US20130097351A1 - System and Method for High-Performance, Low-Power Data Center Interconnect Fabric - Google Patents

System and Method for High-Performance, Low-Power Data Center Interconnect Fabric Download PDF

Info

Publication number
US20130097351A1
US20130097351A1 US13/705,428 US201213705428A US2013097351A1 US 20130097351 A1 US20130097351 A1 US 20130097351A1 US 201213705428 A US201213705428 A US 201213705428A US 2013097351 A1 US2013097351 A1 US 2013097351A1
Authority
US
United States
Prior art keywords
processing cores
interrupt
management
computing system
node
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Abandoned
Application number
US13/705,428
Inventor
Mark Bradley Davis
David James Borland
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Silicon Valley Bank Inc
Original Assignee
Calxeda Inc
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Calxeda Inc filed Critical Calxeda Inc
Priority to US13/705,428 priority Critical patent/US20130097351A1/en
Assigned to CALXEDA, INC. reassignment CALXEDA, INC. ASSIGNMENT OF ASSIGNORS INTEREST (SEE DOCUMENT FOR DETAILS). Assignors: BORLAND, DAVID JAMES, DAVIS, MARK BRADLEY
Publication of US20130097351A1 publication Critical patent/US20130097351A1/en
Assigned to SILICON VALLEY BANK reassignment SILICON VALLEY BANK SECURITY AGREEMENT Assignors: CALXEDA, INC.
Assigned to SILICON VALLEY BANK reassignment SILICON VALLEY BANK ASSIGNMENT OF ASSIGNORS INTEREST (SEE DOCUMENT FOR DETAILS). Assignors: CALXEDA, INC.
Assigned to CALXEDA, INC. reassignment CALXEDA, INC. RELEASE OF SECURITY INTEREST Assignors: SILICON VALLEY BANK
Assigned to SILICON VALLEY BANK reassignment SILICON VALLEY BANK CORRECTIVE ASSIGNMENT TO CORRECT THE INCORRECT APPL. NO. 13/708,340 PREVIOUSLY RECORDED AT REEL: 030292 FRAME: 0207. ASSIGNOR(S) HEREBY CONFIRMS THE SECURITY AGREEMENT. Assignors: CALXEDA, INC.
Abandoned legal-status Critical Current

Links

Images

Classifications

    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L45/00Routing or path finding of packets in data switching networks
    • H04L45/74Address processing for routing
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L12/00Data switching networks
    • H04L12/28Data switching networks characterised by path configuration, e.g. LAN [Local Area Networks] or WAN [Wide Area Networks]
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L49/00Packet switching elements
    • H04L49/35Switches specially adapted for specific applications
    • H04L49/356Switches specially adapted for specific applications for storage area networks
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F13/00Interconnection of, or transfer of information or other signals between, memories, input/output devices or central processing units
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F1/00Details not covered by groups G06F3/00 - G06F13/00 and G06F21/00
    • G06F1/26Power supply means, e.g. regulation thereof
    • G06F1/32Means for saving power
    • G06F1/3203Power management, i.e. event-based initiation of a power-saving mode
    • G06F1/3234Power saving characterised by the action undertaken
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F12/00Accessing, addressing or allocating within memory systems or architectures
    • G06F12/02Addressing or allocation; Relocation
    • G06F12/0223User address space allocation, e.g. contiguous or non contiguous base addressing
    • G06F12/0284Multiple user address space allocation, e.g. using different base addresses
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F13/00Interconnection of, or transfer of information or other signals between, memories, input/output devices or central processing units
    • G06F13/14Handling requests for interconnection or transfer
    • G06F13/20Handling requests for interconnection or transfer for access to input/output bus
    • G06F13/24Handling requests for interconnection or transfer for access to input/output bus using interrupt
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F13/00Interconnection of, or transfer of information or other signals between, memories, input/output devices or central processing units
    • G06F13/38Information transfer, e.g. on bus
    • G06F13/40Bus structure
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F3/00Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
    • G06F3/06Digital input from, or digital output to, record carriers, e.g. RAID, emulated record carriers or networked record carriers
    • G06F3/0601Interfaces specially adapted for storage systems
    • G06F3/0602Interfaces specially adapted for storage systems specifically adapted to achieve a particular effect
    • G06F3/0604Improving or facilitating administration, e.g. storage management
    • G06F3/0605Improving or facilitating administration, e.g. storage management by facilitating the interaction with a user or administrator
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F3/00Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
    • G06F3/06Digital input from, or digital output to, record carriers, e.g. RAID, emulated record carriers or networked record carriers
    • G06F3/0601Interfaces specially adapted for storage systems
    • G06F3/0628Interfaces specially adapted for storage systems making use of a particular technique
    • G06F3/0629Configuration or reconfiguration of storage systems
    • G06F3/0631Configuration or reconfiguration of storage systems by allocating resources to storage systems
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F3/00Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
    • G06F3/06Digital input from, or digital output to, record carriers, e.g. RAID, emulated record carriers or networked record carriers
    • G06F3/0601Interfaces specially adapted for storage systems
    • G06F3/0668Interfaces specially adapted for storage systems adopting a particular infrastructure
    • G06F3/067Distributed or networked storage systems, e.g. storage area networks [SAN], network attached storage [NAS]
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F9/00Arrangements for program control, e.g. control units
    • G06F9/06Arrangements for program control, e.g. control units using stored programs, i.e. using an internal store of processing equipment to receive or retain programs
    • G06F9/46Multiprogramming arrangements
    • G06F9/50Allocation of resources, e.g. of the central processing unit [CPU]
    • G06F9/5005Allocation of resources, e.g. of the central processing unit [CPU] to service a request
    • G06F9/5011Allocation of resources, e.g. of the central processing unit [CPU] to service a request the resources being hardware resources other than CPUs, Servers and Terminals
    • G06F9/5016Allocation of resources, e.g. of the central processing unit [CPU] to service a request the resources being hardware resources other than CPUs, Servers and Terminals the resource being the memory
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L45/00Routing or path finding of packets in data switching networks
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L45/00Routing or path finding of packets in data switching networks
    • H04L45/60Router architectures
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L45/00Routing or path finding of packets in data switching networks
    • H04L45/74Address processing for routing
    • H04L45/745Address table lookup; Address filtering
    • H04L45/74591Address table lookup; Address filtering using content-addressable memories [CAM]
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L49/00Packet switching elements
    • H04L49/10Packet switching elements characterised by the switching fabric construction
    • H04L49/109Integrated on microchip, e.g. switch-on-chip
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L49/00Packet switching elements
    • H04L49/15Interconnection of switching modules
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L49/00Packet switching elements
    • H04L49/20Support for services
    • H04L49/201Multicast operation; Broadcast operation
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L49/00Packet switching elements
    • H04L49/25Routing or path finding in a switch fabric
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L49/00Packet switching elements
    • H04L49/25Routing or path finding in a switch fabric
    • H04L49/253Routing or path finding in a switch fabric using establishment or release of connections between ports
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L49/00Packet switching elements
    • H04L49/30Peripheral units, e.g. input or output ports
    • H04L49/3009Header conversion, routing tables or routing tags
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L49/00Packet switching elements
    • H04L49/35Switches specially adapted for specific applications
    • H04L49/351Switches specially adapted for specific applications for local area network [LAN], e.g. Ethernet switches
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L47/00Traffic control in data switching networks
    • H04L47/10Flow control; Congestion control
    • YGENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02BCLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO BUILDINGS, e.g. HOUSING, HOUSE APPLIANCES OR RELATED END-USER APPLICATIONS
    • Y02B70/00Technologies for an efficient end-user side electric power management and consumption
    • Y02B70/10Technologies improving the efficiency by using switched-mode power supplies [SMPS], i.e. efficient power electronics conversion e.g. power factor correction or reduction of losses in power supplies or efficient standby modes
    • YGENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02BCLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO BUILDINGS, e.g. HOUSING, HOUSE APPLIANCES OR RELATED END-USER APPLICATIONS
    • Y02B70/00Technologies for an efficient end-user side electric power management and consumption
    • Y02B70/30Systems integrating technologies related to power network operation and communication or information technologies for improving the carbon footprint of the management of residential or tertiary loads, i.e. smart grids as climate change mitigation technology in the buildings sector, including also the last stages of power distribution and the control, monitoring or operating management systems at local level
    • YGENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02DCLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
    • Y02D10/00Energy efficient computing, e.g. low power processors, power management or thermal management
    • YGENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
    • Y02TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
    • Y02DCLIMATE CHANGE MITIGATION TECHNOLOGIES IN INFORMATION AND COMMUNICATION TECHNOLOGIES [ICT], I.E. INFORMATION AND COMMUNICATION TECHNOLOGIES AIMING AT THE REDUCTION OF THEIR OWN ENERGY USE
    • Y02D30/00Reducing energy consumption in communication networks

Definitions

  • the disclosure relates generally to a switching fabric for a computer-based system.
  • FIGS. 1A and 1B show a classic data center network aggregation as is currently well known.
  • FIG. 1A shows a diagrammatical view of a typical network data center architecture 100 wherein top level switches 101 a - n are at the tops of racks 102 a - n filled with blade servers 107 a - n interspersed with local routers 103 a - f . Additional storage routers and core switches. 105 a - b and additional rack units 108 a - n contain additional servers 104 e - k and routers 106 a - g FIG.
  • 1 b shows an exemplary physical view 110 of a system with peripheral servers 111 a - bn arranged around edge router systems 112 a - h , which are placed around centrally located core switching systems 113 .
  • a - bn arranged around edge router systems 112 a - h , which are placed around centrally located core switching systems 113 .
  • Typically such an aggregation 110 has 1-Gb Ethernet from the rack servers to their top of rack switches, and often 10 Gb Ethernet ports to the edge and core routers.
  • FIGS. 1A and 1B illustrate a typical data center system
  • FIG. 2A illustrates a computing unit that may include a universal address system and method
  • FIG. 2B illustrates a computing system that may include a universal address system and method
  • FIG. 2C is an overview of a network aggregation system
  • FIG. 3 illustrates an overview of an exemplary data center in a rack system
  • FIG. 4 illustrates a high-level topology of a network aggregating system
  • FIG. 5A illustrates a block diagram of an exemplary switch of the network aggregation system
  • FIG. 5B illustrates the MAC address encoding
  • FIG. 6 illustrates a first embodiment of a broadcast mechanism of the network aggregation system
  • FIG. 7 illustrates an example of unicast routing of the network aggregation system
  • FIG. 8 illustrates an example of fault-resistant unicast routing of the network aggregation system
  • FIG. 9 illustrates a second embodiment of a broadcast mechanism of the network aggregation system
  • FIG. 10 illustrates an exemplary system for management of power supplied to multiple processors
  • FIG. 11 illustrates an exemplary data structure that may be maintained by a power management system shown in FIG. 10 ;
  • FIG. 12 an example of a process for power management
  • FIG. 13 illustrates an example of a larger power management system
  • FIG. 14 illustrates an exemplary process for system level power management
  • FIG. 15 illustrates an architectural overview of a multiprocessor chip
  • FIG. 16 illustrates more details of the switching fabric shown in FIG. 15 .
  • the disclosure is particularly applicable to a network aggregation system and method as illustrated and described below and it is in this context that the disclosure will be described. It will be appreciated, however, that the system and method has greater utility since the system and method can be implemented using other elements and architectures that are within the scope of the disclosure and the disclosure is not limited to the illustrative embodiments described below.
  • the system and method also supports a routing using a tree-like or graph topology that supports multiple links per node, where each link is designated as an Up, Down, or Lateral link, or both, within the topology.
  • each node in the system maybe be a combination computational/switch node, or just a switch node, and input/outpout (I/O) can reside on any node as described below in more detail.
  • the system may also provide a system with a segmented Ethernet Media Access Control (MAC) architecture which may have a method of re-purposing MAC IP addresses for inside MACs and outside MACs, and leveraging what would normally be the physical signaling for the MAC to feed into the switch.
  • MAC Seged Ethernet Media Access Control
  • the system may also provide a method of non-spoofing communication, as well as a method of fault-resilient broadcasting, which may have a method of unicast misrouting for fault resilience.
  • a spoofing attack is a situation in which one person or program successfully masquerades as another by falsifying data and thereby gaining an illegitimate advantage.
  • the system may also provide a rigorous security between the management processors, such that management processors can “trust” one another.
  • the management processors there is a management processor within each SoC (the M3 microcontroller, block 906 , FIG. 5A ).
  • the software running on the management processor is trusted because a) the vendor (in this case Smooth-Stone) has developed and verified the code, b) non-vendor code is not allowed to run on the processor. Maintaining a Trust relationship between the management processors allow them to communicate commands (e.g. reboot another node) or request sensitive information from another node without worrying that a user could spoof the request and gain access to information or control of the system.
  • the system may also provide a network proxy that has an integrated microcontroller in an always-on power domain within a system on a chip (SOC) that can take over network proxying for the larger onboard processor, and which may apply to a subtree.
  • SOC system on a chip
  • the system also provide a multi-domaining technique that can dramatically expand the size of a routable fat tree like structure with only trivial changes to the routing header and the routing table.
  • FIG. 2A illustrates a computing unit 210 that is part of a distributed computing system and may include a universal address system and method. In one embodiment, each computing unit may be implemented on a single integrated circuit as shown in FIG. 2A .
  • Each computing unit 210 may include one or more processing cores 212 , such as ARM processing cores, and an associated cache memory 214 , a DDR controller 216 , a not AND logic (NAND) flash memory interface 218 , I/O interfaces 220 , a power management portion 222 , a direct memory access (DMA)/virtual memory management (VMM) support unit 224 described in more detail below and one or more hardware accelerators 226 .
  • processing cores 212 such as ARM processing cores
  • NAND not AND logic
  • NAND not AND logic
  • I/O interfaces 220 I/O interfaces
  • power management portion 222 a power management portion 222
  • DMA direct memory access
  • VMM virtual memory management
  • FIG. 2B illustrates a distributed computing system 230 that may include a universal address system and method.
  • Each computing system 230 may be a node in a processing system in which a plurality of nodes are connected to each other over a link, such as a network.
  • each computing system 230 may further comprise double data rate (DDR) low power RAM 232 , such as 512 Mb of low power DDR RAM in one embodiment, which is direct access memory to the computing system, NAND flash memory 234 , such as 2-8 Gb of NAND flash memory in one embodiment, that acts as persistent storage and stores a file system, an interconnect 236 that connects this computing system to the other computing systems over a link, such as a computer network, and software 238 , such as a Linux operating system, virtual memory management (VMM) software and one or more optimized software functions.
  • the universal address system is implemented using the DMA and VMM support 224 of each computing unit 224 (See FIG.
  • the DMA of the computing unit is a standard mechanism (common in many systems), which can be given a data movement task to perform by the system. In this scenario, such a standard module would be told to copy a page of data via the IO links to the local memory and then to report.
  • the VMM support is a similarly standard function consisting of both software and hardware that is used to check every memory access and convert the virtual page to a physical page reference. In this scenario, the existing mechanisms would use as the first level of the extended mechanism and the VMM software would be used to further translate from local physical page to universal address.
  • FIG. 2C illustrates a network aggregation system 300 .
  • the network aggregation supports one or more high speed links 301 (thick lines), such as a 10-Gb/sec Ethernet communication, that connect an aggregation router 302 and one or more racks 303 , such as three racks 303 a - c as shown in FIG. 3 .
  • the network aggregation system provides multiple high-speed 10 Gb paths, represented by thick lines, between one or more Smooth-Stone computing unit 306 a - d , such as server computers, on shelves within a rack. Further details of each Smooth-Stone computing unit are described in more detail in U.S. Provisional Patent Application Ser. No.
  • An embedded switch 306 a - d in the Smooth-Stone computing units can replace a top-of-rack switch, thus saving a dramatic amount of power and cost, while still providing a 10 Gb Ethernet port to the aggregation router 302 .
  • the network aggregation system switching fabric can integrate traditional Ethernet (1 Gb or 10 Gb) into the XAUI fabric, and the Smooth-Stone computing units can act as a top of rack switch for third-party Ethernet connected servers.
  • a middle rack 303 b illustrates another configuration of a rack in the network aggregation system in which one or more Smooth-Stone computing units 306 e,f can integrate into existing data center racks that already contain a top-of-rack switch 308 a.
  • the IT group can continue to have their other computing units connected via 1 Gb Ethernet up to the existing top-of-rack switch and the internal Smooth-Stone computing units can be connected via 10 Gb XAUI fabric and they can integrate up to the existing top-of-rack switch with either a 1 Gb or 10 Gb Ethernet interconnects as shown in FIG. 2C .
  • a third rack 303 c illustrates a current way that data center racks are traditionally deployed.
  • the thin lines in the third rack 303 c represent 1 Gb Ethernet.
  • the current deployments of data center racks is traditionally 1 Gb Ethernet up to the top-of-rack switch 308 b, and then 10 Gb (thick line 301 ) out from the top of rack switch to the aggregation router.
  • all servers are present in an unknown quantity, while they are pictured here in finite quantities for purposes of clarity and simplicity.
  • no additional routers are needed, as they operate their own XAUI switching fabric, discussed below.
  • FIG. 3 shows an overview of an exemplary “data center in a rack” 400 according to one embodiment of the system.
  • the “data center in a rack” 400 may have 10-Gb Ethernet PHY 401 a - n and 1-Gb private Ethernet PHY 402 ,
  • Large computers (power servers) 403 a - n support search; data mining; indexing; Apache Hadoop, a Java software framework; MapReduce, a software framework introduced by Google to support distributed computing on large data sets on clusters of computers; cloud applications; etc.
  • Computers (servers) 404 a - n with local flash and/or solid-state disk (SSD) support search, MySQL, CDN, software-as-a-service (SaaS), cloud applications, etc.
  • SSD solid-state disk
  • Data center 400 has an array 406 of hard disks, e.g., in a Just a Bunch of Disks (MOD) configuration, and, optionally, Smooth-Stone computing units in a disk form factor (for example, the green boxes in arrays 406 and 407 ), optionally acting as disk controllers.
  • Hard disk servers or SS disk servers may be used for web servers, user applications, and cloud applications, etc.
  • an array 407 of storage servers and historic servers 408 a,b (any size, any vendor) with standard Ethernet interfaces for legacy applications.
  • the data center in a rack 400 uses a proprietary system interconnect approach that dramatically reduces power and wires and enables heterogeneous systems, integrating existing Ethernet-based servers and enabling legacy applications.
  • a complete server or storage server is put in a disk or SSD form factor, with 8-16 SATA interfaces with 4 ServerNodesTM and 8 PCIe x4 interfaces with 4 ServerNodesTM. It supports disk and/or SSD+ServerNodeTM, using a proprietary board paired with a disk(s) and supporting Web server, user applications, cloud applications, disk caching, etc.
  • the Smooth-Stone XAUI system interconnect reduces power, wires and the size of the rack. There is no need for high powered, expensive Ethernet switches and high-power Ethernet Phys on the individual servers. It dramatically reduces cables (cable complexity, costs, significant source of failures). It also enables a heterogeneous server mixture inside the rack, supporting any equipment that uses Ethernet or SATA or PCIe. It can be integrated into the system interconnect.
  • the herein presented aspects of a server-on-a-chip (SOC) with packet switch functionality are focused on network aggregation.
  • SOC server-on-a-chip
  • the SOC is not a fully functionally equivalent to an industry-standard network switch, such as, for example, a Cisco switch or router. But for certain applications discussed throughout this document, it offers a better price/performance ratio as well as a power/performance ratio.
  • It contains a layer 2 packet switch, with routing based on source/destination MAC addresses. It further supports virtual local area network (VLAN), with configurable VLAN filtering on domain incoming packets to minimize unnecessary traffic in a domain.
  • VLAN virtual local area network
  • the embedded MACs within the SOC do have complete VLAN support providing VLAN capability to the overall SOC without the embedded switch explicitly having VLAN support.
  • management processor can also wake up the system by management processor notifying the management processor on link state transitions to reprogram routing configurations to route around faults.
  • Such functionality does not require layer 3 (or above) processing (i.e., it is not a router). It also does not offer complete VLAN support, support for QoS/CoS, address learning, filtering, spanning tree protocol (STP), etc.
  • FIG. 4 shows a high-level topology 800 of the network system that illustrates XAUI connected SoC nodes connected by the switching fabric.
  • the 10 Gb Ethernet ports Eth0 801 a and Eth1 801 b come from the top of the tree.
  • Ovals 802 a - n are Smooth-Stone nodes that comprise both computational processors as well as the embedded switch.
  • the nodes have five XAUI links connected to the internal switch.
  • the switching layers use all five XAUI links for switching.
  • the vast majority of trees and fat trees have active nodes only as leaf nodes, and the other nodes are pure switching nodes. This approach makes routing much more straightforward.
  • Topology 800 has the flexibility to permit every node to be a combination computational and switch node, or just a switch node. Most tree-type implementations have I/O on the leaf nodes, but topology 800 let the I/O be on any node. In general, placing the Ethernet at the top of the tree minimizes the average number of hops to the Ethernet.
  • FIG. 5A illustrates one example implementation of an individual node of the cluster.
  • the A9 Cores ( 905 ) may be optionally enabled, or could be just left powered-off. So the upper level switching nodes (N10-N21) in FIG. 6 can be used as pure switching elements (like traditional implementations), or we can power on the A9 Cores module and use them as complete nodes within the computing cluster.
  • FIG. 5 a shows a block diagram of an exemplary switch 900 according to one aspect of the system and method disclosed herein. It has four areas of interest 910 a - d .
  • Area 910 a corresponds to Ethernet packets between the CPUs and the inside MACs.
  • Area 910 b corresponds to Ethernet frames at the Ethernet physical interface at the inside MACs, that contains the preamble, start of frame, and inter-frame gap fields.
  • Area 910 c corresponds to Ethernet frames at the Ethernet physical interface at the outside MAC, that contains the preamble, start of frame, and inter-frame gap fields.
  • Area 910 d corresponds to Ethernet packets between the processor of routing header 901 and outside MAC 904 .
  • This segmented MAC architecture is asymmetric.
  • the inside MACs have the Ethernet physical signaling interface into the routing header processor, and the outside MAC has an Ethernet packet interface into the routing header processor.
  • the MAC IP is re-purposed for inside MACs and outside MACs, and what would normally be the physical signaling for the MAC to feed into the switch is leveraged.
  • MAC configuration is such that the operating system device drivers of A9 cores 905 manage and control inside Eth0 MAC 902 and inside ETH1 MAC 903 .
  • the device driver of management processor 906 manages and controls Inside Eth2 MAC 907 .
  • Outside Eth MAC 904 is not controlled by a device driver.
  • MAC 904 is configured in Promiscuous mode to pass all frames without any filtering for network monitoring. Initialization of this MAC is coordinated between the hardware instantiation of the MAC and any other necessary management processor initialization.
  • Outside Eth MAC 904 registers are visible to both A9 905 and management processor 906 address maps. Interrupts for Outside Eth MAC 904 are routable to either the A9 or management processor.
  • the XGMAC supports several interruptible events that the CPUs may want to monitor, including any change in XGMII link fault status, hot-plugging or removal of PHY, alive status or link status change, and any RMON counter reaching a value equal to the threshold register.
  • the routing frame header processor may standardize these fields.
  • the XAUI interface may need some or all of these fields.
  • the routing header processor at area 910 d needs to add these going into the switch, and to remove them leaving the switch.
  • these three fields may be removed (if the XAUI interface allows it).
  • the routing header processor at area 910 b will need to strip these going into the switch, and add them back leaving the switch.
  • the routing frame header processor receives an Ethernet frame from a MAC, sending a routing frame to the switch. it also standardizes the preamble, start of frame, and inter-frame gap fields, prepends a routing header, and receives a routing frame from the switch, sending the Ethernet frame into a MAC. This processor then strips the routing header and standardizes the preamble, start of frame, and inter-frame gap fields. Note that all frames that are flowing within the fabric are routing frames, not Ethernet frames. The Ethernet frame/routing frame conversion is done only as the packet is entering or leaving the fabric via a MAC. Note also that the routing logic within the switch may change fields within the routing frame. The Ethernet frame is never modified (except the adding/removing of the preamble, start of frame, and inter-frame gap fields).
  • the routing frame is composed of the routing frame header plus the core part of the Ethernet frame, and is structured as shown in Table 1, below:
  • bit sizing is 4096 nodes ⁇ 12 bit node IDs. These fields may be resized during implementation as needed.
  • the routing frame header consists of the fields shown in Table 2, below:
  • a switch If a switch receives a packet that fails the checksum, the packet is dropped, a statistic counter is incremented, and the management processor is notified.
  • the routing frame processor differentiates between several destination MAC address encodings.
  • MAC addresses are formatted as shown in FIG. 5 b .
  • the following table describes the usage of the 3 byte OUI and 3 byte MC specific field within the MAC address.
  • One of the novel aspects of the system and method disclosed herein is the use of additional address bits to encode an internal to external MAC mapping, as shown also in the Table 3, below, in the second entry under “Fabric Internal Node local address Hits MAC Lookup CAM”.
  • Neighbor Multicast bit 12 bits: Packet sent Multicast set SS_NEIGHBOR_MCAST_MAGIC through all Locally 12 bits: Reserved XAUI links to administered neighboring OUI Switch nodes and not OUI rebroadcast to other nodes
  • SS_MAC_NODE_ENCODED_MAGIC and SS_MAC_LINK_ENCODED_MAGIC are constant identifiers used for uniquely identifying these MAC address types.
  • the term “magic number” is a standard industry term for a constant numerical or text value used to identify a file format or protocol. These magic numbers are configured in two registers (magicNodeEncodedMAC and magicLinkEncodedMAC that default to standard values during hardware initialization, but allow the management processor software to change them if necessary.
  • the header processor contains a MAC Lookup CAM (Content Addressable Memory), macAddrLookup, that maps from 6 byte MAC addresses to 12-bit Node IDs, as shown in Table 4, below.
  • MAC Lookup CAM Content Addressable Memory
  • macAddrLookup maps from 6 byte MAC addresses to 12-bit Node IDs, as shown in Table 4, below.
  • the number of rows in this CAM is implementation dependent, but would be expected to be on the order of 256-1024 rows.
  • the management processor initializes the CAM with Node ID mappings for all the nodes within the SS fabric. There are two types of rows, depending upon the setting of the Node Local bit for the row.
  • the Node Local field allows a 4:1 compression of MAC addresses in the CAM for default MAC addresses, mapping all four MACs into a single row in the CAM table, which is Table 5, below.
  • a Node Encoded Address refers to a Smooth Stone Taken from Local assigned MAC address for a node. It encodes the port # low 2 bits of (MAC0, MAC1, management processor, Rsvd) into a 2- MAC Address bit Port ID in the lowest two bits of the NIC address Input field. Ignores low 2 bits during match. Arbitrary 0 Matches against all 6 bytes Taken from CAM Output field
  • the arbitrary rows in the CAM allow mapping of the MAC address aliases to the nodes.
  • Linux and the MACs
  • the MAC addresses to be reassigned on a network interface (e.g., with ifconfig eth0 hw ether 00:80:48:BA:d1:30). This is sometime used by virtualization/cloud computing to avoid needing to re-ARP after starting a session.
  • the switch architecture provides for a secondary MAC Lookup CAM that only stores the 3 bytes of the NIC Specific part of the MAC address for those addresses that match the Switch OUI.
  • the availability of this local OUT CAM is determined by the implementation. See Table 6, below.
  • the maximum number of nodes limitation for three types of MAC address encodings may be evaluated as follows:
  • Default MAC Addressees management processor sets Node Local mappings for each of the nodes in the fabric. There is one entry in the CAM for each node. Max # of nodes is controlled by maximum # of rows in the MAC Address Lookup CAM,
  • Node Encoded Addresses All the MACs are reprogrammed to use Node Encoded Addresses. In this way the Node IDs are directly encoded into the MAC addresses. No entries in the MAC Lookup CAM are used. Max # of nodes is controlled by maximum # of rows in the Unicast lookup table (easier to make big compared to the Lookup CAM). Note that this also gives us some risk mitigation in case the MAC Lookup CAM logic is busted. Provides use case for the node encoded addresses idea.
  • Arbitrary MAC Address Aliases Takes a row in the CAM. As an example, a 512-row CAM could hold 256 nodes (Node local addresses)+1 MAC address alias per node.
  • the management processor Since the Lookup CAM is only accessed during Routing Header creation, the management processor actually only needs to populate a row if the MAC address within the fabric is being used as a source or destination MAC address within a packet. In other words, if two nodes never will talk to each other, a mapping row does not need to be created. But usually the management processor won't have that knowledge, so it's expected that mappings for all nodes are created in all nodes. Also note that even if an entry is not created in the Lookup CAM, the routing will actually still succeed by routing the packet out the Ethernet gateway, through an external router, back into the Fabric, to the destination node.
  • Table 7 defines how to set fields within the Routing Header for all the fields except for destination node and port.
  • Table 8 defines how to set destination node and port for addresses within the fabric:
  • Table 9 defines how to set destination node and port for addresses outside the fabric:
  • management processor software architecture of the system and method disclosed here currently depends on the ability of management processor nodes to “trust” each other. This more rigorous security on management processor to management processor communication is desirable, as well a better security on private management LANs across the fabric.
  • This fabric issue may be mitigated by simply defining, for environments that require multiple “hard” security domains, that customers simply don't mix security domains within a fabric. In such cases, it may be possible to connect 14-node boards to the top of rack switch, allowing customers to have VLAN granularity control of each 14-node board.
  • the multi-domain fabric architecture addresses the lack of VLAN support by creating secure “tunnels” and domains across the fabric, and it can interoperate with VLAN protected router ports on a 1:1 basis.
  • the approach to domain management in the system and method disclosed here is as follows: Support multiple domain IDs within the fabric. Allow each of the MACs within a node (management processor, MAC0, MAC1, Gateway) to be assigned to a domain ID individually (and tagged with domain 0 if not set). Allow each of the MACs within a node to have a bit indicating access to the management domain.
  • the domain IDs associated with a MAC could only be assigned by the management processor, and could not be altered by the A9.
  • the routing frame processor would tag the routing frame with the domain ID and management domain state associated with that MAC.
  • Domains would provide the effect of tunnels or VLANs, in that they keep packets (both unicast and multicast) within that domain, allowing MACs outside that domain to be able to neither sniff or spoof those packets. Additionally, this approach would employ a five-bit domain ID. It would add options to control domain processing, such as, for example, a switch with a boolean per MAC that defines whether packets are delivered with non-defined (i.e., zero) domain ID, or a switch that has a boolean per MAC that defines whether packets are delivered with defined (non-zero) but non-matching domain IDs. A further option in the switch could turn off node encoded MAC addresses per MAC (eliminating another style of potential attack vector).
  • the management domain bit on all management processor MACs could be marked.
  • the management processor should route on domain 1 (by convention).
  • domain 1 by convention.
  • Such a technique allows all the management processor's to tunnel packets on the management domain so that they cannot be inspected or spoofed by any other devices (inside or outside the fabric), on other VLANs or domains.
  • a gateway MAC that has the management domain bit set could be assigned, keeping management packets private to the management processor domain.
  • the switch fabric could support “multi-tenant” within itself, by associating each gateway MAC with a separate domain.
  • each gateway MAC could connect to an individual port on an outside router, allowing that port to be optionally associated with a VLAN. As the packets come into the gateway, they are tagged with the domain ID, keeping that traffic private to the MACs associated with that domain across the fabric.
  • the switch supports a number of registers (aka CSRs, aka MMRs) to allow software or firmware to control the switch.
  • CSRs aka MMRs
  • MMRs magnetic resonance registers
  • the actual layout of these registers will be defined by the implementation.
  • the fields listed in Table 10 are software read/write. All these registers need to have a mechanism to secure them from writing from the A9 (could be secure mode or on a management processor private bus).
  • the use case here is where the management processor wants to see the gratuitous ARPs that are locally initiated so that it can communicate across the management processor fabric and add corresponding entries into the local unicast routing tables.
  • macAddrLookup Lookup CAM which is MAC address lookup CAM to convert MAC described elsewhere in addresses to Node IDs.
  • macAcceptOtherDomain[MAC] 1 bit[MAC] Defines that the MAC accepts packets that are tagged with a non-zero, non-matching domain ID.
  • macAcceptZeroDomain[MAC] 1 bit[MAC] Defines that the MAC accepts packets that are not tagged with a domain (i.e. 0 domain)
  • macDomainID[MAC] 5 bits[MAC] Defines the Domain ID for each of the 4 MACs. A value of 0 indicates that the domain ID for that MAC is not set.
  • macMgmtDomain[MAC] 1 bit[MAC] Defines that the MAC may access the management domain.
  • magicNodeEncodedMAC 10 bits Magic number for Node Encoded MAC addresses
  • magicLinkEncodedMAC 12 bits Magic number for Link Encoded MAC addresses maxTTL 6 bits Maximum TTL count allowed in a routing header. Exceeding this number of hops causes the switch to drop the packet, update a statistic counter, and inform the management processor.
  • myNodeID 12 bits Need not be contiguous. Subtree's should ideally be numbered within a range to facilitate subtree network proxying.
  • portRemap[INT_PORTS]; Array [INT_PORTS] x Allows remapping of incoming destination 2 bits port IDs to the internal port where it'll be delivered. This register defaults to an equivalence remapping. An example of where this will get remapped is during Network Proxy where the management processor will remap MAC0 packets to be sent to the management processor.
  • INT_PORTS 4. Array elements are the Ports enumeration (management processor, MAC0, MAC1, OUT). 2 bits contents is the Ports enumeration.
  • primaryEthGatewayNode[INT_PORTS] Array [INT_PORTS] Specifies Node ID of primary Ethernet of 12-bit gateway for this node.
  • promiscuousPortVec 4 bits Can be configured for Promiscuous Mode allowing traffic on one or more links to be snooped by the management processor or A9s in order to collect trace data or to implement an Intruder Detection System (IDS). This causes all traffic passing through the switch to be copied to the internal ports defined by this port vector.
  • IDMS Intruder Detection System
  • routeForeignMACsOut 1 bit When enabled, a MAC address that does not contain a myOUI address, will not check the MAC lookup CAM, and will get treated as a MAC lookup CAM miss, thus getting routed to the gateway port.
  • secondaryEthGatewayNode[INT_PORTS] Array [INT_PORTS] Specifies Node ID of secondary Ethernet of 12-bit gateway. Incoming (from OUT) packets routing through the fabric will be sent here.
  • unicastPortsFromOtherExt 1 bit An incoming unicast from an external Gateways gateway will get the gateway node put into the source node field of the routing header. Upon reaching the destination node, this bit will be checked. When the bit is clear, the external gateway node must match the destination gateway node for it to be delivered to internal ports.
  • the registers shown in Table 11 are contained within the Switch implementation, but need not be software accessible.
  • FIG. 6 shows an exemplary broadcast mechanism 1000 according to one aspect of the system and method disclosed herein.
  • the link between nodes N10 1001 and N21 1002 is down, as indicated by the dashed line 1003 .
  • the source node puts an incremented broadcast ID for that source node in the routing frame (rframe.bcastID).
  • N04 1004 initiates a broadcast to all neighbors, i.e., N11 1105 .
  • N11 has not seen the packet, so it broadcasts to all non-incoming neighbors, which, in this example, are N21 1002 , N20 1006 , N03 1007 , and N05 1008 , and accepts the packet internally.
  • Nodes N03 and N05 haven't seen the packet, so they accept the broadcast internally and are done.
  • N21 hasn't seen the packet, so it broadcasts the packet to all active, non-incoming links (e.g., N10, N12 1009 ), and accepts the packet internally.
  • N20 broadcasts the packet to all active, non-incoming links (i.e., N12), and accepts the packet internally.
  • N10 broadcasts down to N00 1010 , N01 1011 , and N02 1012 .
  • N12 rebroadcasts to N06 1013 , N07 1014 , N08 1015 and to one of N21 and N20 (the one it didn't get the broadcast packet from). Note that one of N20 and N21, and N12, see the packet twice. They take action only on their first instance, the secondary times it hits the broadcast CAM as a duplicate, and the packet is ignored.
  • Unicast routing (as shown in FIG. 7 ) is responsible for routing non-multicast (i.e. unicast) packets to the next node, This is done by utilizing a software computed unicastRoute[ ] next node routing table that provides a vector of available links to get to the destination node.
  • the packet will be routed upward until a common parent of (source, destination) is reached. This upward routing can be deterministic, oblivious, or adaptive. The packet is then routed downward to the destination using deterministic routing.
  • FIG. 7 illustrates a packet routing from node N00 1010 to N08 1015 .
  • the packet is routed in the upward phase to the common ancestor (N21) through node N10 1001 , and then a descent phase to the destination.
  • the first candidate link could be chosen deterministically, or an adaptive algorithm could dynamically select either of the links. But, once the node reaches the common ancestor and turns downward, there are no redundant paths (in general) for the node to reach the destination.
  • link weights should represent:
  • Multi-Domaining whose goal is to increase the addressability of nodes to a large number of nodes (e.g., 64 K nodes), without having to increase the size of the unicast routing table to 64 K nodes.
  • the unicast routing table is a single-dimension array indexed by node number (i.e. 0 to MAX_NODES-1), where a typical implementation will be between 256 and 4 K nodes.
  • the unicast routing table When routing to a node within this domain, the unicast routing table is accessed as unicastRoute[ 0 ][node ID], and provides a weighted link vector to route to the specified node ID from the current node.
  • network proxy is the ability of the main processors ( FIG. 5A , 905 ) to maintain network presence while in a low-power sleep/hibernation state, and intelligently wake when further processing is required.
  • the computer to be woken is shut down (sleeping, hibernating, or soft off; i.e., ACPI state G1 or G2), with power reserved for the network card, but not disconnected from its power source.
  • the network card listens for a specific packet containing its MAC address, called the magic packet, broadcast on the broadcast address for that particular subnet (or an entire LAN, though this requires special hardware or configuration).
  • the magic packet is sent on the data link or layer 2 in the OSI model and broadcast to all NICs within the network of the broadcast address; the IP-address (layer 3 in the OSI model) is not used.
  • the network card checks the packet for the correct information. If the magic packet is valid, the network card takes the computer out of hibernation or standby, or starts it up.
  • the magic packet is a broadcast frame containing anywhere within its payload: 6 bytes of ones (resulting in hexadecimal FF FF FF FF FF FF FF), followed by sixteen repetitions of the target computer's MAC address. Since the magic packet is only scanned for the string above, and not actually parsed by a full protocol stack, it may be sent as a broadcast packet of any network- and transport-layer protocol. It is typically sent as a UDP datagram to port 0, 7 or 9, or, in former times, as an IPX packet.
  • the management processor can support these Wake-On-LAN packets. It will get these broadcast packets, will know the MAC addresses for the other MACs on the node, and be able to wake up the main processor as appropriate. No further functionality is needed in the switch to support these Wake-on-LAN packets.
  • a system and method to manage the supply of power to large sets of processors or processor cores in an efficient, closed-loop manner are provided such that rather than the system supplying power that may or may not be used, a processor would request power based on the computing task at hand, which request would then be sent to the power supply system and thus power made available. Further needed is bidirectional communication between the CPU(s) and the power supply stating it has a certain limit, and rather than giving each processor its desired amount of power, said system may give a processor an allocation based on prorated tasks.
  • Some of the leading processor architectures have a thermal management mode that can force the processor to a lower power state; however none at present time imposes similar power reduction dynamically based on the available power resources of the system, as they assume that sufficient power is always available.
  • Each processor typically can run in a number of power states, including low power states where no processing occurs and states where a variable amount of execution can occur (for example, by varying the maximum frequency of the core and often the voltage supplied to the device).
  • This latter mechanism is commonly controlled by monitoring the loading of the node, and if the load is low, decreasing the maximum frequency/voltage of the CPU (the frequency and voltage of the core would be adjusted downward so as to not exceed the power limit set in order to keep the load below the capability limit of the power supply) until the amount of idle is reduced.
  • the reverse is also often the case: if loading is high the frequency/voltage can be increased.
  • Predictive mechanisms also exist where queued transactions are monitored, and if the queue is short or long the voltage and frequency can be altered appropriately.
  • a computational load (specifically in the cloud nature of shared threads across multiple cores of multiple processors) is shared between several functionally identical processors. In this case it's possible to power down (or move into a lower power state) one or more of those servers if the loading is not heavy.
  • a similar situation applies to cooling in an array of multiple processors, although due to the slow increase of temperature, it can be monitored and capacity can be turned on or off (e.g., increase or slow fans). Based on the currently used capacity, enough capacity must still be installed to cool the entire system with each system at peak performance (including any capacity that might be powered down through failure or maintenance).
  • the capacity allocated in both cases must be higher than absolutely necessary, based on the inability to modulate design when capacity limits are approached.
  • This limitation also makes it difficult to install short-term peak clipping capacity that can be used to relieve sudden high load requirements (as there is no way of reducing the load of the system when it is approaching the limits of that peak store).
  • batteries or any other means of storing an energy reserve could be included in the power supply system to provide extra power during peaks; however, when they approach exhaustion the load would need to be scaled down. In some cases, cooling temperatures could simply be allowed to rise for a short period.
  • FIG. 10 shows an overview of an exemplary system 2100 for management of power supplied to multiple processors according to one embodiment of the current disclosure.
  • An array of 16 processors 2101 a - p is shown.
  • Each processor has its own complete computing system, with memory and communication interconnection buses, a power feed, etc. All of these elements of each processor's system are well known in current art and are not shown here, for reasons of simplicity and clarity.
  • Processor 2101 a has an operating system with multiple programs 2101 a 1 - n .
  • One of these programs, 2101 ax is of particular interest. It is the piece that communicates with the system management software of the current disclosure, described in greater detail in the discussion of FIG. 12 , below.
  • the system management software can actually run on any one of the processors 2101 a - p , or it can run on a separate, dedicated processor (not shown).
  • a power supply unit (PSU) 2102 gets a main feed 2103 and distributes it through subfeeds 2103 a - p to each of the processors 101 a - p according to their individual needs.
  • PSU power supply unit
  • more than one processor 2101 b - p can have similar software 2101 b 1 - n through 2101 p 1 - n , including 2101 bx - px .
  • FIG. 11 shows an exemplary table 2200 that could be maintained by a power management system such as management system 2100 , for example, as described in FIG. 10 .
  • Each row 2201 a - p contains records of parameters 2202 a - e that are recorded in columns. They may be updated from time to time as necessary, either if certain changes occur or on an interval basis, etc. It is clear that the five parameters 2202 a - e are only exemplary of any of a great variety of parameters that may be included in table 2200 , so the number of parameters is not restricted to five only.
  • parameters are (reading left to right) CPU ID, actual current usage, desired usage based on tasks awaiting execution by the CPU, permitted usage allocated to the CPU at the moment, and the computational load waiting, for example, processes waiting in queue, with an additional priority rating in some cases (not shown).
  • a record 2201 t sums up the total of the parameter records of rows 2201 a - p for array 101 a - p .
  • Each processor in array 101 a - p may actually be a chip containing multiple CPUs or multiple cores of its own, so, in the case of array 2101 a - p , the actual number of processors involved may be, for example, 256, instead of 16, if each chip were to contain 16 cores.
  • FIG. 12 shows an exemplary process 2300 of the management software executed in any one of the processors of array 2101 a - p or in a dedicated processor (not shown), according to one embodiment of the present disclosure.
  • step 2301 the system starts, and in step 2302 it starts a count of the number of process repetitions in one session.
  • a pre-set maximum which in this example is P
  • step 2305 the system obtains the desired power usage, based on computational requirements and priority between the requirements, from each software instance.
  • the system calculates the power allocation and returns it to the process.
  • step 2307 data about the exchanges in steps 2304 - 2306 is written to and/or read from table 2200 .
  • step 2308 N is incremented and the process loops back to step 2303 until all cores in the array have been addressed, in sequence.
  • step 2303 If, in step 2303 , the full sequence of units has been addressed and N becomes greater than P (YES), the process moves to step 2309 , where the system calculates the power used, the desired power, and the available power for all units that were addressed in steps 2304 - 2306 .
  • step 2310 power is allocated, and in step 2311 the system negotiates with PSU 2102 about available power or available additional power, and then in step 2312 the system updates data in table 2200 .
  • the process may end at step 2313 , and then it may start again based on some pre-set timer or on triggering by a change in power requirements or priorities. In other cases, the process may be set to continuously loop back to step 2302 .
  • a system 2100 has a power allocation that it needs to manage.
  • Each processor is allocated a certain base capacity and must request more capacity from a central resource manager.
  • the central resource manager can signal the processor that it requires it to release capacity (either urgently or more slowly). It is clearly possible for the central resource manager to be duplicated for redundancy and for the managers to remain synchronized. Note that because the power manager controls the power state of the processor it can alter the actual load that is imposed, hence the available system capacity can be used to alter the power state of the processor. This feature is key to this invention, as the system can never over allocate capacity without running the risk of a “brown out.” In addition, the current invention permits consideration of a situation where an amount of capacity is only allocated for a fixed period of time and must be renewed periodically.
  • FIG. 13 shows a simplified overview of an exemplary larger power management system 2400 .
  • multiple installations, typically printed circuit boards, of the type of system shown as system 2100 are stacked vertically (although it is clear that such system multiples may be arranged vertically, horizontally, sequentially, networked, or in any other way).
  • Each system 2100 a - n has CPUs 2101 a - p and PSU 2102 , so that in system 2400 there are PSUs 2102 a - n .
  • System 2400 also contains air conditioning or cooling and heat sensors 2410 a - n and master PSUs 2402 a - n .
  • variable range a-n for PSU 2402 a - n simply indicates a variable, finite numeric quantity, and should not be construed to be an exact number.
  • a variable number of PSUs 2402 a - n may be turned on or turned off, thus keeping the system running optimally and reducing problems of overheating.
  • FIG. 14 shows an exemplary process 2500 of the system-level management software, according to one embodiment of the present invention.
  • process 2500 is similar to process 2300 . Additionally incorporated are controls of the air conditioning or cooling and heat sensors 2410 a - n .
  • step 2501 the system starts, and in step 2502 , it collects all data from PSU 2102 a - n .
  • step 2503 the system assesses outside and inside temperatures of each PSU 2102 a - n and the current heat loads, as well as available air conditioning or cooling performance.
  • additional main PSUs are accordingly added or removed, and new power ceilings are distributed to CPUs 2101 a - n .
  • step 2505 the process ends.
  • the individual power managers request capacity and it is granted by the central resource manager (CRM) (for example, 50 nodes request 5 units of extra capacity allowing full execution). If other nodes request the same capacity, the CRM can similarly grant the request (assuming that the peak loads do not align, or it may over allocate its capacity).
  • CCM central resource manager
  • the backup battery or any other suitable energy reserve, including but not limited to mechanical storage (flywheel, pressure tanks etc.) or electronic storage (all types of capacitors, inductors etc.), here all jointly referred to a “backup battery”, is capable of supplying power for 100 ms at peak load, so the CRM has 100 ms to reduce the capacity to the new limit of 450 units (actually it has double that this time if the battery can be fully drained, because part of the load may be supplied by the single functioning power supply).
  • the CRM signals each power controller in each processor that it must reduce its usage quickly.
  • the CRM requesting capacity more slowly from some processors (for example moving them to power down states) and using this spare capacity to increase performance in nodes that are suffering large backlogs.
  • the backup battery can have some of its energy allocated for short periods to allow peak clipping (the processor requests increase capacity and is granted it, but only for a few seconds).
  • a similar mechanism can be used to allocate cooling capacity (although the longer time constants make the mechanism easier).
  • a less aggressive system can allocate more total power and have more capacity after failure; while more aggressive systems can allocate less total power and not allow all processors to run at full power even in the situation where redundancy is still active. More complex redundancy arrangements can be considered (e.g., N+1), etc.
  • capacity is allocated to different processors from a central pool and the individual processors must coordinate their use.
  • a system and a method and architecture that allow many processors to share limited communication resources with efficient power and speed, as well as chip real estate and power consumption are provided.
  • this goal is achieved by a variety of changes to typical system architecture, signified by a typically chip internal (so called on-board, but sometimes system internal) virtualized communication fabric added between the multi-CPU cores (referred to as “the cores”) and the external communication ports for communicating with the outside world, both to external sources and to other multi-processor chips in a large network.
  • the cores typically chip internal (so called on-board, but sometimes system internal) virtualized communication fabric added between the multi-CPU cores (referred to as “the cores”) and the external communication ports for communicating with the outside world, both to external sources and to other multi-processor chips in a large network.
  • the cores typically chip internal (so called on-board, but sometimes system internal) virtualized communication fabric added between the multi-CPU cores (referred to as “the cores”) and the external communication ports for communicating with the outside world,
  • FIG. 15 shows a midlevel architectural overview of a multiprocessor chip 3400 according to one embodiment.
  • the multiple processor cores 3415 a - n are, in this example, ARM Cortex A9, including the ARM NEON SIMD processor.
  • Multiple communication ports 3407 connect to various devices, which are discussed in greater detail below.
  • An auxiliary processor 3445 such as a ARM Cortex M3, is used to power manage the processors 3415 a - n and to wake them up, let them sleep, or put them to sleep as needed, as well as to manage voltage/frequency scaling of the processor cores 3415 a - n for load-driven power management.
  • An intelligent switching fabric 3427 connects one or more peripheral elements 3417 - 3423 on one side and the actual ports 3429 , 3430 and 3452 - 3455 on the other side.
  • This switching fabric which is discussed in greater detail below, allows various different elements to be used in different ways. For example, to reduce the number of ports connected, a communication media access control (MAC), such as MACs 3421 and 3422 , actually is split in half.
  • MAC media access control
  • pending communication requests are managed by the auxiliary processor 3445 , which is intricately involved in managing the switching fabric.
  • the switching fabric allows the processor(s) 3415 a - n to go into a sleep mode or to enter power down mode, while the auxiliary processor responds to communication requests for those processors that are asleep or off, and keeps those requests hanging in the switching fabric until the processors are started again after which the auxiliary processor 3445 then lets the processors 3415 a - n receive the data.
  • the interfaces 3452 - 3455 which connect these chips to the neighboring chips.
  • Elements 3424 , 3425 and 3426 are extended beyond their respective standard functional parts as discussed throughout this document, namely an ARM® generic interrupt controller GIC 3412 , a debugging and testing unit Coresight Debug/JTAG section 3409 , and an accelerator coherence port (ACP) 3413 that all help maintain memory and I/O coherence, allowing the auxiliary processor core to interact “invisibly” with all kinds of aspects involved with both power management and communication management to effect the use of the novel switching fabric 1427 .
  • ACP accelerator coherence port
  • FIG. 16 shows a slightly more detailed view of the switching fabric, as does FIG. 17 .
  • FIG. 15 in particular shows the different paths that can be created within the switching fabric, as controlled by a set of routers 3504 and 3505 , with one router for internal communications and the other router for external communications, respectively, The routers themselves are typical in such a system, for internal routing and external routing respectively. These routers are primarily responsible for arbitrating and managing the control signals of the various data paths between the “processor side” 3501 of the MACs (or other communication units) and the external faced side of those communication units 3528 - 3555 . Although distinct data paths are shown, not all paths exist as physical connections. Rather, they can be made available as part of the logical switching.
  • the SOC reflects interrupts between application processors and their associated power microcontrollers.
  • the GIC reflects the processor 1415 a - n interrupt lines to the auxiliary processor to allow the auxiliary processor to wake the processor 1415 a - n cores when an interrupt needs to be processed, as previously discussed, as well as in other locations herein.
  • interrupts are steered to the auxiliary processor where the event is seen. Most events cause a wakeup of the subsystems, but the interrupt is not removed. Rather, it is retained and once a processor wakes up and is ready to start, the interrupt is taken directly by the GIC. In some cases, interrupts are turned into level sensitive (or masking) to the microcontroller so as not to bury the microcontroller in interrupts.
  • the auxiliary processor microcontroller 3445 enables visibility into the processor 3415 a - n application processor 3445 interrupts when the application processor goes into low power state, and then the auxiliary processor knows to wake up the processor 3415 a - n application processor. In some cases, interrupts are turned into level sensitive interrupts (or masked) to the microcontroller to not bury the microcontroller in interrupts and overwhelm the system. In some other cases, the microcontroller enables visibility into application processor interrupts when application processors go into a low power state, thus the microcontroller can know to wake up the application processor.

Abstract

A system and method are provided that support a routing using a tree-like or graph topology that supports multiple links per node, where each link is designated as an Up, Down, or Lateral link, or both, within the topology. The system may use a segmented MAC architecture which may have a method of re-purposing MAC IP addresses for inside MACs and outside MACs, and leveraging what would normally be the physical signaling for the MAC to feed into the switch.

Description

    CROSS REFERENCE TO RELATED APPLICATIONS
  • This continuation patent application claims priority to co-pending U.S. Non-Provisional Patent Application having Ser. No. 12/794,996 filed Jun. 7, 2010 entitled “SYSTEM AND METHOD FOR HIGH-PERFORMANCE, LOW-POWER DATA CENTER INTERCONNECT FABRIC”, which claims priority to United States Provisional Patent Application having Ser. No. 61/256,723 filed Oct. 30, 2009 entitled “SYSTEM AND METHOD FOR ENHANCED COMMUNICATIONS IN A MULTI-PROCESSOR SYSTEM ON A CHIP (SOC)”, both of these applications having a common applicant herewith and being incorporated herein in their entirety by reference.
  • FIELD
  • The disclosure relates generally to a switching fabric for a computer-based system.
  • BACKGROUND
  • With the continued growth of the internet, web-based companies and systems and the proliferation of computers, there are numerous data centers that house multiple server computers in a location that is temperature controlled and can be externally managed as is well known.
  • FIGS. 1A and 1B show a classic data center network aggregation as is currently well known. FIG. 1A shows a diagrammatical view of a typical network data center architecture 100 wherein top level switches 101 a-n are at the tops of racks 102 a-n filled with blade servers 107 a-n interspersed with local routers 103 a-f. Additional storage routers and core switches. 105 a-b and additional rack units 108 a-n contain additional servers 104 e-k and routers 106 a-g FIG. 1 b shows an exemplary physical view 110 of a system with peripheral servers 111 a-bn arranged around edge router systems 112 a-h, which are placed around centrally located core switching systems 113. Typically such an aggregation 110 has 1-Gb Ethernet from the rack servers to their top of rack switches, and often 10 Gb Ethernet ports to the edge and core routers.
  • However, what is needed is a system and method for packet switching functionality focused on network aggregation that reduces size and power requirements of typical systems while reducing cost all at the same time and it is to this end that the disclosure is directed.
  • BRIEF DESCRIPTION OF THE DRAWINGS
  • FIGS. 1A and 1B illustrate a typical data center system;
  • FIG. 2A illustrates a computing unit that may include a universal address system and method;
  • FIG. 2B illustrates a computing system that may include a universal address system and method;
  • FIG. 2C is an overview of a network aggregation system;
  • FIG. 3 illustrates an overview of an exemplary data center in a rack system;
  • FIG. 4 illustrates a high-level topology of a network aggregating system;
  • FIG. 5A illustrates a block diagram of an exemplary switch of the network aggregation system;
  • FIG. 5B illustrates the MAC address encoding;
  • FIG. 6 illustrates a first embodiment of a broadcast mechanism of the network aggregation system;
  • FIG. 7 illustrates an example of unicast routing of the network aggregation system;
  • FIG. 8 illustrates an example of fault-resistant unicast routing of the network aggregation system;
  • FIG. 9 illustrates a second embodiment of a broadcast mechanism of the network aggregation system;
  • FIG. 10 illustrates an exemplary system for management of power supplied to multiple processors;
  • FIG. 11 illustrates an exemplary data structure that may be maintained by a power management system shown in FIG. 10;
  • FIG. 12 an example of a process for power management;
  • FIG. 13 illustrates an example of a larger power management system;
  • FIG. 14 illustrates an exemplary process for system level power management;
  • FIG. 15 illustrates an architectural overview of a multiprocessor chip; and
  • FIG. 16 illustrates more details of the switching fabric shown in FIG. 15.
  • DETAILED DESCRIPTION OF ONE OR MORE EMBODIMENTS
  • The disclosure is particularly applicable to a network aggregation system and method as illustrated and described below and it is in this context that the disclosure will be described. It will be appreciated, however, that the system and method has greater utility since the system and method can be implemented using other elements and architectures that are within the scope of the disclosure and the disclosure is not limited to the illustrative embodiments described below.
  • The system and method also supports a routing using a tree-like or graph topology that supports multiple links per node, where each link is designated as an Up, Down, or Lateral link, or both, within the topology. In addition, each node in the system maybe be a combination computational/switch node, or just a switch node, and input/outpout (I/O) can reside on any node as described below in more detail. The system may also provide a system with a segmented Ethernet Media Access Control (MAC) architecture which may have a method of re-purposing MAC IP addresses for inside MACs and outside MACs, and leveraging what would normally be the physical signaling for the MAC to feed into the switch. The system may also provide a method of non-spoofing communication, as well as a method of fault-resilient broadcasting, which may have a method of unicast misrouting for fault resilience. In the context of network security, a spoofing attack is a situation in which one person or program successfully masquerades as another by falsifying data and thereby gaining an illegitimate advantage.
  • The system may also provide a rigorous security between the management processors, such that management processors can “trust” one another. In the example system shown in FIG. 5A (which is described below in more detail), there is a management processor within each SoC (the M3 microcontroller, block 906, FIG. 5A). The software running on the management processor is trusted because a) the vendor (in this case Smooth-Stone) has developed and verified the code, b) non-vendor code is not allowed to run on the processor. Maintaining a Trust relationship between the management processors allow them to communicate commands (e.g. reboot another node) or request sensitive information from another node without worrying that a user could spoof the request and gain access to information or control of the system.
  • The system may also provide a network proxy that has an integrated microcontroller in an always-on power domain within a system on a chip (SOC) that can take over network proxying for the larger onboard processor, and which may apply to a subtree. The system also provide a multi-domaining technique that can dramatically expand the size of a routable fat tree like structure with only trivial changes to the routing header and the routing table.
  • FIG. 2A illustrates a computing unit 210 that is part of a distributed computing system and may include a universal address system and method. In one embodiment, each computing unit may be implemented on a single integrated circuit as shown in FIG. 2A. Each computing unit 210 may include one or more processing cores 212, such as ARM processing cores, and an associated cache memory 214, a DDR controller 216, a not AND logic (NAND) flash memory interface 218, I/O interfaces 220, a power management portion 222, a direct memory access (DMA)/virtual memory management (VMM) support unit 224 described in more detail below and one or more hardware accelerators 226.
  • FIG. 2B illustrates a distributed computing system 230 that may include a universal address system and method. Each computing system 230 may be a node in a processing system in which a plurality of nodes are connected to each other over a link, such as a network. In addition to the computing unit 210, each computing system 230 may further comprise double data rate (DDR) low power RAM 232, such as 512 Mb of low power DDR RAM in one embodiment, which is direct access memory to the computing system, NAND flash memory 234, such as 2-8 Gb of NAND flash memory in one embodiment, that acts as persistent storage and stores a file system, an interconnect 236 that connects this computing system to the other computing systems over a link, such as a computer network, and software 238, such as a Linux operating system, virtual memory management (VMM) software and one or more optimized software functions. In one embodiment, the universal address system is implemented using the DMA and VMM support 224 of each computing unit 224 (See FIG. 2A) in combination with the VMM software 238 (shown in FIG. 2B). The DMA of the computing unit is a standard mechanism (common in many systems), which can be given a data movement task to perform by the system. In this scenario, such a standard module would be told to copy a page of data via the IO links to the local memory and then to report. The VMM support is a similarly standard function consisting of both software and hardware that is used to check every memory access and convert the virtual page to a physical page reference. In this scenario, the existing mechanisms would use as the first level of the extended mechanism and the VMM software would be used to further translate from local physical page to universal address.
  • FIG. 2C illustrates a network aggregation system 300. The network aggregation supports one or more high speed links 301 (thick lines), such as a 10-Gb/sec Ethernet communication, that connect an aggregation router 302 and one or more racks 303, such as three racks 303 a-c as shown in FIG. 3. In a first rack 303 a, the network aggregation system provides multiple high-speed 10 Gb paths, represented by thick lines, between one or more Smooth-Stone computing unit 306 a-d, such as server computers, on shelves within a rack. Further details of each Smooth-Stone computing unit are described in more detail in U.S. Provisional Patent Application Ser. No. 61/256,723 filed on Oct. 30, 2009 and entitled “System and Method for Enhanced Communications in a Multi-Processor System of a Chip (SOC)” which is incorporated herein in its entirety by reference. An embedded switch 306 a-d in the Smooth-Stone computing units can replace a top-of-rack switch, thus saving a dramatic amount of power and cost, while still providing a 10 Gb Ethernet port to the aggregation router 302. The network aggregation system switching fabric can integrate traditional Ethernet (1 Gb or 10 Gb) into the XAUI fabric, and the Smooth-Stone computing units can act as a top of rack switch for third-party Ethernet connected servers.
  • A middle rack 303 b illustrates another configuration of a rack in the network aggregation system in which one or more Smooth-Stone computing units 306 e,f can integrate into existing data center racks that already contain a top-of-rack switch 308 a. In this case, the IT group can continue to have their other computing units connected via 1 Gb Ethernet up to the existing top-of-rack switch and the internal Smooth-Stone computing units can be connected via 10 Gb XAUI fabric and they can integrate up to the existing top-of-rack switch with either a 1 Gb or 10 Gb Ethernet interconnects as shown in FIG. 2C. A third rack 303 c illustrates a current way that data center racks are traditionally deployed. The thin lines in the third rack 303 c represent 1 Gb Ethernet. Thus, the current deployments of data center racks is traditionally 1 Gb Ethernet up to the top-of-rack switch 308 b, and then 10 Gb (thick line 301) out from the top of rack switch to the aggregation router. Note that all servers are present in an unknown quantity, while they are pictured here in finite quantities for purposes of clarity and simplicity. Also, using the enhanced SS servers, no additional routers are needed, as they operate their own XAUI switching fabric, discussed below.
  • FIG. 3 shows an overview of an exemplary “data center in a rack” 400 according to one embodiment of the system. The “data center in a rack” 400 may have 10-Gb Ethernet PHY 401 a-n and 1-Gb private Ethernet PHY 402, Large computers (power servers) 403 a-n support search; data mining; indexing; Apache Hadoop, a Java software framework; MapReduce, a software framework introduced by Google to support distributed computing on large data sets on clusters of computers; cloud applications; etc. Computers (servers) 404 a-n with local flash and/or solid-state disk (SSD) support search, MySQL, CDN, software-as-a-service (SaaS), cloud applications, etc. A single, large, slow-speed fan 405 augments the convection cooling of the vertically mounted servers above it. Data center 400 has an array 406 of hard disks, e.g., in a Just a Bunch of Disks (MOD) configuration, and, optionally, Smooth-Stone computing units in a disk form factor (for example, the green boxes in arrays 406 and 407), optionally acting as disk controllers. Hard disk servers or SS disk servers may be used for web servers, user applications, and cloud applications, etc. Also shown are an array 407 of storage servers and historic servers 408 a,b (any size, any vendor) with standard Ethernet interfaces for legacy applications.
  • The data center in a rack 400 uses a proprietary system interconnect approach that dramatically reduces power and wires and enables heterogeneous systems, integrating existing Ethernet-based servers and enabling legacy applications. In one aspect, a complete server or storage server is put in a disk or SSD form factor, with 8-16 SATA interfaces with 4 ServerNodes™ and 8 PCIe x4 interfaces with 4 ServerNodes™. It supports disk and/or SSD+ServerNode™, using a proprietary board paired with a disk(s) and supporting Web server, user applications, cloud applications, disk caching, etc.
  • The Smooth-Stone XAUI system interconnect reduces power, wires and the size of the rack. There is no need for high powered, expensive Ethernet switches and high-power Ethernet Phys on the individual servers. It dramatically reduces cables (cable complexity, costs, significant source of failures). It also enables a heterogeneous server mixture inside the rack, supporting any equipment that uses Ethernet or SATA or PCIe. It can be integrated into the system interconnect.
  • The herein presented aspects of a server-on-a-chip (SOC) with packet switch functionality are focused on network aggregation. The SOC is not a fully functionally equivalent to an industry-standard network switch, such as, for example, a Cisco switch or router. But for certain applications discussed throughout this document, it offers a better price/performance ratio as well as a power/performance ratio. It contains a layer 2 packet switch, with routing based on source/destination MAC addresses. It further supports virtual local area network (VLAN), with configurable VLAN filtering on domain incoming packets to minimize unnecessary traffic in a domain. The embedded MACs within the SOC do have complete VLAN support providing VLAN capability to the overall SOC without the embedded switch explicitly having VLAN support. It can also wake up the system by management processor notifying the management processor on link state transitions to reprogram routing configurations to route around faults. Such functionality does not require layer 3 (or above) processing (i.e., it is not a router). It also does not offer complete VLAN support, support for QoS/CoS, address learning, filtering, spanning tree protocol (STP), etc.
  • FIG. 4 shows a high-level topology 800 of the network system that illustrates XAUI connected SoC nodes connected by the switching fabric. The 10 Gb Ethernet ports Eth0 801 a and Eth1 801 b come from the top of the tree. Ovals 802 a-n are Smooth-Stone nodes that comprise both computational processors as well as the embedded switch. The nodes have five XAUI links connected to the internal switch. The switching layers use all five XAUI links for switching. Level 0 leaf nodes 802 d, e (i.e., N0n nodes, or Nxy, where x=level and y=item number) only use one XAUI link to attach to the interconnect, leaving four high-speed ports that can be used as XAUI, 10 Gb Ethernet, PCIe, SATA, etc., for attachment to I/O. The vast majority of trees and fat trees have active nodes only as leaf nodes, and the other nodes are pure switching nodes. This approach makes routing much more straightforward. Topology 800 has the flexibility to permit every node to be a combination computational and switch node, or just a switch node. Most tree-type implementations have I/O on the leaf nodes, but topology 800 let the I/O be on any node. In general, placing the Ethernet at the top of the tree minimizes the average number of hops to the Ethernet.
  • In more detail, the ovals shown in the tree-oriented topology in FIG. 6 represent independent nodes within a computing cluster. FIG. 5A illustrates one example implementation of an individual node of the cluster. When looking at a conventional implementation of a topology e.g. in FIG. 6, usually computing nodes are found in the lower level leaf nodes (e.g. N00-N08), and the upper level nodes don't have computing elements but are just network switching elements (N10-N21). With the node architecture shown in FIG. 6A, the A9 Cores (905) may be optionally enabled, or could be just left powered-off. So the upper level switching nodes (N10-N21) in FIG. 6 can be used as pure switching elements (like traditional implementations), or we can power on the A9 Cores module and use them as complete nodes within the computing cluster.
  • The switch architecture calls for a routing frame to be prepended to the Ethernet frame. The switch operates only against fields within the routing frame, and does not inspect the Ethernet frame directly. FIG. 5 a shows a block diagram of an exemplary switch 900 according to one aspect of the system and method disclosed herein. It has four areas of interest 910 a-d. Area 910 a corresponds to Ethernet packets between the CPUs and the inside MACs. Area 910 b corresponds to Ethernet frames at the Ethernet physical interface at the inside MACs, that contains the preamble, start of frame, and inter-frame gap fields. Area 910 c corresponds to Ethernet frames at the Ethernet physical interface at the outside MAC, that contains the preamble, start of frame, and inter-frame gap fields. Area 910 d corresponds to Ethernet packets between the processor of routing header 901 and outside MAC 904. This segmented MAC architecture is asymmetric. The inside MACs have the Ethernet physical signaling interface into the routing header processor, and the outside MAC has an Ethernet packet interface into the routing header processor. Thus the MAC IP is re-purposed for inside MACs and outside MACs, and what would normally be the physical signaling for the MAC to feed into the switch is leveraged. MAC configuration is such that the operating system device drivers of A9 cores 905 manage and control inside Eth0 MAC 902 and inside ETH1 MAC 903. The device driver of management processor 906 manages and controls Inside Eth2 MAC 907. Outside Eth MAC 904 is not controlled by a device driver. MAC 904 is configured in Promiscuous mode to pass all frames without any filtering for network monitoring. Initialization of this MAC is coordinated between the hardware instantiation of the MAC and any other necessary management processor initialization. Outside Eth MAC 904 registers are visible to both A9 905 and management processor 906 address maps. Interrupts for Outside Eth MAC 904 are routable to either the A9 or management processor. The XGMAC supports several interruptible events that the CPUs may want to monitor, including any change in XGMII link fault status, hot-plugging or removal of PHY, alive status or link status change, and any RMON counter reaching a value equal to the threshold register.
  • In some cases, there may be Preamble, Start of Frame, and Inter-Frame gap fields across XAUI, depending on the specific micro-architecture. The routing frame header processor may standardize these fields. The XAUI interface may need some or all of these fields. In this case, the routing header processor at area 910 d needs to add these going into the switch, and to remove them leaving the switch. To reduce the number of bytes that need to be sent over XAUI, these three fields may be removed (if the XAUI interface allows it). In this case, the routing header processor at area 910 b will need to strip these going into the switch, and add them back leaving the switch.
  • The routing frame header processor receives an Ethernet frame from a MAC, sending a routing frame to the switch. it also standardizes the preamble, start of frame, and inter-frame gap fields, prepends a routing header, and receives a routing frame from the switch, sending the Ethernet frame into a MAC. This processor then strips the routing header and standardizes the preamble, start of frame, and inter-frame gap fields. Note that all frames that are flowing within the fabric are routing frames, not Ethernet frames. The Ethernet frame/routing frame conversion is done only as the packet is entering or leaving the fabric via a MAC. Note also that the routing logic within the switch may change fields within the routing frame. The Ethernet frame is never modified (except the adding/removing of the preamble, start of frame, and inter-frame gap fields).
  • The routing frame is composed of the routing frame header plus the core part of the Ethernet frame, and is structured as shown in Table 1, below:
  • TABLE 1
    Routing
    Frame Header Ethernet Frame Packet
    RF MAC MAC Ethertype/ Payload CRC32
    Header destination Source Length (data and
    padding)
  • Note that the implementation assumptions for bit sizing are 4096 nodes→12 bit node IDs. These fields may be resized during implementation as needed.
  • The routing frame header consists of the fields shown in Table 2, below:
  • TABLE 2
    Width
    Field (Bits) Notes
    Domain ID
    5 Domain ID associated with this packet. 0 indicates
    that no domain has been specified.
    Mgmt Domain 1 Specifies that the packet is allowed on the private
    management domain.
    Source Node 12 Source node ID
    Source Port
    2 0 = MAC0, 1 = MAC1, 2 = MAC_management
    processor, 3 = MAC_OUT
    Dest Node 12 Destination node ID
    Dest Port
    2 0 = MAC0, 1 = MAC1, 2 = MAC_management
    processor, 3 = MAC_OUT
    RF Type
    2 Routing Frame Type (0 = Unicast, 1 = Multicast,
    2 = Neighbor Multicast, 3 = Link Directed)
    TTL 6 Time to Live—# of hops that this frame has existed.
    Switch will drop packet if the TTL threshold is exceeded
    (and notify management processor of exception).
    Broadcast ID 5 Broadcast ID for this source node for this broadcast
    packet.
    Checksum Checksum of the frame header fields.
    Total 46 +checksum
  • If a switch receives a packet that fails the checksum, the packet is dropped, a statistic counter is incremented, and the management processor is notified.
  • The routing frame processor differentiates between several destination MAC address encodings. As a reminder, MAC addresses are formatted as shown in FIG. 5 b. The following table describes the usage of the 3 byte OUI and 3 byte MC specific field within the MAC address. One of the novel aspects of the system and method disclosed herein is the use of additional address bits to encode an internal to external MAC mapping, as shown also in the Table 3, below, in the second entry under “Fabric Internal Node local address Hits MAC Lookup CAM”.
  • TABLE 3
    MAC Address
    Type
    3 bytes OUI 3 bytes NIC Specific Operation
    External Multicast bit Arbitrary Packet unicast
    Misses MAC not set routed to
    Lookup CAM gateway node #.
    Fabric Internal Arbitrary Node local address (meaning Packet unicast
    Node local low 2 bits—port unit routed to
    address ID) are not present. MAC fabric node #
    Hits MAC Lookup CAM for entry obtained from
    Lookup CAM marked as Node Local. MAC Lookup CAM
    Fabric Internal Arbitrary Arbitrary Packet unicast
    Arbitrary MAC routed to
    address fabric node #
    Hits MAC obtained from
    Lookup CAM MAC Lookup CAM
    Node Encoded Unicast 10 bits: Packet
    Unicast Locally SS_MAC_NODE_ENCODED_MAGIC unicast
    administered 12 bits: Node ID routed to
    OUI == Switch 2 bits: Port ID Node ID.
    OUI
    Link Encoded Unicast 12 bits: Packet sent
    Unicast Locally SS_MAC_LINK_ENCODED_MAGIC down specific
    administered 7 bits: Reserved Link #.
    OUI == Switch 3 bits: Link # (0-4)
    OUI 2 bits: Port
    Multicast/ Multicast bit Arbitrary Packet
    Broadcast set broadcast
    routed through
    fabric and
    gateways.
    Neighbor Multicast bit 12 bits: Packet sent
    Multicast set SS_NEIGHBOR_MCAST_MAGIC through all
    Locally 12 bits: Reserved XAUI links to
    administered neighboring
    OUI = Switch nodes and not
    OUI rebroadcast
    to other nodes
  • Further, other novel aspects can be found in Table 3 under “Node Encoded Unicast” as well as “Link Encoded Unicast,” allowing one internal node or link to address all external MAC sections, and the “Neighbor Multicast” entry, allowing a multicast to neighboring nodes.
  • Note that the values SS_MAC_NODE_ENCODED_MAGIC and SS_MAC_LINK_ENCODED_MAGIC are constant identifiers used for uniquely identifying these MAC address types. The term “magic number” is a standard industry term for a constant numerical or text value used to identify a file format or protocol. These magic numbers are configured in two registers (magicNodeEncodedMAC and magicLinkEncodedMAC that default to standard values during hardware initialization, but allow the management processor software to change them if necessary.
  • The header processor contains a MAC Lookup CAM (Content Addressable Memory), macAddrLookup, that maps from 6 byte MAC addresses to 12-bit Node IDs, as shown in Table 4, below.
  • TABLE 4
    MAC Lookup CAM Input MAC Lookup CAM Output
    Node Local MAC Address Node ID Port ID
    1 bit 6 bytes 12 bits 2 bits
  • The number of rows in this CAM is implementation dependent, but would be expected to be on the order of 256-1024 rows. The management processor initializes the CAM with Node ID mappings for all the nodes within the SS fabric. There are two types of rows, depending upon the setting of the Node Local bit for the row. The Node Local field allows a 4:1 compression of MAC addresses in the CAM for default MAC addresses, mapping all four MACs into a single row in the CAM table, which is Table 5, below.
  • TABLE 5
    MAC
    Address Node
    Type Local MAC Address Port ID
    Node 1 A Node Encoded Address refers to a Smooth Stone Taken from
    Local assigned MAC address for a node. It encodes the port # low 2 bits of
    (MAC0, MAC1, management processor, Rsvd) into a 2- MAC Address
    bit Port ID in the lowest two bits of the NIC address Input
    field. Ignores low 2 bits during match.
    Arbitrary 0 Matches against all 6 bytes Taken from
    CAM Output
    field
  • The arbitrary rows in the CAM allow mapping of the MAC address aliases to the nodes. Linux (and the MACs) allow the MAC addresses to be reassigned on a network interface (e.g., with ifconfig eth0 hw ether 00:80:48:BA:d1:30). This is sometime used by virtualization/cloud computing to avoid needing to re-ARP after starting a session.
  • The switch architecture provides for a secondary MAC Lookup CAM that only stores the 3 bytes of the NIC Specific part of the MAC address for those addresses that match the Switch OUI. The availability of this local OUT CAM is determined by the implementation. See Table 6, below.
  • TABLE 6
    MAC Lookup CAM Input MAC Lookup CAM Output
    MAC Address NIC Specific Node ID Port ID
    3 bytes 12 bits 2 bits
  • The maximum number of nodes limitation for three types of MAC address encodings may be evaluated as follows:
  • 1. Default MAC Addressees—management processor sets Node Local mappings for each of the nodes in the fabric. There is one entry in the CAM for each node. Max # of nodes is controlled by maximum # of rows in the MAC Address Lookup CAM,
  • 2. Node Encoded Addresses—All the MACs are reprogrammed to use Node Encoded Addresses. In this way the Node IDs are directly encoded into the MAC addresses. No entries in the MAC Lookup CAM are used. Max # of nodes is controlled by maximum # of rows in the Unicast lookup table (easier to make big compared to the Lookup CAM). Note that this also gives us some risk mitigation in case the MAC Lookup CAM logic is busted. Provides use case for the node encoded addresses idea.
  • 3. Arbitrary MAC Address Aliases—Takes a row in the CAM. As an example, a 512-row CAM could hold 256 nodes (Node local addresses)+1 MAC address alias per node.
  • Since the Lookup CAM is only accessed during Routing Header creation, the management processor actually only needs to populate a row if the MAC address within the fabric is being used as a source or destination MAC address within a packet. In other words, if two nodes never will talk to each other, a mapping row does not need to be created. But usually the management processor won't have that knowledge, so it's expected that mappings for all nodes are created in all nodes. Also note that even if an entry is not created in the Lookup CAM, the routing will actually still succeed by routing the packet out the Ethernet gateway, through an external router, back into the Fabric, to the destination node.
  • Table 7 defines how to set fields within the Routing Header for all the fields except for destination node and port.
  • TABLE 7
    Field Set To
    Domain ID Set to the macDomainID field for the MAC that
    the packet came from.
    Mgmt Set to the macMgmtDomain field for the MAC that
    Domain the packet came from.
    Source Node Switch Node ID
    Source Port Source MAC Port ID
    RF Type Multicast (if dstMAC multicast and not Neighbor
    Multicast format)
    Neighbor Multicast (if dstMAC multicast and is
    Neighbor Multicast format)
    Link Directed (is Link Encoded format)
    Unicast (if not one of the above)
    TTL 0
    Broadcast If dstMAC is unicast - Set to 0
    ID If dstMAC is multicast - Set to incremented local
    broadcast ID (bcastIDNext++ & 0xf)
  • Table 8 defines how to set destination node and port for addresses within the fabric:
  • TABLE 8
    Field: Field:
    Destination Destination
    Case Node Port
    Node Encoded Dest Address Dest Node Dest Port
    Link Encoded Dest Address Encoded Link Dest Port
    Hits Lookup CAM (node local) CAM Dest Node Dest MAC
    (low 2 bits)
    Hits Lookup CAM (not node local) CAM Dest Node CAM Dest Port
  • Table 9 defines how to set destination node and port for addresses outside the fabric:
  • TABLE 9
    Field: Field:
    Destination Destination
    Case Node Port
    Came in an OUT Ethernet, but no Drop packet, update statistics counter
    secondary gateway defined
    Came in an OUT Ethernet, and secondaryEthGatewayNode[OUT] OUT
    secondary gateway defined
    From an Inside MAC, but no Drop packet, update statistics
    primary gateway defined counter, and notify management
    processor
    From an Inside MAC, and primaryEthGatewayNode[fromPort] OUT
    primary gateway defined
  • Additionally, the management processor software architecture of the system and method disclosed here currently depends on the ability of management processor nodes to “trust” each other. This more rigorous security on management processor to management processor communication is desirable, as well a better security on private management LANs across the fabric. This fabric issue may be mitigated by simply defining, for environments that require multiple “hard” security domains, that customers simply don't mix security domains within a fabric. In such cases, it may be possible to connect 14-node boards to the top of rack switch, allowing customers to have VLAN granularity control of each 14-node board.
  • The multi-domain fabric architecture that has been described addresses the lack of VLAN support by creating secure “tunnels” and domains across the fabric, and it can interoperate with VLAN protected router ports on a 1:1 basis.
  • The approach to domain management in the system and method disclosed here is as follows: Support multiple domain IDs within the fabric. Allow each of the MACs within a node (management processor, MAC0, MAC1, Gateway) to be assigned to a domain ID individually (and tagged with domain 0 if not set). Allow each of the MACs within a node to have a bit indicating access to the management domain. The domain IDs associated with a MAC could only be assigned by the management processor, and could not be altered by the A9. For frames generated by MACs (both inside and outside), the routing frame processor would tag the routing frame with the domain ID and management domain state associated with that MAC. Domains would provide the effect of tunnels or VLANs, in that they keep packets (both unicast and multicast) within that domain, allowing MACs outside that domain to be able to neither sniff or spoof those packets. Additionally, this approach would employ a five-bit domain ID. It would add options to control domain processing, such as, for example, a switch with a boolean per MAC that defines whether packets are delivered with non-defined (i.e., zero) domain ID, or a switch that has a boolean per MAC that defines whether packets are delivered with defined (non-zero) but non-matching domain IDs. A further option in the switch could turn off node encoded MAC addresses per MAC (eliminating another style of potential attack vector).
  • To keep management processor to management processor communication secure, the management domain bit on all management processor MACs could be marked. Generally, the management processor should route on domain 1 (by convention). Such a technique allows all the management processor's to tunnel packets on the management domain so that they cannot be inspected or spoofed by any other devices (inside or outside the fabric), on other VLANs or domains. Further, to provide a secure management LAN, a gateway MAC that has the management domain bit set could be assigned, keeping management packets private to the management processor domain. Additionally, the switch fabric could support “multi-tenant” within itself, by associating each gateway MAC with a separate domain. For example, each gateway MAC could connect to an individual port on an outside router, allowing that port to be optionally associated with a VLAN. As the packets come into the gateway, they are tagged with the domain ID, keeping that traffic private to the MACs associated with that domain across the fabric.
  • The switch supports a number of registers (aka CSRs, aka MMRs) to allow software or firmware to control the switch. The actual layout of these registers will be defined by the implementation. The fields listed in Table 10 are software read/write. All these registers need to have a mechanism to secure them from writing from the A9 (could be secure mode or on a management processor private bus).
  • TABLE 10
    Field Size Notes
    Adaptive
    1 bit Adaptive unicast routing enabled.
    broadcastLateral 1 bit Enable to have broadcasts go through lateral
    links, rather than just Up and Down links.
    Turning this off will work for most topologies
    and will reduce # duplicate broadcast packets.
    intPortBroadcastVec 4 bits Vector of ports to send internally generated
    broadcast packet into.
    extPortBroadcastVec 4 bits Vector of ports to send externally generated
    broadcast packet into.
    linkDir[LINKS] Array [LINKS] x Specifies link direction for each link
    2 bits (0 = DOWN, 1 = LATERAL, 2 = UP, 3 = Rsvd)
    linkState 5 bits Link state vector for each of the 5 links. Bit
    set indicates that link is active (trained and
    linked).
    linkType[LINKS] Array [LINKS] x Specifies type of each link
    2 bits (0 = No Link, 1 = XAUI, 2 = Ethernet}
    localBroadcastM3Snoop 1 bit When set, then we'll always send a copy of
    the locally initiated broadcast into the
    management processor. The use case here is
    where the management processor wants to see
    the gratuitous ARPs that are locally initiated
    so that it can communicate across the
    management processor fabric and add
    corresponding entries into the local unicast
    routing tables.
    macAddrLookup Lookup CAM which is MAC address lookup CAM to convert MAC
    described elsewhere in addresses to Node IDs.
    the document
    macAcceptOtherDomain[MAC] 1 bit[MAC] Defines that the MAC accepts packets that are
    tagged with a non-zero, non-matching domain
    ID.
    macAcceptZeroDomain[MAC] 1 bit[MAC] Defines that the MAC accepts packets that are
    not tagged with a domain (i.e. 0 domain)
    macDomainID[MAC] 5 bits[MAC] Defines the Domain ID for each of the 4
    MACs. A value of 0 indicates that the domain
    ID for that MAC is not set.
    macMgmtDomain[MAC] 1 bit[MAC] Defines that the MAC may access the
    management domain. Setting this tags the
    management domain in the routing frame, as
    well as allows the switch to route
    management frame packets into this MAC.
    magicNodeEncodedMAC 10 bits Magic number for Node Encoded MAC
    addresses
    magicLinkEncodedMAC 12 bits Magic number for Link Encoded MAC
    addresses
    maxTTL 6 bits Maximum TTL count allowed in a routing
    header. Exceeding this number of hops causes
    the switch to drop the packet, update a
    statistic counter, and inform the management
    processor.
    myNodeID 12 bits Need not be contiguous. Subtree's should
    ideally be numbered within a range to
    facilitate subtree network proxying.
    myOUI 3 bytes 3 upper bytes of MAC addresses in fabric.
    Should be the same for all nodes in the fabric.
    nodeRangeEnable 1 bit Enables the expanded Node ID matching of
    [nodeRangeLo, nodeRangeHi]. Used for
    Network Proxying through a subtree. When
    enabled, a packet will be routed into the node
    (rather than through the node) if either
    DstNode == myNodeID OR (nodeRangeLo <=
    DstNode <= nodeRangeHi).
    nodeRangeHi 12 bits Enabled with nodeRangeEnable. Specifies
    high node ID of node range match.
    nodeRangeLo 12 bits Enabled with nodeRangeEnable. Specifies
    low node ID of node range match.
    noFlowControl 1 bit When enabled, there will be no flow control.
    portRemap[INT_PORTS]; Array [INT_PORTS] x Allows remapping of incoming destination
    2 bits port IDs to the internal port where it'll be
    delivered. This register defaults to an
    equivalence remapping. An example of where
    this will get remapped is during Network
    Proxy where the management processor will
    remap MAC0 packets to be sent to the
    management processor.
    INT_PORTS = 4. Array elements are the Ports
    enumeration (management processor, MAC0,
    MAC1, OUT).
    2 bits contents is the Ports enumeration.
    primaryEthGatewayNode[INT_PORTS] Array [INT_PORTS] Specifies Node ID of primary Ethernet
    of 12-bit gateway for this node. Packets destined to
    node IDs that aren't within the fabric will get
    routed here.
    promiscuousPortVec 4 bits Can be configured for Promiscuous Mode
    allowing traffic on one or more links to be
    snooped by the management processor or A9s
    in order to collect trace data or to implement
    an Intruder Detection System (IDS). This
    causes all traffic passing through the switch to
    be copied to the internal ports defined by this
    port vector.
    routeForeignMACsOut 1 bit When enabled, a MAC address that does not
    contain a myOUI address, will not check the
    MAC lookup CAM, and will get treated as a
    MAC lookup CAM miss, thus getting routed
    to the gateway port. This saves latency in the
    common case of not populating the CAM
    with foreign MAC aliases.
    secondaryEthGatewayNode[INT_PORTS] Array [INT_PORTS] Specifies Node ID of secondary Ethernet
    of 12-bit gateway. Incoming (from OUT) packets
    routing through the fabric will be sent here.
    unicastPortsFromOtherExt 1 bit An incoming unicast from an external
    Gateways gateway will get the gateway node put into
    the source node field of the routing header.
    Upon reaching the destination node, this bit
    will be checked. When the bit is clear, the
    external gateway node must match the
    destination gateway node for it to be delivered
    to internal ports. This is to handle the case
    where the fabric is connected to an external
    learning switch that hasn't yet learned the
    mac/port relationship, and floods the unicast
    packet down multiple ports. This will prevent
    a fabric node from getting the unicast packet
    multiple times.
    unicastRoute[NODES] Array [NODES] of Link vector of unicast next route. 10 bits is 2-
    10 bits bit weight for each of 5 links.
  • The registers shown in Table 11 are contained within the Switch implementation, but need not be software accessible.
  • TABLE 11
    Field Size Notes
    bcastIDNext
    5 bits Next broadcast sequence ID to issue
    next. Hardware will increment this
    for each broadcast packet initiated
    by this node.
    bcastIDSeen[BCAST_ID_LEN] Array [BCAST_ID_LEN] FIFO list of broadcast tags seen by
    of 5 bits. this node.
    bcastIDSeenNext # bits to index into Next array position into
    BCAST_ID_LEN bcastIDSeen[ ] to insert a broadcast
    tag.
  • Note that software should be able to update the routing tables (unicastRoute) and the macAddrLookup CAM atomically with respect to active packet routing. One implementation will be to hold off routing access to these tables during an update operation.
  • Broadcast/Multicast Routing
  • FIG. 6 shows an exemplary broadcast mechanism 1000 according to one aspect of the system and method disclosed herein. The link between nodes N10 1001 and N21 1002 is down, as indicated by the dashed line 1003. During routing header generation of multicast packets, the source node puts an incremented broadcast ID for that source node in the routing frame (rframe.bcastID). When a node receives a multicast routing frame (i.e. rframe.rfType==Multicast∥rframe.rfType==NeighborMulticast), it checks to see whether it has already seen this broadcast packet. The check is done by accessing the bcastIDSeen CAM with a tag formed with the broadcast source node and the broadcast ID. If it has already been seen (i.e. CAM hit), no action is be performed. If the broadcast frame has not been seen before, it broadcasts it to appropriate internal ports and external gateways (intPortBroadcastVec register) and rebroadcasts it through all outward XAUI links except for the link it came in on. Note that it only broadcasts through laterals if the broadcastLateral register is set. It is unnecessary to broadcast laterals on most topologies, and doing so may reduce the number of duplicated broadcast packets by disabling it. It then adds this broadcast tag to the bcastIDSeen CAM in FIFO order. In FIG. 7, N041004 initiates a broadcast to all neighbors, i.e., N111105. N11 has not seen the packet, so it broadcasts to all non-incoming neighbors, which, in this example, are N21 1002, N201006, N03 1007, and N05 1008, and accepts the packet internally. Nodes N03 and N05 haven't seen the packet, so they accept the broadcast internally and are done. N21 hasn't seen the packet, so it broadcasts the packet to all active, non-incoming links (e.g., N10, N12 1009), and accepts the packet internally. N20 broadcasts the packet to all active, non-incoming links (i.e., N12), and accepts the packet internally. N10 broadcasts down to N00 1010, N011011, and N02 1012. N12 rebroadcasts to N06 1013, N07 1014, N08 1015 and to one of N21 and N20 (the one it didn't get the broadcast packet from). Note that one of N20 and N21, and N12, see the packet twice. They take action only on their first instance, the secondary times it hits the broadcast CAM as a duplicate, and the packet is ignored.
  • Unicast Routing Unicast to Other Node
  • Unicast routing (as shown in FIG. 7) is responsible for routing non-multicast (i.e. unicast) packets to the next node, This is done by utilizing a software computed unicastRoute[ ] next node routing table that provides a vector of available links to get to the destination node.
      • Condition
      • rframe.rfType==Unicast
      • Routing
  • There are substantial complexities related to routing around faults. Fault free routing and routing around faults will be discussed separately.
  • Traditionally in tree routing, the packet will be routed upward until a common parent of (source, destination) is reached. This upward routing can be deterministic, oblivious, or adaptive. The packet is then routed downward to the destination using deterministic routing.
  • As an example, FIG. 7 illustrates a packet routing from node N00 1010 to N08 1015. The packet is routed in the upward phase to the common ancestor (N21) through node N101001, and then a descent phase to the destination.
  • Note that during the upward phase at node N10, there are two candidate links (N10,N21) and (N10,N20). The first candidate link could be chosen deterministically, or an adaptive algorithm could dynamically select either of the links. But, once the node reaches the common ancestor and turns downward, there are no redundant paths (in general) for the node to reach the destination.
  • Unicast Routing in the Presence of No Faults
  • Each link is annotated within this unicastRoute table with a 2-bit linkWeight where software can express the relative cost/distance to the destination node via this link. By convention, link weights should represent:
      • 0=No route
      • 3=Direct next-hop connection
      • 1 and 2=Software computed relative costs. As an example if there are routes across 3 links with costs of 2 hops, 3 hops, and 6 hops, the first two links could be assigned weight=2 and the 6 hops path could be assigned weight=1.
  • Algorithm for fault-free unicast routing:
      • Get link weight vector from the unicast routing table
        • linkWeightVector=unicastRoute[rframe.dstNode]
      • Remove link that it came in on to remove possibility of sending it back
      • Remove any links that are not up
      • At this point, have a candidate list of links with associated link weights.
      • Iterate through link weights, starting with highest priority (3) down through 1. Gather candidate list of links at this priority, stopping once the candidate list has at least one link. The result is a candidate list of links at the highest priority. As an example, if there are 2 links at weight=2, and 2 links at weight=1, the prioritized candidate list will contain the two links at weight-2.
      • The adaptive register is checked to determine whether to do adaptive or deterministic routing.
        • adaptive==0 indicates that deterministic routing is to be used, so the first link is chosen from the prioritized candidate list.
        • adaptive==1 indicates that adaptive routing is to be used. The switch implementation will choose an algorithm for adaptively choosing the target link from the prioritized candidate list. This adaptive algorithm could be as simple as round-robin around the list. Alternatively, may choose to factor in other attributes e.g. FIFO free depth, link speed, . . .
          • An implementation option could be to add a register option to allow the router to adaptively choose from all non-zero weights, or to only adaptively choose from the highest priority candidate lists.
      • The packet is sent out the selected link.
    Fault-Resilient Unicast Routing
  • A couple of issues contribute to the complexity of fault-resilient unicast routing:
      • The desire to do fault routing with only localized knowledge. A node implicitly knows that a link is down to a neighbor node. We choose a design to avoid having to communicate that a link (or node) goes down elsewhere in the fabric due to the complexities of maintaining a global, unified state in the presence of failures.
      • The nature of routing in a tree. During the ascent phase of packet routing, links can be adaptively chosen from redundant links so it can be straightforward to avoid a link with the normal adaptive link selection.
      • But, once the packet starts descending, traditionally there is not redundant paths for the descent path (that follow the routing rules), so fault routing can become challenging.
      • FIG. 8 illustrates a link failure (N10,N21) and unicast routing selected the (N10, N20) link using the normal adaptive routing algorithm previously described. But note, if the packet is routed up to N20 and link (N20,N12) is down, it has no easy path to get to the destination.
  • We have two approaches to handling routing around fails:
      • Software can compose alternative but non-desirable routes with weight=1. We'll call these escape routes. These are low priority routes that may violate the strict routing rules used during routing around faults. As an example, if the link (N20, N12) was down, the unicastRoute[N08] entry for N20 could contain link to N12 with weight-2 and a link to N11 with weight=1. In this way, the normal adaptive routing algorithms will automatically do the N20->N11->N21->N12->N08 path.
      • The fabric architecture includes a technique that we refer to as “misrouting”. Misrouting provides for iterative backtracking.
      • Both of these techniques will provide substantial unicast fault-resilience.
    Unicast Misrouting
  • As an example, consider the following topology, with 3 links 1101, 1102 and 1103 that have failed (shown in FIG. 9). Consider a unicast route from N0 to N3. We'll consider the following routing to understand the misrouting technique, understanding that this is only one of several routes that could have been chosen adaptively.
      • Packet routed N0 to N6.
      • Packet routed N6 to N10
      • N10 sees that it has no paths to get to N3, other than the link it came in on. N10 sets the misrouting bit in the routing header, and sends it back to N6.
      • N6 sees that the packet is being misrouted, sets the bit for the N 10 link in the misrouteVector in the routing header, chooses an alternative link that has not been misrouted, and sends the packet to N11.
      • N11 sees that it has no path to N3, other than the link it came in on. misrouting bit is already on, and sends it back to N6.
      • N6 sees that the packet is being misrouted, adds N11 link to the misrouteVector (now contains N10 and N11 link IDs), chooses an alternative link that has not been misrouted, and sends it N7.
      • N7 sees that the misrouting bit is set, but does have a valid link to N3 (to N12), and thus clears the misrouting bit in the header, and forwards the packet to N 12.
      • N12 sends to N9.
      • N9 unicastRoute now likely contains link to N3 (weight=3) and link to N8 (weight=2). Normal adaptive routing will not choose the direct link to N3 since it's down, and will route the packet to N8, then finally to N3.
      • If N6 had exhausted its list of candidate links (meaning the misrouleVector masked them all), the implementation then has two choices:
        • drop the packet and inform the M3 of the failure to route.
        • clear the misrouteVector leaving misrouting set, and forward the packet through one of the downward facing links (if one exists). This will retry misrouting at one layer lower. The implementation may want to have a register bit (enableRecursiveMisrouting) to enable this retry at lower layer option.
          There is a register enableMisrouting that allows software to control whether the switch will initiate the misrouting algorithm.
    Multi-Domaining
  • Also known to the inventors is Multi-Domaining, whose goal is to increase the addressability of nodes to a large number of nodes (e.g., 64 K nodes), without having to increase the size of the unicast routing table to 64 K nodes.
  • As currently described, the unicast routing table is a single-dimension array indexed by node number (i.e. 0 to MAX_NODES-1), where a typical implementation will be between 256 and 4 K nodes.
  • This section will now describe how the current architecture is altered to support multiple domains, with 64 K max nodes.
      • The node namespace is changed from a node ID from 0 to MAX_NODES-1, to a 2-tuple of (domain ID, node ID), where both domain ID and node ID range from 0 to 255. So, there can effectively be 256 domains where each domain can contain up to 256 nodes.
      • The unicast routing table is changed from a single dimension table of size MAX_NODES, to a two-dimension table of size 256. The unicast routing table is now changed from a structure of unicastRoute[NODES] to unicastRoute[2][256].
  • Local domain routing: When routing to a node within this domain, the unicast routing table is accessed as unicastRoute[0][node ID], and provides a weighted link vector to route to the specified node ID from the current node.
        • Remote domain routing: When routing to a node within a remote domain, the unicast routing table is accessed as unicastRoute[1][domain ID], and provides a weighted link vector to route to the specified domain ID from the current node.
      • Routing frame: One bit is added to the routing frame, dstRemote, which is set true when routing to a remote domain.
      • Locally administered MAC addresses: The section below describes the Node Encoded
  • Unicast MAC address encoding as follows:
  • Node Unicast 10 bits:
    Encoded Locally SS_MAC_NODE_ENCODED_MAGIC
    Unicast administered 12 bits: Node ID
    OUI == Switch 2 bits: Port ID
    OUI
  • This gets altered for multi-domaining as follows:
  • Node Unicast 6 bits:
    Encoded Locally SS_MAC_NODE_ENCODED_MAGIC
    Unicast administered 8 bits: Domain ID
    OUI == Switch 8 bits: Node ID
    OUI
    2 bits: Port ID
      • Creating the routing frame header: Table 2 describes the algorithms for creating the routing frame header. This is augmented in the multi-domaining case by:
  • if ( dstDomain == myDomainID ) { // Route to local domain
    rframe.dstRemote = false;
    rframe.dstNode = dstNode;
    }
    else { // Route to remote domain
    rframe.dstRemote = true;
    rframe.dstNode = dstDomain;
  • Network Proxy
  • The concept of network proxy is the ability of the main processors (FIG. 5A, 905) to maintain network presence while in a low-power sleep/hibernation state, and intelligently wake when further processing is required. There are several architectural features related to Network Proxy:
      • There is a CSR (portRemap) to allow the remapping of Port IDs. In effect, when the switch is to deliver a packet to an internal MAC0 port (e.g. FIG. 5A, 902), this Port Remapping CSR allows software to remap MAC0 to the management processor MAC (e.g. FIG. 5A, 907) and have the packet delivered to the management processor for Network Proxy processing. This remapping CSR could also be used to remap MAC1 traffic to MAC0, or MAC1 traffic to the management processor.
      • Normally, the switch looks at the destination node ID of the routing frame to decide whether the packet is delivered to an internal port within the node, or gets routed to other XAUI connected nodes. This is done by matching Destination Node ID to “My Node ID”. The Node ID Match register (nodeRangeLo, nodeRangeHi) causes the packet to be delivered to an internal port within the node if nodeRangeLo<=Destination_Node<=nodeRangeHi∥myNodeID==Destination_Node. This allows a node to proxy for a subtree of nodes.
        A typical use sequence would be of the form:
      • Management processor maintains the IP to MAC address mappings for MAC0 and MAC1 on the node. This can be done via either explicit communication of these mappings from the main processor OS to the management processor, or can be done implicitly by having the management processor snoop local gratuitous ARP broadcasts.
      • The main processor coordinates with the management processor to go to a low power dormant state. During this transition, the management processor sets up the Port ID remapping CSR to route MAC0 and MAC1 traffic to the management processor.
      • The management processor processes any incoming MAC0/MAC1 packets. There are 3 categories of processing:
      • Respond to some classes of transactions that require simple responses (e.g. ARP responses and ICMP ping).
      • Dump and ignore some classes of packets, typically unicast or broadcast packets that are targeting other computers.
      • Decide that the main processor must be woken to process some classes of packets. The management processor will wake the main processor, undo the Port ID remapping register, and re-send the packets back through the switch where they will get rerouted back to MAC0/1.
    Wake-on-LAN Magic Packet
  • In a traditional desktop computer, the computer to be woken is shut down (sleeping, hibernating, or soft off; i.e., ACPI state G1 or G2), with power reserved for the network card, but not disconnected from its power source. The network card listens for a specific packet containing its MAC address, called the magic packet, broadcast on the broadcast address for that particular subnet (or an entire LAN, though this requires special hardware or configuration). The magic packet is sent on the data link or layer 2 in the OSI model and broadcast to all NICs within the network of the broadcast address; the IP-address (layer 3 in the OSI model) is not used. When the listening computer receives this packet, the network card checks the packet for the correct information. If the magic packet is valid, the network card takes the computer out of hibernation or standby, or starts it up.
  • The magic packet is a broadcast frame containing anywhere within its payload: 6 bytes of ones (resulting in hexadecimal FF FF FF FF FF FF), followed by sixteen repetitions of the target computer's MAC address. Since the magic packet is only scanned for the string above, and not actually parsed by a full protocol stack, it may be sent as a broadcast packet of any network- and transport-layer protocol. It is typically sent as a UDP datagram to port 0, 7 or 9, or, in former times, as an IPX packet.
  • Using the Network Proxy architecture just described, the management processor can support these Wake-On-LAN packets. It will get these broadcast packets, will know the MAC addresses for the other MACs on the node, and be able to wake up the main processor as appropriate. No further functionality is needed in the switch to support these Wake-on-LAN packets.
  • Power Control Features
  • A system and method to manage the supply of power to large sets of processors or processor cores in an efficient, closed-loop manner are provided such that rather than the system supplying power that may or may not be used, a processor would request power based on the computing task at hand, which request would then be sent to the power supply system and thus power made available. Further needed is bidirectional communication between the CPU(s) and the power supply stating it has a certain limit, and rather than giving each processor its desired amount of power, said system may give a processor an allocation based on prorated tasks.
  • Additionally needed is a method of prioritization that may be used to reallocate power among processors, so the allocation does not have to be a linear cut across the board.
  • Some of the leading processor architectures have a thermal management mode that can force the processor to a lower power state; however none at present time imposes similar power reduction dynamically based on the available power resources of the system, as they assume that sufficient power is always available.
  • Each processor typically can run in a number of power states, including low power states where no processing occurs and states where a variable amount of execution can occur (for example, by varying the maximum frequency of the core and often the voltage supplied to the device). This latter mechanism is commonly controlled by monitoring the loading of the node, and if the load is low, decreasing the maximum frequency/voltage of the CPU (the frequency and voltage of the core would be adjusted downward so as to not exceed the power limit set in order to keep the load below the capability limit of the power supply) until the amount of idle is reduced. The reverse is also often the case: if loading is high the frequency/voltage can be increased. Predictive mechanisms also exist where queued transactions are monitored, and if the queue is short or long the voltage and frequency can be altered appropriately. Finally, in some cases a computational load (specifically in the cloud nature of shared threads across multiple cores of multiple processors) is shared between several functionally identical processors. In this case it's possible to power down (or move into a lower power state) one or more of those servers if the loading is not heavy.
  • Currently there is no connection between power supply generation to the processors and the power states of each processor. Power supplies are provisioned so that each processor can run at maximum performance (or close to it) and the redundancy supplied is sufficient to maintain this level, even if one power supply has failed (in effect double the maximum expected supply is provided). In part, this is done because there is no way of limiting or influencing the power state of each processor based on the available supply.
  • A similar situation applies to cooling in an array of multiple processors, although due to the slow increase of temperature, it can be monitored and capacity can be turned on or off (e.g., increase or slow fans). Based on the currently used capacity, enough capacity must still be installed to cool the entire system with each system at peak performance (including any capacity that might be powered down through failure or maintenance).
  • In effect, the capacity allocated in both cases must be higher than absolutely necessary, based on the inability to modulate design when capacity limits are approached. This limitation also makes it difficult to install short-term peak clipping capacity that can be used to relieve sudden high load requirements (as there is no way of reducing the load of the system when it is approaching the limits of that peak store). As an example, batteries or any other means of storing an energy reserve could be included in the power supply system to provide extra power during peaks; however, when they approach exhaustion the load would need to be scaled down. In some cases, cooling temperatures could simply be allowed to rise for a short period.
  • FIG. 10 shows an overview of an exemplary system 2100 for management of power supplied to multiple processors according to one embodiment of the current disclosure. An array of 16 processors 2101 a-p is shown. Each processor has its own complete computing system, with memory and communication interconnection buses, a power feed, etc. All of these elements of each processor's system are well known in current art and are not shown here, for reasons of simplicity and clarity. Processor 2101 a has an operating system with multiple programs 2101 a 1-n. One of these programs, 2101 ax, is of particular interest. It is the piece that communicates with the system management software of the current disclosure, described in greater detail in the discussion of FIG. 12, below. The system management software can actually run on any one of the processors 2101 a-p, or it can run on a separate, dedicated processor (not shown). A power supply unit (PSU) 2102 gets a main feed 2103 and distributes it through subfeeds 2103 a-p to each of the processors 101 a-p according to their individual needs. In some cases more than one processor 2101 b-p can have similar software 2101 b 1-n through 2101 p 1-n, including 2101 bx-px.
  • FIG. 11 shows an exemplary table 2200 that could be maintained by a power management system such as management system 2100, for example, as described in FIG. 10. Each row 2201 a-p contains records of parameters 2202 a-e that are recorded in columns. They may be updated from time to time as necessary, either if certain changes occur or on an interval basis, etc. It is clear that the five parameters 2202 a-e are only exemplary of any of a great variety of parameters that may be included in table 2200, so the number of parameters is not restricted to five only. In this example, parameters are (reading left to right) CPU ID, actual current usage, desired usage based on tasks awaiting execution by the CPU, permitted usage allocated to the CPU at the moment, and the computational load waiting, for example, processes waiting in queue, with an additional priority rating in some cases (not shown). A record 2201 t sums up the total of the parameter records of rows 2201 a-p for array 101 a-p. Each processor in array 101 a-p may actually be a chip containing multiple CPUs or multiple cores of its own, so, in the case of array 2101 a-p, the actual number of processors involved may be, for example, 256, instead of 16, if each chip were to contain 16 cores.
  • FIG. 12 shows an exemplary process 2300 of the management software executed in any one of the processors of array 2101 a-p or in a dedicated processor (not shown), according to one embodiment of the present disclosure. In step 2301 the system starts, and in step 2302 it starts a count of the number of process repetitions in one session. In step 2303 the system checks to see whether the count exceeds a pre-set maximum, which in this example is P, the number of units in array 2101 a-p that must be addressed. It is clear that because P represents a number, there is no practical limitation to the numeric value of P. If the count does not exceed the set maximum (NO), in step 2304 the system receives current readings from unit N, which in this example is chip 2101 n. Each chip, as noted previously, may contain multiple CPUs. In some implementations, power need is assessed on a per-chip basis, while in other implementations, power need is assessed for each separate CPU or core in a chip. In step 2305, the system obtains the desired power usage, based on computational requirements and priority between the requirements, from each software instance. In step 2306 the system calculates the power allocation and returns it to the process. In step 2307 data about the exchanges in steps 2304-2306 is written to and/or read from table 2200. In step 2308, N is incremented and the process loops back to step 2303 until all cores in the array have been addressed, in sequence. If, in step 2303, the full sequence of units has been addressed and N becomes greater than P (YES), the process moves to step 2309, where the system calculates the power used, the desired power, and the available power for all units that were addressed in steps 2304-2306. In step 2310 power is allocated, and in step 2311 the system negotiates with PSU 2102 about available power or available additional power, and then in step 2312 the system updates data in table 2200. The process may end at step 2313, and then it may start again based on some pre-set timer or on triggering by a change in power requirements or priorities. In other cases, the process may be set to continuously loop back to step 2302.
  • In the current disclosure as described in the discussions of FIGS. 10-12, a system 2100 has a power allocation that it needs to manage. Each processor is allocated a certain base capacity and must request more capacity from a central resource manager. In addition, the central resource manager can signal the processor that it requires it to release capacity (either urgently or more slowly). It is clearly possible for the central resource manager to be duplicated for redundancy and for the managers to remain synchronized. Note that because the power manager controls the power state of the processor it can alter the actual load that is imposed, hence the available system capacity can be used to alter the power state of the processor. This feature is key to this invention, as the system can never over allocate capacity without running the risk of a “brown out.” In addition, the current invention permits consideration of a situation where an amount of capacity is only allocated for a fixed period of time and must be renewed periodically.
  • FIG. 13 shows a simplified overview of an exemplary larger power management system 2400. In this example, multiple installations, typically printed circuit boards, of the type of system shown as system 2100 are stacked vertically (although it is clear that such system multiples may be arranged vertically, horizontally, sequentially, networked, or in any other way). Each system 2100 a-n has CPUs 2101 a-p and PSU 2102, so that in system 2400 there are PSUs 2102 a-n. System 2400 also contains air conditioning or cooling and heat sensors 2410 a-n and master PSUs 2402 a-n. In this example, the variable range a-n for PSU 2402 a-n simply indicates a variable, finite numeric quantity, and should not be construed to be an exact number. Depending on the total requirements of PSUs 2102 a-n, a variable number of PSUs 2402 a-n may be turned on or turned off, thus keeping the system running optimally and reducing problems of overheating.
  • FIG. 14 shows an exemplary process 2500 of the system-level management software, according to one embodiment of the present invention. In essence, process 2500 is similar to process 2300. Additionally incorporated are controls of the air conditioning or cooling and heat sensors 2410 a-n. In step 2501 the system starts, and in step 2502, it collects all data from PSU 2102 a-n. In step 2503 the system assesses outside and inside temperatures of each PSU 2102 a-n and the current heat loads, as well as available air conditioning or cooling performance. In step 2504 additional main PSUs are accordingly added or removed, and new power ceilings are distributed to CPUs 2101 a-n. In step 2505 the process ends.
  • In some cases several of the nodes in a system may require greater performance (based on loading). The individual power managers request capacity and it is granted by the central resource manager (CRM) (for example, 50 nodes request 5 units of extra capacity allowing full execution). If other nodes request the same capacity, the CRM can similarly grant the request (assuming that the peak loads do not align, or it may over allocate its capacity).
  • In the event of a power supply failure, the CRM detects such. The backup battery, or any other suitable energy reserve, including but not limited to mechanical storage (flywheel, pressure tanks etc.) or electronic storage (all types of capacitors, inductors etc.), here all jointly referred to a “backup battery”, is capable of supplying power for 100 ms at peak load, so the CRM has 100 ms to reduce the capacity to the new limit of 450 units (actually it has double that this time if the battery can be fully drained, because part of the load may be supplied by the single functioning power supply). The CRM signals each power controller in each processor that it must reduce its usage quickly. This operation takes a certain amount of time, as typically the scheduler needs to react to the lower frequency of the system; however, it should be achievable within the 100 ms. After this point each processor is going to be running at a lower capacity, which implies slower throughput of the system (each processor has 4.5 units of capacity, which is enough for minimum throughput).
  • Further adjustment of the system can be done by the CRM requesting capacity more slowly from some processors (for example moving them to power down states) and using this spare capacity to increase performance in nodes that are suffering large backlogs. In addition, in an aggressive case, the backup battery can have some of its energy allocated for short periods to allow peak clipping (the processor requests increase capacity and is granted it, but only for a few seconds).
  • A similar mechanism can be used to allocate cooling capacity (although the longer time constants make the mechanism easier).
  • A less aggressive system can allocate more total power and have more capacity after failure; while more aggressive systems can allocate less total power and not allow all processors to run at full power even in the situation where redundancy is still active. More complex redundancy arrangements can be considered (e.g., N+1), etc. The key is that capacity is allocated to different processors from a central pool and the individual processors must coordinate their use.
  • For a system where the individual processors are smaller and have better low power modes (i.e., bigger differences between high and low power) this approach is even more applicable. Communication to the CRM can be done by any mechanism. The requirement is that it must be quick so that the failure case time constant can be met, at least for most of the nodes. It's likely that Ethernet packets or messages to board controllers are sufficient.
  • Communications Features
  • A system and a method and architecture that allow many processors to share limited communication resources with efficient power and speed, as well as chip real estate and power consumption are provided. In general terms, this goal is achieved by a variety of changes to typical system architecture, signified by a typically chip internal (so called on-board, but sometimes system internal) virtualized communication fabric added between the multi-CPU cores (referred to as “the cores”) and the external communication ports for communicating with the outside world, both to external sources and to other multi-processor chips in a large network. Typically, such networks are organized as trees, fat trees, meshes, hypercubes, or toroids, allowing each chip to communicate with its neighbors.
  • FIG. 15 shows a midlevel architectural overview of a multiprocessor chip 3400 according to one embodiment. The multiple processor cores 3415 a-n are, in this example, ARM Cortex A9, including the ARM NEON SIMD processor. Multiple communication ports 3407 connect to various devices, which are discussed in greater detail below. An auxiliary processor 3445, such as a ARM Cortex M3, is used to power manage the processors 3415 a-n and to wake them up, let them sleep, or put them to sleep as needed, as well as to manage voltage/frequency scaling of the processor cores 3415 a-n for load-driven power management. An intelligent switching fabric 3427 connects one or more peripheral elements 3417-3423 on one side and the actual ports 3429, 3430 and 3452-3455 on the other side. This switching fabric, which is discussed in greater detail below, allows various different elements to be used in different ways. For example, to reduce the number of ports connected, a communication media access control (MAC), such as MACs 3421 and 3422, actually is split in half. In another example of the function of the switching fabric, pending communication requests are managed by the auxiliary processor 3445, which is intricately involved in managing the switching fabric. The switching fabric allows the processor(s) 3415 a-n to go into a sleep mode or to enter power down mode, while the auxiliary processor responds to communication requests for those processors that are asleep or off, and keeps those requests hanging in the switching fabric until the processors are started again after which the auxiliary processor 3445 then lets the processors 3415 a-n receive the data. Of particular use are the interfaces 3452-3455, which connect these chips to the neighboring chips. Elements 3424, 3425 and 3426 are extended beyond their respective standard functional parts as discussed throughout this document, namely an ARM® generic interrupt controller GIC 3412, a debugging and testing unit Coresight Debug/JTAG section 3409, and an accelerator coherence port (ACP) 3413 that all help maintain memory and I/O coherence, allowing the auxiliary processor core to interact “invisibly” with all kinds of aspects involved with both power management and communication management to effect the use of the novel switching fabric 1427.
  • FIG. 16 shows a slightly more detailed view of the switching fabric, as does FIG. 17. FIG. 15 in particular shows the different paths that can be created within the switching fabric, as controlled by a set of routers 3504 and 3505, with one router for internal communications and the other router for external communications, respectively, The routers themselves are typical in such a system, for internal routing and external routing respectively. These routers are primarily responsible for arbitrating and managing the control signals of the various data paths between the “processor side” 3501 of the MACs (or other communication units) and the external faced side of those communication units 3528-3555. Although distinct data paths are shown, not all paths exist as physical connections. Rather, they can be made available as part of the logical switching.
  • Reflection of Interrupts Between Application Processors and Their Associated Power Microcontrollers
  • In reference to FIG. 15, the SOC reflects interrupts between application processors and their associated power microcontrollers. The GIC reflects the processor 1415 a-n interrupt lines to the auxiliary processor to allow the auxiliary processor to wake the processor 1415 a-n cores when an interrupt needs to be processed, as previously discussed, as well as in other locations herein.
  • Further, if an individual core is in dormant mode, then just sending the interrupt to the core has little effect. Thus the system needs to monitor the nIRQOUT and nFIQOUT signals so the interrupt goes to the GIC and is then reflected out of those pins—this signals the PMU (aka the auxiliary processor) to wake up the core.
  • If the whole processor subsystem is powered down, the interrupts are steered to the auxiliary processor where the event is seen. Most events cause a wakeup of the subsystems, but the interrupt is not removed. Rather, it is retained and once a processor wakes up and is ready to start, the interrupt is taken directly by the GIC. In some cases, interrupts are turned into level sensitive (or masking) to the microcontroller so as not to bury the microcontroller in interrupts.
  • The auxiliary processor microcontroller 3445 enables visibility into the processor 3415 a -n application processor 3445 interrupts when the application processor goes into low power state, and then the auxiliary processor knows to wake up the processor 3415 a-n application processor. In some cases, interrupts are turned into level sensitive interrupts (or masked) to the microcontroller to not bury the microcontroller in interrupts and overwhelm the system. In some other cases, the microcontroller enables visibility into application processor interrupts when application processors go into a low power state, thus the microcontroller can know to wake up the application processor.
  • While the foregoing has been with reference to a particular embodiment of the invention, it will be appreciated by those skilled in the art that changes in this embodiment may be made without departing from the principles and spirit of the disclosure, the scope of which is defined by the appended claims.

Claims (21)

1. A system on a chip, comprising:
one or more processing cores;
one or more management processors coupled to each one of the one or more processing cores;
one or more communication interfaces; and
one or more interrupt controllers coupled between each one of the one or more processing cores and the one or more management processors for enabling an interrupt transmitted for reception by a first one of the one or more processing cores to be reflected to the one or more management processors from the first one of the one or more processing cores while the first one of the one or more processing cores is in the inactive state.
2. The system on a chip of claim 1, further comprising:
a switching fabric coupled between the one or more processing cores, the one or more management processors and the one or more communication interfaces, wherein the one or more interrupt controllers coupled to the switching fabric for enabling the interrupt transmitted for reception by at least one of the one or more processing cores to be reflected to the one or more management processors from the first one of the one or more processing cores while the first one of the one or more processing cores is in the inactive state.
3. The system on a chip of claim I wherein the one or more management processors cause the interrupt to be provided to the first one of the one or more processing cores in response to the first one of the one or more processing cores being transitioned from the inactive state to an active state.
4. The system on a chip of claim 3 wherein:
the interrupt is maintained by the one or more management processors until the first one of the one or more processing cores being transitioned from the inactive state to the active state; and
the interrupt is handled directly by the one or more interrupt controllers in response to the first one of the one or more processing cores being transitioned from the inactive state to the active state.
5. The system on a chip of claim 1 wherein:
the one or more management processors cause the interrupt directed to the first one of the one or more processing cores to be held in the switching fabric while the first one of the one or more processing cores is in the inactive state;
the one or more management processors assess the one or more processing cores to determine a second one of the one or more processing cores that is currently in an active state; and
the one or more management processors cause the communication request to be delivered to the second one of the one or more processing cores for allowing the second one of the one or more processing cores to perform the task initiated by the communication request after determining that the second one of the one or more processing cores is currently in the active state.
6. The system on a chip of claim 5 wherein:
the one or more management processors assess the second one of the one or more processing cores to determine an available processing power capacity prior to causes the communication request to be delivered to the second one of the one or more processing cores; and
the one or more management processors cause the communication request to be delivered to the second one of the one or more processing cores in response to determining that the second one of the one or more processing cores has sufficient processing power available for performing the task to be initiated by the communication request.
7. A computing system, comprising:
one or more server on a chip units each having one or more processing cores and one or more power management portions coupled between each one of the one or more processing cores one or more processing cores;
one or more interconnect portions couple to each one of the one or more server on a chip units for enabling the computing system to be communicatively connected to one or more other computing systems; and
one or more interrupt controllers coupled between each one of the one or more processing cores and the one or more power management portions for enabling an interrupt transmitted for reception by a first one of the one or more processing cores to be reflected to the one or more management processors from the first one of the one or more processing cores while the first one of the one or more processing cores is in the inactive state,
8. The computing system of claim 7 wherein:
the one or more server on a chip units each include a switching fabric coupled between the one or more processing cores, the power management portions and the one or more communication interfaces thereof, and
the one or more interrupt controllers are coupled to the switching fabric for enabling the interrupt transmitted for reception by at least one of the one or more processing cores to be reflected to the one or more management processors from the first one of the one or more processing cores while the first one of the one or more processing cores is in the inactive state.
9. The computing system of claim 7 wherein the one or more power management portions cause the interrupt to be provided to the first one of the one or more processing cores in response to the first one of the one or more processing cores being transitioned from the inactive state to an active state.
10. The computing system of claim 9 wherein:
the interrupt is maintained by the one or more power management portions until the first one of the one or more processing cores being transitioned from the inactive state to the active state; and
the interrupt is handled directly by the one or more interrupt controllers in response to the first one of the one or more processing cores being transitioned from the inactive state to the active state.
11. The computing system of claim 7 wherein:
the one or more power management portion cause the interrupt directed to the first one of the one or more processing cores to be held in the switching fabric while the first one of the one or more processing cores is in the inactive state;
the one or more power management portion assess the one or more processing cores to determine a second one of the one or more processing cores that is currently in an active state; and
the one or more power management portion cause the communication request to be delivered to the second one of the one or more processing cores for allowing the second one of the one or more processing cores to perform the task initiated by the communication request after determining that the second one of the one or more processing cores is currently in the active state.
12. The computing system of claim 11 wherein:
the one or more management processors assess the second one of the one or more processing cores to determine an available processing power capacity prior to causes the communication request to be delivered to the second one of the one or more processing cores; and
the one or more management processors cause the communication request to be delivered to the second one of the one or more processing cores in response to determining that the second one of the one or more processing cores has sufficient processing power available for performing the task to be initiated by the communication request.
13. A computing system, comprising:
one or more server on a chip units each having one or more processing cores and one or more power management portions coupled between each one of the one or more processing cores one or more processing cores;
one or more interconnect portions couple to each one of the one or more server on a chip units for enabling the computing system to be communicatively connected to one or more other computing systems;
one or more interrupt controllers coupled between each one of the one or more processing cores and the one or more power management portions for enabling an interrupt transmitted for reception by a first one of the one or more processing cores to be reflected to the one or more management processors from the first one of the one or more processing cores while the first one of the one or more processing cores is in the inactive state
operating system software accessible by each one of the one or more processing cores of the one or more server on a chip units; and
a first memory structure coupled to one or more direct memory access portions of each one of the one or more server on a chip units for providing direct access memory functionality within the computing system.
14. The computing system of claim 13 wherein:
the one or more server on a chip units each include a switching fabric coupled between the one or more processing cores, the power management portions and the one or more communication interfaces thereof; and
the one or more interrupt controllers are coupled to the switching fabric for enabling the interrupt transmitted for reception by at least one of the one or more processing cores to be reflected to the one or more management processors from the first one of the one or more processing cores while the first one of the one or more processing cores is in the inactive state.
15. The computing system of claim 13 wherein the one or more power management portions cause the interrupt to be provided to the first one of the one or more processing cores in response to the first one of the one or more processing cores being transitioned from the inactive state to an active state.
16. The computing system of claim 15 wherein:
the interrupt is maintained by the one or more power management portions until the first one of the one or more processing cores being transitioned from the inactive state to the active state; and
the interrupt is handled directly by the one or more interrupt controllers in response to the first one of the one or more processing cores being transitioned from the inactive state to the active state,
17. The computing system of claim 13 wherein:
the one or more power management portion cause the interrupt directed to the first one of the one or more processing cores to be held in the switching fabric while the first one of the one or more processing cores is in the inactive state;
the one or more power management portion assess the one or more processing cores to determine a second one of the one or more processing cores that is currently in an active state; and
the one or more power management portion cause the communication request to be delivered to the second one of the one or more processing cores for allowing the second one of the one or more processing cores to perform the task initiated by the communication request after determining that the second one of the one or more processing cores is currently in the active state.
18. The computing system of claim 17 wherein:
the one or more management processors assess the second one of the one or more processing cores to determine an available processing power capacity prior to causes the communication request to be delivered to the second one of the one or more processing cores; and
the one or more management processors cause the communication request to be delivered to the second one of the one or more processing cores in response to determining that the second one of the one or more processing cores has sufficient processing power available for performing the task to be initiated by the communication request.
19. The computing system of claim 13, further comprising:
a second memory structure coupled to one or more memory interfaces of each one of the one or more server on a chip units for providing persistent storage functionality within the computing system.
20. The computing system of claim 19 wherein the one or more memory interfaces of the one or more server on a chip units includes at least one of:
a NAND flash interface;
a eMMC interface;
a PCIe interface;
a SATA interface;
a SD interface; and
a SAS interface.
21. The computing system of claim 19 wherein the one or more memory interfaces of the one or more server on a chip units includes:
a eMMC interface;
a PCIe interface;
a SATA interface;
a SD interface; and
a SAS interface.
US13/705,428 2009-10-30 2012-12-05 System and Method for High-Performance, Low-Power Data Center Interconnect Fabric Abandoned US20130097351A1 (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
US13/705,428 US20130097351A1 (en) 2009-10-30 2012-12-05 System and Method for High-Performance, Low-Power Data Center Interconnect Fabric

Applications Claiming Priority (3)

Application Number Priority Date Filing Date Title
US25672309P 2009-10-30 2009-10-30
US12/794,996 US20110103391A1 (en) 2009-10-30 2010-06-07 System and method for high-performance, low-power data center interconnect fabric
US13/705,428 US20130097351A1 (en) 2009-10-30 2012-12-05 System and Method for High-Performance, Low-Power Data Center Interconnect Fabric

Related Parent Applications (1)

Application Number Title Priority Date Filing Date
US12/794,996 Continuation US20110103391A1 (en) 2009-09-24 2010-06-07 System and method for high-performance, low-power data center interconnect fabric

Publications (1)

Publication Number Publication Date
US20130097351A1 true US20130097351A1 (en) 2013-04-18

Family

ID=43922457

Family Applications (11)

Application Number Title Priority Date Filing Date
US12/794,996 Abandoned US20110103391A1 (en) 2009-09-24 2010-06-07 System and method for high-performance, low-power data center interconnect fabric
US13/624,725 Active US9405584B2 (en) 2009-10-30 2012-09-21 System and method for high-performance, low-power data center interconnect fabric with addressing and unicast routing
US13/624,731 Active US9075655B2 (en) 2009-10-30 2012-09-21 System and method for high-performance, low-power data center interconnect fabric with broadcast or multicast addressing
US13/705,428 Abandoned US20130097351A1 (en) 2009-10-30 2012-12-05 System and Method for High-Performance, Low-Power Data Center Interconnect Fabric
US13/705,414 Active US8737410B2 (en) 2009-10-30 2012-12-05 System and method for high-performance, low-power data center interconnect fabric
US13/705,340 Active US9008079B2 (en) 2009-10-30 2012-12-05 System and method for high-performance, low-power data center interconnect fabric
US13/705,386 Active US8745302B2 (en) 2009-10-30 2012-12-05 System and method for high-performance, low-power data center interconnect fabric
US13/728,308 Active 2031-09-06 US9262225B2 (en) 2009-10-30 2012-12-27 Remote memory access functionality in a cluster of data processing nodes
US14/334,931 Active US9454403B2 (en) 2009-10-30 2014-07-18 System and method for high-performance, low-power data center interconnect fabric
US15/042,489 Active 2030-07-23 US10135731B2 (en) 2009-10-30 2016-02-12 Remote memory access functionality in a cluster of data processing nodes
US15/254,111 Active US9866477B2 (en) 2009-10-30 2016-09-01 System and method for high-performance, low-power data center interconnect fabric

Family Applications Before (3)

Application Number Title Priority Date Filing Date
US12/794,996 Abandoned US20110103391A1 (en) 2009-09-24 2010-06-07 System and method for high-performance, low-power data center interconnect fabric
US13/624,725 Active US9405584B2 (en) 2009-10-30 2012-09-21 System and method for high-performance, low-power data center interconnect fabric with addressing and unicast routing
US13/624,731 Active US9075655B2 (en) 2009-10-30 2012-09-21 System and method for high-performance, low-power data center interconnect fabric with broadcast or multicast addressing

Family Applications After (7)

Application Number Title Priority Date Filing Date
US13/705,414 Active US8737410B2 (en) 2009-10-30 2012-12-05 System and method for high-performance, low-power data center interconnect fabric
US13/705,340 Active US9008079B2 (en) 2009-10-30 2012-12-05 System and method for high-performance, low-power data center interconnect fabric
US13/705,386 Active US8745302B2 (en) 2009-10-30 2012-12-05 System and method for high-performance, low-power data center interconnect fabric
US13/728,308 Active 2031-09-06 US9262225B2 (en) 2009-10-30 2012-12-27 Remote memory access functionality in a cluster of data processing nodes
US14/334,931 Active US9454403B2 (en) 2009-10-30 2014-07-18 System and method for high-performance, low-power data center interconnect fabric
US15/042,489 Active 2030-07-23 US10135731B2 (en) 2009-10-30 2016-02-12 Remote memory access functionality in a cluster of data processing nodes
US15/254,111 Active US9866477B2 (en) 2009-10-30 2016-09-01 System and method for high-performance, low-power data center interconnect fabric

Country Status (6)

Country Link
US (11) US20110103391A1 (en)
EP (2) EP2494748B1 (en)
JP (1) JP2013509808A (en)
KR (1) KR101516216B1 (en)
CN (2) CN104836755B (en)
WO (1) WO2011053488A1 (en)

Cited By (12)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US9720864B2 (en) 2013-11-18 2017-08-01 Samsung Electronics Co., Ltd. Flexible server system
US10033664B2 (en) 2014-03-28 2018-07-24 Airbus Operations Gmbh Ethernet switch and method for establishing forwarding patterns in an Ethernet switch
US11467883B2 (en) 2004-03-13 2022-10-11 Iii Holdings 12, Llc Co-allocating a reservation spanning different compute resources types
US11494235B2 (en) 2004-11-08 2022-11-08 Iii Holdings 12, Llc System and method of providing system jobs within a compute environment
US11496415B2 (en) 2005-04-07 2022-11-08 Iii Holdings 12, Llc On-demand access to compute resources
US11522952B2 (en) 2007-09-24 2022-12-06 The Research Foundation For The State University Of New York Automatic clustering for self-organizing grids
US11526304B2 (en) 2009-10-30 2022-12-13 Iii Holdings 2, Llc Memcached server functionality in a cluster of data processing nodes
US11630704B2 (en) 2004-08-20 2023-04-18 Iii Holdings 12, Llc System and method for a workload management and scheduling module to manage access to a compute environment according to local and non-local user identity information
US11650857B2 (en) 2006-03-16 2023-05-16 Iii Holdings 12, Llc System and method for managing a hybrid computer environment
US11652706B2 (en) 2004-06-18 2023-05-16 Iii Holdings 12, Llc System and method for providing dynamic provisioning within a compute environment
US11658916B2 (en) 2005-03-16 2023-05-23 Iii Holdings 12, Llc Simple integration of an on-demand compute environment
US11720290B2 (en) 2009-10-30 2023-08-08 Iii Holdings 2, Llc Memcached server functionality in a cluster of data processing nodes

Families Citing this family (214)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US9876735B2 (en) 2009-10-30 2018-01-23 Iii Holdings 2, Llc Performance and power optimized computer system architectures and methods leveraging power optimized tree fabric interconnect
US9077654B2 (en) 2009-10-30 2015-07-07 Iii Holdings 2, Llc System and method for data center security enhancements leveraging managed server SOCs
US8599863B2 (en) * 2009-10-30 2013-12-03 Calxeda, Inc. System and method for using a multi-protocol fabric module across a distributed server interconnect fabric
US20110103391A1 (en) * 2009-10-30 2011-05-05 Smooth-Stone, Inc. C/O Barry Evans System and method for high-performance, low-power data center interconnect fabric
US9069929B2 (en) 2011-10-31 2015-06-30 Iii Holdings 2, Llc Arbitrating usage of serial port in node card of scalable and modular servers
US20130107444A1 (en) 2011-10-28 2013-05-02 Calxeda, Inc. System and method for flexible storage and networking provisioning in large scalable processor installations
US9465771B2 (en) 2009-09-24 2016-10-11 Iii Holdings 2, Llc Server on a chip and node cards comprising one or more of same
US9054990B2 (en) * 2009-10-30 2015-06-09 Iii Holdings 2, Llc System and method for data center security enhancements leveraging server SOCs or server fabrics
US9648102B1 (en) * 2012-12-27 2017-05-09 Iii Holdings 2, Llc Memcached server functionality in a cluster of data processing nodes
US9680770B2 (en) 2009-10-30 2017-06-13 Iii Holdings 2, Llc System and method for using a multi-protocol fabric module across a distributed server interconnect fabric
US9311269B2 (en) 2009-10-30 2016-04-12 Iii Holdings 2, Llc Network proxy for high-performance, low-power data center interconnect fabric
US8594100B2 (en) 2010-03-31 2013-11-26 International Business Machines Corporation Data frame forwarding using a distributed virtual bridge
US8358661B2 (en) * 2010-04-20 2013-01-22 International Business Machines Corporation Remote adapter configuration
US8619796B2 (en) 2010-04-22 2013-12-31 International Business Machines Corporation Forwarding data frames with a distributed fiber channel forwarder
WO2011156746A2 (en) * 2010-06-11 2011-12-15 California Institute Of Technology Systems and methods for rapid processing and storage of data
US9525647B2 (en) 2010-07-06 2016-12-20 Nicira, Inc. Network control apparatus and method for creating and modifying logical switching elements
US8830823B2 (en) 2010-07-06 2014-09-09 Nicira, Inc. Distributed control platform for large-scale production networks
US8447909B2 (en) 2010-07-19 2013-05-21 International Business Machines Corporation Register access in distributed virtual bridge environment
US8856321B2 (en) * 2011-03-31 2014-10-07 International Business Machines Corporation System to improve operation of a data center with heterogeneous computing clouds
US8924752B1 (en) 2011-04-20 2014-12-30 Apple Inc. Power management for a graphics processing unit or other circuit
US9066160B2 (en) * 2011-07-07 2015-06-23 Alcatel Lucent Apparatus and method for protection in a data center
US8612583B2 (en) * 2011-07-29 2013-12-17 Cisco Technology, Inc. Network management system scheduling for low power and lossy networks
CN102742251A (en) * 2011-08-11 2012-10-17 华为技术有限公司 A node aggregation system for implementing a symmetric multi-processing system
US8861400B2 (en) 2012-01-18 2014-10-14 International Business Machines Corporation Requesting multicast membership information in a distributed switch in response to a miss event
US8891535B2 (en) 2012-01-18 2014-11-18 International Business Machines Corporation Managing a global forwarding table in a distributed switch
US9128949B2 (en) 2012-01-18 2015-09-08 Cloudera, Inc. Memory allocation buffer for reduction of heap fragmentation
US20130250802A1 (en) * 2012-03-26 2013-09-26 Praveen Yalagandula Reducing cabling costs in a datacenter network
US9390461B1 (en) * 2012-05-08 2016-07-12 Apple Inc. Graphics hardware mode controls
US20130346655A1 (en) * 2012-06-22 2013-12-26 Advanced Micro Devices, Inc. Bus agent capable of supporting extended atomic operations and method therefor
CN102801599B (en) * 2012-07-26 2015-09-30 华为技术有限公司 A kind of communication means and system
US9699263B1 (en) 2012-08-17 2017-07-04 Sandisk Technologies Llc. Automatic read and write acceleration of data accessed by virtual machines
CN104903874A (en) * 2012-09-06 2015-09-09 百科容(科技)公司 Large-scale data storage and delivery system
US10454997B2 (en) * 2012-09-07 2019-10-22 Avigilon Corporation Distributed physical security system
US9507406B2 (en) 2012-09-21 2016-11-29 Atmel Corporation Configuring power domains of a microcontroller system
US9618991B1 (en) 2012-09-27 2017-04-11 Google Inc. Large-scale power back-up for data centers
US9537793B2 (en) * 2012-10-10 2017-01-03 Cisco Technology, Inc. Ensuring any-to-any reachability with opportunistic layer 3 forwarding in massive scale data center environments
US9170971B2 (en) 2012-12-26 2015-10-27 Iii Holdings 2, Llc Fabric discovery for a cluster of nodes
US11132277B2 (en) 2012-12-28 2021-09-28 Iii Holdings 2, Llc System and method for continuous low-overhead monitoring of distributed applications running on a cluster of data processing nodes
US9356884B2 (en) * 2013-01-17 2016-05-31 Cisco Technology, Inc. MSDC scaling through on-demand path update
US9372825B1 (en) * 2013-02-27 2016-06-21 Netapp, Inc. Global non-volatile solid-state cache in a network storage system
US9389940B2 (en) 2013-02-28 2016-07-12 Silicon Graphics International Corp. System and method for error logging
US9870830B1 (en) 2013-03-14 2018-01-16 Sandisk Technologies Llc Optimal multilevel sensing for reading data from a storage medium
KR102044023B1 (en) * 2013-03-14 2019-12-02 삼성전자주식회사 Data Storage System based on a key-value and Operating Method thereof
US20140344431A1 (en) * 2013-05-16 2014-11-20 Aspeed Technology Inc. Baseboard management system architecture
CN104166628B (en) * 2013-05-17 2018-05-18 华为技术有限公司 The methods, devices and systems of managing internal memory
CN103297560B (en) * 2013-05-21 2018-09-07 江苏中科羿链通信技术有限公司 A kind of method and server of data flow classification
US9330055B2 (en) * 2013-06-04 2016-05-03 International Business Machines Corporation Modular architecture for extreme-scale distributed processing applications
US9304577B2 (en) 2013-06-05 2016-04-05 Avago Technologies General Ip (Singapore) Pte. Ltd. Reducing power consumption and wakeup latency in SSD controllers by not resetting flash devices
US9477276B2 (en) * 2013-06-13 2016-10-25 Dell Products L.P. System and method for switch management
US9619389B1 (en) * 2013-07-11 2017-04-11 Unigen Corporation System for a backward and forward application environment compatible distributed shared coherent storage
US9146814B1 (en) * 2013-08-26 2015-09-29 Amazon Technologies, Inc. Mitigating an impact of a datacenter thermal event
US9639463B1 (en) 2013-08-26 2017-05-02 Sandisk Technologies Llc Heuristic aware garbage collection scheme in storage systems
US9383807B2 (en) 2013-10-01 2016-07-05 Atmel Corporation Configuring power domains of a microcontroller system
US9703816B2 (en) 2013-11-19 2017-07-11 Sandisk Technologies Llc Method and system for forward reference logging in a persistent datastore
US9582058B2 (en) 2013-11-29 2017-02-28 Sandisk Technologies Llc Power inrush management of storage devices
US9306863B2 (en) * 2013-12-06 2016-04-05 Intel Corporation Link transfer, bit error detection and link retry using flit bundles asynchronous to link fabric packets
KR200476881Y1 (en) * 2013-12-09 2015-04-10 네이버비즈니스플랫폼 주식회사 Booth apparatus for supplying cooling air
US9497283B2 (en) * 2013-12-13 2016-11-15 Oracle International Corporation System and method for providing data interoperability in a distributed data grid
US9654852B2 (en) * 2013-12-24 2017-05-16 Nec Corporation Scalable hybrid packet/circuit switching network architecture
US10313438B1 (en) * 2013-12-30 2019-06-04 Emc Corporation Partitioned key-value store with one-sided communications for secondary global key lookup by range-knowledgeable clients
CN105247814B (en) * 2013-12-30 2018-09-21 华为技术有限公司 The method and apparatus for managing the physical location of the network equipment
US9438435B2 (en) 2014-01-31 2016-09-06 Intenational Business Machines Corporation Secure, multi-tenancy aware and bandwidth-efficient data center multicast
US9734063B2 (en) 2014-02-27 2017-08-15 École Polytechnique Fédérale De Lausanne (Epfl) Scale-out non-uniform memory access
US9703636B2 (en) * 2014-03-01 2017-07-11 Sandisk Technologies Llc Firmware reversion trigger and control
US9547553B1 (en) 2014-03-10 2017-01-17 Parallel Machines Ltd. Data resiliency in a shared memory pool
US9626400B2 (en) 2014-03-31 2017-04-18 Sandisk Technologies Llc Compaction of information in tiered data structure
US9626399B2 (en) 2014-03-31 2017-04-18 Sandisk Technologies Llc Conditional updates for reducing frequency of data modification operations
US9697267B2 (en) 2014-04-03 2017-07-04 Sandisk Technologies Llc Methods and systems for performing efficient snapshots in tiered data structures
US9781027B1 (en) 2014-04-06 2017-10-03 Parallel Machines Ltd. Systems and methods to communicate with external destinations via a memory network
WO2015156788A1 (en) * 2014-04-09 2015-10-15 Hewlett-Packard Development Company, L.P. Identifying suspicious activity in a load test
US9965185B2 (en) 2015-01-20 2018-05-08 Ultrata, Llc Utilization of a distributed index to provide object memory fabric coherency
US9846658B2 (en) * 2014-04-21 2017-12-19 Cisco Technology, Inc. Dynamic temporary use of packet memory as resource memory
US9594688B1 (en) 2014-12-09 2017-03-14 Parallel Machines Ltd. Systems and methods for executing actions using cached data
US9529622B1 (en) 2014-12-09 2016-12-27 Parallel Machines Ltd. Systems and methods for automatic generation of task-splitting code
US9690713B1 (en) 2014-04-22 2017-06-27 Parallel Machines Ltd. Systems and methods for effectively interacting with a flash memory
US10050901B2 (en) * 2014-04-22 2018-08-14 Cisco Technology, Inc. Efficient management and configuration of in-band resources
WO2015167500A1 (en) * 2014-04-30 2015-11-05 Hewlett Packard Development Company, L.P. Flood disable on network switch
US9497140B2 (en) * 2014-05-14 2016-11-15 International Business Machines Corporation Autonomous multi-node network configuration and self-awareness through establishment of a switch port group
US9703491B2 (en) 2014-05-30 2017-07-11 Sandisk Technologies Llc Using history of unaligned writes to cache data and avoid read-modify-writes in a non-volatile storage device
US10656840B2 (en) 2014-05-30 2020-05-19 Sandisk Technologies Llc Real-time I/O pattern recognition to enhance performance and endurance of a storage device
US10372613B2 (en) 2014-05-30 2019-08-06 Sandisk Technologies Llc Using sub-region I/O history to cache repeatedly accessed sub-regions in a non-volatile storage device
US10114557B2 (en) 2014-05-30 2018-10-30 Sandisk Technologies Llc Identification of hot regions to enhance performance and endurance of a non-volatile storage device
US10146448B2 (en) 2014-05-30 2018-12-04 Sandisk Technologies Llc Using history of I/O sequences to trigger cached read ahead in a non-volatile storage device
US10162748B2 (en) 2014-05-30 2018-12-25 Sandisk Technologies Llc Prioritizing garbage collection and block allocation based on I/O history for logical address regions
US10656842B2 (en) 2014-05-30 2020-05-19 Sandisk Technologies Llc Using history of I/O sizes and I/O sequences to trigger coalesced writes in a non-volatile storage device
US9652381B2 (en) 2014-06-19 2017-05-16 Sandisk Technologies Llc Sub-block garbage collection
US9397939B2 (en) * 2014-06-24 2016-07-19 International Business Machines Corporation Hybrid approach for performance enhancing proxies
US9684367B2 (en) * 2014-06-26 2017-06-20 Atmel Corporation Power trace port for tracing states of power domains
US10382279B2 (en) * 2014-06-30 2019-08-13 Emc Corporation Dynamically composed compute nodes comprising disaggregated components
US9852138B2 (en) 2014-06-30 2017-12-26 EMC IP Holding Company LLC Content fabric for a distributed file system
US9720868B2 (en) * 2014-07-07 2017-08-01 Xilinx, Inc. Bridging inter-bus communications
US10133611B2 (en) * 2014-10-07 2018-11-20 Synopsys, Inc. Side channel communication hardware driver
US9588863B2 (en) * 2014-10-21 2017-03-07 International Business Machines Corporation Generation and application of stressmarks in a computer system
JP6525555B2 (en) * 2014-11-04 2019-06-05 キヤノン株式会社 INFORMATION PROCESSING APPARATUS, CONTROL METHOD THEREOF, AND PROGRAM
CN104378237A (en) * 2014-11-24 2015-02-25 英业达科技有限公司 Method for judging service node state
US9690705B1 (en) 2014-12-09 2017-06-27 Parallel Machines Ltd. Systems and methods for processing data sets according to an instructed order
US9781225B1 (en) 2014-12-09 2017-10-03 Parallel Machines Ltd. Systems and methods for cache streams
US9639473B1 (en) 2014-12-09 2017-05-02 Parallel Machines Ltd. Utilizing a cache mechanism by copying a data set from a cache-disabled memory location to a cache-enabled memory location
US9753873B1 (en) 2014-12-09 2017-09-05 Parallel Machines Ltd. Systems and methods for key-value transactions
US10298709B1 (en) * 2014-12-31 2019-05-21 EMC IP Holding Company LLC Performance of Hadoop distributed file system operations in a non-native operating system
EP3248097B1 (en) 2015-01-20 2022-02-09 Ultrata LLC Object memory data flow instruction execution
US9684689B2 (en) * 2015-02-03 2017-06-20 Ca, Inc. Distributed parallel processing system having jobs processed by nodes based on authentication using unique identification of data
US10169467B2 (en) * 2015-03-18 2019-01-01 Microsoft Technology Licensing, Llc Query formulation via task continuum
US9792248B2 (en) 2015-06-02 2017-10-17 Microsoft Technology Licensing, Llc Fast read/write between networked computers via RDMA-based RPC requests
US9886210B2 (en) 2015-06-09 2018-02-06 Ultrata, Llc Infinite memory fabric hardware implementation with router
US9971542B2 (en) 2015-06-09 2018-05-15 Ultrata, Llc Infinite memory fabric streams and APIs
US10698628B2 (en) 2015-06-09 2020-06-30 Ultrata, Llc Infinite memory fabric hardware implementation with memory
US10853277B2 (en) * 2015-06-24 2020-12-01 Intel Corporation Systems and methods for isolating input/output computing resources
US20160378344A1 (en) * 2015-06-24 2016-12-29 Intel Corporation Processor and platform assisted nvdimm solution using standard dram and consolidated storage
US10148592B1 (en) * 2015-06-29 2018-12-04 Amazon Technologies, Inc. Prioritization-based scaling of computing resources
US10021008B1 (en) 2015-06-29 2018-07-10 Amazon Technologies, Inc. Policy-based scaling of computing resource groups
US10034070B1 (en) * 2015-09-06 2018-07-24 Netronome Systems, Inc. Low cost multi-server array architecture
US10725963B2 (en) 2015-09-12 2020-07-28 Microsoft Technology Licensing, Llc Distributed lock-free RDMA-based memory allocation and de-allocation
US9658671B2 (en) * 2015-09-28 2017-05-23 Qualcomm Incorporated Power-aware CPU power grid design
US10713210B2 (en) 2015-10-13 2020-07-14 Microsoft Technology Licensing, Llc Distributed self-directed lock-free RDMA-based B-tree key-value manager
US9906370B2 (en) 2015-11-16 2018-02-27 International Business Machines Corporation Trust relationship management amongst racks in a data center
US10375167B2 (en) 2015-11-20 2019-08-06 Microsoft Technology Licensing, Llc Low latency RDMA-based distributed storage
US9985954B2 (en) 2015-11-25 2018-05-29 International Business Machines Corporation Sponsored trust relationship management between multiple racks
US10241676B2 (en) 2015-12-08 2019-03-26 Ultrata, Llc Memory fabric software implementation
US10235063B2 (en) 2015-12-08 2019-03-19 Ultrata, Llc Memory fabric operations and coherency using fault tolerant objects
CN115061971A (en) 2015-12-08 2022-09-16 乌尔特拉塔有限责任公司 Memory fabric operation and consistency using fault tolerant objects
CA3006773A1 (en) 2015-12-08 2017-06-15 Ultrata, Llc Memory fabric software implementation
US10523796B2 (en) * 2015-12-22 2019-12-31 Intel Corporation Techniques for embedding fabric address information into locally-administered Ethernet media access control addresses (MACs) and a multi-node fabric system implementing the same
CN105550157B (en) 2015-12-24 2017-06-27 中国科学院计算技术研究所 A kind of Fractal Tree structured communication structure, method, control device and intelligent chip
US10178027B2 (en) 2016-01-27 2019-01-08 Oracle International Corporation System and method for supporting inter subnet partitions in a high performance computing environment
US10536334B2 (en) 2016-01-28 2020-01-14 Oracle International Corporation System and method for supporting subnet number aliasing in a high performance computing environment
US10659340B2 (en) 2016-01-28 2020-05-19 Oracle International Corporation System and method for supporting VM migration between subnets in a high performance computing environment
US10616118B2 (en) 2016-01-28 2020-04-07 Oracle International Corporation System and method for supporting aggressive credit waiting in a high performance computing environment
US10374926B2 (en) 2016-01-28 2019-08-06 Oracle International Corporation System and method for monitoring logical network traffic flows using a ternary content addressable memory in a high performance computing environment
US10630816B2 (en) 2016-01-28 2020-04-21 Oracle International Corporation System and method for supporting shared multicast local identifiers (MILD) ranges in a high performance computing environment
US10171353B2 (en) 2016-03-04 2019-01-01 Oracle International Corporation System and method for supporting dual-port virtual router in a high performance computing environment
US9921997B2 (en) * 2016-04-01 2018-03-20 Intel Corporation Mechanism for PCIE cable topology discovery in a rack scale architecture environment
US10114790B2 (en) * 2016-05-17 2018-10-30 Microsemi Solutions (U.S.), Inc. Port mirroring for peripheral component interconnect express devices
US10713202B2 (en) * 2016-05-25 2020-07-14 Samsung Electronics Co., Ltd. Quality of service (QOS)-aware input/output (IO) management for peripheral component interconnect express (PCIE) storage system with reconfigurable multi-ports
US10762030B2 (en) * 2016-05-25 2020-09-01 Samsung Electronics Co., Ltd. Storage system, method, and apparatus for fast IO on PCIE devices
US10547412B2 (en) * 2016-06-30 2020-01-28 Cisco Technology, Inc. System and method to measure and score application health via correctable errors
US11042496B1 (en) * 2016-08-17 2021-06-22 Amazon Technologies, Inc. Peer-to-peer PCI topology
US10891253B2 (en) 2016-09-08 2021-01-12 Microsoft Technology Licensing, Llc Multicast apparatuses and methods for distributing data to multiple receivers in high-performance computing and cloud-based networks
US10606339B2 (en) * 2016-09-08 2020-03-31 Qualcomm Incorporated Coherent interconnect power reduction using hardware controlled split snoop directories
US10277677B2 (en) 2016-09-12 2019-04-30 Intel Corporation Mechanism for disaggregated storage class memory over fabric
EP3523721A1 (en) 2016-10-05 2019-08-14 Kaleao Limited Hyperscale architecture
EP3549350A4 (en) 2016-11-29 2021-03-24 Intel Corporation Technolgies for millimeter wave rack interconnects
US20180150256A1 (en) 2016-11-29 2018-05-31 Intel Corporation Technologies for data deduplication in disaggregated architectures
US10530643B2 (en) * 2016-12-09 2020-01-07 Lenovo Enterprise Solutions (Singapore) Pte. Ltd. Automatic management network provisioning
US10911261B2 (en) * 2016-12-19 2021-02-02 Intel Corporation Method, apparatus and system for hierarchical network on chip routing
US11153164B2 (en) 2017-01-04 2021-10-19 International Business Machines Corporation Live, in-line hardware component upgrades in disaggregated systems
US10534598B2 (en) 2017-01-04 2020-01-14 International Business Machines Corporation Rolling upgrades in disaggregated systems
US10394475B2 (en) 2017-03-01 2019-08-27 International Business Machines Corporation Method and system for memory allocation in a disaggregated memory architecture
US10228884B2 (en) 2017-03-08 2019-03-12 Hewlett Packard Enterprise Development Lp Issuing write requests to a fabric
US10686729B2 (en) 2017-03-29 2020-06-16 Fungible, Inc. Non-blocking any-to-any data center network with packet spraying over multiple alternate data paths
US10425707B2 (en) 2017-03-29 2019-09-24 Fungible, Inc. Non-blocking, full-mesh data center network having optical permutors
US10637685B2 (en) 2017-03-29 2020-04-28 Fungible, Inc. Non-blocking any-to-any data center network having multiplexed packet spraying within access node groups
WO2018191257A1 (en) 2017-04-10 2018-10-18 Fungible, Inc. Relay consistent memory management in a multiple processor system
US11216306B2 (en) * 2017-06-29 2022-01-04 Intel Corporation Technologies for dynamically sharing remote resources across remote computing nodes
EP3625939A1 (en) * 2017-07-10 2020-03-25 Fungible, Inc. Access node for data centers
EP3625679A1 (en) 2017-07-10 2020-03-25 Fungible, Inc. Data processing unit for stream processing
US10649829B2 (en) * 2017-07-10 2020-05-12 Hewlett Packard Enterprise Development Lp Tracking errors associated with memory access operations
US10757040B2 (en) 2017-07-11 2020-08-25 Cisco Technology, Inc. Efficient distribution of peer zone database in Fibre Channel fabric
US10489304B2 (en) 2017-07-14 2019-11-26 Arm Limited Memory address translation
US10353826B2 (en) 2017-07-14 2019-07-16 Arm Limited Method and apparatus for fast context cloning in a data processing system
US10565126B2 (en) 2017-07-14 2020-02-18 Arm Limited Method and apparatus for two-layer copy-on-write
US10613989B2 (en) 2017-07-14 2020-04-07 Arm Limited Fast address translation for virtual machines
US10467159B2 (en) 2017-07-14 2019-11-05 Arm Limited Memory node controller
US10592424B2 (en) 2017-07-14 2020-03-17 Arm Limited Range-based memory system
US10534719B2 (en) 2017-07-14 2020-01-14 Arm Limited Memory system for a data processing network
US10911405B1 (en) * 2017-07-31 2021-02-02 Amazon Technologies, Inc. Secure environment on a server
WO2019068010A1 (en) 2017-09-29 2019-04-04 Fungible, Inc. Network access node virtual fabrics configured dynamically over an underlay network
WO2019068017A1 (en) 2017-09-29 2019-04-04 Fungible, Inc. Resilient network communication using selective multipath packet flow spraying
US10841245B2 (en) 2017-11-21 2020-11-17 Fungible, Inc. Work unit stack data structures in multiple core processor system for stream data processing
KR102524290B1 (en) 2017-12-26 2023-04-21 현대자동차주식회사 Ethernet Switch, In-vehicle Network Configuration Method and Vehicle
US11321136B2 (en) * 2017-12-28 2022-05-03 Intel Corporation Techniques for collective operations in distributed systems
US10540288B2 (en) 2018-02-02 2020-01-21 Fungible, Inc. Efficient work unit processing in a multicore system
US10489331B2 (en) 2018-03-16 2019-11-26 Apple Inc. Remote service discovery and inter-process communication
US11016823B2 (en) 2018-03-16 2021-05-25 Apple Inc. Remote service discovery and inter-process communication
US10986043B1 (en) * 2018-03-30 2021-04-20 Facebook, Inc. Distributed network switches of data centers
US10608921B2 (en) 2018-04-19 2020-03-31 Cisco Technology, Inc. Routing in fat tree networks using negative disaggregation advertisements
US10841367B2 (en) 2018-05-17 2020-11-17 International Business Machines Corporation Optimizing dynamical resource allocations for cache-dependent workloads in disaggregated data centers
US10936374B2 (en) 2018-05-17 2021-03-02 International Business Machines Corporation Optimizing dynamic resource allocations for memory-dependent workloads in disaggregated data centers
US10601903B2 (en) 2018-05-17 2020-03-24 International Business Machines Corporation Optimizing dynamical resource allocations based on locality of resources in disaggregated data centers
US10893096B2 (en) 2018-05-17 2021-01-12 International Business Machines Corporation Optimizing dynamical resource allocations using a data heat map in disaggregated data centers
US10977085B2 (en) 2018-05-17 2021-04-13 International Business Machines Corporation Optimizing dynamical resource allocations in disaggregated data centers
US11330042B2 (en) 2018-05-17 2022-05-10 International Business Machines Corporation Optimizing dynamic resource allocations for storage-dependent workloads in disaggregated data centers
US11221886B2 (en) 2018-05-17 2022-01-11 International Business Machines Corporation Optimizing dynamical resource allocations for cache-friendly workloads in disaggregated data centers
US10891206B2 (en) * 2018-05-31 2021-01-12 International Business Machines Corporation Disaster recovery orchestration and capacity planning in disaggregated datacenters
US10719418B2 (en) 2018-05-31 2020-07-21 International Business Machines Corporation Replicating workload data according to a degree of resiliency for disaster recovery in disaggregated datacenters
US10983881B2 (en) 2018-05-31 2021-04-20 International Business Machines Corporation Disaster recovery and replication in disaggregated datacenters
US11036599B2 (en) 2018-05-31 2021-06-15 International Business Machines Corporation Disaster recovery and replication according to workload priorities in disaggregated datacenters
US11243846B2 (en) 2018-05-31 2022-02-08 International Business Machines Corporation Replicating workload and state data for disaster recovery in disaggregated datacenters
US10929035B2 (en) * 2018-07-18 2021-02-23 Sap Se Memory management via dynamic tiering pools
US10884850B2 (en) 2018-07-24 2021-01-05 Arm Limited Fault tolerant memory system
US10942861B2 (en) * 2018-07-30 2021-03-09 Micron Technology, Inc. Configurable logic block networks and managing coherent memory in the same
US10824215B2 (en) 2018-07-31 2020-11-03 Nutanix, Inc. Managing power budget of multiple computing node clusters in a computing rack system
US10977198B2 (en) 2018-09-12 2021-04-13 Micron Technology, Inc. Hybrid memory system interface
FR3087979B1 (en) * 2018-10-31 2021-08-06 Silkan Rt DATA TRANSMISSION SYSTEM
US10929175B2 (en) 2018-11-21 2021-02-23 Fungible, Inc. Service chaining hardware accelerators within a data stream processing integrated circuit
US10915370B2 (en) 2018-11-29 2021-02-09 International Business Machines Corporation Inter-host communication without data copy in disaggregated systems
US11038749B2 (en) * 2018-12-24 2021-06-15 Intel Corporation Memory resource allocation in an end-point device
US11301404B2 (en) * 2019-02-04 2022-04-12 American Megatrends International, Llc Enabling high availability in server SAN enabled storage box
US10884642B2 (en) * 2019-03-27 2021-01-05 Silicon Motion, Inc. Method and apparatus for performing data-accessing management in a storage server
US20200371692A1 (en) * 2019-05-22 2020-11-26 Microsoft Technology Licensing, Llc Memory disaggregation for compute nodes
EP3942757A4 (en) * 2019-05-23 2023-05-31 Hewlett Packard Enterprise Development LP System and method for facilitating data-driven intelligent network with flow control of individual applications and traffic flows
CN110149235B (en) * 2019-05-28 2020-11-24 中山大学 Tree-shaped network proxy system supporting multi-user and multi-network protocol and capable of being dynamically expanded
CN110188948B (en) * 2019-05-30 2022-03-08 广西防城港核电有限公司 Processing and guiding method for simulator fault
CN110399753A (en) * 2019-06-27 2019-11-01 苏州浪潮智能科技有限公司 A kind of control method, system, storage medium and the server of machine box for server lock
CN110719193B (en) * 2019-09-12 2021-02-02 无锡江南计算技术研究所 High-performance computing-oriented high-reliability universal tree network topology method and structure
CN112532501B (en) * 2019-09-18 2023-04-18 中国电信股份有限公司 Host physical address processing method and device and computer readable storage medium
US11184245B2 (en) 2020-03-06 2021-11-23 International Business Machines Corporation Configuring computing nodes in a three-dimensional mesh topology
CN115428409B (en) * 2020-04-24 2023-04-11 株式会社东阳特克尼卡 Packet capturing device and method
US11620254B2 (en) * 2020-06-03 2023-04-04 International Business Machines Corporation Remote direct memory access for container-enabled networks
US11853798B2 (en) 2020-09-03 2023-12-26 Microsoft Technology Licensing, Llc Disaggregated memory pool assignment
US11481116B2 (en) 2020-09-09 2022-10-25 Microsoft Technology Licensing, Llc Computing device with independently coherent nodes
CN113824632B (en) * 2021-09-03 2023-04-18 比威网络技术有限公司 Method and device for compressing path points in safe hierarchical multipath routing
CN114124814B (en) * 2021-11-19 2023-08-29 海光信息技术股份有限公司 Network on chip, control and configuration method, device, routing unit and equipment
WO2023128357A1 (en) * 2021-12-29 2023-07-06 한국과학기술원 Software-based simulator for disaggregated architecture system, and method therefor

Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5781187A (en) * 1994-05-31 1998-07-14 Advanced Micro Devices, Inc. Interrupt transmission via specialized bus cycle within a symmetrical multiprocessing system
US6711691B1 (en) * 1999-05-13 2004-03-23 Apple Computer, Inc. Power management for computer systems
US7673164B1 (en) * 2004-12-13 2010-03-02 Massachusetts Institute Of Technology Managing power in a parallel processing environment
US8060775B1 (en) * 2007-06-14 2011-11-15 Symantec Corporation Method and apparatus for providing dynamic multi-pathing (DMP) for an asymmetric logical unit access (ALUA) based storage system
US8122269B2 (en) * 2009-01-07 2012-02-21 International Business Machines Corporation Regulating power consumption in a multi-core processor by dynamically distributing power and processing requests by a managing core to a configuration of processing cores

Family Cites Families (361)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5594908A (en) 1989-12-27 1997-01-14 Hyatt; Gilbert P. Computer system having a serial keyboard, a serial display, and a dynamic memory with memory refresh
US5396635A (en) 1990-06-01 1995-03-07 Vadem Corporation Power conservation apparatus having multiple power reduction levels dependent upon the activity of the computer system
US5451936A (en) 1991-06-20 1995-09-19 The Johns Hopkins University Non-blocking broadcast network
JPH08123763A (en) 1994-10-26 1996-05-17 Nec Corp Memory assigning system for distributed processing system
US6055618A (en) * 1995-10-31 2000-04-25 Cray Research, Inc. Virtual maintenance network in multiprocessing system having a non-flow controlled virtual maintenance channel
JP3541335B2 (en) * 1996-06-28 2004-07-07 富士通株式会社 Information processing apparatus and distributed processing control method
US6842430B1 (en) * 1996-10-16 2005-01-11 Koninklijke Philips Electronics N.V. Method for configuring and routing data within a wireless multihop network and a wireless network for implementing the same
JP3662378B2 (en) * 1996-12-17 2005-06-22 川崎マイクロエレクトロニクス株式会社 Network repeater
US5908468A (en) 1997-10-24 1999-06-01 Advanced Micro Devices, Inc. Data transfer network on a chip utilizing a multiple traffic circle topology
US5968176A (en) 1997-05-29 1999-10-19 3Com Corporation Multilayer firewall system
US5971804A (en) 1997-06-30 1999-10-26 Emc Corporation Backplane having strip transmission line ethernet bus
US6507586B1 (en) 1997-09-18 2003-01-14 International Business Machines Corporation Multicast data transmission over a one-way broadband channel
KR100286375B1 (en) 1997-10-02 2001-04-16 윤종용 Radiator of electronic system and computer system having the same
US6252878B1 (en) * 1997-10-30 2001-06-26 Cisco Technology, Inc. Switched architecture access server
US5901048A (en) 1997-12-11 1999-05-04 International Business Machines Corporation Printed circuit board with chip collar
KR100250437B1 (en) * 1997-12-26 2000-04-01 정선종 Path control device for round robin arbitration and adaptation
US6192414B1 (en) 1998-01-27 2001-02-20 Moore Products Co. Network communications system manager
US8108508B1 (en) 1998-06-22 2012-01-31 Hewlett-Packard Development Company, L.P. Web server chip for network manageability
US6373841B1 (en) 1998-06-22 2002-04-16 Agilent Technologies, Inc. Integrated LAN controller and web server chip
US6181699B1 (en) * 1998-07-01 2001-01-30 National Semiconductor Corporation Apparatus and method of assigning VLAN tags
US6314501B1 (en) 1998-07-23 2001-11-06 Unisys Corporation Computer system and method for operating multiple operating systems in different partitions of the computer system and for allowing the different partitions to communicate with one another through shared memory
US6574238B1 (en) * 1998-08-26 2003-06-03 Intel Corporation Inter-switch link header modification
WO2000059240A1 (en) 1999-03-31 2000-10-05 British Telecommunications Public Limited Company Progressive routing in a communications network
US8346971B2 (en) * 1999-05-04 2013-01-01 At&T Intellectual Property I, Lp Data transfer, synchronising applications, and low latency networks
US7970929B1 (en) * 2002-03-19 2011-06-28 Dunti Llc Apparatus, system, and method for routing data to and from a host that is moved from one location on a communication system to another location on the communication system
US6442137B1 (en) 1999-05-24 2002-08-27 Advanced Micro Devices, Inc. Apparatus and method in a network switch for swapping memory access slots between gigabit port and expansion port
US7020695B1 (en) 1999-05-28 2006-03-28 Oracle International Corporation Using a cluster-wide shared repository to provide the latest consistent definition of the cluster (avoiding the partition-in time problem)
US6446192B1 (en) 1999-06-04 2002-09-03 Embrace Networks, Inc. Remote monitoring and control of equipment over computer networks using a single web interfacing chip
US6697359B1 (en) 1999-07-02 2004-02-24 Ancor Communications, Inc. High performance switch fabric element and switch systems
US7801132B2 (en) 1999-11-09 2010-09-21 Synchrodyne Networks, Inc. Interface system and methodology having scheduled connection responsive to common time reference
US6857026B1 (en) 1999-12-14 2005-02-15 Nortel Networks Limited Using alternate routes for fail-over in a communication network
US8171204B2 (en) 2000-01-06 2012-05-01 Super Talent Electronics, Inc. Intelligent solid-state non-volatile memory device (NVMD) system with multi-level caching of multiple channels
US6608564B2 (en) 2000-01-25 2003-08-19 Hewlett-Packard Development Company, L.P. Removable memory cartridge system for use with a server or other processor-based device
US20020107903A1 (en) 2000-11-07 2002-08-08 Richter Roger K. Methods and systems for the order serialization of information in a network processing environment
US6990063B1 (en) * 2000-03-07 2006-01-24 Cisco Technology, Inc. Distributing fault indications and maintaining and using a data structure indicating faults to route traffic in a packet switching system
US6556952B1 (en) 2000-05-04 2003-04-29 Advanced Micro Devices, Inc. Performance monitoring and optimizing of controller parameters
US7080078B1 (en) 2000-05-09 2006-07-18 Sun Microsystems, Inc. Mechanism and apparatus for URI-addressable repositories of service advertisements and other content in a distributed computing environment
US7143153B1 (en) 2000-11-09 2006-11-28 Ciena Corporation Internal network device dynamic health monitoring
JP2001333091A (en) * 2000-05-23 2001-11-30 Fujitsu Ltd Communication equipment
US6816750B1 (en) 2000-06-09 2004-11-09 Cirrus Logic, Inc. System-on-a-chip
US6668308B2 (en) 2000-06-10 2003-12-23 Hewlett-Packard Development Company, L.P. Scalable architecture based on single-chip multiprocessing
US6452809B1 (en) 2000-11-10 2002-09-17 Galactic Computing Corporation Scalable internet engine
US7032119B2 (en) 2000-09-27 2006-04-18 Amphus, Inc. Dynamic power and workload management for multi-server system
US6760861B2 (en) 2000-09-29 2004-07-06 Zeronines Technology, Inc. System, method and apparatus for data processing and storage to provide continuous operations independent of device failure or disaster
US7274705B2 (en) 2000-10-03 2007-09-25 Broadcom Corporation Method and apparatus for reducing clock speed and power consumption
US20020040425A1 (en) 2000-10-04 2002-04-04 David Chaiken Multi-dimensional integrated circuit connection network using LDT
US7165120B1 (en) 2000-10-11 2007-01-16 Sun Microsystems, Inc. Server node with interated networking capabilities
US6954463B1 (en) 2000-12-11 2005-10-11 Cisco Technology, Inc. Distributed packet processing architecture for network access servers
US7616646B1 (en) 2000-12-12 2009-11-10 Cisco Technology, Inc. Intraserver tag-switched distributed packet processing for network access servers
JP3532153B2 (en) 2000-12-22 2004-05-31 沖電気工業株式会社 Level shifter control circuit
AU2001297630A1 (en) 2000-12-29 2002-09-12 Ming Qiu Server array hardware architecture and system
US20020097732A1 (en) * 2001-01-19 2002-07-25 Tom Worster Virtual private network protocol
US6977939B2 (en) 2001-01-26 2005-12-20 Microsoft Corporation Method and apparatus for emulating ethernet functionality over a serial bus
US7339786B2 (en) 2001-03-05 2008-03-04 Intel Corporation Modular server architecture with Ethernet routed across a backplane utilizing an integrated Ethernet switch module
US7093280B2 (en) 2001-03-30 2006-08-15 Juniper Networks, Inc. Internet security system
US20030196126A1 (en) 2002-04-11 2003-10-16 Fung Henry T. System, method, and architecture for dynamic server power management and dynamic workload management for multi-server environment
US20020159437A1 (en) 2001-04-27 2002-10-31 Foster Michael S. Method and system for network configuration discovery in a network manager
US20020161917A1 (en) * 2001-04-30 2002-10-31 Shapiro Aaron M. Methods and systems for dynamic routing of data in a network
AU2002308616A1 (en) 2001-05-07 2002-11-18 Vitesse Semiconductor Corporation A system and a method for processing data packets or frames
US7161901B2 (en) 2001-05-07 2007-01-09 Vitesse Semiconductor Corporation Automatic load balancing in switch fabrics
US6766389B2 (en) 2001-05-18 2004-07-20 Broadcom Corporation System on a chip for networking
DE10127198A1 (en) 2001-06-05 2002-12-19 Infineon Technologies Ag Physical address provision method for processor system with virtual addressing uses hierarchy mapping process for conversion of virtual address
US6950895B2 (en) 2001-06-13 2005-09-27 Intel Corporation Modular server architecture
US6501660B1 (en) 2001-06-22 2002-12-31 Sun Microsystems, Inc. Reliable card detection in a CPCI system
US7159017B2 (en) * 2001-06-28 2007-01-02 Fujitsu Limited Routing mechanism for static load balancing in a partitioned computer system with a fully connected network
US7200662B2 (en) * 2001-07-06 2007-04-03 Juniper Networks, Inc. Integrated rule network management system
US6813676B1 (en) 2001-07-27 2004-11-02 Lsi Logic Corporation Host interface bypass on a fabric based array controller
US6944786B2 (en) * 2001-07-27 2005-09-13 International Business Machines Corporation Network node failover using multicast address or port
US6968470B2 (en) 2001-08-07 2005-11-22 Hewlett-Packard Development Company, L.P. System and method for power management in a server system
US6724635B2 (en) 2001-08-07 2004-04-20 Hewlett-Packard Development Company, L.P. LCD panel for a server system
US7325050B2 (en) 2001-09-19 2008-01-29 Dell Products L.P. System and method for strategic power reduction in a computer system
US7337333B2 (en) 2001-09-19 2008-02-26 Dell Products L.P. System and method for strategic power supply sequencing in a computer system with multiple processing resources and multiple power supplies
US6779086B2 (en) 2001-10-16 2004-08-17 International Business Machines Corporation Symmetric multiprocessor systems with an independent super-coherent cache directory
US7447197B2 (en) * 2001-10-18 2008-11-04 Qlogic, Corporation System and method of providing network node services
US8325716B2 (en) 2001-10-22 2012-12-04 Broadcom Corporation Data path optimization algorithm
US6963948B1 (en) 2001-11-01 2005-11-08 Advanced Micro Devices, Inc. Microcomputer bridge architecture with an embedded microcontroller
US7310319B2 (en) 2001-11-02 2007-12-18 Intel Corporation Multiple-domain processing system using hierarchically orthogonal switching fabric
US7464016B2 (en) 2001-11-09 2008-12-09 Sun Microsystems, Inc. Hot plug and hot pull system simulation
US7209657B1 (en) 2001-12-03 2007-04-24 Cheetah Omni, Llc Optical routing using a star switching fabric
US7599360B2 (en) * 2001-12-26 2009-10-06 Cisco Technology, Inc. Methods and apparatus for encapsulating a frame for transmission in a storage area network
US20030140190A1 (en) 2002-01-23 2003-07-24 Sun Microsystems, Inc. Auto-SCSI termination enable in a CPCI hot swap system
US7340777B1 (en) 2003-03-31 2008-03-04 Symantec Corporation In memory heuristic system and method for detecting viruses
US7284067B2 (en) 2002-02-20 2007-10-16 Hewlett-Packard Development Company, L.P. Method for integrated load balancing among peer servers
US20030172191A1 (en) 2002-02-22 2003-09-11 Williams Joel R. Coupling of CPU and disk drive to form a server and aggregating a plurality of servers into server farms
US7096377B2 (en) 2002-03-27 2006-08-22 Intel Corporation Method and apparatus for setting timing parameters
US20030202520A1 (en) * 2002-04-26 2003-10-30 Maxxan Systems, Inc. Scalable switch fabric system and apparatus for computer networks
US7095738B1 (en) * 2002-05-07 2006-08-22 Cisco Technology, Inc. System and method for deriving IPv6 scope identifiers and for mapping the identifiers into IPv6 addresses
US7353530B1 (en) 2002-05-10 2008-04-01 At&T Corp. Method and apparatus for assigning communication nodes to CMTS cards
US7161904B2 (en) 2002-06-04 2007-01-09 Fortinet, Inc. System and method for hierarchical metering in a virtual router based network switch
US7376125B1 (en) 2002-06-04 2008-05-20 Fortinet, Inc. Service processing switch
US7415723B2 (en) 2002-06-11 2008-08-19 Pandya Ashish A Distributed network security system and a hardware processor therefor
US7453870B2 (en) * 2002-06-12 2008-11-18 Intel Corporation Backplane for switch fabric
US7525904B1 (en) * 2002-06-20 2009-04-28 Cisco Technology, Inc. Redundant packet routing and switching device and method
US7180866B1 (en) * 2002-07-11 2007-02-20 Nortel Networks Limited Rerouting in connection-oriented communication networks and communication systems
US7039018B2 (en) * 2002-07-17 2006-05-02 Intel Corporation Technique to improve network routing using best-match and exact-match techniques
US7286544B2 (en) 2002-07-25 2007-10-23 Brocade Communications Systems, Inc. Virtualized multiport switch
US7286527B2 (en) 2002-07-26 2007-10-23 Brocade Communications Systems, Inc. Method and apparatus for round trip delay measurement in a bi-directional, point-to-point, serial data channel
US8295288B2 (en) 2002-07-30 2012-10-23 Brocade Communications System, Inc. Registered state change notification for a fibre channel network
US7055044B2 (en) 2002-08-12 2006-05-30 Hewlett-Packard Development Company, L.P. System and method for voltage management of a processor to optimize performance and power dissipation
EP1394985A1 (en) 2002-08-28 2004-03-03 Siemens Aktiengesellschaft Test method for network path between network elements in communication networks
US20110090633A1 (en) 2002-09-23 2011-04-21 Josef Rabinovitz Modular sata data storage device assembly
US7080283B1 (en) 2002-10-15 2006-07-18 Tensilica, Inc. Simultaneous real-time trace and debug for multiple processing core systems on a chip
US8199636B1 (en) * 2002-10-18 2012-06-12 Alcatel Lucent Bridged network system with traffic resiliency upon link failure
US7792113B1 (en) 2002-10-21 2010-09-07 Cisco Technology, Inc. Method and system for policy-based forwarding
US6661671B1 (en) 2002-11-27 2003-12-09 International Business Machines Corporation Apparatus, method and article of manufacture for determining power permission for a blade spanning power back planes
US7512788B2 (en) 2002-12-10 2009-03-31 International Business Machines Corporation Method and apparatus for anonymous group messaging in a distributed messaging system
US7917658B2 (en) 2003-01-21 2011-03-29 Emulex Design And Manufacturing Corporation Switching apparatus and method for link initialization in a shared I/O environment
US8024548B2 (en) 2003-02-18 2011-09-20 Christopher Joseph Daffron Integrated circuit microprocessor that constructs, at run time, integrated reconfigurable logic into persistent finite state machines from pre-compiled machine code instruction sequences
US7447147B2 (en) 2003-02-28 2008-11-04 Cisco Technology, Inc. Ethernet switch with configurable alarms
US7039771B1 (en) 2003-03-10 2006-05-02 Marvell International Ltd. Method and system for supporting multiple external serial port devices using a serial port controller in embedded disk controllers
US7216123B2 (en) * 2003-03-28 2007-05-08 Board Of Trustees Of The Leland Stanford Junior University Methods for ranking nodes in large directed graphs
US20040215650A1 (en) 2003-04-09 2004-10-28 Ullattil Shaji Interfaces and methods for group policy management
US7047372B2 (en) * 2003-04-15 2006-05-16 Newisys, Inc. Managing I/O accesses in multiprocessor systems
US20040215991A1 (en) 2003-04-23 2004-10-28 Dell Products L.P. Power-up of multiple processors when a voltage regulator module has failed
US7334064B2 (en) 2003-04-23 2008-02-19 Dot Hill Systems Corporation Application server blade for embedded storage appliance
US20040215864A1 (en) 2003-04-28 2004-10-28 International Business Machines Corporation Non-disruptive, dynamic hot-add and hot-remove of non-symmetric data processing system resources
US7685254B2 (en) 2003-06-10 2010-03-23 Pandya Ashish A Runtime adaptable search processor
US7400996B2 (en) 2003-06-26 2008-07-15 Benjamin Thomas Percer Use of I2C-based potentiometers to enable voltage rail variation under BMC control
US7512067B2 (en) 2003-07-21 2009-03-31 Qlogic, Corporation Method and system for congestion control based on optimum bandwidth allocation in a fibre channel switch
US7477655B2 (en) 2003-07-21 2009-01-13 Qlogic, Corporation Method and system for power control of fibre channel switches
US7894348B2 (en) 2003-07-21 2011-02-22 Qlogic, Corporation Method and system for congestion control in a fibre channel switch
US7646767B2 (en) 2003-07-21 2010-01-12 Qlogic, Corporation Method and system for programmable data dependant network routing
JP2005041127A (en) 2003-07-23 2005-02-17 Brother Ind Ltd Status information notification system, network terminal device and communication processing device
US7412588B2 (en) 2003-07-25 2008-08-12 International Business Machines Corporation Network processor system on chip with bridge coupling protocol converting multiprocessor macro core local bus to peripheral interfaces coupled system bus
US7353362B2 (en) 2003-07-25 2008-04-01 International Business Machines Corporation Multiprocessor subsystem in SoC with bridge between processor clusters interconnetion and SoC system bus
US7170315B2 (en) 2003-07-31 2007-01-30 Actel Corporation Programmable system on a chip
US7028125B2 (en) 2003-08-04 2006-04-11 Inventec Corporation Hot-pluggable peripheral input device coupling system
US7620736B2 (en) * 2003-08-08 2009-11-17 Cray Canada Corporation Network topology having nodes interconnected by extended diagonal links
US7512808B2 (en) 2003-08-29 2009-03-31 Trend Micro, Inc. Anti-computer viral agent suitable for innoculation of computing devices
US7934005B2 (en) 2003-09-08 2011-04-26 Koolspan, Inc. Subnet box
US7174470B2 (en) 2003-10-14 2007-02-06 Hewlett-Packard Development Company, L.P. Computer data bus interface control
JP2007507990A (en) 2003-10-14 2007-03-29 ラプター・ネツトワークス・テクノロジー・インコーポレイテツド Switching system with distributed switching structure
US7415543B2 (en) 2003-11-12 2008-08-19 Lsi Corporation Serial port initialization in storage system controllers
US7916638B2 (en) 2003-12-24 2011-03-29 Alcatel Lucent Time-independent deficit round robin method and system
US7380039B2 (en) * 2003-12-30 2008-05-27 3Tera, Inc. Apparatus, method and system for aggregrating computing resources
US7109760B1 (en) 2004-01-05 2006-09-19 Integrated Device Technology, Inc. Delay-locked loop (DLL) integrated circuits that support efficient phase locking of clock signals having non-unity duty cycles
EP1709530A2 (en) * 2004-01-20 2006-10-11 Broadcom Corporation System and method for supporting multiple users
JP4248420B2 (en) 2004-02-06 2009-04-02 日本電信電話株式会社 Handover control method for mobile communication network
US7664110B1 (en) 2004-02-07 2010-02-16 Habanero Holdings, Inc. Input/output controller for coupling the processor-memory complex to the fabric in fabric-backplane interprise servers
US7873693B1 (en) * 2004-02-13 2011-01-18 Habanero Holdings, Inc. Multi-chassis fabric-backplane enterprise servers
US7583661B2 (en) 2004-03-05 2009-09-01 Sid Chaudhuri Method and apparatus for improved IP networks and high-quality services
US7865582B2 (en) 2004-03-24 2011-01-04 Hewlett-Packard Development Company, L.P. System and method for assigning an application component to a computing resource
ITMI20040600A1 (en) 2004-03-26 2004-06-26 Atmel Corp DSP SYSTEM ON DOUBLE PROCESSOR WITH MOBILE COMB IN THE COMPLEX DOMAIN
EP1591906A1 (en) * 2004-04-27 2005-11-02 Texas Instruments Incorporated Efficient data transfer from an ASIC to a host using DMA
WO2005109718A1 (en) * 2004-05-05 2005-11-17 Gigamon Systems Llc Asymmetric packet switch and a method of use
US7203063B2 (en) 2004-05-21 2007-04-10 Hewlett-Packard Development Company, L.P. Small form factor liquid loop cooling system
ES2246702B2 (en) * 2004-06-02 2007-06-16 L &amp; M DATA COMMUNICATIONS, S.A. ETHERNET UNIVERSAL TELECOMMUNICATIONS SERVICE.
US7467358B2 (en) 2004-06-03 2008-12-16 Gwangju Institute Of Science And Technology Asynchronous switch based on butterfly fat-tree for network on chip application
EP1760895A4 (en) 2004-06-15 2011-07-06 Fujitsu Component Ltd Transceiver module
JP4334419B2 (en) 2004-06-30 2009-09-30 富士通株式会社 Transmission equipment
US7586904B2 (en) 2004-07-15 2009-09-08 Broadcom Corp. Method and system for a gigabit Ethernet IP telephone chip with no DSP core, which uses a RISC core with instruction extensions to support voice processing
US9264384B1 (en) 2004-07-22 2016-02-16 Oracle International Corporation Resource virtualization mechanism including virtual host bus adapters
JP4455206B2 (en) 2004-07-29 2010-04-21 キヤノン株式会社 Image forming apparatus and control method thereof
US7466712B2 (en) * 2004-07-30 2008-12-16 Brocade Communications Systems, Inc. System and method for providing proxy and translation domains in a fibre channel router
US7657756B2 (en) 2004-10-08 2010-02-02 International Business Machines Corporaiton Secure memory caching structures for data, integrity and version values
US7257655B1 (en) 2004-10-13 2007-08-14 Altera Corporation Embedded PCI-Express implementation
US7802023B2 (en) 2004-10-15 2010-09-21 Sony Computer Entertainment Inc. Methods and apparatus for supporting multiple configurations in a multi-processor system
US7620057B1 (en) * 2004-10-19 2009-11-17 Broadcom Corporation Cache line replacement with zero latency
US20060090025A1 (en) 2004-10-25 2006-04-27 Tufford Robert C 9U payload module configurations
US7760720B2 (en) * 2004-11-09 2010-07-20 Cisco Technology, Inc. Translating native medium access control (MAC) addresses to hierarchical MAC addresses and their use
US7644215B2 (en) 2004-11-10 2010-01-05 Tekelec Methods and systems for providing management in a telecommunications equipment shelf assembly using a shared serial bus
US7278582B1 (en) 2004-12-03 2007-10-09 Sun Microsystems, Inc. Hardware security module (HSM) chip card
TWM270514U (en) 2004-12-27 2005-07-11 Quanta Comp Inc Blade server system
US8533777B2 (en) 2004-12-29 2013-09-10 Intel Corporation Mechanism to determine trust of out-of-band management agents
US7676841B2 (en) 2005-02-01 2010-03-09 Fmr Llc Network intrusion mitigation
JP4489030B2 (en) * 2005-02-07 2010-06-23 株式会社ソニー・コンピュータエンタテインメント Method and apparatus for providing a secure boot sequence within a processor
US8140770B2 (en) 2005-02-10 2012-03-20 International Business Machines Corporation Data processing system and method for predictively selecting a scope of broadcast of an operation
US7467306B2 (en) 2005-03-08 2008-12-16 Hewlett-Packard Development Company, L.P. Methods and systems for allocating power to an electronic device
US7881332B2 (en) 2005-04-01 2011-02-01 International Business Machines Corporation Configurable ports for a host ethernet adapter
JP4591185B2 (en) 2005-04-28 2010-12-01 株式会社日立製作所 Server device
US7363463B2 (en) 2005-05-13 2008-04-22 Microsoft Corporation Method and system for caching address translations from multiple address spaces in virtual machines
US7586841B2 (en) * 2005-05-31 2009-09-08 Cisco Technology, Inc. System and method for protecting against failure of a TE-LSP tail-end node
US7596144B2 (en) 2005-06-07 2009-09-29 Broadcom Corp. System-on-a-chip (SoC) device with integrated support for ethernet, TCP, iSCSI, RDMA, and network application acceleration
US8200739B2 (en) 2005-06-23 2012-06-12 Telefonaktiebolaget L M Ericsson (Publ) Arrangement and method relating to load distribution
JP2007012000A (en) 2005-07-04 2007-01-18 Hitachi Ltd Storage controller and storage system
US7307837B2 (en) 2005-08-23 2007-12-11 International Business Machines Corporation Method and apparatus for enforcing of power control in a blade center chassis
US7461274B2 (en) 2005-08-23 2008-12-02 International Business Machines Corporation Method for maximizing server utilization in a resource constrained environment
US7315456B2 (en) 2005-08-29 2008-01-01 Hewlett-Packard Development Company, L.P. Configurable IO subsystem
US8982778B2 (en) * 2005-09-19 2015-03-17 Qualcomm Incorporated Packet routing in a wireless communications environment
US7382154B2 (en) 2005-10-03 2008-06-03 Honeywell International Inc. Reconfigurable network on a chip
US8516165B2 (en) 2005-10-19 2013-08-20 Nvidia Corporation System and method for encoding packet header to enable higher bandwidth efficiency across bus links
US7574590B2 (en) 2005-10-26 2009-08-11 Sigmatel, Inc. Method for booting a system on a chip integrated circuit
CN100417118C (en) 2005-10-28 2008-09-03 华为技术有限公司 System and method for renewing network mobile node position in wireless net-like network
CN2852260Y (en) 2005-12-01 2006-12-27 华为技术有限公司 Server
EP1808994A1 (en) 2006-01-12 2007-07-18 Alcatel Lucent Universal switch for transporting packet data frames
EP1977311A2 (en) 2006-01-13 2008-10-08 Sun Microsystems, Inc. Compact rackmount storage server
EP1977635A2 (en) 2006-01-13 2008-10-08 Sun Microsystems, Inc. Modular blade server
US20070174390A1 (en) * 2006-01-20 2007-07-26 Avise Partners Customer service management
US7991817B2 (en) 2006-01-23 2011-08-02 California Institute Of Technology Method and a circuit using an associative calculator for calculating a sequence of non-associative operations
US20070180310A1 (en) 2006-02-02 2007-08-02 Texas Instruments, Inc. Multi-core architecture with hardware messaging
US7606225B2 (en) * 2006-02-06 2009-10-20 Fortinet, Inc. Integrated security switch
US20070226795A1 (en) * 2006-02-09 2007-09-27 Texas Instruments Incorporated Virtual cores and hardware-supported hypervisor integrated circuits, systems, methods and processes of manufacture
US9177176B2 (en) 2006-02-27 2015-11-03 Broadcom Corporation Method and system for secure system-on-a-chip architecture for multimedia data processing
US20090133129A1 (en) 2006-03-06 2009-05-21 Lg Electronics Inc. Data transferring method
FR2898753B1 (en) 2006-03-16 2008-04-18 Commissariat Energie Atomique SEMI-DISTRIBUTED CONTROL CHIP SYSTEM
US7555666B2 (en) 2006-05-04 2009-06-30 Dell Products L.P. Power profiling application for managing power allocation in an information handling system
JP2007304687A (en) 2006-05-09 2007-11-22 Hitachi Ltd Cluster constitution and its control means
US7660922B2 (en) 2006-05-12 2010-02-09 Intel Corporation Mechanism to flexibly support multiple device numbers on point-to-point interconnect upstream ports
US20070280230A1 (en) * 2006-05-31 2007-12-06 Motorola, Inc Method and system for service discovery across a wide area network
US7522468B2 (en) 2006-06-08 2009-04-21 Unity Semiconductor Corporation Serial memory interface
CN101094125A (en) * 2006-06-23 2007-12-26 华为技术有限公司 Exchange structure in ATCA / ATCA300 expanded exchange bandwidth
US7693072B2 (en) * 2006-07-13 2010-04-06 At&T Intellectual Property I, L.P. Method and apparatus for configuring a network topology with alternative communication paths
US20080040463A1 (en) 2006-08-08 2008-02-14 International Business Machines Corporation Communication System for Multiple Chassis Computer Systems
CN101127696B (en) 2006-08-15 2012-06-27 华为技术有限公司 Data forwarding method for layer 2 network and network and node devices
EP1892913A1 (en) * 2006-08-24 2008-02-27 Siemens Aktiengesellschaft Method and arrangement for providing a wireless mesh network
US20080052437A1 (en) 2006-08-28 2008-02-28 Dell Products L.P. Hot Plug Power Policy for Modular Chassis
US7802082B2 (en) 2006-08-31 2010-09-21 Intel Corporation Methods and systems to dynamically configure computing apparatuses
US8599685B2 (en) * 2006-09-26 2013-12-03 Cisco Technology, Inc. Snooping of on-path IP reservation protocols for layer 2 nodes
US7853754B1 (en) 2006-09-29 2010-12-14 Tilera Corporation Caching in multicore and multiprocessor architectures
US8684802B1 (en) 2006-10-27 2014-04-01 Oracle America, Inc. Method and apparatus for balancing thermal variations across a set of computer systems
US8447872B2 (en) 2006-11-01 2013-05-21 Intel Corporation Load balancing in a storage system
US7992151B2 (en) 2006-11-30 2011-08-02 Intel Corporation Methods and apparatuses for core allocations
WO2008070191A2 (en) * 2006-12-06 2008-06-12 Fusion Multisystems, Inc. (Dba Fusion-Io) Apparatus, system, and method for a reconfigurable baseboard management controller
US20080140771A1 (en) * 2006-12-08 2008-06-12 Sony Computer Entertainment Inc. Simulated environment computing framework
US20080140930A1 (en) 2006-12-08 2008-06-12 Emulex Design & Manufacturing Corporation Virtual drive mapping
US8271604B2 (en) * 2006-12-19 2012-09-18 International Business Machines Corporation Initializing shared memories for sharing endpoints across a plurality of root complexes
CN101212345A (en) 2006-12-31 2008-07-02 联想(北京)有限公司 Blade server management system
US8407428B2 (en) 2010-05-20 2013-03-26 Hicamp Systems, Inc. Structured memory coprocessor
US8504791B2 (en) 2007-01-26 2013-08-06 Hicamp Systems, Inc. Hierarchical immutable content-addressable memory coprocessor
JP5106020B2 (en) 2007-02-08 2012-12-26 パナソニック株式会社 Pattern formation method
US7865614B2 (en) 2007-02-12 2011-01-04 International Business Machines Corporation Method and apparatus for load balancing with server state change awareness
FI120088B (en) 2007-03-01 2009-06-30 Kone Corp Arrangement and method of monitoring the security circuit
US7870907B2 (en) 2007-03-08 2011-01-18 Weatherford/Lamb, Inc. Debris protection for sliding sleeve
JP4370336B2 (en) 2007-03-09 2009-11-25 株式会社日立製作所 Low power consumption job management method and computer system
US20080239649A1 (en) 2007-03-29 2008-10-02 Bradicich Thomas M Design structure for an interposer for expanded capability of a blade server chassis system
US7783910B2 (en) 2007-03-30 2010-08-24 International Business Machines Corporation Method and system for associating power consumption of a server with a network address assigned to the server
US20090097200A1 (en) 2007-04-11 2009-04-16 Viswa Sharma Modular blade for providing scalable mechanical, electrical and environmental functionality in the enterprise using advancedtca boards
JP4815385B2 (en) 2007-04-13 2011-11-16 株式会社日立製作所 Storage device
US7515412B2 (en) 2007-04-26 2009-04-07 Enermax Technology Corporation Cooling structure for power supply
US7715400B1 (en) 2007-04-26 2010-05-11 3 Leaf Networks Node identification for distributed shared memory system
US7925795B2 (en) 2007-04-30 2011-04-12 Broadcom Corporation Method and system for configuring a plurality of network interfaces that share a physical interface
DE102007020296A1 (en) 2007-04-30 2008-11-13 Philip Behrens Device and method for the wireless production of a contact
PT103744A (en) * 2007-05-16 2008-11-17 Coreworks S A ARCHITECTURE OF ACCESS TO THE NETWORK CORE.
US7552241B2 (en) 2007-05-18 2009-06-23 Tilera Corporation Method and system for managing a plurality of I/O interfaces with an array of multicore processor resources in a semiconductor chip
US7693167B2 (en) * 2007-05-22 2010-04-06 Rockwell Collins, Inc. Mobile nodal based communication system, method and apparatus
WO2008147926A1 (en) 2007-05-25 2008-12-04 Venkat Konda Fully connected generalized butterfly fat tree networks
US20080294851A1 (en) * 2007-05-25 2008-11-27 Nokia Corporation Method, apparatus, computer program product, and system for management of shared memory
US8141143B2 (en) * 2007-05-31 2012-03-20 Imera Systems, Inc. Method and system for providing remote access to resources in a secure data center over a network
US7783813B2 (en) 2007-06-14 2010-08-24 International Business Machines Corporation Multi-node configuration of processor cards connected via processor fabrics
JP4962152B2 (en) 2007-06-15 2012-06-27 日立電線株式会社 Opto-electric composite transmission assembly
US8140719B2 (en) 2007-06-21 2012-03-20 Sea Micro, Inc. Dis-aggregated and distributed data-center architecture using a direct interconnect fabric
EP2009554A1 (en) * 2007-06-25 2008-12-31 Stmicroelectronics SA Method for transferring data from a source target to a destination target, and corresponding network interface
US7761687B2 (en) 2007-06-26 2010-07-20 International Business Machines Corporation Ultrascalable petaflop parallel supercomputer
US8060760B2 (en) 2007-07-13 2011-11-15 Dell Products L.P. System and method for dynamic information handling system prioritization
US7688578B2 (en) 2007-07-19 2010-03-30 Hewlett-Packard Development Company, L.P. Modular high-density computer system
WO2009023563A1 (en) 2007-08-10 2009-02-19 Smith Robert B Path redundant hardware efficient communications interconnect system
CN101369958A (en) * 2007-08-15 2009-02-18 华为技术有限公司 Fast rerouting method and label exchange router
US7840703B2 (en) * 2007-08-27 2010-11-23 International Business Machines Corporation System and method for dynamically supporting indirect routing within a multi-tiered full-graph interconnect architecture
US7921686B2 (en) 2007-08-28 2011-04-12 Cisco Technology, Inc. Highly scalable architecture for application network appliances
US7898941B2 (en) * 2007-09-11 2011-03-01 Polycom, Inc. Method and system for assigning a plurality of MACs to a plurality of processors
US20090080428A1 (en) * 2007-09-25 2009-03-26 Maxxan Systems, Inc. System and method for scalable switch fabric for computer network
US20090251867A1 (en) 2007-10-09 2009-10-08 Sharma Viswa N Reconfigurable, modularized fpga-based amc module
US7739475B2 (en) 2007-10-24 2010-06-15 Inventec Corporation System and method for updating dirty data of designated raw device
US7822841B2 (en) 2007-10-30 2010-10-26 Modern Grids, Inc. Method and system for hosting multiple, customized computing clusters
EP2061191A1 (en) 2007-11-13 2009-05-20 STMicroelectronics (Grenoble) SAS Buffering architecture for packet injection and extraction in on-chip networks.
US8068433B2 (en) 2007-11-26 2011-11-29 Microsoft Corporation Low power operation of networked devices
US7877622B2 (en) 2007-12-13 2011-01-25 International Business Machines Corporation Selecting between high availability redundant power supply modes for powering a computer system
US7962771B2 (en) 2007-12-31 2011-06-14 Intel Corporation Method, system, and apparatus for rerouting interrupts in a multi-core processor
US8345431B2 (en) 2008-01-02 2013-01-01 Microelectronics Assembly Technologies, Inc. Thin multi-chip flex module
US7779148B2 (en) 2008-02-01 2010-08-17 International Business Machines Corporation Dynamic routing based on information of not responded active source requests quantity received in broadcast heartbeat signal and stored in local data structure for other processor chips
US8015379B2 (en) * 2008-02-01 2011-09-06 International Business Machines Corporation Wake-and-go mechanism with exclusive system bus response
US20090204837A1 (en) 2008-02-11 2009-08-13 Udaykumar Raval Power control system and method
US20090204834A1 (en) 2008-02-11 2009-08-13 Nvidia Corporation System and method for using inputs as wake signals
US8854831B2 (en) 2012-04-10 2014-10-07 Arnouse Digital Devices Corporation Low power, high density server and portable device for use with same
US8082400B1 (en) 2008-02-26 2011-12-20 Hewlett-Packard Development Company, L.P. Partitioning a memory pool among plural computing nodes
US8156362B2 (en) 2008-03-11 2012-04-10 Globalfoundries Inc. Hardware monitoring and decision making for transitioning in and out of low-power state
TWI354213B (en) 2008-04-01 2011-12-11 Inventec Corp Server
US20090259864A1 (en) 2008-04-10 2009-10-15 Nvidia Corporation System and method for input/output control during power down mode
US8762759B2 (en) 2008-04-10 2014-06-24 Nvidia Corporation Responding to interrupts while in a reduced power state
BRPI0910949B1 (en) 2008-04-16 2020-09-15 Telefonaktiebolaget Lm Ericsson (Publ) METHOD AND SYSTEM FOR DETECTING AND CORRECTING INCOMPATIBILITY, AND, MAINTENANCE ASSOCIATION END POINT
US7742844B2 (en) 2008-04-21 2010-06-22 Dell Products, Lp Information handling system including cooling devices and methods of use thereof
JP5075727B2 (en) 2008-04-25 2012-11-21 株式会社日立製作所 Stream distribution system and failure detection method
US7861110B2 (en) 2008-04-30 2010-12-28 Egenera, Inc. System, method, and adapter for creating fault-tolerant communication busses from standard components
US7725603B1 (en) 2008-04-30 2010-05-25 Network Appliance, Inc. Automatic network cluster path management
US20090282419A1 (en) 2008-05-09 2009-11-12 International Business Machines Corporation Ordered And Unordered Network-Addressed Message Control With Embedded DMA Commands For A Network On Chip
US7921315B2 (en) 2008-05-09 2011-04-05 International Business Machines Corporation Managing power consumption in a data center based on monitoring circuit breakers
US9391874B2 (en) * 2008-05-12 2016-07-12 Telefonaktiebolaget L M Ericsson (Publ) Re-routing traffic in a communications network
US20100008038A1 (en) 2008-05-15 2010-01-14 Giovanni Coglitore Apparatus and Method for Reliable and Efficient Computing Based on Separating Computing Modules From Components With Moving Parts
WO2009140631A2 (en) 2008-05-15 2009-11-19 Smooth-Stone, Inc. Distributed computing system with universal address system and method
US8775718B2 (en) 2008-05-23 2014-07-08 Netapp, Inc. Use of RDMA to access non-volatile solid-state memory in a network storage system
US7519843B1 (en) 2008-05-30 2009-04-14 International Business Machines Corporation Method and system for dynamic processor speed control to always maximize processor performance based on processing load and available power
US7904345B2 (en) 2008-06-10 2011-03-08 The Go Daddy Group, Inc. Providing website hosting overage protection by transference to an overflow server
US8244918B2 (en) 2008-06-11 2012-08-14 International Business Machines Corporation Resource sharing expansion card
IL192140A0 (en) 2008-06-12 2009-02-11 Ethos Networks Ltd Method and system for transparent lan services in a packet network
US8886985B2 (en) 2008-07-07 2014-11-11 Raritan Americas, Inc. Automatic discovery of physical connectivity between power outlets and IT equipment
WO2010009164A2 (en) 2008-07-14 2010-01-21 The Regents Of The University Of California Architecture to enable energy savings in networked computers
US20100026408A1 (en) 2008-07-30 2010-02-04 Jeng-Jye Shau Signal transfer for ultra-high capacity circuits
US8031703B2 (en) 2008-08-14 2011-10-04 Dell Products, Lp System and method for dynamic maintenance of fabric subsets in a network
US8132034B2 (en) 2008-08-28 2012-03-06 Dell Products L.P. System and method for managing information handling system power supply capacity utilization based on load sharing power loss
US8804710B2 (en) 2008-12-29 2014-08-12 Juniper Networks, Inc. System architecture for a scalable and distributed multi-stage switch fabric
JP5428267B2 (en) 2008-09-26 2014-02-26 富士通株式会社 Power supply control system and power supply control method
US8484493B2 (en) 2008-10-29 2013-07-09 Dell Products, Lp Method for pre-chassis power multi-slot blade identification and inventory
US8068482B2 (en) 2008-11-13 2011-11-29 Qlogic, Corporation Method and system for network switch element
US10255463B2 (en) 2008-11-17 2019-04-09 International Business Machines Corporation Secure computer architecture
JP5151924B2 (en) 2008-11-19 2013-02-27 富士通株式会社 Power management proxy device, server device, server power management method using proxy device, proxy device power management program, server device power management program
US20100161909A1 (en) 2008-12-18 2010-06-24 Lsi Corporation Systems and Methods for Quota Management in a Memory Appliance
US20100158005A1 (en) * 2008-12-23 2010-06-24 Suvhasis Mukhopadhyay System-On-a-Chip and Multi-Chip Systems Supporting Advanced Telecommunication Functions
US20100169479A1 (en) 2008-12-26 2010-07-01 Electronics And Telecommunications Research Institute Apparatus and method for extracting user information using client-based script
US8918488B2 (en) 2009-02-04 2014-12-23 Citrix Systems, Inc. Methods and systems for automated management of virtual resources in a cloud computing environment
US8510744B2 (en) 2009-02-24 2013-08-13 Siemens Product Lifecycle Management Software Inc. Using resource defining attributes to enhance thread scheduling in processors
GB2468137A (en) 2009-02-25 2010-09-01 Advanced Risc Mach Ltd Blade server with on board battery power
JP5816407B2 (en) 2009-02-27 2015-11-18 ルネサスエレクトロニクス株式会社 Semiconductor integrated circuit device
US8725946B2 (en) 2009-03-23 2014-05-13 Ocz Storage Solutions, Inc. Mass storage system and method of using hard disk, solid-state media, PCIe edge connector, and raid controller
US8140871B2 (en) 2009-03-27 2012-03-20 International Business Machines Corporation Wake on Lan for blade server
TWI358016B (en) 2009-04-17 2012-02-11 Inventec Corp Server
US8127128B2 (en) 2009-05-04 2012-02-28 International Business Machines Corporation Synchronization of swappable module in modular system
TWM377621U (en) 2009-05-25 2010-04-01 Advantech Co Ltd Interface card with hardware monitor and function extension, computer device and single board
US8004922B2 (en) 2009-06-05 2011-08-23 Nxp B.V. Power island with independent power characteristics for memory and logic
US9001846B2 (en) 2009-06-09 2015-04-07 Broadcom Corporation Physical layer device with dual medium access controller path
US8321688B2 (en) * 2009-06-12 2012-11-27 Microsoft Corporation Secure and private backup storage and processing for trusted computing and data services
US8745238B2 (en) 2009-07-17 2014-06-03 Hewlett-Packard Development Company, L.P. Virtual hot inserting functions in a shared I/O environment
CN101989212B (en) 2009-07-31 2015-01-07 国际商业机器公司 Method and device for providing virtual machine management program for starting blade server
US8340120B2 (en) 2009-09-04 2012-12-25 Brocade Communications Systems, Inc. User selectable multiple protocol network interface device
US8934347B1 (en) * 2009-09-21 2015-01-13 Tilera Corporation Low latency dynamic route selection
US9054990B2 (en) 2009-10-30 2015-06-09 Iii Holdings 2, Llc System and method for data center security enhancements leveraging server SOCs or server fabrics
US8599863B2 (en) 2009-10-30 2013-12-03 Calxeda, Inc. System and method for using a multi-protocol fabric module across a distributed server interconnect fabric
US9465771B2 (en) 2009-09-24 2016-10-11 Iii Holdings 2, Llc Server on a chip and node cards comprising one or more of same
US9876735B2 (en) 2009-10-30 2018-01-23 Iii Holdings 2, Llc Performance and power optimized computer system architectures and methods leveraging power optimized tree fabric interconnect
US20110103391A1 (en) 2009-10-30 2011-05-05 Smooth-Stone, Inc. C/O Barry Evans System and method for high-performance, low-power data center interconnect fabric
TW201112936A (en) 2009-09-29 2011-04-01 Inventec Corp Electronic device
US9014198B2 (en) 2009-10-05 2015-04-21 Vss Monitoring, Inc. Apparatus and system for aggregating captured network traffic
US8194659B2 (en) 2009-10-06 2012-06-05 Red Hat, Inc. Mechanism for processing messages using logical addresses
US8571031B2 (en) 2009-10-07 2013-10-29 Intel Corporation Configurable frame processing pipeline in a packet switch
US9680770B2 (en) 2009-10-30 2017-06-13 Iii Holdings 2, Llc System and method for using a multi-protocol fabric module across a distributed server interconnect fabric
US9311269B2 (en) 2009-10-30 2016-04-12 Iii Holdings 2, Llc Network proxy for high-performance, low-power data center interconnect fabric
US9767070B2 (en) 2009-11-06 2017-09-19 Hewlett Packard Enterprise Development Lp Storage system with a memory blade that generates a computational result for a storage device
US20110119344A1 (en) 2009-11-17 2011-05-19 Susan Eustis Apparatus And Method For Using Distributed Servers As Mainframe Class Computers
US20110191514A1 (en) 2010-01-29 2011-08-04 Inventec Corporation Server system
JP5648926B2 (en) 2010-02-01 2015-01-07 日本電気株式会社 Network system, controller, and network control method
TW201128395A (en) 2010-02-08 2011-08-16 Hon Hai Prec Ind Co Ltd Computer motherboard
US20110210975A1 (en) 2010-02-26 2011-09-01 Xgi Technology, Inc. Multi-screen signal processing device and multi-screen system
US8397092B2 (en) 2010-03-24 2013-03-12 Emulex Design & Manufacturing Corporation Power management for input/output devices by creating a virtual port for redirecting traffic
KR101641108B1 (en) 2010-04-30 2016-07-20 삼성전자주식회사 Target device providing debugging functionality and test system comprising the same
US8045328B1 (en) 2010-05-04 2011-10-25 Chenbro Micom Co., Ltd. Server and cooler moduel arrangement
US8839238B2 (en) 2010-06-11 2014-09-16 International Business Machines Corporation Dynamic virtual machine shutdown without service interruptions
US8830823B2 (en) 2010-07-06 2014-09-09 Nicira, Inc. Distributed control platform for large-scale production networks
US8812400B2 (en) 2010-07-09 2014-08-19 Hewlett-Packard Development Company, L.P. Managing a memory segment using a memory virtual appliance
CN103026669B (en) 2010-08-20 2015-07-01 日本电气株式会社 Communication system, control apparatus, and communication method
CN102385417B (en) 2010-08-25 2013-02-20 英业达股份有限公司 Rack-mounted server
JP2012053504A (en) 2010-08-31 2012-03-15 Hitachi Ltd Blade server device
US8601288B2 (en) 2010-08-31 2013-12-03 Sonics, Inc. Intelligent power controller
WO2012037494A1 (en) 2010-09-16 2012-03-22 Calxeda, Inc. Performance and power optimized computer system architectures and methods leveraging power optimized tree fabric interconnect
US8688899B2 (en) * 2010-09-28 2014-04-01 Fusion-Io, Inc. Apparatus, system, and method for an interface between a memory controller and a non-volatile memory controller using a command protocol
US20120081850A1 (en) 2010-09-30 2012-04-05 Dell Products L.P. Rack Assembly for Housing and Providing Power to Information Handling Systems
US8941981B2 (en) 2010-10-22 2015-01-27 Xplore Technologies Corp. Computer with high intensity screen
US8738860B1 (en) 2010-10-25 2014-05-27 Tilera Corporation Computing in parallel processing environments
DE102011056141A1 (en) 2010-12-20 2012-06-21 Samsung Electronics Co., Ltd. A negative voltage generator, decoder, non-volatile memory device and memory system using a negative voltage
US20120198252A1 (en) 2011-02-01 2012-08-02 Kirschtein Phillip M System and Method for Managing and Detecting Server Power Connections
US8670450B2 (en) 2011-05-13 2014-03-11 International Business Machines Corporation Efficient software-based private VLAN solution for distributed virtual switches
US8806090B2 (en) * 2011-05-31 2014-08-12 Micron Technology, Inc. Apparatus including buffer allocation management and related methods
US8547825B2 (en) 2011-07-07 2013-10-01 International Business Machines Corporation Switch fabric management
US8683125B2 (en) 2011-11-01 2014-03-25 Hewlett-Packard Development Company, L.P. Tier identification (TID) for tiered memory characteristics
US9565132B2 (en) 2011-12-27 2017-02-07 Intel Corporation Multi-protocol I/O interconnect including a switching fabric
WO2013101142A1 (en) * 2011-12-30 2013-07-04 Intel Corporation Low latency cluster computing
US8782321B2 (en) 2012-02-08 2014-07-15 Intel Corporation PCI express tunneling over a multi-protocol I/O interconnect
US8954698B2 (en) * 2012-04-13 2015-02-10 International Business Machines Corporation Switching optically connected memory
US20130290643A1 (en) 2012-04-30 2013-10-31 Kevin T. Lim Using a cache in a disaggregated memory architecture
US20130290650A1 (en) 2012-04-30 2013-10-31 Jichuan Chang Distributed active data storage system
US9286472B2 (en) 2012-05-22 2016-03-15 Xockets, Inc. Efficient packet handling, redirection, and inspection using offload processors
US20140115278A1 (en) * 2012-10-23 2014-04-24 Analog Devices, Inc. Memory architecture
US9304896B2 (en) 2013-08-05 2016-04-05 Iii Holdings 2, Llc Remote memory ring buffers in a cluster of data processing nodes

Patent Citations (5)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US5781187A (en) * 1994-05-31 1998-07-14 Advanced Micro Devices, Inc. Interrupt transmission via specialized bus cycle within a symmetrical multiprocessing system
US6711691B1 (en) * 1999-05-13 2004-03-23 Apple Computer, Inc. Power management for computer systems
US7673164B1 (en) * 2004-12-13 2010-03-02 Massachusetts Institute Of Technology Managing power in a parallel processing environment
US8060775B1 (en) * 2007-06-14 2011-11-15 Symantec Corporation Method and apparatus for providing dynamic multi-pathing (DMP) for an asymmetric logical unit access (ALUA) based storage system
US8122269B2 (en) * 2009-01-07 2012-02-21 International Business Machines Corporation Regulating power consumption in a multi-core processor by dynamically distributing power and processing requests by a managing core to a configuration of processing cores

Cited By (23)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US11467883B2 (en) 2004-03-13 2022-10-11 Iii Holdings 12, Llc Co-allocating a reservation spanning different compute resources types
US11652706B2 (en) 2004-06-18 2023-05-16 Iii Holdings 12, Llc System and method for providing dynamic provisioning within a compute environment
US11630704B2 (en) 2004-08-20 2023-04-18 Iii Holdings 12, Llc System and method for a workload management and scheduling module to manage access to a compute environment according to local and non-local user identity information
US11656907B2 (en) 2004-11-08 2023-05-23 Iii Holdings 12, Llc System and method of providing system jobs within a compute environment
US11886915B2 (en) 2004-11-08 2024-01-30 Iii Holdings 12, Llc System and method of providing system jobs within a compute environment
US11861404B2 (en) 2004-11-08 2024-01-02 Iii Holdings 12, Llc System and method of providing system jobs within a compute environment
US11762694B2 (en) 2004-11-08 2023-09-19 Iii Holdings 12, Llc System and method of providing system jobs within a compute environment
US11709709B2 (en) 2004-11-08 2023-07-25 Iii Holdings 12, Llc System and method of providing system jobs within a compute environment
US11537434B2 (en) 2004-11-08 2022-12-27 Iii Holdings 12, Llc System and method of providing system jobs within a compute environment
US11537435B2 (en) 2004-11-08 2022-12-27 Iii Holdings 12, Llc System and method of providing system jobs within a compute environment
US11494235B2 (en) 2004-11-08 2022-11-08 Iii Holdings 12, Llc System and method of providing system jobs within a compute environment
US11658916B2 (en) 2005-03-16 2023-05-23 Iii Holdings 12, Llc Simple integration of an on-demand compute environment
US11533274B2 (en) 2005-04-07 2022-12-20 Iii Holdings 12, Llc On-demand access to compute resources
US11496415B2 (en) 2005-04-07 2022-11-08 Iii Holdings 12, Llc On-demand access to compute resources
US11765101B2 (en) 2005-04-07 2023-09-19 Iii Holdings 12, Llc On-demand access to compute resources
US11831564B2 (en) 2005-04-07 2023-11-28 Iii Holdings 12, Llc On-demand access to compute resources
US11522811B2 (en) 2005-04-07 2022-12-06 Iii Holdings 12, Llc On-demand access to compute resources
US11650857B2 (en) 2006-03-16 2023-05-16 Iii Holdings 12, Llc System and method for managing a hybrid computer environment
US11522952B2 (en) 2007-09-24 2022-12-06 The Research Foundation For The State University Of New York Automatic clustering for self-organizing grids
US11720290B2 (en) 2009-10-30 2023-08-08 Iii Holdings 2, Llc Memcached server functionality in a cluster of data processing nodes
US11526304B2 (en) 2009-10-30 2022-12-13 Iii Holdings 2, Llc Memcached server functionality in a cluster of data processing nodes
US9720864B2 (en) 2013-11-18 2017-08-01 Samsung Electronics Co., Ltd. Flexible server system
US10033664B2 (en) 2014-03-28 2018-07-24 Airbus Operations Gmbh Ethernet switch and method for establishing forwarding patterns in an Ethernet switch

Also Published As

Publication number Publication date
EP3070894B1 (en) 2018-07-25
US20130022040A1 (en) 2013-01-24
US20130044587A1 (en) 2013-02-21
US8745302B2 (en) 2014-06-03
CN104836755A (en) 2015-08-12
US20110103391A1 (en) 2011-05-05
US9454403B2 (en) 2016-09-27
US9008079B2 (en) 2015-04-14
JP2013509808A (en) 2013-03-14
EP2494748B1 (en) 2016-04-20
US20160373354A1 (en) 2016-12-22
CN105357152A (en) 2016-02-24
KR101516216B1 (en) 2015-05-04
WO2011053488A1 (en) 2011-05-05
US9075655B2 (en) 2015-07-07
CN102668473A (en) 2012-09-12
US9262225B2 (en) 2016-02-16
US8737410B2 (en) 2014-05-27
EP2494748A1 (en) 2012-09-05
US20150071113A1 (en) 2015-03-12
KR20120095405A (en) 2012-08-28
US20160239415A1 (en) 2016-08-18
EP2494748A4 (en) 2013-07-03
US20130089104A1 (en) 2013-04-11
CN104836755B (en) 2018-06-15
US9866477B2 (en) 2018-01-09
US10135731B2 (en) 2018-11-20
US20140359044A1 (en) 2014-12-04
US9405584B2 (en) 2016-08-02
US20130097448A1 (en) 2013-04-18
CN102668473B (en) 2015-12-16
US20130094499A1 (en) 2013-04-18
EP3070894A1 (en) 2016-09-21

Similar Documents

Publication Publication Date Title
US8737410B2 (en) System and method for high-performance, low-power data center interconnect fabric
US9977763B2 (en) Network proxy for high-performance, low-power data center interconnect fabric
US11588624B2 (en) Technologies for load balancing a network
US11625335B2 (en) Adaptive address translation caches
US10205653B2 (en) Fabric discovery for a cluster of nodes
US10877695B2 (en) Memcached server functionality in a cluster of data processing nodes
CN113810312B (en) System and method for managing memory resources
US10254987B2 (en) Disaggregated memory appliance having a management processor that accepts request from a plurality of hosts for management, configuration and provisioning of memory
US9648102B1 (en) Memcached server functionality in a cluster of data processing nodes
EP3198806B1 (en) Network communications using pooled memory in rack-scale architecture
US20160124872A1 (en) Disaggregated memory appliance
US11720290B2 (en) Memcached server functionality in a cluster of data processing nodes
EP3531633B1 (en) Technologies for load balancing a network

Legal Events

Date Code Title Description
AS Assignment

Owner name: CALXEDA, INC., TEXAS

Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNORS:DAVIS, MARK BRADLEY;BORLAND, DAVID JAMES;REEL/FRAME:029750/0032

Effective date: 20130130

AS Assignment

Owner name: SILICON VALLEY BANK, CALIFORNIA

Free format text: SECURITY AGREEMENT;ASSIGNOR:CALXEDA, INC.;REEL/FRAME:030292/0207

Effective date: 20130422

STCB Information on status: application discontinuation

Free format text: ABANDONED -- FAILURE TO RESPOND TO AN OFFICE ACTION

AS Assignment

Owner name: SILICON VALLEY BANK, CALIFORNIA

Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNOR:CALXEDA, INC.;REEL/FRAME:033281/0855

Effective date: 20140701

Owner name: CALXEDA, INC., TEXAS

Free format text: RELEASE OF SECURITY INTEREST;ASSIGNOR:SILICON VALLEY BANK;REEL/FRAME:033281/0887

Effective date: 20140703

AS Assignment

Owner name: SILICON VALLEY BANK, CALIFORNIA

Free format text: CORRECTIVE ASSIGNMENT TO CORRECT THE INCORRECT APPL. NO. 13/708,340 PREVIOUSLY RECORDED AT REEL: 030292 FRAME: 0207. ASSIGNOR(S) HEREBY CONFIRMS THE SECURITY AGREEMENT;ASSIGNOR:CALXEDA, INC.;REEL/FRAME:035121/0172

Effective date: 20130422