
H04L 12/851 - Actions liées au type de trafic, p.ex. qualité de service ou priorité
H04L 12/741 - Traitement de l'adressage d’en-tête pour le routage, p.ex. table de correspondance
H04L 12/937 - Commande de la commutation, p.ex. arbitrage
40.
SYSTEM AND METHOD FOR FACILITATING EFFICIENT MANAGEMENT OF NON-IDEMPOTENT OPERATIONS IN A NETWORK INTERFACE CONTROLLER (NIC)
A network interface controller (NIC) capable of efficient management of non-idempotent operations is provided. The NIC can be equipped with a network interface, storage management logic block, and an operation management logic block. During operation, the network interface can receive a request for an operation from a remote device. The storage management logic block can store, in a local data structure, outcome of operations executed by the NIC. The operation management logic block can determine whether the NIC has previously executed the operation. If the NIC has previously executed the operation, the operation management logic block can obtain an outcome of the operation from the data structure and generate a response comprising the obtained outcome for responding to the request.
G06F 13/38 - Transfert d'informations, p. ex. sur un bus
G06F 13/16 - Gestion de demandes d'interconnexion ou de transfert pour l'accès au bus de mémoire
G06F 13/28 - Gestion de demandes d'interconnexion ou de transfert pour l'accès au bus d'entrée/sortie utilisant le transfert par rafale, p. ex. acces direct à la mémoire, vol de cycle
H04L 12/861 - Mise en mémoire tampon de paquets ou mise en file d’attente; Ordonnancement de file d’attente
41.
SYSTEM AND METHOD FOR FACILITATING EFFICIENT MESSAGE MATCHING IN A NETWORK INTERFACE CONTROLLER (NIC)
A network interface controller (NIC) capable of performing message passing interface (MPI) list matching is provided. The NIC can include a host interface, a network interface, and a hardware list-processing engine (LPE). The host interface can couple the NIC to a host device. The network interface can couple the NIC to a network. During operation, the LPE can receive a match request and perform MPI list matching based on the received match request.
Methods and systems are provided for performing lossy dropping and ECN marking in a flow-based network. The system can maintain state information of individual packet flows, which can be set up or released dynamically based on injected data. Each flow can be provided with a flow-specific input queue upon arriving at a switch. Packets of a respective flow are acknowledged after reaching the egress point of the network, and the acknowledgement packets are sent back to the ingress point of the flow along the same data path. As a result, each switch can obtain state information of each flow and perform per-flow packet dropping and ECN marking.
Methods and systems are provided for controlling wide LAG and ECMP in a network. At the ingress edge of the network, a switch can identify packets as LAG or ECMP packets, and allow them to be forwarded through the switch fabric using multiple output ports or paths.
H04L 12/709 - Prévention ou récupération du défaut de routage, p.ex. reroutage, redondance de route "virtual router redundancy protocol" [VRRP] ou "hot standby router protocol" [HSRP] par redondance des chemins d’accès par chemins actifs parallèles M + N
H04L 12/743 - Traitement de l'adressage d’en-tête pour le routage, p.ex. table de correspondance par des techniques de hachage
H04L 12/935 - Interfaces de commutation, p.ex. détails de port
H04L 12/879 - Opérations simples sur la mémoire-tampon, p.ex. pointeurs de mémoire-tampon ou descripteurs de mémoire-tampon
H04L 29/12 - Dispositions, appareils, circuits ou systèmes non couverts par un seul des groupes caractérisés par le terminal de données
44.
METHOD AND SYSTEM FOR PROVIDING NETWORK INGRESS FAIRNESS BETWEEN APPLICATIONS
Methods and systems are provided to facilitate network ingress fairness between applications. At an ingress port of a network, the applications providing data communications are reviewed so that and arbitration process can be used to fairly allocate bandwidth at that ingress port. In a typical process, the bandwidth is allocated based upon the number of flow channels, irrespective of the source and characteristics of those flow channels. At the ingress port, an examination of the application providing the data communication will allow for a more appropriate allocation of input bandwidth.
A printed circuit board includes additional stitching vias placed at strategic location within a connection matrix, which provides additional isolation and further accommodates high-speed communication capabilities. The stitching vias have a variable length or depth, depending on related structures within the circuit board, so as to avoid any interference with underlining escape routing, or alternative signal transmission structures. More specifically, these stitching vias help to eliminate cross-talk in the via field caused by the close proximity of signal carrying structures. Further, differential signal communication is better accommodated based upon this reduction in cross-talk.
To eliminate signal loss and sources of signal attenuation, a connection methodology is utilized which enables high-speed signals to be directly communicated from particular integrated circuits housed on a printed circuit board, to other locations within a system. More specifically, a signal escape strategy directly connects a high-speed cable to a point on the circuit board which is very close to the integrated circuit itself. A back-side connection methodology is utilized so that electrical signals pass directly from the integrated circuit through a via, to a connection point on the backside of the circuit board. To accommodate this connection, a specially designed interposer and related paddle cards are utilized so the high-speed communication cable can be easily attached.
A method for prefetching data into a cache is provided. The method allocates an outstanding request buffer (“ORB”). The method stores in an address field of the ORB an address and a number of blocks. The method issues prefetch requests for a degree number of blocks starting at the address. When a prefetch response is received for all the prefetch requests, the method adjusts the address of the next block to prefetch and adjusts the number of blocks remaining to be retrieved and then issues prefetch requests for a degree number of blocks starting at the adjusted address. The prefetching pauses when a maximum distance between the reads of the prefetched blocks and the last prefetched block is reached. When a read request for a prefetched block is received, the method resumes prefetching when a resume criterion is satisfied.
G06F 12/00 - Accès à, adressage ou affectation dans des systèmes ou des architectures de mémoires
G06F 12/0862 - Adressage d’un niveau de mémoire dans lequel l’accès aux données ou aux blocs de données désirés nécessite des moyens d’adressage associatif, p. ex. mémoires cache avec pré-lecture
G06F 12/1045 - Traduction d'adresses utilisant des moyens de traduction d’adresse associatifs ou pseudo-associatifs, p. ex. un répertoire de pages actives [TLB] associée à une mémoire cache de données
G06F 12/0886 - Accès par mots de longueur variable
09 - Appareils et instruments scientifiques et électriques
Produits et services
Computer hardware for data interconnect fabric systems and solutions for computing clusters in high performance computers and supercomputers to increase the speed and performance and flexibility of computer system communications
49.
FLEXIBLE AND ADAPTABLE COMPUTING SYSTEM INFRASTRUCTURE
To achieve multiple benefits, a high speed computing system is configured in a hierarchical manner with flexibility and re-configurability concerns maximized. This begins with a particular cabinet architecture which is specifically designed to accommodate various needs and considerations. The cabinet or rack is designed to receive various chassis assemblies depending on the particular needs and or functions involved. These may include a compute chassis, a switch chassis, or a rectifier chassis, which can be incorporated into the cabinet. Within each chassis, specific components are then inserted, with each of these components being in a subsystem configuration. For example, the compute chassis is specifically designed to receive a number of compute blades. Similarly, the switch chassis is designed to receive a number of switch blades. Lastly, the rectifier chassis is configured to receive a number of rectifiers. Collectively, the multiple blades and chassis are all configured to cooperate with one another in an efficient manner. While various subassemblies are utilized, the cabinet or rack does accommodate certain centralized functions such as cooling and power distribution.
G06F 15/16 - Associations de plusieurs calculateurs numériques comportant chacun au moins une unité arithmétique, une unité programme et un registre, p. ex. pour le traitement simultané de plusieurs programmes
H05K 7/14 - Montage de la structure de support dans l'enveloppe, sur cadre ou sur bâti
H05K 7/20 - Modifications en vue de faciliter la réfrigération, l'aération ou le chauffage
50.
Method for impedance compensation in printed circuit boards
The various structures forming communication paths on a printed circuit board can create several undesired effects, especially when high frequency signals are considered. Non-functional pads created during the manufacturing process have the potential to create an undesired effect, but when the overall collection of non-functional pads are carefully configured, an optimized communication path can be formed. More specifically, by selectively removing some collection of the non-functional pads, the high frequency characteristics of the communication paths can be optimized.
A system is provided for allocating memory for data of a program for execution by a computer system with a multi-tier memory that includes LBM and HBM. The system accesses a data structure map that maps data structures of the program to the memory addresses within an address space of the program to which the data structures are initially allocated. The system executes the program to collect statistics relating to memory requests and memory bandwidth utilization of the program. The system determines an extent to which each data structure is used by a high memory utilization portion of the program based on the data structure map and the collected statistics. The system generates a memory allocation plan that favors allocating data structures in HBM based on the extent to which the data structures are used by a high memory utilization portion of the program.
A method for prefetching data into a cache is provided. The method allocates an outstanding request buffer (“ORB”). The method stores in an address field of the ORB an address and a number of blocks. The method issues prefetch requests for a degree number of blocks starting at the address. When a prefetch response is received for all the prefetch requests, the method adjusts the address of the next block to prefetch and adjusts the number of blocks remaining to be retrieved and then issues prefetch requests for a degree number of blocks starting at the adjusted address. The prefetching pauses when a maximum distance between the reads of the prefetched blocks and the last prefetched block is reached. When a read request for a prefetched block is received, the method resumes prefetching when a resume criterion is satisfied.
G06F 12/00 - Accès à, adressage ou affectation dans des systèmes ou des architectures de mémoires
G06F 12/0862 - Adressage d’un niveau de mémoire dans lequel l’accès aux données ou aux blocs de données désirés nécessite des moyens d’adressage associatif, p. ex. mémoires cache avec pré-lecture
G06F 12/1045 - Traduction d'adresses utilisant des moyens de traduction d’adresse associatifs ou pseudo-associatifs, p. ex. un répertoire de pages actives [TLB] associée à une mémoire cache de données
A resiliency system detects and corrects memory errors reported by a memory system of a computing system using previously stored error correction information. When a program stores data into a memory location, the resiliency system executing on the computing system generates and stores error correction information. When the program then executes a load instruction to retrieve the data from the memory location, the load instruction completes normally if there is no memory error. If, however, there is a memory error, the computing system passes control to the resiliency system (e.g., via a trap) to handle the memory error. The resiliency system retrieves the error correction information for the memory location and re-creates the data of the memory location. The resiliency system stores the data as if the load instruction had completed normally and passes control to the next instruction of the program.
G06F 11/10 - Détection ou correction d'erreur par introduction de redondance dans la représentation des données, p. ex. en utilisant des codes de contrôle en ajoutant des chiffres binaires ou des symboles particuliers aux données exprimées suivant un code, p. ex. contrôle de parité, exclusion des 9 ou des 11
G06F 3/06 - Entrée numérique à partir de, ou sortie numérique vers des supports d'enregistrement
G06F 11/14 - Détection ou correction d'erreur dans les données par redondance dans les opérations, p. ex. en utilisant différentes séquences d'opérations aboutissant au même résultat
G06F 11/20 - Détection ou correction d'erreur dans une donnée par redondance dans le matériel en utilisant un masquage actif du défaut, p. ex. en déconnectant les éléments défaillants ou en insérant des éléments de rechange
G06F 11/16 - Détection ou correction d'erreur dans une donnée par redondance dans le matériel
G06F 11/08 - Détection ou correction d'erreur par introduction de redondance dans la représentation des données, p. ex. en utilisant des codes de contrôle
A resiliency system detects and corrects memory errors reported by a memory system of a computing system using previously stored error correction information. When a program stores data into a memory location, the resiliency system executing on the computing system generates and stores error correction information. When the program then executes a load instruction to retrieve the data from the memory location, the load instruction completes normally if there is no memory error. If, however, there is a memory error, the computing system passes control to the resiliency system (e.g., via a trap) to handle the memory error. The resiliency system retrieves the error correction information for the memory location and re-creates the data of the memory location. The resiliency system stores the data as if the load instruction had completed normally and passes control to the next instruction of the program.
G06F 11/16 - Détection ou correction d'erreur dans une donnée par redondance dans le matériel
G06F 11/10 - Détection ou correction d'erreur par introduction de redondance dans la représentation des données, p. ex. en utilisant des codes de contrôle en ajoutant des chiffres binaires ou des symboles particuliers aux données exprimées suivant un code, p. ex. contrôle de parité, exclusion des 9 ou des 11
G06F 11/14 - Détection ou correction d'erreur dans les données par redondance dans les opérations, p. ex. en utilisant différentes séquences d'opérations aboutissant au même résultat
G06F 11/20 - Détection ou correction d'erreur dans une donnée par redondance dans le matériel en utilisant un masquage actif du défaut, p. ex. en déconnectant les éléments défaillants ou en insérant des éléments de rechange
G06F 3/06 - Entrée numérique à partir de, ou sortie numérique vers des supports d'enregistrement
G06F 11/08 - Détection ou correction d'erreur par introduction de redondance dans la représentation des données, p. ex. en utilisant des codes de contrôle
55.
System and method for dampening power swings in distributed computer environments
In a large scale computing system, a supervisory system is utilized to monitor the operations and requests of multiple components, and to manage such requests so that overall power considerations for the entire system are considered. The supervisory system has the ability to identify requests and aggregations of simultaneous requests that will create an adverse power effect, and to apply overall control methodologies which will help to minimize these adverse effects.
Computer systems having heat exchangers for cooling computer components are disclosed herein. The computer systems include a computer cabinet having an air inlet, an air outlet spaced apart from the air inlet, and a plurality of computer module compartments positioned between the air inlet and the air outlet. The air inlet, the air outlet, and the computer module compartments define an air flow path through the computer cabinet. The computer systems also include a heat exchanger positioned between two adjacent computer module compartments. The heat exchanger includes a plurality of heat exchange elements canted relative to the air flow path.
A system and algorithm configured to generate diversity at the traffic source so that packets are uniformly distributed over all of the available paths, but to increase the likelihood of taking a minimal path with each hop the packet takes. This is achieved by configuring routing biases so as to prefer non-minimal paths at the injection point, but increasingly prefer minimal paths as the packet proceeds, referred to herein as Increasing Minimal Bias (IMB).
H04L 12/26 - Dispositions de surveillance; Dispositions de test
H04L 12/801 - Commande de flux ou commande de congestion
H04L 12/733 - Sélection d’un chemin de longueur minimum ou de nombre de sauts minimum
H04L 12/721 - Procédures de routage, p.ex. routage par le chemin le plus court, routage par la source, routage à état de lien ou routage par vecteur de distance
H04L 12/741 - Traitement de l'adressage d’en-tête pour le routage, p.ex. table de correspondance
A resiliency system detects and corrects memory errors reported by a memory system of a computing system using previously stored error correction information. When a program stores data into a memory location, the resiliency system executing on the computing system generates and stores error correction information. When the program then executes a load instruction to retrieve the data from the memory location, the load instruction completes normally if there is no memory error. If, however, there is a memory error, the computing system passes control to the resiliency system (e.g., via a trap) to handle the memory error. The resiliency system retrieves the error correction information for the memory location and re-creates the data of the memory location. The resiliency system stores the data as if the load instruction had completed normally and passes control to the next instruction of the program.
G06F 11/14 - Détection ou correction d'erreur dans les données par redondance dans les opérations, p. ex. en utilisant différentes séquences d'opérations aboutissant au même résultat
G06F 11/20 - Détection ou correction d'erreur dans une donnée par redondance dans le matériel en utilisant un masquage actif du défaut, p. ex. en déconnectant les éléments défaillants ou en insérant des éléments de rechange
G06F 11/10 - Détection ou correction d'erreur par introduction de redondance dans la représentation des données, p. ex. en utilisant des codes de contrôle en ajoutant des chiffres binaires ou des symboles particuliers aux données exprimées suivant un code, p. ex. contrôle de parité, exclusion des 9 ou des 11
G06F 3/06 - Entrée numérique à partir de, ou sortie numérique vers des supports d'enregistrement
G06F 11/08 - Détection ou correction d'erreur par introduction de redondance dans la représentation des données, p. ex. en utilisant des codes de contrôle
A method and system for detecting congestion in a network of nodes, abating the network congestion, and identifying the cause of the network congestion is provided. A congestion detection system may comprise a detection system, an abatement system, and a causation system. The detection system monitors the performance of network components such as the network interface controllers and tiles of routers to determine whether the network is congested such that a delay in delivering packets becomes unacceptable. Upon detecting that the network is congested, an abatement system abates the congestion by limiting the rate at which packets are injected into the network from the nodes. Upon detecting that the network is congested, a causation system may identify the job that is executing on a node that is the cause of the network congestion.
H04L 12/801 - Commande de flux ou commande de congestion
G06F 15/173 - Communication entre processeurs utilisant un réseau d'interconnexion, p. ex. matriciel, de réarrangement, pyramidal, en étoile ou ramifié
H04L 12/26 - Dispositions de surveillance; Dispositions de test
H04L 29/08 - Procédure de commande de la transmission, p.ex. procédure de commande du niveau de la liaison
H04L 12/24 - Dispositions pour la maintenance ou la gestion
A method and system for detecting congestion in a network of nodes, abating the network congestion, and identifying the cause of the network congestion is provided. A congestion detection system may comprise a detection system, an abatement system, and a causation system. The detection system monitors the performance of network components such as the network interface controllers and tiles of routers to determine whether the network is congested such that a delay in delivering packets becomes unacceptable. Upon detecting that the network is congested, an abatement system abates the congestion by limiting the rate at which packets are injected into the network from the nodes. Upon detecting that the network is congested, a causation system may identify the job that is executing on a node that is the cause of the network congestion.
H04L 12/801 - Commande de flux ou commande de congestion
H04L 12/825 - Commande adaptative, à la source ou aux nœuds intermédiaires, sur réception d'avis de congestion, p.ex. X-on X-off
H04L 12/26 - Dispositions de surveillance; Dispositions de test
H04L 12/933 - Cœur de commutateur, p.ex. barres croisées, mémoire partagée ou support partagé
H04L 12/773 - Architecture du routeur pour supporter la commutation de couche 3, p.ex. commutation IP, relais de commutation de cellules [CSR] ou commutation d’étiquettes
A parallelization assistant tool system to assist in parallelization of a computer program is disclosed. The system directs the execution of instrumented code of the computer program to collect performance statistics information relating to execution of loops within the computer program. The system provides a user interface for presenting to a programmer the performance statistics information collected for a loop within the computer program so that the programmer can prioritize efforts to parallelize the computer program. The system generates inlined source code of a loop by aggressively inlining functions substantially without regard to compilation performance, execution performance, or both. The system analyzes the inlined source code to determine the data-sharing attributes of the variables of the loop. The system may generate compiler directives to specify the data-sharing attributes of the variables.
A data-processing system and method for performing collective operations. Some embodiments provide a plurality of leaf software processes, a plurality of collective engines (CEs), and a network operatively coupled to the plurality of CEs, wherein collective operations messages are sent between CEs. Each of the plurality of hierarchies includes a root, leaf CEs, and one or more intermediate levels of CEs between the root and the leaf CEs. Each CE except the root is configured to have a parent CE, and each non-leaf CE in the hierarchy that is not the root CE and not one of the leaf CEs has one or more child CEs. Data is sent from software processes to one or more of the plurality of CEs, and data is received to one or more software processes from one or more of the plurality of collective engines. The root CE outputs a final result.
G06F 15/16 - Associations de plusieurs calculateurs numériques comportant chacun au moins une unité arithmétique, une unité programme et un registre, p. ex. pour le traitement simultané de plusieurs programmes
H04L 29/08 - Procédure de commande de la transmission, p.ex. procédure de commande du niveau de la liaison
H04L 12/715 - Routage hiérarchique, p.ex. réseaux en grappe ou routage inter-domaine
H04L 12/751 - Mise à jour ou découverte de la topologie
H04L 12/26 - Dispositions de surveillance; Dispositions de test
An improved method for the prevention of deadlock in a massively parallel processor (MPP) system wherein, prior to a process sending messages to another process running on a remote processor, the process allocates space in a deadlock-avoidance FIFO. The allocated space provides a “landing zone” for requests that the software process (the application software) will subsequently issue using a remote-memory-access function. In some embodiments, the deadlock-avoidance (DLA) function provides two different deadlock-avoidance schemes: controlled discard and persistent reservation. In some embodiments, the software process determines which scheme will be used at the time the space is allocated.
A system and method for cooling a plurality of electronics cabinets having horizontally positioned electronics assemblies. The system includes at least one blower configured to direct air horizontally across the electronics assemblies, and at least one intercooler configured to extract heat from the air flow such that the system is room neutral, meaning that the ambient temperature remains constant during operation of the system. A plurality of chassis backplanes and power supplies may also include an intercooler, wherein the intercoolers are electronically controlled such that the system is room neutral.
A system for updating an index into a tuple table of tuples is provided. An indexing system updates an index into a tuple table using fine-grain locking of the index. The index includes a values table with an entry for each index value of an index field that references a value-tuple table that includes, for each tuple with the index value, a row that identifies a tuple of the tuple table with that indexed value. After a new tuple is added to the tuple table with a value, the index is updated by locking the entry in the values table, updating the value-tuple table for the value, and then unlocking the entry. When the index is accessed for locating tuples with a value, the accessor locks the entry in the values table for the value, uses the value-tuple table to locate the tuples, and unlocks the entry.
A method and system for detecting congestion in a network of nodes, abating the network congestion, and identifying the cause of the network congestion is provided. A congestion detection system may comprise a detection system, an abatement system, and a causation system. The detection system monitors the performance of network components such as the network interface controllers and tiles of routers to determine whether the network is congested such that a delay in delivering packets becomes unacceptable. Upon detecting that the network is congested, an abatement system abates the congestion by limiting the rate at which packets are injected into the network from the nodes. Upon detecting that the network is congested, a causation system may identify the job that is executing on a node that is the cause of the network congestion.
H04L 12/801 - Commande de flux ou commande de congestion
H04L 12/825 - Commande adaptative, à la source ou aux nœuds intermédiaires, sur réception d'avis de congestion, p.ex. X-on X-off
H04L 12/933 - Cœur de commutateur, p.ex. barres croisées, mémoire partagée ou support partagé
H04L 12/773 - Architecture du routeur pour supporter la commutation de couche 3, p.ex. commutation IP, relais de commutation de cellules [CSR] ou commutation d’étiquettes
H04L 12/26 - Dispositions de surveillance; Dispositions de test
A system for providing cross-exception event handling is provided. The system allows a source thread to throw an event (e.g., exception) as part of structured event handling of a programming language that specifies a target thread. When the event is thrown, the source thread starts a handler thread to handle the event in a current context of the target thread. The handler thread is passed an indication of the event and the target thread and sets its context to be consistent with that of handling events in the target thread. The handler thread then handles the event. The source thread may continue its execution in parallel or may terminate its execution as specified in a statement that threw the event. Execution of the target thread may be aborted and its execution continued at an exit statement of an enclosing structured event handling construct—as specified when the event was thrown.
A method and system for detecting congestion in a network of nodes, abating the network congestion, and identifying the cause of the network congestion is provided. A congestion detection system may comprise a detection system, an abatement system, and a causation system. The detection system monitors the performance of network components such as the network interface controllers and tiles of routers to determine whether the network is congested such that a delay in delivering packets becomes unacceptable. Upon detecting that the network is congested, an abatement system abates the congestion by limiting the rate at which packets are injected into the network from the nodes. Upon detecting that the network is congested, a causation system may identify the job that is executing on a node that is the cause of the network congestion.
H04L 12/801 - Commande de flux ou commande de congestion
G06F 15/173 - Communication entre processeurs utilisant un réseau d'interconnexion, p. ex. matriciel, de réarrangement, pyramidal, en étoile ou ramifié
H04L 12/26 - Dispositions de surveillance; Dispositions de test
H04L 29/08 - Procédure de commande de la transmission, p.ex. procédure de commande du niveau de la liaison
H04L 12/24 - Dispositions pour la maintenance ou la gestion
A parallelization assistant tool system to assist in parallelization of a computer program is disclosed. The system directs the execution of instrumented code of the computer program to collect performance statistics information relating to execution of loops within the computer program. The system provides a user interface for presenting to a programmer the performance statistics information collected for a loop within the computer program so that the programmer can prioritize efforts to parallelize the computer program. The system generates inlined source code of a loop by aggressively inlining functions substantially without regard to compilation performance, execution performance, or both. The system analyzes the inlined source code to determine the data-sharing attributes of the variables of the loop. The system may generate compiler directives to specify the data-sharing attributes of the variables.
A method and system for inferring facts in parallel in a multiprocessor computing environment is provided. An inference system infers facts by applying rules to a collection of existing facts. For each existing fact, the inference system schedules a thread to apply the rules to that existing fact. As a thread infers a new fact (i.e., one that is not already in the collection of facts), the thread adds that inferred fact to the collection of facts. When a thread adds a new fact to the collection, the thread also applies the rules to that new fact. After the threads complete execution, the inference system may apply the rules to the facts of the collection, including the newly inferred facts, by again launching a thread for each fact to apply the rules to that fact. The inference system performs this processing iteratively until a termination condition is satisfied.
A computer system is operable to identify subfields that differ in two data elements using a bit matrix compare function between a first matrix filled with pattern elements and a reference pattern.
G06F 7/57 - Unités arithmétiques et logiques [UAL], c.-à-d. dispositions ou dispositifs pour accomplir plusieurs des opérations couvertes par les groupes ou pour accomplir des opérations logiques
73.
Cooling systems and heat exchangers for cooling computer components
Computer systems having heat exchangers for cooling computer components are disclosed herein. The computer systems include a computer cabinet having an air inlet, an air outlet spaced apart from the air inlet, and a plurality of computer module compartments positioned between the air inlet and the air outlet. The air inlet, the air outlet, and the computer module compartments define an air flow path through the computer cabinet. The computer systems also include a heat exchanger positioned between two adjacent computer module compartments. The heat exchanger includes a plurality of heat exchange elements canted relative to the air flow path.
H05K 7/20 - Modifications en vue de faciliter la réfrigération, l'aération ou le chauffage
F28D 1/04 - Appareils échangeurs de chaleur comportant des ensembles de canalisations fixes pour une seule des sources de potentiel calorifique, les deux sources étant en contact chacune avec un côté de la paroi de la canalisation, dans lesquels l'autre source de potentiel calorifique est une grande masse de fluide, p. ex. radiateurs domestiques ou de moteur de voiture avec des canalisations d'échange de chaleur immergées dans la masse du fluide avec canalisations tubulaires
F28D 1/053 - Appareils échangeurs de chaleur comportant des ensembles de canalisations fixes pour une seule des sources de potentiel calorifique, les deux sources étant en contact chacune avec un côté de la paroi de la canalisation, dans lesquels l'autre source de potentiel calorifique est une grande masse de fluide, p. ex. radiateurs domestiques ou de moteur de voiture avec des canalisations d'échange de chaleur immergées dans la masse du fluide avec canalisations tubulaires les canalisations étant rectilignes
F28F 1/02 - Éléments tubulaires de section transversale non circulaire
F28F 1/12 - Éléments tubulaires ou leurs ensembles avec moyens pour augmenter la surface de transfert de chaleur, p. ex. avec des ailettes, avec des saillies, avec des évidements ces moyens étant uniquement à l'extérieur de l'élément tubulaire
F28D 21/00 - Appareils échangeurs de chaleur non couverts par l'un des groupes
74.
Systems and methods for debugging applications using dual code generation
Systems and methods provide a debugger that debugs code using two versions of code, an optimized and a debuggable version of object code for subroutines, methods or functions. The debugger causes the appropriate version of the code to be executed depending on whether debug commands have been applied with respect to particular subroutines, methods or functions.
A reconnection system re-forms a control tree for an application that is executed in parallel without terminating execution of the application. The reconnection system detects when a node of a control tree has failed and directs the nodes that have not failed to reconnect to effect the re-forming of the control tree without the failed node and without terminating the application. Upon being directed to reconnect, a node identifies new child nodes that are to be its child nodes in the re-formed control tree. The node maintains the existing connection with each of its current child nodes that is also a new child node, terminates the existing connection with each of its current child nodes that is not also a new child node, establishes a new connection with any new child node that is not a current child node, and directs each new child node to reconnect.
G06F 11/00 - Détection d'erreursCorrection d'erreursContrôle de fonctionnement
G06F 11/14 - Détection ou correction d'erreur dans les données par redondance dans les opérations, p. ex. en utilisant différentes séquences d'opérations aboutissant au même résultat
H04L 12/753 - Découverte de l’arborescence de routage, p.ex. conversion de la topologie maillée de réseau en topologie arborescente
76.
Cooling systems and heat exchangers for cooling computer components
Computer systems having heat exchangers for cooling computer components are disclosed herein. The computer systems include a computer cabinet having an air inlet, an air outlet spaced apart from the air inlet, and a plurality of computer module compartments positioned between the air inlet and the air outlet. The air inlet, the air outlet, and the computer module compartments define an air flow path through the computer cabinet. The computer systems also include a heat exchanger positioned between two adjacent computer module compartments. The heat exchanger includes a plurality of heat exchange elements canted relative to the air flow path.
H05K 7/20 - Modifications en vue de faciliter la réfrigération, l'aération ou le chauffage
F28D 1/04 - Appareils échangeurs de chaleur comportant des ensembles de canalisations fixes pour une seule des sources de potentiel calorifique, les deux sources étant en contact chacune avec un côté de la paroi de la canalisation, dans lesquels l'autre source de potentiel calorifique est une grande masse de fluide, p. ex. radiateurs domestiques ou de moteur de voiture avec des canalisations d'échange de chaleur immergées dans la masse du fluide avec canalisations tubulaires
F28D 1/053 - Appareils échangeurs de chaleur comportant des ensembles de canalisations fixes pour une seule des sources de potentiel calorifique, les deux sources étant en contact chacune avec un côté de la paroi de la canalisation, dans lesquels l'autre source de potentiel calorifique est une grande masse de fluide, p. ex. radiateurs domestiques ou de moteur de voiture avec des canalisations d'échange de chaleur immergées dans la masse du fluide avec canalisations tubulaires les canalisations étant rectilignes
F28F 1/02 - Éléments tubulaires de section transversale non circulaire
F28F 1/12 - Éléments tubulaires ou leurs ensembles avec moyens pour augmenter la surface de transfert de chaleur, p. ex. avec des ailettes, avec des saillies, avec des évidements ces moyens étant uniquement à l'extérieur de l'élément tubulaire
H01L 23/473 - Dispositions pour le refroidissement, le chauffage, la ventilation ou la compensation de la température impliquant le transfert de chaleur par des fluides en circulation par une circulation de liquides
F28D 21/00 - Appareils échangeurs de chaleur non couverts par l'un des groupes
77.
Mapping vector representations onto a predicated scalar multi-threaded system
A system implementing a method for generating code for execution based on a SIMT model with parallel units of threads is provided. The system identifies a loop within a program that includes vector processing. The system generates instructions for a thread that include an instruction to set a predicate based on whether the thread of a parallel unit corresponds to a vector element. The system also generates instructions to perform the vector processing via scalar operations predicated on the predicate. As a result, the system generates instructions to perform the vector processing but to avoid branch divergence within the parallel unit of threads that would be needed to check whether a thread corresponds to a vector element.
A method and system in a computer system for dynamically providing a graphical representation of a data store of entries via a matrix interface is disclosed. A dynamic graph system provides a matrix interface that exposes to an application program a graphical representation of data stored in a data store such as a semantic database storing triples. To the application program, the matrix interface represents the graph as a sparse adjacency matrix that is stored in compressed form. Each entry of the data store is considered to represent a link between nodes of the graph. Each entry has a first field and a second field identifying the nodes connected by the link and a third field with a value for the link that connects the identified nodes. The first, second, and third fields represent the rows, column, and elements of the adjacency matrix.
A system and algorithm configured to generate diversity at the traffic source so that packets are uniformly distributed over all of the available paths, but to increase the likelihood of taking a minimal path with each hop the packet takes. This is achieved by configuring routing biases so as to prefer non-minimal paths at the injection point, but increasingly prefer minimal paths as the packet proceeds, referred to herein as Increasing Minimal Bias (IMB).
A system for updating an index into a tuple table of tuples is provided. An indexing system updates an index into a tuple table using fine-grain locking of the index. The index includes a values table with an entry for each index value of an index field that references a value-tuple table that includes, for each tuple with the index value, a row that identifies a tuple of the tuple table with that indexed value. After a new tuple is added to the tuple table with a value, the index is updated by locking the entry in the values table, updating the value-tuple table for the value, and then unlocking the entry. When the index is accessed for locating tuples with a value, the accessor locks the entry in the values table for the value, uses the value-tuple table to locate the tuples, and unlocks the entry.
A method of scheduling requests from various services to a data storage resource, includes receiving service requests, the service requests including metadata specifying a service ID and a data size of payload data associated with the request, at least some of the service IDs having service throughput metadata specifying a required service throughput associated therewith; arranging the requests into FIFO throttled queues based on the service ID; setting a deadline for processing of a request in a throttled queue, the deadline selected in dependence upon the size of the request and the required service throughput associated therewith; providing a time credit value for each throttled queue, the time credit value including an accumulated value of the time by which a deadline for that queue has been missed; comparing the time credit value of a throttled queue to the time required to service the next request in that throttled queue.
A method and system for inferring facts in parallel in a multiprocessor computing environment is provided. An inference system infers facts by applying rules to a collection of existing facts. For each existing fact, the inference system schedules a thread to apply the rules to that existing fact. As a thread infers a new fact (i.e., one that is not already in the collection of facts), the thread adds that inferred fact to the collection of facts. When a thread adds a new fact to the collection, the thread also applies the rules to that new fact. After the threads complete execution, the inference system may apply the rules to the facts of the collection, including the newly inferred facts, by again launching a thread for each fact to apply the rules to that fact. The inference system performs this processing iteratively until a termination condition is satisfied.
A resiliency system detects and corrects memory errors reported by a memory system of a computing system using previously stored error correction information. When a program stores data into a memory location, the resiliency system executing on the computing system generates and stores error correction information. When the program then executes a load instruction to retrieve the data from the memory location, the load instruction completes normally if there is no memory error. If, however, there is a memory error, the computing system passes control to the resiliency system (e.g., via a trap) to handle the memory error. The resiliency system retrieves the error correction information for the memory location and re-creates the data of the memory location. The resiliency system stores the data as if the load instruction had completed normally and passes control to the next instruction of the program.
G06F 11/14 - Détection ou correction d'erreur dans les données par redondance dans les opérations, p. ex. en utilisant différentes séquences d'opérations aboutissant au même résultat
G06F 11/20 - Détection ou correction d'erreur dans une donnée par redondance dans le matériel en utilisant un masquage actif du défaut, p. ex. en déconnectant les éléments défaillants ou en insérant des éléments de rechange
G06F 11/10 - Détection ou correction d'erreur par introduction de redondance dans la représentation des données, p. ex. en utilisant des codes de contrôle en ajoutant des chiffres binaires ou des symboles particuliers aux données exprimées suivant un code, p. ex. contrôle de parité, exclusion des 9 ou des 11
G06F 11/08 - Détection ou correction d'erreur par introduction de redondance dans la représentation des données, p. ex. en utilisant des codes de contrôle
84.
Rack mounted electronics having connectors with heat cooling fingers
A system and method for cooling a plurality of connectors interfacing electrical and optical signals to circuit boards in an electronics cabinet, such as backplane connectors routing signals to circuit boards housed in card cage assemblies. Heat pipes coupled to the connectors efficiently remove heat from the connectors and sink the connector heat to a cold junction of a liquid cooling system, which cooling system may also extract heat from air flow cooling the circuit boards such that the system is room neutral, meaning that the ambient temperature remains constant during operation of the system. The heat connector cooling system is effective where connectors are outside of an air flow cooling envelope that may cool the circuit boards.
Computer cabinets, such as supercomputer cabinets, having progressive air velocity cooling systems are described herein. In one embodiment, a computer cabinet includes an air mover positioned beneath a plurality of computer module compartments. The computer module compartments can be arranged in tiers with the computer modules in each successive tier being positioned closer together than the computer modules in the tier directly below. The computer cabinet can also include one or more shrouds, flow restrictors, and/or sidewalls that further control the direction and/or speed of the cooling air flow through the cabinet.
A method of writing data to a distributed file system including a file system client, a server and a storage resource target, includes generating, on the client, a write request including a byte stream to be written to the storage resource target; formatting, on the client, the byte stream into sectors in accordance with the T10 protocol, the sectors including a data field and a protection information field, the protection information field including a guard field, an application field and a reference field; computing, on the client, checksum data for the guard field; sending, across a network, the data and the protection information to the server; verifying, in T10-capable hardware on the server, the checksum data for the guard field; verifying, on the storage resource target, the checksum data for the guard field; and storing the data on the storage resource target.
G06F 11/08 - Détection ou correction d'erreur par introduction de redondance dans la représentation des données, p. ex. en utilisant des codes de contrôle
G06F 11/00 - Détection d'erreursCorrection d'erreursContrôle de fonctionnement
G06F 17/30 - Recherche documentaire; Structures de bases de données à cet effet
H04L 29/08 - Procédure de commande de la transmission, p.ex. procédure de commande du niveau de la liaison
G06F 11/10 - Détection ou correction d'erreur par introduction de redondance dans la représentation des données, p. ex. en utilisant des codes de contrôle en ajoutant des chiffres binaires ou des symboles particuliers aux données exprimées suivant un code, p. ex. contrôle de parité, exclusion des 9 ou des 11
G06F 3/06 - Entrée numérique à partir de, ou sortie numérique vers des supports d'enregistrement
A multi-layer printed circuit board has a number of landing pads that are configured to engage a connector secured thereto. Between the landing pads associated with different signals is at least one micro via that is electrically connected to a ground plane on an outer surface of the multi-layer printed circuit board, and a ground plane on an inner layer of the multi-layer printed circuit board.
A multi-layer printed circuit board has a number of landing pads that are configured to engage a connector secured thereto. Between the landing pads associated with different signals is at least one micro via that is electrically connected to a ground plane on an outer surface of the multi-layer printed circuit board, and a ground plane on an inner layer of the multi-layer printed circuit board.
A system for allowing dynamic changing of routing information of a network interconnect while avoiding deadlocks and preserving packet ordering. A network resiliency system detects when an error in the network interconnect occurs and dynamically generates new routing information for the routers that factors in the detected error. The network resiliency system then generates new routing information that factors in the failure. The network resiliency system then directs the network interconnect to enter a quiescent state in which no packets are transiting through the network interconnect. After the network interconnect enters the quiescent state, the network resiliency system directs the loading of the new routing information into the routing tables of the network interconnect and then directs the network interconnect to start injecting request packets into the network interconnect.
A system for allowing dynamic changing of routing information of a network interconnect while avoiding deadlocks and preserving packet ordering. A network resiliency system detects when an error in the network interconnect occurs and dynamically generates new routing information for the routers that factors in the detected error. The network resiliency system then generates new routing information that factors in the failure. The network resiliency system then directs the network interconnect to enter a quiescent state in which no packets are transiting through the network interconnect. After the network interconnect enters the quiescent state, the network resiliency system directs the loading of the new routing information into the routing tables of the network interconnect and then directs the network interconnect to start injecting request packets into the network interconnect.
A method and apparatus to provide specifiable ordering between and among vector and scalar operations within a single streaming processor (SSP) via a local synchronization (Lsync) instruction that operates within a relaxed memory consistency model. Various aspects of that relaxed memory consistency model are described. Further, a combined memory synchronization and barrier synchronization (Msync) for a multistreaming processor (MSP) system is described. Also, a global synchronization (Gsync) instruction provides synchronization even outside a single MSP system is described. Advantageously, the pipeline or queue of pending memory requests does not need to be drained before the synchronization operation, nor is it required to refrain from determining addresses for and inserting subsequent memory accesses into the pipeline.
A method and system for detecting congestion in a network of nodes, abating the network congestion, and identifying the cause of the network congestion is provided. A congestion detection system may comprise a detection system, an abatement system, and a cauzation system. The detection system monitors the performance of network components such as the network interface controllers and tiles of routers to determine whether the network is congested such that a delay in delivering packets becomes unacceptable. Upon detecting that the network is congested, an abatement system abates the congestion by limiting the rate at which packets are injected into the network from the nodes. Upon detecting that the network is congested, a cauzation system may identify the job that is executing on a node that is the cause of the network congestion.
H04L 1/00 - Dispositions pour détecter ou empêcher les erreurs dans l'information reçue
H04L 12/26 - Dispositions de surveillance; Dispositions de test
G06F 15/173 - Communication entre processeurs utilisant un réseau d'interconnexion, p. ex. matriciel, de réarrangement, pyramidal, en étoile ou ramifié
H04L 12/24 - Dispositions pour la maintenance ou la gestion
A method and system for detecting congestion in a network of nodes, abating the network congestion, and identifying the cause of the network congestion is provided. A congestion detection system may comprise a detection system, an abatement system, and a causation system. The detection system monitors the performance of network components such as the network interface controllers and tiles of routers to determine whether the network is congested such that a delay in delivering packets becomes unacceptable. Upon detecting that the network is congested, an abatement system abates the congestion by limiting the rate at which packets are injected into the network from the nodes. Upon detecting that the network is congested, a causation system may identify the job that is executing on a node that is the cause of the network congestion.
H04J 1/00 - Systèmes multiplex à division de fréquence
H04L 12/933 - Cœur de commutateur, p.ex. barres croisées, mémoire partagée ou support partagé
H04L 12/801 - Commande de flux ou commande de congestion
H04L 12/825 - Commande adaptative, à la source ou aux nœuds intermédiaires, sur réception d'avis de congestion, p.ex. X-on X-off
H04L 12/773 - Architecture du routeur pour supporter la commutation de couche 3, p.ex. commutation IP, relais de commutation de cellules [CSR] ou commutation d’étiquettes
H04L 12/26 - Dispositions de surveillance; Dispositions de test
A method and system for detecting congestion in a network of nodes, abating the network congestion, and identifying the cause of the network congestion is provided. A congestion detection system may comprise a detection system, an abatement system, and a causation system. The detection system monitors the performance of network components such as the network interface controllers and tiles of routers to determine whether the network is congested such that a delay in delivering packets becomes unacceptable. Upon detecting that the network is congested, an abatement system abates the congestion by limiting the rate at which packets are injected into the network from the nodes. Upon detecting that the network is congested, a causation system may identify the job that is executing on a node that is the cause of the network congestion.
A processor core, comprises one or more vector units operable to change between a fine-grained vector mode having a shorter maximum vector length and a coarse-grained vector mode having a longer maximum vector length. Changing vector modes comprises halting all instruction stream execution in the core, flushing one or more registers in a register space, reconfiguring one or more vector registers in the register space, and restarting instruction execution in the core.
A multiprocessor computer system comprises a plurality of nodes, wherein the nodes are ordered using a snaking dimension-ordered numbering. An application placement module is operable to place an application in nodes with preference given to nodes ordered near one another.
G06F 15/173 - Communication entre processeurs utilisant un réseau d'interconnexion, p. ex. matriciel, de réarrangement, pyramidal, en étoile ou ramifié
97.
Systems and associated methods for controllably cooling computer components
Computer systems and associated methods for cooling computer components are disclosed herein. One embodiment of a computer system includes a computer cabinet having an air inlet spaced apart from an air outlet. The computer system also includes heat exchangers positioned in the computer cabinet, and a heat removal system in fluid communication with the heat exchangers. The computer system additionally includes at least one sensor for monitoring heat transfer between the computer cabinet and the room. The computer system further includes a control system operatively coupled to the at least one sensor, the control system including a computer-readable medium holding instructions for determining whether heat transfer between the computer cabinet and the room is balanced based on information from the sensor, and if not, adjusting a parameter to balance the heat transfer.
One embodiment includes an integrated circuit including an input circuit, a first diode including a first anode and a first cathode, with the first cathode coupled to a first voltage, the first anode coupled to the input circuit at a node via a first mechanical switch, a second diode including a second anode and a second cathode, with the second cathode coupled to the node via a second mechanical switch, the second anode coupled to a ground and a resistor coupled to the input circuit between the integrated circuit and the node, wherein in a first mode of operating, the first mechanical switch and the second mechanical switch are conducting, and in a second mode of operating, the first and second mechanical switches are nonconducting.
H02H 3/20 - Circuits de protection de sécurité pour déconnexion automatique due directement à un changement indésirable des conditions électriques normales de travail avec ou sans reconnexion sensibles à un excès de tension
H02H 9/04 - Circuits de protection de sécurité pour limiter l'excès de courant ou de tension sans déconnexion sensibles à un excès de tension
99.
Air conditioning systems for computer systems and associated methods
Computer systems with air cooling systems and associated methods are disclosed herein. In several embodiments, a computer system can include a computer cabinet holding multiple computer modules, and an air mover positioned in the computer cabinet. The computer system can also include an airflow restrictor positioned proximate to an air outlet of the computer cabinet, and an overhead heat exchanger mated to the computer cabinet proximate to the air outlet.
Systems and methods provide a debugger that debugs code using two versions of code, an optimized and a debuggable version of object code for subroutines, methods or functions. The debugger causes the appropriate version of the code to be executed depending on whether debug commands have been applied with respect to particular subroutines, methods or functions.
