US20140201409A1 - Offload processor modules for connection to system memory, and corresponding methods and systems - Google Patents

Offload processor modules for connection to system memory, and corresponding methods and systems Download PDF

Info

Publication number
US20140201409A1
US20140201409A1 US13/913,409 US201313913409A US2014201409A1 US 20140201409 A1 US20140201409 A1 US 20140201409A1 US 201313913409 A US201313913409 A US 201313913409A US 2014201409 A1 US2014201409 A1 US 2014201409A1
Authority
US
United States
Prior art keywords
processor
memory
data
module
offload
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
US13/913,409
Inventor
Parin Bhadrik Dalal
Stephen Paul Belair
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.)
XOCKETS Inc
Xockets IP LLC
Original Assignee
Xockets IP LLC
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 Xockets IP LLC filed Critical Xockets IP LLC
Priority to US13/913,409 priority Critical patent/US20140201409A1/en
Publication of US20140201409A1 publication Critical patent/US20140201409A1/en
Assigned to Xockets IP, LLC reassignment Xockets IP, LLC NUNC PRO TUNC ASSIGNMENT (SEE DOCUMENT FOR DETAILS). Assignors: BELAIR, STEPHEN PAUL, DALAL, PARIN BHADRIK
Assigned to XOCKETS, INC. reassignment XOCKETS, INC. ASSIGNMENT OF ASSIGNORS INTEREST (SEE DOCUMENT FOR DETAILS). Assignors: Xockets IP, LLC
Abandoned legal-status Critical Current

Links

Images

Classifications

    • 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
    • G06F13/16Handling requests for interconnection or transfer for access to memory bus
    • G06F13/1605Handling requests for interconnection or transfer for access to memory bus based on arbitration
    • G06F13/1652Handling requests for interconnection or transfer for access to memory bus based on arbitration in a multiprocessor architecture
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F12/00Accessing, addressing or allocating within memory systems or architectures
    • G06F12/02Addressing or allocation; Relocation
    • G06F12/08Addressing or allocation; Relocation in hierarchically structured memory systems, e.g. virtual memory systems
    • G06F12/0802Addressing of a memory level in which the access to the desired data or data block requires associative addressing means, e.g. caches
    • G06F12/0806Multiuser, multiprocessor or multiprocessing cache systems
    • G06F12/0815Cache consistency protocols
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F12/00Accessing, addressing or allocating within memory systems or architectures
    • G06F12/02Addressing or allocation; Relocation
    • G06F12/08Addressing or allocation; Relocation in hierarchically structured memory systems, e.g. virtual memory systems
    • G06F12/0802Addressing of a memory level in which the access to the desired data or data block requires associative addressing means, e.g. caches
    • G06F12/0875Addressing of a memory level in which the access to the desired data or data block requires associative addressing means, e.g. caches with dedicated cache, e.g. instruction or stack
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F12/00Accessing, addressing or allocating within memory systems or architectures
    • G06F12/02Addressing or allocation; Relocation
    • G06F12/08Addressing or allocation; Relocation in hierarchically structured memory systems, e.g. virtual memory systems
    • G06F12/10Address translation
    • G06F12/1027Address translation using associative or pseudo-associative address translation means, e.g. translation look-aside buffer [TLB]
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F12/00Accessing, addressing or allocating within memory systems or architectures
    • G06F12/02Addressing or allocation; Relocation
    • G06F12/08Addressing or allocation; Relocation in hierarchically structured memory systems, e.g. virtual memory systems
    • G06F12/10Address translation
    • G06F12/1081Address translation for peripheral access to main memory, e.g. direct memory access [DMA]
    • 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
    • G06F13/16Handling requests for interconnection or transfer for access to memory bus
    • 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
    • G06F13/28Handling requests for interconnection or transfer for access to input/output bus using burst mode transfer, e.g. direct memory access DMA, cycle steal
    • G06F13/285Halt processor DMA
    • 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
    • G06F13/36Handling requests for interconnection or transfer for access to common bus or bus system
    • G06F13/362Handling requests for interconnection or transfer for access to common bus or bus system with centralised access control
    • 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
    • G06F13/4004Coupling between buses
    • G06F13/4022Coupling between buses using switching circuits, e.g. switching matrix, connection or expansion network
    • 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
    • G06F13/4063Device-to-bus coupling
    • G06F13/4068Electrical coupling
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F15/00Digital computers in general; Data processing equipment in general
    • G06F15/16Combinations of two or more digital computers each having at least an arithmetic unit, a program unit and a register, e.g. for a simultaneous processing of several programs
    • G06F15/161Computing infrastructure, e.g. computer clusters, blade chassis or hardware partitioning
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F15/00Digital computers in general; Data processing equipment in general
    • G06F15/16Combinations of two or more digital computers each having at least an arithmetic unit, a program unit and a register, e.g. for a simultaneous processing of several programs
    • G06F15/163Interprocessor communication
    • G06F15/173Interprocessor communication using an interconnection network, e.g. matrix, shuffle, pyramid, star, snowflake
    • G06F15/17337Direct connection machines, e.g. completely connected computers, point to point communication networks
    • 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
    • G06F9/30Arrangements for executing machine instructions, e.g. instruction decode
    • G06F9/38Concurrent instruction execution, e.g. pipeline, look ahead
    • G06F9/3877Concurrent instruction execution, e.g. pipeline, look ahead using a slave processor, e.g. coprocessor
    • 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
    • G06F9/461Saving or restoring of program or task context
    • 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
    • G06F9/48Program initiating; Program switching, e.g. by interrupt
    • G06F9/4806Task transfer initiation or dispatching
    • G06F9/4843Task transfer initiation or dispatching by program, e.g. task dispatcher, supervisor, operating system
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L47/00Traffic control in data switching networks
    • H04L47/10Flow control; Congestion control
    • H04L47/19Flow control; Congestion control at layers above the network layer
    • H04L47/193Flow control; Congestion control at layers above the network layer at the transport layer, e.g. TCP related
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L47/00Traffic control in data switching networks
    • H04L47/10Flow control; Congestion control
    • H04L47/24Traffic characterised by specific attributes, e.g. priority or QoS
    • H04L47/2441Traffic characterised by specific attributes, e.g. priority or QoS relying on flow classification, e.g. using integrated services [IntServ]
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L47/00Traffic control in data switching networks
    • H04L47/50Queue scheduling
    • H04L47/56Queue scheduling implementing delay-aware scheduling
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L47/00Traffic control in data switching networks
    • H04L47/50Queue scheduling
    • H04L47/62Queue scheduling characterised by scheduling criteria
    • H04L47/624Altering the ordering of packets in an individual queue
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L47/00Traffic control in data switching networks
    • H04L47/50Queue scheduling
    • H04L47/62Queue scheduling characterised by scheduling criteria
    • H04L47/6295Queue scheduling characterised by scheduling criteria using multiple queues, one for each individual QoS, connection, flow or priority
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L49/00Packet switching elements
    • H04L49/90Buffering arrangements
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L61/00Network arrangements, protocols or services for addressing or naming
    • H04L61/09Mapping addresses
    • H04L61/10Mapping addresses of different types
    • H04L61/103Mapping addresses of different types across network layers, e.g. resolution of network layer into physical layer addresses or address resolution protocol [ARP]
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L61/00Network arrangements, protocols or services for addressing or naming
    • H04L61/09Mapping addresses
    • H04L61/25Mapping addresses of the same type
    • H04L61/2503Translation of Internet protocol [IP] addresses
    • H04L61/2592Translation of Internet protocol [IP] addresses using tunnelling or encapsulation
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L67/00Network arrangements or protocols for supporting network services or applications
    • H04L67/01Protocols
    • H04L67/10Protocols in which an application is distributed across nodes in the network
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L67/00Network arrangements or protocols for supporting network services or applications
    • H04L67/01Protocols
    • H04L67/10Protocols in which an application is distributed across nodes in the network
    • H04L67/1097Protocols in which an application is distributed across nodes in the network for distributed storage of data in networks, e.g. transport arrangements for network file system [NFS], storage area networks [SAN] or network attached storage [NAS]
    • GPHYSICS
    • G06COMPUTING; CALCULATING OR COUNTING
    • G06FELECTRIC DIGITAL DATA PROCESSING
    • G06F2212/00Indexing scheme relating to accessing, addressing or allocation within memory systems or architectures
    • G06F2212/10Providing a specific technical effect
    • G06F2212/1016Performance improvement
    • G06F2212/1024Latency reduction
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L2101/00Indexing scheme associated with group H04L61/00
    • H04L2101/60Types of network addresses
    • H04L2101/686Types of network addresses using dual-stack hosts, e.g. in Internet protocol version 4 [IPv4]/Internet protocol version 6 [IPv6] networks
    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04LTRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
    • H04L49/00Packet switching elements
    • H04L49/40Constructional details, e.g. power supply, mechanical construction or backplane
    • 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

Definitions

  • the present invention relates generally to processing modules, and more particularly to offload processing modules that can be physically connected to a system memory bus to process data independent of a host processor of the system.
  • IO input/output
  • Servers can run multiple applications, each associated with a specific state running on the server.
  • Common server applications include an Apache web server, a MySQL database application, PHP hypertext preprocessing, video or audio processing with Kaltura supported software, packet filters, application cache, management and application switches, accounting, analytics, and logging.
  • servers can be limited by computational and memory storage costs associated with switching between applications.
  • the overhead associated with storing the session state of each application can result in poor performance due to constant switching between applications.
  • Dividing applications between multiple processor cores can help alleviate the application switching problem, but does not eliminate it.
  • Advanced processors often only have eight to sixteen cores, while hundreds of application or session states may be required.
  • Enterprises also store and process their large amounts of data in a variety of ways.
  • One manner in which enterprises store data is by using relational databases and corresponding relational database management systems (RDBMS).
  • RDBMS relational database management systems
  • structured data may be collected, normalized, formatted and stored in an RDBMS.
  • Tools based on standardized data languages such as the Structured Query Language (SQL) may be used for accessing and processing structured data.
  • SQL Structured Query Language
  • it is estimated that such formatted structured data represents only a tiny fraction of an enterprise's stored data.
  • All organizations are becoming increasingly aware that substantial information and knowledge resides in unstructured data (i.e. “Big Data”) repositories. Accordingly, simple and effective access to both structured and unstructured data are seen as necessary for maximizing the value of enterprise informational resources.
  • SAN In-memory processing and Storage Area Network (SAN)-like architecture are used for traditional SQL queries, while commodity or shared nothing architectures (each computing node, consisting of a processor, local memory, and disk resources, shares nothing with other nodes in the computing cluster) are usually used for processing unstructured data.
  • SAN Storage Area Network
  • a computing system architecture, hardware, and operational method that supports input-output (IO) intensive networked applications, as well as structured and unstructured data queries is needed.
  • IO input-output
  • Such a system needs to readily handle high throughput data processing, be able to provide high parallelism for dividing tasks among multiple processors, and further provide efficient context switching to support multiple users or applications.
  • FIG. 1-0 shows a system according to an embodiment.
  • FIG. 1-1 shows a system flow according to an embodiment.
  • FIGS. 2-0 to 2 - 3 show processor modules according to various embodiments.
  • FIG. 2-4 shows a conventional dual-in-line memory module.
  • FIG. 2-5 shows a system according to another embodiment.
  • FIGS. 2-6 to 2 - 11 show processor module operations according to an embodiment.
  • FIG. 2-12 shows a method according to an embodiment.
  • FIG. 2-13 shows a method according to another embodiment.
  • FIG. 3 shows protocol stacks for processors according to embodiments.
  • FIG. 4 shows a partitioning of system loads according to an embodiment.
  • FIG. 5 shows a partitioning of system loads according to another embodiment.
  • FIG. 6 shows a method according to another embodiment.
  • offload processors are included on offload modules that connect to a system memory bus.
  • Such offload processors are in addition to any host processors connected to the system memory bus, and can operate on data transferred over the system memory bus independent of any host processors.
  • offload processors have access to a low latency memory, which can enable rapid storage and retrieval of context data for rapid context switching.
  • processing modules can populate physical slots for connecting in-line memory modules (e.g., DIMMs) to a system memory bus.
  • computing tasks can be automatically executed by offload processors according to data embedded within write data received over the system memory bus.
  • write data can include a “metadata” portion that identifies how the write data is to be processed.
  • FIG. 2-0 is a block diagram of a processing module 200 according to one embodiment.
  • a processing module 200 can include a physical in-line module connector 202 , a memory interface 204 , arbiter logic 206 , offload processor(s) 208 , local memory 210 , and control logic 212 .
  • a connector 202 can provide a physical connection to system memory bus. This is in contrast to a host processor which can access a system memory bus via a memory controller, or the like.
  • a connector 202 can be compatible with a dual in-line memory module (DIMM) slot of a computing system. Accordingly, a system including multiple DIMM slots can be populated with one or more processing modules 200 , or a mix of processing modules and DIMM modules.
  • DIMM dual in-line memory module
  • a memory interface 204 can detect data transfers on a system memory bus, and in appropriate cases, enable write data to be stored in the processing module 200 and/or read data to be read out from the processing module 200 .
  • a memory interface 204 can be a slave interface, thus data transfers are controlled by a master device separate from the processing module.
  • a memory interface 204 can be a direct memory access (DMA) slave, to accommodate DMA transfers over a system memory initiated by a DMA master.
  • DMA master can be a device different from a host processor.
  • processing module 200 can receive data for processing (e.g., DMA write), and transfer processed data out (e.g., DMA read) without consuming host processor resources.
  • Arbiter logic 206 can arbitrate between conflicting accesses of data within processing module 200 .
  • arbiter logic 206 can arbitrate between accesses by offload processor 208 and accesses external to the processor module 200 .
  • a processing module 200 can include multiple locations that are operated on at the same time.
  • accesses arbitrated by arbiter logic 206 can include accesses to physical system memory space occupied by the processor module 200 , as well as accesses to resources (e.g., processor resources).
  • arbitration rules for arbiter logic 206 can vary according to application. In some embodiments, such arbitration rules are fixed for a given processor module 200 . In such cases, different applications can be accommodated by switching out different processing modules. However, in alternate embodiments, such arbitration rules can be configurable.
  • Offload processor 208 can include one or more processors that can operate on data transferred over the system memory bus.
  • offload processors can run a general operating system which can run an application, such as Apache (as but one very particular example), enabling processor contexts to be saved and retrieved. Computing tasks executed by offload processor 208 can be handled by the hardware scheduler.
  • Offload processors 208 can operate on data buffered in the processor module 200 .
  • offload processors 208 can access data stored elsewhere in a system memory space.
  • offload processors 208 can include a cache memory configured to store context information.
  • An offload processor 208 can include multiple cores or one core.
  • a processor module 200 can be included in a system having a host processor (not shown).
  • offload processors 208 can be a different type of processor as compared to the host processor.
  • offload processors 208 can consume less power and/or have less computing power than a host processor.
  • offload processors 208 can be “wimpy” core processors, while a host processor can be a “brawny” core processor.
  • offload processors 208 can have equivalent computing power to any host processor.
  • a host processor can be an x86 type processor, while an offload processor 208 can include an ARM, ARC, Tensilica, MIPS, Strong/ARM, or RISC type processor, as but a few examples.
  • Local memory 210 can be connected to offload processor 208 to enable the storing of context information. Accordingly, an offload processor 208 can store current context information, and then switch to a new computing task, then subsequently retrieve the context information to resume the prior task.
  • local memory 210 can be a low latency memory with respect to other memories in a system.
  • storing of context information can include copying an offload processor 208 cache.
  • a same space within local memory 210 is accessible by multiple offload processors 208 of the same type. In this way, a context stored by one offload processor can be resumed by a different offload processor.
  • Control logic 212 can control processing tasks executed by offload processor(s).
  • control logic 212 can be considered a hardware scheduler that can be conceptualized as including a data evaluator 214 , scheduler 216 and a switch controller 218 .
  • a data evaluator 214 can extract “metadata” from write data transferred over a system memory bus.
  • “Metadata”, as used herein, can be any information embedded at one or more predetermined locations of a block of write data that indicates processing to be performed on all or a portion of the block of write data and/or indicate a particular task/process to which the data belongs (e.g., classification data).
  • metadata can be data that indicates a higher level organization for the block of write data.
  • metadata can be header information of one or more network packets (which may or may not be encapsulated within a higher layer packet structure).
  • a scheduler 216 can order computing tasks for offload processor(s) 208 .
  • scheduler 216 can generate a schedule that is continually updated as write data for processing is received.
  • a scheduler 216 can generate such a schedule based on the ability to switch contexts of offload processor(s) 208 . In this way, on-module computing priorities can be adjusted on the fly.
  • a scheduler 216 can assign a portion of physical address space (e.g., memory locations within local memory 210 ) to an offload processor 208 , according to computing tasks. The offload processor 208 can then switch between such different spaces, saving context information prior to each switch, and subsequently restoring context information when returning to the memory space.
  • Switch controller 218 can control computing operations of offload processor(s) 208 .
  • switch controller 218 can order offload processor(s) 208 to switch contexts.
  • a context switch operation can be an “atomic” operation, executed in response to a single command from switch controller 218 .
  • a switch controller 218 can issue an instruction set that stores current context information, recalls context information, etc.
  • processor module 200 can include a buffer memory (not shown).
  • a buffer memory can store received write data on board the processor module.
  • a buffer memory can be implemented on an entirely different set of memory devices, or can be a memory embedded with logic and/or the offload processor. In the latter case, arbiter logic 206 can arbitrate access to the buffer memory.
  • a buffer memory can correspond to a portion of a system physical memory space. The remaining portion of the system memory space can correspond to other like processor modules and/or memory modules connected to the same system memory bus.
  • buffer memory can be different than local memory 210 .
  • buffer memory can have a slower access time than local memory 210 .
  • buffer memory and local memory can be implemented with like memory devices.
  • write data for processing can have an expected maximum flow rate.
  • a processor module 200 can be configured to operate on such data at, or faster than, such a flow rate. In this way, a master device (not shown) can write data to a processor module without danger of overwriting data “in process”.
  • the various computing elements of a processor module 200 can be implemented as one or more integrated circuit devices (ICs). It is understood that the various components shown in FIG. 2-0 can be formed in the same or different ICs.
  • control logic 212 , memory interface 214 , and/or arbiter logic 206 can be implemented on one or more logic ICs, while offload processor(s) 208 and local memory 210 are separate ICs.
  • Logic ICs can be fixed logic (e.g., application specific ICs), programmable logic (e.g., field programmable gate arrays, FPGAs), or combinations thereof.
  • the foregoing hardware and systems can provide improved computational performance as compared to traditional computing systems.
  • Conventional systems including those based on x86 processors, are often ill-equipped to handle such high volume applications. Even idling, x86 processors use a significant amount of power, and near continuous operation for high bandwidth packet analysis or other high volume processing tasks make the processor energy costs one of the dominant price factors.
  • conventional systems can have issues with the high cost of context switching wherein a host processor is required to execute instructions which can include switching from one thread to another. Such a switch can require storing and recalling the context for the thread. If such context data is resident in a host cache memory, such a context switch can occur relatively quickly. However, if such context data is no longer in cache memory (i.e., a cache miss), the data must be recalled from system memory, which can incur a multi-cycle latency. Continuous cache misses during context switching can adversely impact system performance.
  • FIG. 2-1 shows a processor module 200 - 1 according to one very particular embodiment which is capable of reducing issues associated with high volume processing or context switching associated with many conventional server systems.
  • a processor module 200 - 1 can include ICs 220 - 0 / 1 mounted to a printed circuit board (PCB) type substrate 222 .
  • PCB type substrate 222 can include in-line module connector 202 , which in one very particular embodiment, can be a DIMM compatible connector.
  • IC 220 - 0 can be a system-on-chip (SoC) type device, integrating multiple functions.
  • SoC system-on-chip
  • an IC 220 - 0 can include embedded processor(s), logic and memory.
  • Such embedded processor(s) can be offload processor(s) 208 as described herein, or equivalents.
  • Such logic can be any of controller logic 212 , memory interface 204 and/or arbiter logic 206 , as described herein, or equivalents.
  • Such memory can be any of local memory 210 , cache memory for offload processor(s) 208 , or buffer memory, as described herein, or equivalents.
  • Logic IC 220 - 1 can provide logic functions not included IC 220 - 0 .
  • FIG. 2-2 shows a processor module 200 - 2 according to another very particular embodiment.
  • a processor module 200 - 2 can include ICs 220 - 2 , - 3 , - 4 , - 5 mounted to a PCB type substrate 222 , like that of FIG. 2-1 .
  • processor module functions are distributed among single purpose type ICs.
  • IC 220 - 2 can be a processor IC, which can be an offload processor 208 .
  • IC 220 - 3 can be a memory IC which can include local memory 210 , buffer memory, or combinations thereof.
  • IC 220 - 4 can be a logic IC which can include control logic 212 , and in one very particular embodiment, can be an FPGA.
  • IC 220 - 5 can be another logic IC which can include memory interface 204 and arbiter logic 206 , and in one very particular embodiment, can also be an FPGA.
  • FIGS. 2-1 and 2 - 2 represent but two of various implementations.
  • the various functions of a processor module can be distributed over any suitable number of ICs, including a single SoC type IC.
  • FIG. 2-3 shows an opposing side of a processor module 200 - 1 or 200 - 2 according to a very particular embodiment.
  • Processor module 200 - 3 can include a number of memory ICs, one shown as 220 - 6 , mounted to a PCB type substrate 222 , like that of FIG. 2-1 . It is understood that various processing and logic components can be mounted on an opposing side to that shown.
  • a memory IC 220 - 6 can be configured to represent a portion of the physical memory space of a system.
  • Memory ICs 220 - 6 can perform any or all of the following functions: operate independently of other processor module components, providing system memory accessed in a conventional fashion; serve as buffer memory, storing write data that can be processed with other processor module components, or serve as local memory for storing processor context information.
  • FIG. 2-4 shows a conventional DIMM module (i.e., it serves only a memory function) that can populate a memory bus along with processor modules as described herein, or equivalents.
  • FIG. 2-5 shows a system 230 according to one embodiment.
  • a system 230 can include a system memory bus 228 accessible via multiple in-line module slots (one shown as 226 ).
  • any or all of the slots 226 can be occupied by a processor module 200 as described herein, or an equivalent.
  • available slots can be occupied by conventional in-line memory modules 224 .
  • slots 226 can be DIMM slots.
  • a processor module 200 can occupy one slot. However, in other embodiments, a processor module can occupy multiple slots.
  • a system memory bus 228 can be further interfaced with one or more host processors and/or input/output device (not shown).
  • processor module operations of a processor module according to particular embodiments will now be described.
  • FIGS. 2-6 to 2 - 11 show processor module operations according to various embodiments.
  • FIGS. 2-6 to 2 - 11 show a processor module like that of FIG. 2-0 , along with a system memory bus 228 , and a buffer memory 232 .
  • a buffer memory 232 can part of processor module 200 . In such a case, arbitration between accesses via system memory bus 228 and offload processors can be controlled by arbiter logic 206 .
  • write data 234 - 0 can be received on system memory bus 228 (circle “1”).
  • such an action can include the writing of data to a particular physical address space range of a system memory.
  • such an action can be a DMA write independent of any host processor.
  • Write data 234 - 0 can include metadata (MD) as well as data to be processed (Data).
  • write data 234 - 0 can correspond to a particular processing operation (Session 0 ).
  • Control logic 212 can access metadata (MD) of the write data 234 - 0 to determine a type of processing to be performed (circle “2”) and/or classification of such data.
  • an action can include a direct read from a physical address (i.e., MD location is at a predetermined location).
  • such an action can be an indirect read (i.e., MD is accessed via pointer, or the like).
  • the action shown by circle “2” can be performed by any of: a read by control logic 212 or read by an offload processor 208 .
  • scheduler 216 can create a processing schedule, or modify an existing schedule to accommodate the new computing task (circle “3”).
  • the switch controller 218 can direct one or more offload processors 208 be begin processing data according to MD of the write data (circles “4”, “5”).
  • processing of data can include any of the following and equivalents: offload processor 208 can process write data stored in a buffer memory of the processor module 200 , with accesses being arbitrated by arbiter logic 206 , offload processor 208 can operate on data previously received, offload processor 208 can receive and operate on data stored at a location different than the processor module 200 .
  • additional write data 234 - 1 can be received on system memory bus 228 (circle “6”).
  • Write data 234 - 1 can include metadata that indicates a different processing operation (Session 1 ) than that for write data 234 - 0 .
  • Control logic 212 can access metadata (MD) of the new write data 234 - 1 to determine a type of processing to be performed (circle “7”).
  • the scheduler 216 can modify the current schedule to accommodate the new computing task (circle “8”).
  • the modified schedule re-tasks offload processor 208 .
  • switch controller 218 can direct the offload processor 208 to store its current context (ContextA) in local memory 210 (circle “9”).
  • offload processor(s) 208 can begin the new processing task (circle “10”). Consequently, offload processor(s) 208 can maintain a new context (ContextB) corresponding to the new processing task.
  • ContextB a new context
  • a processing task by offload processor 208 can be completed.
  • processing can modify write data 234 - 1 , and such data can be read out over system memory bus 228 (circle “11”).
  • scheduler 216 can update a schedule.
  • switch controller 218 can direct offload processor(s) 208 to restore the previously saved context (ContextA) from local memory 210 (circle “12”).
  • ContextA previously saved context
  • a restored context e.g., ContextA
  • a restored context may have been stored by an offload processor different from the one that saved the context in the first place.
  • offload processor(s) 208 can return to processing data according to the previous task (Session 0 ) (circle “13”).
  • FIG. 2-12 shows a method 240 according an embodiment.
  • a method 240 can include detecting the write of session data to a system memory with a module interface 242 . Such an action can include determining if received write data has metadata (i.e., data identifying a particular processing). It is understood that “session data” is data corresponding to a particular processing task. Further, it is understood that MD accompanying (or embedded within) session data can identify sessions having priorities with respect to one another.
  • a module interface can be a slave interface for an in-line module.
  • a method 240 can determine if current offload processing is sufficient for a new session or change of session 244 . Such an action takes into account a processing time required for any current sessions.
  • a hardware schedule (schedule for controlling offload processor(s)) can be revised and the new session can be assigned to an offload processor.
  • one or more offload processors can be selected for re-tasking (e.g., a context switch) 250 and the hardware schedule can be modified accordingly 252 .
  • the selected offload processors can save their current context data 254 and then switch to the new session 256 .
  • revision of a hardware schedule ( 252 ) can include storing a context switch (e.g., in the case a new session has a lower priority than current sessions). In such a case, actions 254 and 256 would not occur until a later point in time.
  • FIG. 2-13 shows a method 260 according another embodiment.
  • a method 260 can include determining if a computing session for an offload processor is complete 262 or has been terminated 264 . In such cases (Y from 262 / 264 ), it can be determined if the freed module offload processor (i.e., an offload processor whose session is complete/terminated) has a stored context 266 . That is, it can be determined if freed processor was previously operating on a session.
  • the freed module offload processor i.e., an offload processor whose session is complete/terminated
  • the offload processor can restore the previous context 268 . If a free offload processor has no stored context, it can be assigned to an existing session (if possible) 270 . An existing hardware schedule can be updated correspondingly 272 .
  • processor modules can be employed to accomplish various processing tasks. According to some embodiments, processor modules can be attached to a system memory bus to operate on network packet data. Such embodiments will now be described.
  • FIG. 1-0 shows a system 101 that can transport packet data to one or more computational units (one shown as 100 ) located on a module, which in particular embodiments, can include a connector compatible with an existing memory module.
  • a computational unit 100 can include a processor module as described in embodiments herein, or an equivalent.
  • a computational unit 100 can be capable of intercepting or otherwise accessing packets sent over a memory bus 116 and carrying out processing on such packets, including but not limited to termination or metadata processing.
  • a system memory bus 116 can be a system memory bus like those described herein, or equivalents (e.g., 228 ).
  • packets corresponding to a particular flow can be transported to a storage location accessible by, or included within computational unit 100 . Such transportation can occur without consuming resources of a host processor module 106 c , connected to memory bus 116 . In particular embodiments, such transport can occur without interrupting the host processor module 106 c . In such an arrangement, a host processor module 106 c does not have to handle incoming flows. Incoming flows can be directed to computational unit 100 , which in particular embodiments can include a general purpose processor 108 i . Such general purpose processors 108 i can be capable of running code for terminating incoming flows.
  • a general purpose processor 108 i can run code for terminating particular network flow session types, such as Apache video sessions, as but one example.
  • a general purpose processor 108 i can process metadata of a packet.
  • metadata can include one or more fields of a header for the packet, or a header encapsulated further within the packet.
  • a system 101 can carry out any of the following functions: 1) transport packets of a flow to a destination occupied by, or accessible by, a computational unit 100 without interrupting a host processor module 106 c; 2) transport packets to an offload processor 108 i capable of terminating session flows (i.e., the offload processor is responsible for terminating session flows); 3) transport packets to midplane switch that can process the metadata associated with a packet and make a switching decision; 4) provide a novel high speed packet terminating system.
  • Embodiments as disclosed herein can enable high speed packet termination by reducing context switch overhead of a host processor.
  • Embodiments can provide any of the following functions: 1) offload computation tasks to one or more processors via a system memory bus, without the knowledge of the host processor, or significant host processor involvement; 2) interconnect servers in a rack or amongst racks by employing offload processors as switches; or 3) use I/O virtualization to redirect incoming packets to different offload processors.
  • a system 101 can include an I/O device 102 which can receive packet or other I/O data from an external source.
  • I/O device 102 can include physical or virtual functions generated by the physical device to receive a packet or other I/O data from the network or another computer or virtual machine.
  • an I/O device 102 can include a network interface card (NIC) having input buffer 102 a (e.g., DMA ring buffer) and an I/O virtualization function 102 b.
  • NIC network interface card
  • an I/O device 102 can write a descriptor including details of the necessary memory operation for the packet (i.e. read/write, source/destination). Such a descriptor can be assigned a virtual memory location (e.g., by an operating system of the system 101 ). I/O device 102 then communicates with an input output memory management unit (IOMMU) 104 which can translate virtual addresses to corresponding physical addresses with an IOMMU function 104 b . In the particular embodiment shown, a translation look-aside buffer (TLB) 104 a can be used for such translation.
  • IOMMU input output memory management unit
  • TLB translation look-aside buffer
  • Virtual function reads or writes data between I/O device and system memory locations can then be executed with a direct memory transfer (e.g., DMA) via a memory controller 106 b of the system 101 .
  • An I/O device 102 can be connected to IOMMU 104 by a host bus 112 .
  • a host bus 112 can be a peripheral interconnect (PCI) type bus.
  • IOMMU 104 can be connected to a host processing section 106 at a central processing unit I/O (CPUIO) 106 a .
  • CPUIO central processing unit I/O
  • such a connection 114 can support a HyperTransport (HT) protocol.
  • a host processing section 106 can include the CPUIO 106 a , memory controller 106 b , processing core 106 c and corresponding provisioning agent 106 d.
  • a computational unit 100 can interface with the system bus 116 via standard in-line module connection, which in very particular embodiments can include a DIMM type slot.
  • a memory bus 116 can be a DDR3 type memory bus. Alternate embodiments can include any suitable system memory bus.
  • Packet data can be sent by memory controller 106 b via memory bus 116 to a DMA slave interface 110 a .
  • DMA slave interface 110 a can be adapted to receive encapsulated read/write instructions from a DMA write over the memory bus 116 .
  • a hardware scheduler ( 108 b /c/d/e/h) can perform traffic management on incoming packets by categorizing them according to flow using session metadata. Packets can be queued for output in an onboard memory ( 110 b / 108 a / 108 m ) based on session priority.
  • the hardware scheduler determines that a packet for a particular session is ready to be processed by the offload processor 108 i , the onboard memory is signaled for a context switch to that session. Utilizing this method of prioritization, context switching overhead can be reduced, as compared to conventional approaches. That is, a hardware scheduler can handle context switching decisions and thus optimize the performance of the downstream resource (e.g., offload processor 108 i ).
  • an offload processor 108 i can be a “wimpy” core” type processor.
  • a host processor 106 c can be a “brawny core” type processor (e.g., an x86 or any other processor capable of handling “heavy touch” computational operations).
  • an I/O device 102 can be configured to trigger host processor interrupts in response to incoming packets, according to embodiments, such interrupts can be disabled, thereby reducing processing overhead for the host processor 106 c .
  • an offload processor 108 i can include an ARM, ARC, Tensilica, MIPS, Strong/ARM or any other processor capable of handling “light touch” operations.
  • an offload processor can run a general purpose operating system for executing a plurality of sessions, which can be optimized to work in conjunction with the hardware scheduler in order to reduce context switching overhead.
  • a system 101 can receive packets from an external network over a network interface.
  • the packets are destined for either a host processor 106 c or an offload processor 108 i based on the classification logic and schematics employed by I/O device 102 .
  • I/O device 102 can operate as a virtualized NIC, with packets for a particular logical network or to a certain virtual MAC (VMAC) address can be directed into separate queues and sent over to the destination logical entity.
  • VMAC virtual MAC
  • Such an arrangement can transfer packets to different entities.
  • each such entity can have a virtual driver, a virtual device model that it uses to communicate with virtual network interfaces it is connected to.
  • multiple devices can be used to redirect traffic to specific memory addresses. So, each of the network devices operates as if it is transferring the packets to the memory location of a logical entity. However, in reality, such packets are transferred to memory addresses where they can be handled by one or more offload processors (e.g., 108 i ). In particular embodiments such transfers are to physical memory addresses, thus logical entities can be removed from the processing, and a host processor can be free from such packet handling.
  • offload processors e.g., 108 i
  • embodiments can be conceptualized as providing a memory “black box” to which specific network data can be fed.
  • a memory black box can handle the data (e.g., process it) and respond back when such data is requested.
  • I/O device 102 can receive data packets from a network or from a computing device.
  • the data packets can have certain characteristics, including transport protocol number, source and destination port numbers, source and destination IP addresses, for example.
  • the data packets can further have metadata that is processed ( 108 d ) that helps in their classification and management.
  • I/O device 102 can include, but is not limited to, peripheral component interconnect (PCI) and/or PCI express (PCIe) devices connecting with a host motherboard via PCI or PCIe bus 9 (e.g., 112 ).
  • PCI peripheral component interconnect
  • PCIe PCI express
  • Examples of I/O devices include a network interface controller (NIC), a host bus adapter, a converged network adapter, an ATM network interface, etc.
  • the I/O device may be virtualized to provide for multiple virtual devices each of which can perform some of the functions of the physical I/O device.
  • the 10 virtualization program (e.g., 102 b ) according to an embodiment, can redirect traffic to different memory locations (and thus to different offload processors attached to modules on a memory bus).
  • an I/O device 102 e.g., a network card
  • IOV input/output virtualization
  • VF virtual function
  • Each virtual function interface may be provided with resources during runtime for dedicated usage.
  • Examples of the CF and VF may include the physical function and virtual functions under schemes such as Single Root I/O Virtualization or Multi-Root I/O Virtualization architecture.
  • the CF acts as the physical resources that sets up and manages virtual resources.
  • the CF is also capable of acting as a full-fledged 10 device.
  • the VF is responsible for providing an abstraction of a virtual device for communication with multiple logical entities/multiple memory regions.
  • the operating system/the hypervisor/any of the virtual machines/user code running on a host processor 106 c may be loaded with a device model, a VF driver and a driver for a CF.
  • the device model may be used to create an emulation of a physical device for the host processor 106 c to recognize each of the multiple VFs that are created.
  • the device model may be replicated multiple times to give the impression to a VF driver (a driver that interacts with a virtual 10 device) that it is interacting with a physical device of a particular type.
  • a certain device module may be used to emulate a network adapter such as the Intel® Ethernet Converged Network Adapter (CNA) X540-T2, so that the I/O device 102 believes it is interacting with such an adapter.
  • CNA Intel® Ethernet Converged Network Adapter
  • each of the virtual functions may have the capability to support the functions of the above said CNA, i.e., each of the Physical Functions should be able to support such functionality.
  • the device model and the VF driver can be run in either privileged or non-privileged mode. In some embodiments, there is no restriction with regard to who hosts/runs the code corresponding to the device model and the VF driver. The code, however, has the capability to create multiple copies of device model and VF driver so as to enable multiple copies of said I/O interface to be created.
  • An application or provisioning agent 106 d may create a virtual I/O address space for each VF, during runtime and allocate part of the physical address space to it. For example, if an application handling the VF driver instructs it to read or write packets from or to memory addresses 0xaaaa to 0xfff, the device driver may write I/O descriptors into a descriptor queue with a head and tail pointer that are changed dynamically as queue entries are filled.
  • the data structure may be of another type as well, including but not limited to a ring structure 102 a or hash table.
  • the VF can read from or write data to the address location pointed to by the driver. Further, on completing the transfer of data to the address space allocated to the driver, interrupts, which are usually triggered to the host processor to handle said network packets, can be disabled. Allocating a specific I/O space to a device can include allocating said IO space a specific physical memory space occupied.
  • the descriptor may comprise only a write operation, if the descriptor is associated with a specific data structure for handling incoming packets. Further, the descriptor for each of the entries in the incoming data structure may be constant so as to redirect all data write to a specific memory location. In an alternate embodiment, the descriptor for consecutive entries may point to consecutive entries in memory so as to direct incoming packets to consecutive memory locations.
  • said operating system may create a defined physical address space for an application supporting the VF drivers and allocate a virtual memory address space to the application or provisioning agent 106 d , thereby creating a mapping for each virtual function between said virtual address and a physical address space.
  • Said mapping between virtual memory address space and physical memory space may be stored in IOMMU tables (e.g., a TLB 104 a ).
  • the application performing memory reads or writes may supply virtual addresses to say virtual function, and the host processor OS may allocate a specific part of the physical memory location to such an application.
  • VF may be configured to generate requests such as read and write which may be part of a direct memory access (DMA) read or write operation, for example.
  • the virtual addresses is be translated by the IOMMU 104 to their corresponding physical addresses and the physical addresses may be provided to the memory controller for access. That is, the IOMMU 104 may modify the memory requests sourced by the I/O devices to change the virtual address in the request to a physical address, and the memory request may be forwarded to the memory controller for memory access.
  • the memory request may be forwarded over a bus 114 that supports a protocol such as HyperTransport 114 .
  • the VF may in such cases carry out a direct memory access by supplying the virtual memory address to the IOMMU 104 .
  • said application may directly code the physical address into the VF descriptors if the VF allows for it. If the VF cannot support physical addresses of the form used by the host processor 106 c , an aperture with a hardware size supported by the VF device may be coded into the descriptor so that the VF is informed of the target hardware address of the device. Data that is transferred to an aperture may be mapped by a translation table to a defined physical address space in the system memory.
  • the DMA operations may be initiated by software executed by the processors, programming the I/O devices directly or indirectly to perform the DMA operations.
  • computational unit 100 can be implemented with one or more FPGAs.
  • computational unit 100 can include FPGA 110 in which can be formed a DMA slave device module 110 a and arbiter 110 f .
  • a DMA slave module 110 a can be any device suitable for attachment to a memory bus 116 that can respond to DMA read/write requests.
  • a DMA slave module 110 a can be another interface capable of block data transfers over memory bus 116 .
  • the DMA slave module 110 a can be capable of receiving data from a DMA controller (when it performs a read from a ‘memory’ or from a peripheral) or transferring data to a DMA controller (when it performs a write instruction on the DMA slave module 110 a ).
  • the DMA slave module 110 a may be adapted to receive DMA read and write instructions encapsulated over a memory bus, (e.g., in the form of a DDR data transmission, such as a packet or data burst), or any other format that can be sent over the corresponding memory bus.
  • a DMA slave module 110 a can reconstruct the DMA read/write instruction from the memory R/W packet.
  • the DMA slave module 110 a may be adapted to respond to these instructions in the form of data reads/data writes to the DMA master, which could either be housed in a peripheral device, in the case of a PCIe bus, or a system DMA controller in the case of an ISA bus.
  • I/O data that is received by the DMA device 110 a can then queued for arbitration.
  • Arbitration can include the process of scheduling packets of different flows, such that they are provided access to available bandwidth based on a number of parameters.
  • an arbiter 110 f provides resource access to one or more requestors. If multiple requestors request access, an arbiter 110 f can determine which requestor becomes the accessor and then passes data from the accessor to the resource interface, and the downstream resource can begin execution on the data. After the data has been completely transferred to a resource, and the resource has competed execution, the arbiter 110 f can transfer control to a different requestor and this cycle repeats for all available requestors. In the embodiment of FIG. 1-10 , arbiter 110 f can notify other portions of computational unit 100 (e.g., 108 ) of incoming data.
  • a computation unit 100 can utilize an arbitration scheme shown in U.S. Pat. No. 7,813,283, issued to Dalal on Oct. 12, 2010, the contents of which are incorporated herein by reference.
  • Other suitable arbitration schemes known in art could be implemented in embodiments herein.
  • the arbitration scheme of the current invention might be implemented using an OpenFlow switch and an OpenFlow controller.
  • computational unit 100 can further include notify/prefetch circuits 110 c which can prefetch data stored in a buffer memory 110 b in response to DMA slave module 110 a , and as arbitrated by arbiter 110 f . Further, arbiter 110 f can access other portions of the computational unit 100 via a memory mapped I/O ingress path 110 e and egress path 110 g.
  • a hardware scheduler can include a scheduling circuit 108 b /n to implement traffic management of incoming packets. Packets from a certain source, relating to a certain traffic class, pertaining to a specific application or flowing to a certain socket are referred to as part of a session flow and are classified using session metadata. Such classification can be performed by classifier 108 e.
  • session metadata 108 d can serve as the criterion by which packets are prioritized and scheduled and as such, incoming packets can be reordered based on their session metadata. This reordering of packets can occur in one or more buffers and can modify the traffic shape of these flows.
  • the scheduling discipline chosen for this prioritization, or traffic management (TM) can affect the traffic shape of flows and micro-flows through delay (buffering), bursting of traffic (buffering and bursting), smoothing of traffic (buffering and rate-limiting flows), dropping traffic (choosing data to discard so as to avoid exhausting the buffer), delay jitter (temporally shifting cells of a flow by different amounts) and by not admitting a connection (e.g., cannot simultaneously guarantee existing service (SLAs) with an additional flow's SLA).
  • SLAs existing service
  • computational unit 100 can serve as part of a switch fabric, and provide traffic management with depth-limited output queues, the access to which is arbitrated by a scheduling circuit 108 b /n.
  • Such output queues are managed using a scheduling discipline to provide traffic management for incoming flows.
  • the session flows queued in each of these queues can be sent out through an output port to a downstream network element.
  • a conventional traffic management circuit doesn't take into account the handling and management of data by downstream elements except for meeting the SLA agreements it already has with said downstream elements.
  • a scheduler circuit 108 b /n can allocate a priority to each of the output queues and carry out reordering of incoming packets to maintain persistence of session flows in these queues.
  • a scheduler circuit 108 b /n can be used to control the scheduling of each of these persistent sessions into a general purpose operating system (OS) 108 j , executed on an offload processor 108 i . Packets of a particular session flow, as defined above, can belong to a particular queue.
  • the scheduler circuit 108 b /n may control the prioritization of these queues such that they are arbitrated for handling by a general purpose (GP) processing resource (e.g., offload processor 108 i ) located downstream.
  • GP general purpose
  • An OS 108 j running on a downstream processor 108 i can allocate execution resources such as processor cycles and memory to a particular queue it is currently handling.
  • the OS 108 j may further allocate a thread or a group of threads for that particular queue, so that it is handled distinctly by the general purpose processing element 108 i as a separate entity.
  • Dedicated computing resources e.g., 108 i
  • memory space and session context information for each of the sessions can provide a way of handling, processing and/or terminating each of the session flows at the general purpose processor 108 i .
  • the scheduler circuit 108 b /n can exploit this functionality of the execution resource to queue session flows for scheduling downstream.
  • the scheduler circuit 108 b /n can be informed of the state of the execution resource(s) (e.g., 108 i ), the current session that is run on the execution resource; the memory space allocated to it, the location of the session context in the processor cache.
  • a scheduler circuit 108 b /n can further include switching circuits to change execution resources from one state to another.
  • the scheduler circuit 108 b /n can use such a capability to arbitrate between the queues that are ready to be switched into the downstream execution resource.
  • the downstream execution resource can be optimized to reduce the penalty and overhead associated with context switch between resources. This is further exploited by the scheduler circuit 108 b /n to carry out seamless switching between queues, and consequently their execution as different sessions by the execution resource.
  • a scheduler circuit 108 b /n can schedule different sessions on a downstream processing resource, wherein the two are operated in coordination to reduce the overhead during context switches.
  • An important factor in decreasing the latency of services and engineering computational availability can be hardware context switching synchronized with network queuing.
  • a pipeline coordinates swapping in of the cache (e.g., L2 cache) of the corresponding resource (e.g., 108 i ) and transfers the reassembled I/O data into the memory space of the executing process.
  • the scheduler circuit 108 b /n
  • a maximum context size can be assumed as data processed.
  • a queue can be provisioned as the greater of computational resource and network bandwidth resource.
  • a computation resource can be an ARM A9 processor running at 800 MHz, while a network bandwidth can be 3 Gbps of bandwidth.
  • embodiments can utilize computation having many parallel sessions (such that the hardware's prefetching of session-specific data offloads a large portion of the host processor load) and having minimal general purpose processing of data.
  • a scheduler circuit 108 b /n can be conceptualized as arbitrating, not between outgoing queues at line rate speeds, but arbitrating between terminated sessions at very high speeds.
  • the stickiness of sessions across a pipeline of stages, including a general purpose OS, can be a scheduler circuit optimizing any or all such stages of such a pipeline.
  • a scheduling scheme can be used as shown in U.S. Pat. No. 7,760,715 issued to Dalal on Jul. 20, 2010, incorporated herein by reference. This scheme can be useful when it is desirable to rate limit the flows for preventing the downstream congestion of another resource specific to the over-selected flow, or for enforcing service contracts for particular flows.
  • Embodiments can include arbitration scheme that allows for service contracts of downstream resources, such as general purpose OS that can be enforced seamlessly.
  • a hardware scheduler can provide for the classification of incoming packet data into session flows based on session metadata. It can further provide for traffic management of these flows before they are arbitrated and queued as distinct processing entities on the offload processors.
  • offload processors can be general purpose processing units capable of handling packets of different application or transport sessions. Such offload processors can be low power processors capable of executing general purpose instructions.
  • the offload processors could be any suitable processor, including but not limited to: ARM, ARC, Tensilica, MIPS, StrongARM or any other processor that serves the functions described herein.
  • Such offload processors have a general purpose OS running on them, wherein the general purpose OS is optimized to reduce the penalty associated with context switching between different threads or group of threads.
  • context switches on host processors can be computationally intensive processes that require the register save area, process context in the cache and TLB entries to be restored if they are invalidated or overwritten.
  • Instruction Cache misses in host processing systems can lead to pipeline stalls and data cache misses lead to operation stall and such cache misses reduce processor efficiency and increase processor overhead.
  • an OS 108 j running on the offload processors 108 i in association with a scheduler circuit 108 b /n can operate together to reduce the context switch overhead incurred between different processing entities running on it.
  • Embodiments can include a cooperative mechanism between a scheduler circuit and the OS on the offload processor 108 i , wherein the OS sets up session context to be physically contiguous (physically colored allocator for session heap and stack) in the cache; then communicates the session color, size, and starting physical address to the scheduler circuit upon session initialization.
  • a scheduler circuit can identify the session context in the cache by using these parameters and initiate a bulk transfer of these contents to an external low latency memory.
  • the scheduler circuit can manage the prefetch of the old session if its context was saved to a local memory 108 g .
  • a local memory 108 g can be low latency memory, such as a reduced latency dynamic random access memory (RLDRAM), as but one very particular embodiment.
  • RLDRAM reduced latency dynamic random access memory
  • session context can be identified distinctly in the cache.
  • context size can be limited to ensure fast switching speeds.
  • embodiments can include a bulk transfer mechanism to transfer out session context to a local memory 108 g .
  • the cache contents stored therein can then be retrieved and prefetched during context switch back to a previous session.
  • Different context session data can be tagged and/or identified within the local memory 108 g for fast retrieval.
  • context stored by one offload processor may be recalled by a different offload processor.
  • FIG. 1-0 also shows an offload processor tunnel connection 608 k , as well as a memory interface 108 m and port 1081 (which can be an accelerator coherency port (ACP)).
  • Memory interface 108 m can access buffer memory 108 a.
  • FIG. 1-1 shows a system flow according to an embodiment.
  • Packet or other I/O data can be received at an I/O device 120 .
  • An I/O device can be physical device, virtual device or combination thereof.
  • Interrupts generated from the I/O data intended for a host processor 124 can be disabled, allowing such I/O data to be processed without resources of the host processor 124 .
  • An IOMMU 121 can map received data to physical addresses of a system address space.
  • DMA master 125 can transmit such data to such memory addresses by operation of a memory controller 122 .
  • Memory controller 122 can execute DRAM transfers over a memory bus with a DMA Slave.
  • a hardware scheduler 123 can schedule processing of such data with an offload processor 126 .
  • a type of processing can be indicated by metadata within the I/O data.
  • such data can be stored in an onboard memory 129 .
  • one or more offload processors 126 can executing computing functions in response to the I/O data.
  • such computing functions can operate on the I/O data, and such data can be subsequently read out on memory bus via a read request processed by DMA Slave 127 .
  • processors architectures such as MIPS may include deep instructions pipelines to improve the number of instructions per cycle. Further, the ability to run a multi-threaded programming environment results in enhanced usage of existing processor resources.
  • processor architecture may include multiple processor cores. Multi-core architectures comprising of the same type of cores, referred to as homogeneous core architectures, provide higher instruction throughput by parallelizing threads or processes across multiple cores. However, in such homogeneous core architectures, the shared resources, such as memory, are amortized over a small number of processors.
  • Memory and I/O accesses can incur a high amount of processor overhead.
  • context switches in conventional general purpose processing units can be computationally intensive. It is therefore desirable to reducing context switch overhead in a networked computing resource handling a plurality of networked applications in order to increase processor throughput.
  • Conventional server loads can require complex transport, high memory bandwidth, extreme amounts of data bandwidth (randomly accessed, parallelized, and highly available), but often with light touch processing: HTML, video, packet-level services, security, and analytics. Further, idle processors still consume more than 50% of their peak power consumption.
  • complex transport, data bandwidth intensive, frequent random access oriented, ‘light’ touch processing loads can be handled behind a socket abstraction created on the offload processor cores.
  • “heavy” touch, computing intensive loads can be handled by a socket abstraction on a host processor core (e.g., x86 processor cores).
  • a host processor core e.g., x86 processor cores.
  • Such software sockets can allow for a natural partitioning of these loads between ARM and x86 processor cores.
  • server loads can be broken up across the offload processing cores and the host processing cores.
  • FIG. 3 shows protocol stacks that can be included in a system according to embodiments.
  • a host processor e.g., 106 c
  • Such a protocol stack 317 can include one or more applications (application) 318 sitting on an operating system (OS) 319 .
  • an OS can include a Xockets Socket 330 and Xockets Tunneling Driver 320 which can access XIMMs as described herein or equivalents.
  • Socket 330 can facilitates communication between a host processor and an offload processor module (e.g., 100 ) and Driver 320 can enable transmission of packet data to an offload processor module (e.g., 100 ) (e.g., Ethernet-over-DDR tunneling).
  • a brawny core protocol stack 317 can further include a Hypervisor 312 to supervise sessions and/or enable virtual switches 310 as described herein, or equivalents.
  • An offload processor can include wimpy core protocol stack 300 .
  • a protocol stack 300 can include a single session OS 302 which can run an application 303 .
  • Additional software functions 304 can control context switching, prefetching of data, and memory mapped scheduling.
  • the offload processors can rapidly switch contexts and read from different parts of memory in order to service them.
  • Queuing and reassembly functions ( 320 ) can take decrypted incoming fragments of data, assemble them into their original form and queue them for processing on one of multiple offload processors onboard a module (e.g., 100 ).
  • Input-output memory management software e.g., IOMMU of 308
  • IOMMU Input-output memory management software
  • Direct memory access e.g., R/DMA of 308
  • R/DMA Real-Time Transport Stream
  • An offload processor can also utilize a virtual switching software ( 312 ) to provide switching as described herein.
  • Header services ( 310 ) can process header data of received packets.
  • Example embodiments of offload processors can include, but are not limited to, ARM A9 Cortex processors, which have a clock speed of 800 MHz and a data handling capacity of 3 Ghz.
  • the queue depth for the traffic management circuit can be configured to be the smaller of the processing power and the network bandwidth. Given the lopsided nature of this ratio, in order to handle complete network bandwidth, sessions can be of a lightweight processing nature. Further, sessions to can be switched with minimum context switch overhead to allow the offload processor to process the high bandwidth network traffic. Further, the offload processors can provide session handling capacity greater than conventional approaches due to the ability to terminate sessions with little or no overhead.
  • the offload processors according to embodiments are favorably disposed to handle complete offload of Apache video routing, as but one very particular embodiment.
  • systems when equipped with many XIMMs, each containing multiple “wimpy” cores, systems may be placed near the top of rack, where they can be used as a cache for data and a processing resource for rack hot content or hot code, a means for interconnecting between racks and TOR switches, a mid tier between TOR switches and second-level switches, rack-level packet filtering, logging, and analytics, or various types of rack-level control plane agents.
  • Simple passive optical mux/demux-ing can separate high bandwidth ports on the x86 systems into many lower bandwidth ports as needed.
  • Embodiments can be favorably disposed to handle Apache, HTML, and application cache and rack level mid plane functions.
  • a network of XIMMs and a host x86 processors may be used to provide routing overlays.
  • FIG. 4 is a flow schematic wherein network packets 450 are transferred to offload processors 430 mounted with memory device 410 , which can be wimpy core devices, completely without intervention of the host CPU 420 , which can be a brawny core device.
  • the offload processors 430 can act as full-fledged processors hosting server applications.
  • packets 450 can be received via an I/O device 440 (e.g., NIC).
  • a host processor 420 can be free to execute other operations 660 while offload processors 430 service network packets 450 .
  • FIG. 5 is an alternate embodiment, in which server loads are partitioned such that packet meta data processing, routing overlays, filtering, packet logging and other hygiene functions are offloaded to the offload processors ( 530 ) mounted with memory devices 510 , while and the host processor ( 520 ) implements server sessions.
  • Offload processors 530 can be wimpy core devices, while host processor 520 can be a brawny core device.
  • packets can flow through an I/O device 540 and offload processors 530 can be mounted with a memory device 510 .
  • a network of offload processor modules i.e., XIMMs
  • each comprising a plurality of said offload processors may be employed to provide video overlays by associating said offload processors with local memory elements, including closely located DIMMs or solid state storage devices (SSDs).
  • the network of XIMM modules may be used to perform memory read or writes for prefetching the data contents before they are serviced.
  • real-time transport protocol RTP
  • Prefetches can be physically issued as (R)DMAs to other (remote) local DIMMs/SSDs.
  • the number of the videos is limited and can be kept in local Xockets DIMMs.
  • CDN public cloud/content delivery network
  • prefetching can be balanced against peer-to-peer distribution protocols (e.g. P4P) so that blocks of data can be efficiently sourced from all relevant servers.
  • the bandwidth metric indicates how many streams can be sustained when using 10 Mbps (1 Mbps) streams. As the stream bandwidth goes down the number of streams goes up and the same session limitation becomes manifest in the RTP processing of server.
  • Architecture according to such embodiments can allow over 10,000 high definition streams to be sustained in a 1 U (one rack unit) form factor.
  • a complex publish and subscribership model for handling pipelined computational tasks partitioned across a network of x86 cores and offload processor cores, can be implemented.
  • Each task in the pipeline may be handled by the type of cores that are most favorably disposed for it.
  • offload processor modules e.g., Xockets DIMMs
  • the mid-plane defined by Xockets DIMMs can drive and receive the large PCI-e 3.0 bandwidth connecting Map steps with Reduce steps within a rack and outside of the rack. Because the shuffle step is often the bottleneck, the number of reducers is kept to a minimum so that CPUs are not overwhelmed with having to filter keys. With traffic-managed according to embodiments, the number of Reducers can rival the number of Mappers.
  • FIG. 6 shows a method which can start 602 and fetch input data from a file system (e.g., Hadoop Distributed File System) 604 .
  • a file system e.g., Hadoop Distributed File System
  • Such data can be fetched to wimpy core devices (e.g., offload processors as described herein or equivalents).
  • wimpy core devices e.g., offload processors as described herein or equivalents.
  • Such input data can be partitioned into splits by the wimpy core devices 606 .
  • Input pairs (which can include a key and value) for such splits can be obtained 608 .
  • a map function can be performed on all input pairs with brawny core devices (e.g., host processor(s)) 610 . All the mapping operation results can be reduced and sorted based on key values with brawny core devices 612 . Results can be written back to the file system 614 .
  • Such an operation can be accomplished via wimpy core devices.
  • embodiments can employ the Xocket DIMMs to implement rack level disks using memory mapped file paradigm. Such embodiments can effectively unify all of the contents on the Xockets DIMMs on the rack to every x86 processor socket.

Abstract

A processor module can include an in-line module connector configured to physically connect to an in-line memory slot of a system memory bus; a data interface configured to receive write data from the system memory bus, via the in-line module connector, and according to a predetermined protocol; and at least one offload processor configured to process the write data according to instruction data within the write data; and wherein hardware scheduling logic mounted in the processor module include an arbiter that arbitrates between conflicting data access requirements within the processor module, and a scheduler to order computing tasks, both arbiter and scheduler being mounted on the in-line module and configured to control operations of the at least one offload processor.

Description

    PRIORITY CLAIMS
  • This application claims the benefit of U.S. Provisional Patent Applications 61/753,892 filed on Jan. 17, 2013, 61/753,895 filed on Jan. 17, 2013, 61/753,899 filed on Jan. 17, 2013, 61/753,901 filed on Jan. 17, 2013, 61/753,903 filed on Jan. 17, 2013, 61/753,904 filed on Jan. 17, 2013, 61/753,906 filed on Jan. 17, 2013, 61/753,907 filed on Jan. 17, 2013, and 61/753,910 filed on Jan. 17, 2013, the contents all of which are incorporated by reference herein.
  • TECHNICAL FIELD
  • The present invention relates generally to processing modules, and more particularly to offload processing modules that can be physically connected to a system memory bus to process data independent of a host processor of the system.
  • BACKGROUND
  • Enterprises often rely on input/output (IO) intensive networked applications running on dedicated servers that support associated “state”, context or session-defined applications. Servers can run multiple applications, each associated with a specific state running on the server. Common server applications include an Apache web server, a MySQL database application, PHP hypertext preprocessing, video or audio processing with Kaltura supported software, packet filters, application cache, management and application switches, accounting, analytics, and logging.
  • Unfortunately, servers can be limited by computational and memory storage costs associated with switching between applications. When multiple applications are constantly required to be available, the overhead associated with storing the session state of each application can result in poor performance due to constant switching between applications. Dividing applications between multiple processor cores can help alleviate the application switching problem, but does not eliminate it. Advanced processors often only have eight to sixteen cores, while hundreds of application or session states may be required.
  • Enterprises also store and process their large amounts of data in a variety of ways. One manner in which enterprises store data is by using relational databases and corresponding relational database management systems (RDBMS). Such data, usually referred to as structured data, may be collected, normalized, formatted and stored in an RDBMS. Tools based on standardized data languages such as the Structured Query Language (SQL) may be used for accessing and processing structured data. However, it is estimated that such formatted structured data represents only a tiny fraction of an enterprise's stored data. All organizations are becoming increasingly aware that substantial information and knowledge resides in unstructured data (i.e. “Big Data”) repositories. Accordingly, simple and effective access to both structured and unstructured data are seen as necessary for maximizing the value of enterprise informational resources.
  • However, the platforms that are currently being used to handle structured and unstructured data substantially differ in their architecture. In-memory processing and Storage Area Network (SAN)-like architecture are used for traditional SQL queries, while commodity or shared nothing architectures (each computing node, consisting of a processor, local memory, and disk resources, shares nothing with other nodes in the computing cluster) are usually used for processing unstructured data.
  • A computing system architecture, hardware, and operational method that supports input-output (IO) intensive networked applications, as well as structured and unstructured data queries is needed. Such a system needs to readily handle high throughput data processing, be able to provide high parallelism for dividing tasks among multiple processors, and further provide efficient context switching to support multiple users or applications.
  • BRIEF DESCRIPTION OF THE DRAWINGS
  • FIG. 1-0 shows a system according to an embodiment.
  • FIG. 1-1 shows a system flow according to an embodiment.
  • FIGS. 2-0 to 2-3 show processor modules according to various embodiments.
  • FIG. 2-4 shows a conventional dual-in-line memory module.
  • FIG. 2-5 shows a system according to another embodiment.
  • FIGS. 2-6 to 2-11 show processor module operations according to an embodiment.
  • FIG. 2-12 shows a method according to an embodiment.
  • FIG. 2-13 shows a method according to another embodiment.
  • FIG. 3 shows protocol stacks for processors according to embodiments.
  • FIG. 4 shows a partitioning of system loads according to an embodiment.
  • FIG. 5 shows a partitioning of system loads according to another embodiment.
  • FIG. 6 shows a method according to another embodiment.
  • DETAILED DESCRIPTION
  • Various embodiments of the present invention will now be described in detail with reference to a number of drawings. The embodiments show processing modules, systems, and methods in which offload processors are included on offload modules that connect to a system memory bus. Such offload processors are in addition to any host processors connected to the system memory bus, and can operate on data transferred over the system memory bus independent of any host processors. In particular embodiments, offload processors have access to a low latency memory, which can enable rapid storage and retrieval of context data for rapid context switching. In very particular embodiments, processing modules can populate physical slots for connecting in-line memory modules (e.g., DIMMs) to a system memory bus.
  • In some embodiments, computing tasks can be automatically executed by offload processors according to data embedded within write data received over the system memory bus. In particular embodiments, such write data can include a “metadata” portion that identifies how the write data is to be processed.
  • FIG. 2-0 is a block diagram of a processing module 200 according to one embodiment. A processing module 200 can include a physical in-line module connector 202, a memory interface 204, arbiter logic 206, offload processor(s) 208, local memory 210, and control logic 212. A connector 202 can provide a physical connection to system memory bus. This is in contrast to a host processor which can access a system memory bus via a memory controller, or the like. In very particular embodiments, a connector 202 can be compatible with a dual in-line memory module (DIMM) slot of a computing system. Accordingly, a system including multiple DIMM slots can be populated with one or more processing modules 200, or a mix of processing modules and DIMM modules.
  • A memory interface 204 can detect data transfers on a system memory bus, and in appropriate cases, enable write data to be stored in the processing module 200 and/or read data to be read out from the processing module 200. In some embodiments, a memory interface 204 can be a slave interface, thus data transfers are controlled by a master device separate from the processing module. In very particular embodiments, a memory interface 204 can be a direct memory access (DMA) slave, to accommodate DMA transfers over a system memory initiated by a DMA master. Such a DMA master can be a device different from a host processor. In such configurations, processing module 200 can receive data for processing (e.g., DMA write), and transfer processed data out (e.g., DMA read) without consuming host processor resources.
  • Arbiter logic 206 can arbitrate between conflicting accesses of data within processing module 200. In some embodiments, arbiter logic 206 can arbitrate between accesses by offload processor 208 and accesses external to the processor module 200. It is understood that a processing module 200 can include multiple locations that are operated on at the same time. It is understood that accesses arbitrated by arbiter logic 206 can include accesses to physical system memory space occupied by the processor module 200, as well as accesses to resources (e.g., processor resources). Accordingly, arbitration rules for arbiter logic 206 can vary according to application. In some embodiments, such arbitration rules are fixed for a given processor module 200. In such cases, different applications can be accommodated by switching out different processing modules. However, in alternate embodiments, such arbitration rules can be configurable.
  • Offload processor 208 can include one or more processors that can operate on data transferred over the system memory bus. In some embodiments, offload processors can run a general operating system which can run an application, such as Apache (as but one very particular example), enabling processor contexts to be saved and retrieved. Computing tasks executed by offload processor 208 can be handled by the hardware scheduler. Offload processors 208 can operate on data buffered in the processor module 200. In addition or alternatively, offload processors 208 can access data stored elsewhere in a system memory space. In some embodiments, offload processors 208 can include a cache memory configured to store context information. An offload processor 208 can include multiple cores or one core.
  • A processor module 200 can be included in a system having a host processor (not shown). In some embodiments, offload processors 208 can be a different type of processor as compared to the host processor. In particular embodiments, offload processors 208 can consume less power and/or have less computing power than a host processor. In very particular embodiments, offload processors 208 can be “wimpy” core processors, while a host processor can be a “brawny” core processor. In alternate embodiments, offload processors 208 can have equivalent computing power to any host processor. In very particular embodiments, a host processor can be an x86 type processor, while an offload processor 208 can include an ARM, ARC, Tensilica, MIPS, Strong/ARM, or RISC type processor, as but a few examples.
  • Local memory 210 can be connected to offload processor 208 to enable the storing of context information. Accordingly, an offload processor 208 can store current context information, and then switch to a new computing task, then subsequently retrieve the context information to resume the prior task. In very particular embodiments, local memory 210 can be a low latency memory with respect to other memories in a system. In some embodiments, storing of context information can include copying an offload processor 208 cache.
  • In some embodiments, a same space within local memory 210 is accessible by multiple offload processors 208 of the same type. In this way, a context stored by one offload processor can be resumed by a different offload processor.
  • Control logic 212 can control processing tasks executed by offload processor(s). In some embodiments, control logic 212 can be considered a hardware scheduler that can be conceptualized as including a data evaluator 214, scheduler 216 and a switch controller 218. A data evaluator 214 can extract “metadata” from write data transferred over a system memory bus. “Metadata”, as used herein, can be any information embedded at one or more predetermined locations of a block of write data that indicates processing to be performed on all or a portion of the block of write data and/or indicate a particular task/process to which the data belongs (e.g., classification data). In some embodiments, metadata can be data that indicates a higher level organization for the block of write data. As but one very particular embodiment, metadata can be header information of one or more network packets (which may or may not be encapsulated within a higher layer packet structure).
  • A scheduler 216 can order computing tasks for offload processor(s) 208. In some embodiments, scheduler 216 can generate a schedule that is continually updated as write data for processing is received. In very particular embodiments, a scheduler 216 can generate such a schedule based on the ability to switch contexts of offload processor(s) 208. In this way, on-module computing priorities can be adjusted on the fly. In very particular embodiments, a scheduler 216 can assign a portion of physical address space (e.g., memory locations within local memory 210) to an offload processor 208, according to computing tasks. The offload processor 208 can then switch between such different spaces, saving context information prior to each switch, and subsequently restoring context information when returning to the memory space.
  • Switch controller 218 can control computing operations of offload processor(s) 208. In particular embodiments, according to scheduler 216, switch controller 218 can order offload processor(s) 208 to switch contexts. It is understood that a context switch operation can be an “atomic” operation, executed in response to a single command from switch controller 218. In addition or alternatively, a switch controller 218 can issue an instruction set that stores current context information, recalls context information, etc.
  • In some embodiments, processor module 200 can include a buffer memory (not shown). A buffer memory can store received write data on board the processor module. A buffer memory can be implemented on an entirely different set of memory devices, or can be a memory embedded with logic and/or the offload processor. In the latter case, arbiter logic 206 can arbitrate access to the buffer memory. In some embodiments, a buffer memory can correspond to a portion of a system physical memory space. The remaining portion of the system memory space can correspond to other like processor modules and/or memory modules connected to the same system memory bus. In some embodiments buffer memory can be different than local memory 210. For example, buffer memory can have a slower access time than local memory 210. However, in other embodiments, buffer memory and local memory can be implemented with like memory devices.
  • In very particular embodiments, write data for processing can have an expected maximum flow rate. A processor module 200 can be configured to operate on such data at, or faster than, such a flow rate. In this way, a master device (not shown) can write data to a processor module without danger of overwriting data “in process”.
  • The various computing elements of a processor module 200 can be implemented as one or more integrated circuit devices (ICs). It is understood that the various components shown in FIG. 2-0 can be formed in the same or different ICs. For example, control logic 212, memory interface 214, and/or arbiter logic 206 can be implemented on one or more logic ICs, while offload processor(s) 208 and local memory 210 are separate ICs. Logic ICs can be fixed logic (e.g., application specific ICs), programmable logic (e.g., field programmable gate arrays, FPGAs), or combinations thereof.
  • Advantageously, the foregoing hardware and systems can provide improved computational performance as compared to traditional computing systems. Conventional systems, including those based on x86 processors, are often ill-equipped to handle such high volume applications. Even idling, x86 processors use a significant amount of power, and near continuous operation for high bandwidth packet analysis or other high volume processing tasks make the processor energy costs one of the dominant price factors.
  • In addition, conventional systems can have issues with the high cost of context switching wherein a host processor is required to execute instructions which can include switching from one thread to another. Such a switch can require storing and recalling the context for the thread. If such context data is resident in a host cache memory, such a context switch can occur relatively quickly. However, if such context data is no longer in cache memory (i.e., a cache miss), the data must be recalled from system memory, which can incur a multi-cycle latency. Continuous cache misses during context switching can adversely impact system performance.
  • FIG. 2-1 shows a processor module 200-1 according to one very particular embodiment which is capable of reducing issues associated with high volume processing or context switching associated with many conventional server systems. A processor module 200-1 can include ICs 220-0/1 mounted to a printed circuit board (PCB) type substrate 222. PCB type substrate 222 can include in-line module connector 202, which in one very particular embodiment, can be a DIMM compatible connector. IC 220-0 can be a system-on-chip (SoC) type device, integrating multiple functions. In the very particular embodiment shown, an IC 220-0 can include embedded processor(s), logic and memory. Such embedded processor(s) can be offload processor(s) 208 as described herein, or equivalents. Such logic can be any of controller logic 212, memory interface 204 and/or arbiter logic 206, as described herein, or equivalents. Such memory can be any of local memory 210, cache memory for offload processor(s) 208, or buffer memory, as described herein, or equivalents. Logic IC 220-1 can provide logic functions not included IC 220-0.
  • FIG. 2-2 shows a processor module 200-2 according to another very particular embodiment. A processor module 200-2 can include ICs 220-2, -3, -4, -5 mounted to a PCB type substrate 222, like that of FIG. 2-1. However, unlike FIG. 2-1, processor module functions are distributed among single purpose type ICs. IC 220-2 can be a processor IC, which can be an offload processor 208. IC 220-3 can be a memory IC which can include local memory 210, buffer memory, or combinations thereof. IC 220-4 can be a logic IC which can include control logic 212, and in one very particular embodiment, can be an FPGA. IC 220-5 can be another logic IC which can include memory interface 204 and arbiter logic 206, and in one very particular embodiment, can also be an FPGA.
  • It is understood that FIGS. 2-1 and 2-2 represent but two of various implementations. The various functions of a processor module can be distributed over any suitable number of ICs, including a single SoC type IC.
  • FIG. 2-3 shows an opposing side of a processor module 200-1 or 200-2 according to a very particular embodiment. Processor module 200-3 can include a number of memory ICs, one shown as 220-6, mounted to a PCB type substrate 222, like that of FIG. 2-1. It is understood that various processing and logic components can be mounted on an opposing side to that shown. A memory IC 220-6 can be configured to represent a portion of the physical memory space of a system. Memory ICs 220-6 can perform any or all of the following functions: operate independently of other processor module components, providing system memory accessed in a conventional fashion; serve as buffer memory, storing write data that can be processed with other processor module components, or serve as local memory for storing processor context information.
  • FIG. 2-4 shows a conventional DIMM module (i.e., it serves only a memory function) that can populate a memory bus along with processor modules as described herein, or equivalents.
  • FIG. 2-5 shows a system 230 according to one embodiment. A system 230 can include a system memory bus 228 accessible via multiple in-line module slots (one shown as 226). According to embodiments, any or all of the slots 226 can be occupied by a processor module 200 as described herein, or an equivalent. In the event all slots 226 are not occupied by a processor module 200, available slots can be occupied by conventional in-line memory modules 224. In a very particular embodiment, slots 226 can be DIMM slots.
  • In some embodiments, a processor module 200 can occupy one slot. However, in other embodiments, a processor module can occupy multiple slots.
  • In some embodiments, a system memory bus 228 can be further interfaced with one or more host processors and/or input/output device (not shown).
  • Having described processor modules according to various embodiments, operations of a processor module according to particular embodiments will now be described.
  • FIGS. 2-6 to 2-11 show processor module operations according to various embodiments. FIGS. 2-6 to 2-11 show a processor module like that of FIG. 2-0, along with a system memory bus 228, and a buffer memory 232. It is understood that in some embodiments, a buffer memory 232 can part of processor module 200. In such a case, arbitration between accesses via system memory bus 228 and offload processors can be controlled by arbiter logic 206.
  • Referring to FIG. 2-6, write data 234-0 can be received on system memory bus 228 (circle “1”). In some embodiments, such an action can include the writing of data to a particular physical address space range of a system memory. In a very particular embodiment, such an action can be a DMA write independent of any host processor. Write data 234-0 can include metadata (MD) as well as data to be processed (Data). In the embodiment shown, write data 234-0 can correspond to a particular processing operation (Session0).
  • Control logic 212 can access metadata (MD) of the write data 234-0 to determine a type of processing to be performed (circle “2”) and/or classification of such data. In some embodiments, such an action can include a direct read from a physical address (i.e., MD location is at a predetermined location). In addition or alternatively, such an action can be an indirect read (i.e., MD is accessed via pointer, or the like). The action shown by circle “2” can be performed by any of: a read by control logic 212 or read by an offload processor 208.
  • From extracted metadata, scheduler 216 can create a processing schedule, or modify an existing schedule to accommodate the new computing task (circle “3”).
  • Referring to FIG. 2-7, in response to a scheduler 216, the switch controller 218 can direct one or more offload processors 208 be begin processing data according to MD of the write data (circles “4”, “5”). Such processing of data can include any of the following and equivalents: offload processor 208 can process write data stored in a buffer memory of the processor module 200, with accesses being arbitrated by arbiter logic 206, offload processor 208 can operate on data previously received, offload processor 208 can receive and operate on data stored at a location different than the processor module 200.
  • Referring to FIG. 2-8, additional write data 234-1 can be received on system memory bus 228 (circle “6”). Write data 234-1 can include metadata that indicates a different processing operation (Session1) than that for write data 234-0. Control logic 212 can access metadata (MD) of the new write data 234-1 to determine a type of processing to be performed (circle “7”). From extracted metadata, the scheduler 216 can modify the current schedule to accommodate the new computing task (circle “8”). In the particular example shown, the modified schedule re-tasks offload processor 208. Thus, switch controller 218 can direct the offload processor 208 to store its current context (ContextA) in local memory 210 (circle “9”).
  • Referring to FIG. 2-9, in response to switch controller 218, offload processor(s) 208 can begin the new processing task (circle “10”). Consequently, offload processor(s) 208 can maintain a new context (ContextB) corresponding to the new processing task.
  • Referring to FIG. 2-10, a processing task by offload processor 208 can be completed. In the very particular embodiment shown, such processing can modify write data 234-1, and such data can be read out over system memory bus 228 (circle “11”). In response to the completion of processing task, scheduler 216 can update a schedule. In the example shown, in response to the updated schedule, switch controller 218 can direct offload processor(s) 208 to restore the previously saved context (ContextA) from local memory 210 (circle “12”). As understood from above, a restored context (e.g., ContextA) may have been stored by an offload processor different from the one that saved the context in the first place.
  • Referring to FIG. 2-11, with a previous context restored, offload processor(s) 208 can return to processing data according to the previous task (Session0) (circle “13”).
  • FIG. 2-12 shows a method 240 according an embodiment. A method 240 can include detecting the write of session data to a system memory with a module interface 242. Such an action can include determining if received write data has metadata (i.e., data identifying a particular processing). It is understood that “session data” is data corresponding to a particular processing task. Further, it is understood that MD accompanying (or embedded within) session data can identify sessions having priorities with respect to one another. In particular embodiments, a module interface can be a slave interface for an in-line module.
  • A method 240 can determine if current offload processing is sufficient for a new session or change of session 244. Such an action takes into account a processing time required for any current sessions.
  • If current processing resources can accommodate new session requirements (Y from 244), a hardware schedule (schedule for controlling offload processor(s)) can be revised and the new session can be assigned to an offload processor. If current processing resources cannot accommodate new session requirements (N from 244), one or more offload processors can be selected for re-tasking (e.g., a context switch) 250 and the hardware schedule can be modified accordingly 252. The selected offload processors can save their current context data 254 and then switch to the new session 256. In some embodiments, revision of a hardware schedule (252) can include storing a context switch (e.g., in the case a new session has a lower priority than current sessions). In such a case, actions 254 and 256 would not occur until a later point in time.
  • FIG. 2-13 shows a method 260 according another embodiment. A method 260 can include determining if a computing session for an offload processor is complete 262 or has been terminated 264. In such cases (Y from 262/264), it can be determined if the freed module offload processor (i.e., an offload processor whose session is complete/terminated) has a stored context 266. That is, it can be determined if freed processor was previously operating on a session.
  • If a free offload processor was operating according to another session (Y from 266), the offload processor can restore the previous context 268. If a free offload processor has no stored context, it can be assigned to an existing session (if possible) 270. An existing hardware schedule can be updated correspondingly 272.
  • Processor modules according to embodiments herein can be employed to accomplish various processing tasks. According to some embodiments, processor modules can be attached to a system memory bus to operate on network packet data. Such embodiments will now be described.
  • FIG. 1-0 shows a system 101 that can transport packet data to one or more computational units (one shown as 100) located on a module, which in particular embodiments, can include a connector compatible with an existing memory module. In some embodiments, a computational unit 100 can include a processor module as described in embodiments herein, or an equivalent. A computational unit 100 can be capable of intercepting or otherwise accessing packets sent over a memory bus 116 and carrying out processing on such packets, including but not limited to termination or metadata processing. A system memory bus 116 can be a system memory bus like those described herein, or equivalents (e.g., 228).
  • According to some embodiments, packets corresponding to a particular flow can be transported to a storage location accessible by, or included within computational unit 100. Such transportation can occur without consuming resources of a host processor module 106 c, connected to memory bus 116. In particular embodiments, such transport can occur without interrupting the host processor module 106 c. In such an arrangement, a host processor module 106 c does not have to handle incoming flows. Incoming flows can be directed to computational unit 100, which in particular embodiments can include a general purpose processor 108 i. Such general purpose processors 108 i can be capable of running code for terminating incoming flows.
  • In one very particular embodiment, a general purpose processor 108 i can run code for terminating particular network flow session types, such as Apache video sessions, as but one example.
  • In addition or alternatively, a general purpose processor 108 i can process metadata of a packet. In such embodiments, such metadata can include one or more fields of a header for the packet, or a header encapsulated further within the packet.
  • Referring still to FIG. 1-0, according to embodiments, a system 101 can carry out any of the following functions: 1) transport packets of a flow to a destination occupied by, or accessible by, a computational unit 100 without interrupting a host processor module 106 c; 2) transport packets to an offload processor 108 i capable of terminating session flows (i.e., the offload processor is responsible for terminating session flows); 3) transport packets to midplane switch that can process the metadata associated with a packet and make a switching decision; 4) provide a novel high speed packet terminating system.
  • Conventional packet processing systems can utilize host processors for packet termination. However, due to the context switching involved in handling multiple sessions, conventional approaches require significant processing overhead for such context switching, and can incur memory access and network stack delay.
  • In contrast to conventional approaches, embodiments as disclosed herein can enable high speed packet termination by reducing context switch overhead of a host processor. Embodiments can provide any of the following functions: 1) offload computation tasks to one or more processors via a system memory bus, without the knowledge of the host processor, or significant host processor involvement; 2) interconnect servers in a rack or amongst racks by employing offload processors as switches; or 3) use I/O virtualization to redirect incoming packets to different offload processors.
  • Referring still to FIG. 1-0, a system 101 can include an I/O device 102 which can receive packet or other I/O data from an external source. In some embodiments I/O device 102 can include physical or virtual functions generated by the physical device to receive a packet or other I/O data from the network or another computer or virtual machine. In the very particular embodiment shown, an I/O device 102 can include a network interface card (NIC) having input buffer 102 a (e.g., DMA ring buffer) and an I/O virtualization function 102 b.
  • According to embodiments, an I/O device 102 can write a descriptor including details of the necessary memory operation for the packet (i.e. read/write, source/destination). Such a descriptor can be assigned a virtual memory location (e.g., by an operating system of the system 101). I/O device 102 then communicates with an input output memory management unit (IOMMU) 104 which can translate virtual addresses to corresponding physical addresses with an IOMMU function 104 b. In the particular embodiment shown, a translation look-aside buffer (TLB) 104 a can be used for such translation. Virtual function reads or writes data between I/O device and system memory locations can then be executed with a direct memory transfer (e.g., DMA) via a memory controller 106 b of the system 101. An I/O device 102 can be connected to IOMMU 104 by a host bus 112. In one very particular embodiment, a host bus 112 can be a peripheral interconnect (PCI) type bus. IOMMU 104 can be connected to a host processing section 106 at a central processing unit I/O (CPUIO) 106 a. In the embodiment shown, such a connection 114 can support a HyperTransport (HT) protocol.
  • In the embodiment shown, a host processing section 106 can include the CPUIO 106 a, memory controller 106 b, processing core 106 c and corresponding provisioning agent 106 d.
  • In particular embodiments, a computational unit 100 can interface with the system bus 116 via standard in-line module connection, which in very particular embodiments can include a DIMM type slot. In the embodiment shown, a memory bus 116 can be a DDR3 type memory bus. Alternate embodiments can include any suitable system memory bus. Packet data can be sent by memory controller 106 b via memory bus 116 to a DMA slave interface 110 a. DMA slave interface 110 a can be adapted to receive encapsulated read/write instructions from a DMA write over the memory bus 116.
  • A hardware scheduler (108 b/c/d/e/h) can perform traffic management on incoming packets by categorizing them according to flow using session metadata. Packets can be queued for output in an onboard memory (110 b/108 a/108 m) based on session priority. When the hardware scheduler determines that a packet for a particular session is ready to be processed by the offload processor 108 i, the onboard memory is signaled for a context switch to that session. Utilizing this method of prioritization, context switching overhead can be reduced, as compared to conventional approaches. That is, a hardware scheduler can handle context switching decisions and thus optimize the performance of the downstream resource (e.g., offload processor 108 i).
  • As noted above, in very particular embodiments, an offload processor 108 i can be a “wimpy” core” type processor. According to some embodiments, a host processor 106 c can be a “brawny core” type processor (e.g., an x86 or any other processor capable of handling “heavy touch” computational operations). While an I/O device 102 can be configured to trigger host processor interrupts in response to incoming packets, according to embodiments, such interrupts can be disabled, thereby reducing processing overhead for the host processor 106 c. In some very particular embodiments, an offload processor 108 i can include an ARM, ARC, Tensilica, MIPS, Strong/ARM or any other processor capable of handling “light touch” operations. Preferably, an offload processor can run a general purpose operating system for executing a plurality of sessions, which can be optimized to work in conjunction with the hardware scheduler in order to reduce context switching overhead.
  • Referring still to FIG. 1-0, in operation, a system 101 can receive packets from an external network over a network interface. The packets are destined for either a host processor 106 c or an offload processor 108 i based on the classification logic and schematics employed by I/O device 102. In particular embodiments, I/O device 102 can operate as a virtualized NIC, with packets for a particular logical network or to a certain virtual MAC (VMAC) address can be directed into separate queues and sent over to the destination logical entity. Such an arrangement can transfer packets to different entities. In some embodiments, each such entity can have a virtual driver, a virtual device model that it uses to communicate with virtual network interfaces it is connected to.
  • According to embodiments, multiple devices can be used to redirect traffic to specific memory addresses. So, each of the network devices operates as if it is transferring the packets to the memory location of a logical entity. However, in reality, such packets are transferred to memory addresses where they can be handled by one or more offload processors (e.g., 108 i). In particular embodiments such transfers are to physical memory addresses, thus logical entities can be removed from the processing, and a host processor can be free from such packet handling.
  • Accordingly, embodiments can be conceptualized as providing a memory “black box” to which specific network data can be fed. Such a memory black box can handle the data (e.g., process it) and respond back when such data is requested.
  • Referring still to FIG. 1-0, according to some embodiments, I/O device 102 can receive data packets from a network or from a computing device. The data packets can have certain characteristics, including transport protocol number, source and destination port numbers, source and destination IP addresses, for example. The data packets can further have metadata that is processed (108 d) that helps in their classification and management.
  • I/O device 102 can include, but is not limited to, peripheral component interconnect (PCI) and/or PCI express (PCIe) devices connecting with a host motherboard via PCI or PCIe bus 9 (e.g., 112). Examples of I/O devices include a network interface controller (NIC), a host bus adapter, a converged network adapter, an ATM network interface, etc.
  • In order to provide for an abstraction scheme that allows multiple logical entities to access the same I/O device 102, the I/O device may be virtualized to provide for multiple virtual devices each of which can perform some of the functions of the physical I/O device. The 10 virtualization program (e.g., 102 b) according to an embodiment, can redirect traffic to different memory locations (and thus to different offload processors attached to modules on a memory bus). To achieve this, an I/O device 102 (e.g., a network card) may be partitioned into several function parts; including controlling function (CF) supporting input/output virtualization (IOV) architecture (e.g., single-root IOV) and multiple virtual function (VF) interfaces. Each virtual function interface may be provided with resources during runtime for dedicated usage. Examples of the CF and VF may include the physical function and virtual functions under schemes such as Single Root I/O Virtualization or Multi-Root I/O Virtualization architecture. The CF acts as the physical resources that sets up and manages virtual resources. The CF is also capable of acting as a full-fledged 10 device. The VF is responsible for providing an abstraction of a virtual device for communication with multiple logical entities/multiple memory regions.
  • The operating system/the hypervisor/any of the virtual machines/user code running on a host processor 106 c may be loaded with a device model, a VF driver and a driver for a CF. The device model may be used to create an emulation of a physical device for the host processor 106 c to recognize each of the multiple VFs that are created. The device model may be replicated multiple times to give the impression to a VF driver (a driver that interacts with a virtual 10 device) that it is interacting with a physical device of a particular type.
  • For example, a certain device module may be used to emulate a network adapter such as the Intel® Ethernet Converged Network Adapter (CNA) X540-T2, so that the I/O device 102 believes it is interacting with such an adapter. In such a case, each of the virtual functions may have the capability to support the functions of the above said CNA, i.e., each of the Physical Functions should be able to support such functionality. The device model and the VF driver can be run in either privileged or non-privileged mode. In some embodiments, there is no restriction with regard to who hosts/runs the code corresponding to the device model and the VF driver. The code, however, has the capability to create multiple copies of device model and VF driver so as to enable multiple copies of said I/O interface to be created.
  • An application or provisioning agent 106 d, as part of an application/user level code running in a kernel, may create a virtual I/O address space for each VF, during runtime and allocate part of the physical address space to it. For example, if an application handling the VF driver instructs it to read or write packets from or to memory addresses 0xaaaa to 0xffff, the device driver may write I/O descriptors into a descriptor queue with a head and tail pointer that are changed dynamically as queue entries are filled. The data structure may be of another type as well, including but not limited to a ring structure 102 a or hash table.
  • The VF can read from or write data to the address location pointed to by the driver. Further, on completing the transfer of data to the address space allocated to the driver, interrupts, which are usually triggered to the host processor to handle said network packets, can be disabled. Allocating a specific I/O space to a device can include allocating said IO space a specific physical memory space occupied.
  • In another embodiment, the descriptor may comprise only a write operation, if the descriptor is associated with a specific data structure for handling incoming packets. Further, the descriptor for each of the entries in the incoming data structure may be constant so as to redirect all data write to a specific memory location. In an alternate embodiment, the descriptor for consecutive entries may point to consecutive entries in memory so as to direct incoming packets to consecutive memory locations.
  • Alternatively, said operating system may create a defined physical address space for an application supporting the VF drivers and allocate a virtual memory address space to the application or provisioning agent 106 d, thereby creating a mapping for each virtual function between said virtual address and a physical address space. Said mapping between virtual memory address space and physical memory space may be stored in IOMMU tables (e.g., a TLB 104 a). The application performing memory reads or writes may supply virtual addresses to say virtual function, and the host processor OS may allocate a specific part of the physical memory location to such an application.
  • Alternatively, VF may be configured to generate requests such as read and write which may be part of a direct memory access (DMA) read or write operation, for example. The virtual addresses is be translated by the IOMMU 104 to their corresponding physical addresses and the physical addresses may be provided to the memory controller for access. That is, the IOMMU 104 may modify the memory requests sourced by the I/O devices to change the virtual address in the request to a physical address, and the memory request may be forwarded to the memory controller for memory access. The memory request may be forwarded over a bus 114 that supports a protocol such as HyperTransport 114. The VF may in such cases carry out a direct memory access by supplying the virtual memory address to the IOMMU 104.
  • Alternatively, said application may directly code the physical address into the VF descriptors if the VF allows for it. If the VF cannot support physical addresses of the form used by the host processor 106 c, an aperture with a hardware size supported by the VF device may be coded into the descriptor so that the VF is informed of the target hardware address of the device. Data that is transferred to an aperture may be mapped by a translation table to a defined physical address space in the system memory. The DMA operations may be initiated by software executed by the processors, programming the I/O devices directly or indirectly to perform the DMA operations.
  • Referring still to FIG. 1-0, in particular embodiments, parts of computational unit 100 can be implemented with one or more FPGAs. In the system of FIG. 1-0, computational unit 100 can include FPGA 110 in which can be formed a DMA slave device module 110 a and arbiter 110 f. A DMA slave module 110 a can be any device suitable for attachment to a memory bus 116 that can respond to DMA read/write requests. In alternate embodiments, a DMA slave module 110 a can be another interface capable of block data transfers over memory bus 116. The DMA slave module 110 a can be capable of receiving data from a DMA controller (when it performs a read from a ‘memory’ or from a peripheral) or transferring data to a DMA controller (when it performs a write instruction on the DMA slave module 110 a). The DMA slave module 110 a may be adapted to receive DMA read and write instructions encapsulated over a memory bus, (e.g., in the form of a DDR data transmission, such as a packet or data burst), or any other format that can be sent over the corresponding memory bus.
  • A DMA slave module 110 a can reconstruct the DMA read/write instruction from the memory R/W packet. The DMA slave module 110 a may be adapted to respond to these instructions in the form of data reads/data writes to the DMA master, which could either be housed in a peripheral device, in the case of a PCIe bus, or a system DMA controller in the case of an ISA bus.
  • I/O data that is received by the DMA device 110 a can then queued for arbitration. Arbitration can include the process of scheduling packets of different flows, such that they are provided access to available bandwidth based on a number of parameters. In general, an arbiter 110 f provides resource access to one or more requestors. If multiple requestors request access, an arbiter 110 f can determine which requestor becomes the accessor and then passes data from the accessor to the resource interface, and the downstream resource can begin execution on the data. After the data has been completely transferred to a resource, and the resource has competed execution, the arbiter 110 f can transfer control to a different requestor and this cycle repeats for all available requestors. In the embodiment of FIG. 1-10, arbiter 110 f can notify other portions of computational unit 100 (e.g., 108) of incoming data.
  • Alternatively, a computation unit 100 can utilize an arbitration scheme shown in U.S. Pat. No. 7,813,283, issued to Dalal on Oct. 12, 2010, the contents of which are incorporated herein by reference. Other suitable arbitration schemes known in art could be implemented in embodiments herein. Alternatively, the arbitration scheme of the current invention might be implemented using an OpenFlow switch and an OpenFlow controller.
  • In the very particular embodiment of FIG. 1-0, computational unit 100 can further include notify/prefetch circuits 110 c which can prefetch data stored in a buffer memory 110 b in response to DMA slave module 110 a, and as arbitrated by arbiter 110 f. Further, arbiter 110 f can access other portions of the computational unit 100 via a memory mapped I/O ingress path 110 e and egress path 110 g.
  • Referring to FIG. 1-0, a hardware scheduler can include a scheduling circuit 108 b/n to implement traffic management of incoming packets. Packets from a certain source, relating to a certain traffic class, pertaining to a specific application or flowing to a certain socket are referred to as part of a session flow and are classified using session metadata. Such classification can be performed by classifier 108 e.
  • In some embodiments, session metadata 108 d can serve as the criterion by which packets are prioritized and scheduled and as such, incoming packets can be reordered based on their session metadata. This reordering of packets can occur in one or more buffers and can modify the traffic shape of these flows. The scheduling discipline chosen for this prioritization, or traffic management (TM), can affect the traffic shape of flows and micro-flows through delay (buffering), bursting of traffic (buffering and bursting), smoothing of traffic (buffering and rate-limiting flows), dropping traffic (choosing data to discard so as to avoid exhausting the buffer), delay jitter (temporally shifting cells of a flow by different amounts) and by not admitting a connection (e.g., cannot simultaneously guarantee existing service (SLAs) with an additional flow's SLA).
  • According to embodiments, computational unit 100 can serve as part of a switch fabric, and provide traffic management with depth-limited output queues, the access to which is arbitrated by a scheduling circuit 108 b/n. Such output queues are managed using a scheduling discipline to provide traffic management for incoming flows. The session flows queued in each of these queues can be sent out through an output port to a downstream network element.
  • It is noted that a conventional traffic management circuit doesn't take into account the handling and management of data by downstream elements except for meeting the SLA agreements it already has with said downstream elements.
  • In contrast, according to embodiments a scheduler circuit 108 b/n can allocate a priority to each of the output queues and carry out reordering of incoming packets to maintain persistence of session flows in these queues. A scheduler circuit 108 b/n can be used to control the scheduling of each of these persistent sessions into a general purpose operating system (OS) 108 j, executed on an offload processor 108 i. Packets of a particular session flow, as defined above, can belong to a particular queue. The scheduler circuit 108 b/n may control the prioritization of these queues such that they are arbitrated for handling by a general purpose (GP) processing resource (e.g., offload processor 108 i) located downstream. An OS 108 j running on a downstream processor 108 i can allocate execution resources such as processor cycles and memory to a particular queue it is currently handling. The OS 108 j may further allocate a thread or a group of threads for that particular queue, so that it is handled distinctly by the general purpose processing element 108 i as a separate entity. The fact that there can be multiple sessions running on a GP processing resource, each handling data from a particular session flow resident in a queue established by the scheduler circuit, tightly integrates the scheduler and the downstream resource (e.g., 108 i). This can bring about persistence of session information across the traffic management and scheduling circuit and the general purpose processing resource 108 j.
  • Dedicated computing resources (e.g., 108 i), memory space and session context information for each of the sessions can provide a way of handling, processing and/or terminating each of the session flows at the general purpose processor 108 i. The scheduler circuit 108 b/n can exploit this functionality of the execution resource to queue session flows for scheduling downstream. The scheduler circuit 108 b/n can be informed of the state of the execution resource(s) (e.g., 108 i), the current session that is run on the execution resource; the memory space allocated to it, the location of the session context in the processor cache.
  • According to embodiments, a scheduler circuit 108 b/n can further include switching circuits to change execution resources from one state to another. The scheduler circuit 108 b/n can use such a capability to arbitrate between the queues that are ready to be switched into the downstream execution resource. Further, the downstream execution resource can be optimized to reduce the penalty and overhead associated with context switch between resources. This is further exploited by the scheduler circuit 108 b/n to carry out seamless switching between queues, and consequently their execution as different sessions by the execution resource.
  • A scheduler circuit 108 b/n according to embodiments can schedule different sessions on a downstream processing resource, wherein the two are operated in coordination to reduce the overhead during context switches. An important factor in decreasing the latency of services and engineering computational availability can be hardware context switching synchronized with network queuing. In embodiments, when a queue is selected by a traffic manager, a pipeline coordinates swapping in of the cache (e.g., L2 cache) of the corresponding resource (e.g., 108 i) and transfers the reassembled I/O data into the memory space of the executing process. In certain cases, no packets are pending in the queue, but computation is still pending to service previous packets. Once this process makes a memory reference outside of the data swapped, the scheduler circuit (108 b/n) can enable queued data from an I/O device 102 to continue scheduling the thread.
  • In some embodiments, to provide fair queuing to a process not having data, a maximum context size can be assumed as data processed. In this way, a queue can be provisioned as the greater of computational resource and network bandwidth resource. As but one very particular example, a computation resource can be an ARM A9 processor running at 800 MHz, while a network bandwidth can be 3 Gbps of bandwidth. Given the lopsided nature of this ratio, embodiments can utilize computation having many parallel sessions (such that the hardware's prefetching of session-specific data offloads a large portion of the host processor load) and having minimal general purpose processing of data.
  • Accordingly, in some embodiments, a scheduler circuit 108 b/n can be conceptualized as arbitrating, not between outgoing queues at line rate speeds, but arbitrating between terminated sessions at very high speeds. The stickiness of sessions across a pipeline of stages, including a general purpose OS, can be a scheduler circuit optimizing any or all such stages of such a pipeline.
  • Alternatively, a scheduling scheme can be used as shown in U.S. Pat. No. 7,760,715 issued to Dalal on Jul. 20, 2010, incorporated herein by reference. This scheme can be useful when it is desirable to rate limit the flows for preventing the downstream congestion of another resource specific to the over-selected flow, or for enforcing service contracts for particular flows. Embodiments can include arbitration scheme that allows for service contracts of downstream resources, such as general purpose OS that can be enforced seamlessly.
  • Referring still to FIG. 1-0, a hardware scheduler according to embodiments herein, or equivalents, can provide for the classification of incoming packet data into session flows based on session metadata. It can further provide for traffic management of these flows before they are arbitrated and queued as distinct processing entities on the offload processors.
  • In some embodiments, offload processors (e.g., 108 i) can be general purpose processing units capable of handling packets of different application or transport sessions. Such offload processors can be low power processors capable of executing general purpose instructions. The offload processors could be any suitable processor, including but not limited to: ARM, ARC, Tensilica, MIPS, StrongARM or any other processor that serves the functions described herein. Such offload processors have a general purpose OS running on them, wherein the general purpose OS is optimized to reduce the penalty associated with context switching between different threads or group of threads.
  • In contrast, context switches on host processors can be computationally intensive processes that require the register save area, process context in the cache and TLB entries to be restored if they are invalidated or overwritten. Instruction Cache misses in host processing systems can lead to pipeline stalls and data cache misses lead to operation stall and such cache misses reduce processor efficiency and increase processor overhead.
  • In contrast, an OS 108 j running on the offload processors 108 i in association with a scheduler circuit 108 b/n, can operate together to reduce the context switch overhead incurred between different processing entities running on it. Embodiments can include a cooperative mechanism between a scheduler circuit and the OS on the offload processor 108 i, wherein the OS sets up session context to be physically contiguous (physically colored allocator for session heap and stack) in the cache; then communicates the session color, size, and starting physical address to the scheduler circuit upon session initialization. During an actual context switch, a scheduler circuit can identify the session context in the cache by using these parameters and initiate a bulk transfer of these contents to an external low latency memory. In addition, the scheduler circuit can manage the prefetch of the old session if its context was saved to a local memory 108 g. In particular embodiments, a local memory 108 g can be low latency memory, such as a reduced latency dynamic random access memory (RLDRAM), as but one very particular embodiment. Thus, in embodiments, session context can be identified distinctly in the cache.
  • In some embodiments, context size can be limited to ensure fast switching speeds. In addition or alternatively, embodiments can include a bulk transfer mechanism to transfer out session context to a local memory 108 g. The cache contents stored therein can then be retrieved and prefetched during context switch back to a previous session. Different context session data can be tagged and/or identified within the local memory 108 g for fast retrieval. As noted above, context stored by one offload processor may be recalled by a different offload processor.
  • In the very particular embodiment of FIG. 1-0, multiple offload processing cores can be integrated into a computation FPGA 108. Multiple computational FPGAs can be arbitrated by arbitrator circuits in another FPGA 110. The combination of computational FPGAs (e.g., 108) and arbiter FPGAs (e.g., 110) are referred to as “XIMM” modules or “Xockets DIMM modules” (e.g., computation unit 100). In particular applications, these XIMM modules can provide integrated traffic and thread management circuits that broker execution of multiple sessions on the offload processors.
  • FIG. 1-0 also shows an offload processor tunnel connection 608 k, as well as a memory interface 108 m and port 1081 (which can be an accelerator coherency port (ACP)). Memory interface 108 m can access buffer memory 108 a.
  • FIG. 1-1 shows a system flow according to an embodiment. Packet or other I/O data can be received at an I/O device 120. An I/O device can be physical device, virtual device or combination thereof. Interrupts generated from the I/O data intended for a host processor 124 can be disabled, allowing such I/O data to be processed without resources of the host processor 124.
  • An IOMMU 121 can map received data to physical addresses of a system address space. DMA master 125 can transmit such data to such memory addresses by operation of a memory controller 122. Memory controller 122 can execute DRAM transfers over a memory bus with a DMA Slave. Upon receiving transferred I/O data, a hardware scheduler 123 can schedule processing of such data with an offload processor 126. In some embodiments, a type of processing can be indicated by metadata within the I/O data. Further, in some embodiments such data can be stored in an onboard memory 129. According to instructions from hardware scheduler 123, one or more offload processors 126 can executing computing functions in response to the I/O data. In some embodiments, such computing functions can operate on the I/O data, and such data can be subsequently read out on memory bus via a read request processed by DMA Slave 127.
  • Parallelization of tasks into multiple thread contexts is well known in art to provide for increased throughput. Processors architectures such as MIPS may include deep instructions pipelines to improve the number of instructions per cycle. Further, the ability to run a multi-threaded programming environment results in enhanced usage of existing processor resources. To further increase parallel execution on the hardware, processor architecture may include multiple processor cores. Multi-core architectures comprising of the same type of cores, referred to as homogeneous core architectures, provide higher instruction throughput by parallelizing threads or processes across multiple cores. However, in such homogeneous core architectures, the shared resources, such as memory, are amortized over a small number of processors.
  • Memory and I/O accesses can incur a high amount of processor overhead. Further, context switches in conventional general purpose processing units can be computationally intensive. It is therefore desirable to reducing context switch overhead in a networked computing resource handling a plurality of networked applications in order to increase processor throughput. Conventional server loads can require complex transport, high memory bandwidth, extreme amounts of data bandwidth (randomly accessed, parallelized, and highly available), but often with light touch processing: HTML, video, packet-level services, security, and analytics. Further, idle processors still consume more than 50% of their peak power consumption.
  • In contrast, according to embodiments herein, complex transport, data bandwidth intensive, frequent random access oriented, ‘light’ touch processing loads can be handled behind a socket abstraction created on the offload processor cores. At the same time, “heavy” touch, computing intensive loads can be handled by a socket abstraction on a host processor core (e.g., x86 processor cores). Such software sockets can allow for a natural partitioning of these loads between ARM and x86 processor cores. By usage of new application level sockets, according to embodiments, server loads can be broken up across the offload processing cores and the host processing cores.
  • FIG. 3 shows protocol stacks that can be included in a system according to embodiments. A host processor (e.g., 106 c) can include a brawny core protocol stack 317. Such a protocol stack 317 can include one or more applications (application) 318 sitting on an operating system (OS) 319. Unlike conventional host processing stacks, an OS can include a Xockets Socket 330 and Xockets Tunneling Driver 320 which can access XIMMs as described herein or equivalents. In particular embodiments, Socket 330 can facilitates communication between a host processor and an offload processor module (e.g., 100) and Driver 320 can enable transmission of packet data to an offload processor module (e.g., 100) (e.g., Ethernet-over-DDR tunneling). A brawny core protocol stack 317 can further include a Hypervisor 312 to supervise sessions and/or enable virtual switches 310 as described herein, or equivalents.
  • An offload processor can include wimpy core protocol stack 300. In the embodiment shown, such a protocol stack 300 can include a single session OS 302 which can run an application 303. Additional software functions 304 can control context switching, prefetching of data, and memory mapped scheduling. As packets belonging to different sessions ingress, the offload processors can rapidly switch contexts and read from different parts of memory in order to service them. Queuing and reassembly functions (320) can take decrypted incoming fragments of data, assemble them into their original form and queue them for processing on one of multiple offload processors onboard a module (e.g., 100). Input-output memory management software (e.g., IOMMU of 308) can be provided in order to facilitate safe sharing and usage of physical memory when the arbitration processor switches between virtual sessions for incoming packets. Direct memory access (e.g., R/DMA of 308) can allow for direct read/write to an internal memory of a module (e.g., 100). An offload processor can also utilize a virtual switching software (312) to provide switching as described herein. Header services (310) can process header data of received packets.
  • Example embodiments of offload processors can include, but are not limited to, ARM A9 Cortex processors, which have a clock speed of 800 MHz and a data handling capacity of 3 Ghz. The queue depth for the traffic management circuit can be configured to be the smaller of the processing power and the network bandwidth. Given the lopsided nature of this ratio, in order to handle complete network bandwidth, sessions can be of a lightweight processing nature. Further, sessions to can be switched with minimum context switch overhead to allow the offload processor to process the high bandwidth network traffic. Further, the offload processors can provide session handling capacity greater than conventional approaches due to the ability to terminate sessions with little or no overhead. The offload processors according to embodiments are favorably disposed to handle complete offload of Apache video routing, as but one very particular embodiment.
  • Alternatively in another embodiment, when equipped with many XIMMs, each containing multiple “wimpy” cores, systems may be placed near the top of rack, where they can be used as a cache for data and a processing resource for rack hot content or hot code, a means for interconnecting between racks and TOR switches, a mid tier between TOR switches and second-level switches, rack-level packet filtering, logging, and analytics, or various types of rack-level control plane agents. Simple passive optical mux/demux-ing can separate high bandwidth ports on the x86 systems into many lower bandwidth ports as needed.
  • Embodiments can be favorably disposed to handle Apache, HTML, and application cache and rack level mid plane functions. In other embodiments, a network of XIMMs and a host x86 processors may be used to provide routing overlays.
  • FIG. 4 is a flow schematic wherein network packets 450 are transferred to offload processors 430 mounted with memory device 410, which can be wimpy core devices, completely without intervention of the host CPU 420, which can be a brawny core device. The offload processors 430 can act as full-fledged processors hosting server applications. In one embodiment, packets 450 can be received via an I/O device 440 (e.g., NIC). A host processor 420 can be free to execute other operations 660 while offload processors 430 service network packets 450.
  • FIG. 5 is an alternate embodiment, in which server loads are partitioned such that packet meta data processing, routing overlays, filtering, packet logging and other hygiene functions are offloaded to the offload processors (530) mounted with memory devices 510, while and the host processor (520) implements server sessions. Offload processors 530 can be wimpy core devices, while host processor 520 can be a brawny core device. As in the case of FIG. 4, packets can flow through an I/O device 540 and offload processors 530 can be mounted with a memory device 510.
  • In another embodiment, a network of offload processor modules (i.e., XIMMs), each comprising a plurality of said offload processors may be employed to provide video overlays by associating said offload processors with local memory elements, including closely located DIMMs or solid state storage devices (SSDs). The network of XIMM modules may be used to perform memory read or writes for prefetching the data contents before they are serviced. In this case, real-time transport protocol (RTP) can be processed before packets enter traffic management, and their corresponding video data can be pre-fetched to match the streaming. Prefetches can be physically issued as (R)DMAs to other (remote) local DIMMs/SSDs. For enterprise applications, the number of the videos is limited and can be kept in local Xockets DIMMs. For public cloud/content delivery network (CDN) applications, this allows a rack to provide a shared memory space for the corpus of videos. The prefetching may be setup from any memory DIMM on any machine.
  • It is anticipated that prefetching can be balanced against peer-to-peer distribution protocols (e.g. P4P) so that blocks of data can be efficiently sourced from all relevant servers. The bandwidth metric indicates how many streams can be sustained when using 10 Mbps (1 Mbps) streams. As the stream bandwidth goes down the number of streams goes up and the same session limitation becomes manifest in the RTP processing of server. Architecture according to such embodiments can allow over 10,000 high definition streams to be sustained in a 1U (one rack unit) form factor.
  • In an alternate embodiment shown in FIG. 6, a complex publish and subscribership model, for handling pipelined computational tasks partitioned across a network of x86 cores and offload processor cores, can be implemented. Each task in the pipeline may be handled by the type of cores that are most favorably disposed for it. For example, offload processor modules (e.g., Xockets DIMMs) may be employed to carry out acceleration of Map-Reduce algorithms by an order of magnitude. The mid-plane defined by Xockets DIMMs can drive and receive the large PCI-e 3.0 bandwidth connecting Map steps with Reduce steps within a rack and outside of the rack. Because the shuffle step is often the bottleneck, the number of reducers is kept to a minimum so that CPUs are not overwhelmed with having to filter keys. With traffic-managed according to embodiments, the number of Reducers can rival the number of Mappers.
  • FIG. 6 shows a method which can start 602 and fetch input data from a file system (e.g., Hadoop Distributed File System) 604. Such data can be fetched to wimpy core devices (e.g., offload processors as described herein or equivalents). Such input data can be partitioned into splits by the wimpy core devices 606. Input pairs (which can include a key and value) for such splits can be obtained 608. A map function can be performed on all input pairs with brawny core devices (e.g., host processor(s)) 610. All the mapping operation results can be reduced and sorted based on key values with brawny core devices 612. Results can be written back to the file system 614. Such an operation can be accomplished via wimpy core devices. A method may then end 616.
  • Alternatively, embodiments can employ the Xocket DIMMs to implement rack level disks using memory mapped file paradigm. Such embodiments can effectively unify all of the contents on the Xockets DIMMs on the rack to every x86 processor socket.
  • It should be appreciated that in the foregoing description of exemplary embodiments of the invention, various features of the invention are sometimes grouped together in a single embodiment, figure, or description thereof for the purpose of streamlining the disclosure aiding in the understanding of one or more of the various inventive aspects. This method of disclosure, however, is not to be interpreted as reflecting an intention that the claimed invention requires more features than are expressly recited in each claim. Rather, as the following claims reflect, inventive aspects lie in less than all features of a single foregoing disclosed embodiment. Thus, the claims following the detailed description are hereby expressly incorporated into this detailed description, with each claim standing on its own as a separate embodiment of this invention.
  • It is also understood that the embodiments of the invention may be practiced in the absence of an element and/or step not specifically disclosed. That is, an inventive feature of the invention may be elimination of an element.
  • Accordingly, while the various aspects of the particular embodiments set forth herein have been described in detail, the present invention could be subject to various changes, substitutions, and alterations without departing from the spirit and scope of the invention.

Claims (20)

What is claimed is:
1. A processor module, comprising:
an in-line module connector configured to physically connect to an in-line memory slot of a system memory bus;
a data interface configured to receive write data from the system memory bus, via the in-line module connector, and according to a predetermined protocol; and
at least one offload processor configured to process the write data according to instruction data within the write data; and wherein hardware scheduling logic mounted in the processor module include an arbiter that arbitrates between conflicting data access requirements within the processor module, and a scheduler to order computing tasks, both arbiter and scheduler being mounted on the in-line module and configured to control operations of the at least one offload processor.
2. The processor module of claim 1, wherein:
the in-line module connector is an in-line memory module connector.
3. The processor module of claim 2, wherein:
the in-line module connector is a dual in-line memory module (DIMM) connector.
4. The processor module of claim 1, wherein:
the data interface includes a dual data rate (DDR) memory interface.
5. The processor module of claim 1, wherein:
the data interface includes a slave interface configured to receive and output data according to request from a master device separate from the processor module.
6. The processor module of claim 5, wherein:
the slave interface includes a direct memory access (DMA) slave interface.
7. The processor module of claim 1, further including:
a buffer memory configured to store the write data, and coupled to the offload processor and the data interface.
8. A processor module, comprising:
an in-line module connector configured to physically connect to an in-line memory slot of a system memory bus;
at least one offload processor configured to process data received over the system memory bus via the in-line module connector; and
a hardware scheduler configured to control the processing executed by the offload processor according to instructions within the received data.
9. The processor module of claim 8, wherein:
the hardware scheduler is configured to vary a processing schedule as different data are received over the system memory bus.
10. The processor module of claim 9, wherein:
the hardware scheduler is configured to issue a context switch indication in response to changes in the processing schedule; and
the offload processor is configured to store a current processing context and switch to a different processing operation in response to the context switch indication.
11. The processor module of claim 10, wherein:
the hardware scheduler is configured to issue a context resume indication in response to changes in the processing schedule; and
the offload processor is configured to recall the stored processing context in response to the context resume indication.
12. The processor module of claim 8, further including:
a buffer memory configured to store the data received over the system memory bus.
13. The processor module of claim 12, wherein:
the buffer memory corresponds to a portion of the physical address space of a system memory; and
the hardware scheduler assigns different processing tasks to predetermine sections of the portion of the physical address space.
14. A processor module, comprising:
a support structure;
an in-line module connector, attached to or formed as part of the support structure, and configured to physically connect to an in-line memory slot of a system memory bus;
at least one offload processor physically mounted to the support structure;
memory circuits physically mounted to the support structure and electrically connected to the offload processor; and
logic circuits physically mounted to the support structure and electrically connected to the offload processor and in-line module connector.
15. The processor module of claim 14, wherein:
the support structure comprises a printed circuit board.
16. The processor module of claim 14, wherein:
the offload processor and memory circuits are formed in different integrated circuit devices mounted to the support structure.
17. The processor module of claim 14, wherein:
the memory circuits comprise
buffer memory circuits formed in at least a first memory integrated circuit device (IC) mounted to the support structure, and
context memory circuits formed in a second memory IC mounted to the support structure.
18. The processor module of claim 17, wherein:
the first memory IC has a slower access speed than the second memory IC.
19. The processor module of claim 14, wherein:
the at least one processor circuit is embedded in an integrated circuit device that also includes at least a portion of the logic circuits.
20. The processor module of claim 14, wherein:
at least a portion of the logic circuits comprise a programmable logic integrated circuit device.
US13/913,409 2013-01-17 2013-06-08 Offload processor modules for connection to system memory, and corresponding methods and systems Abandoned US20140201409A1 (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
US13/913,409 US20140201409A1 (en) 2013-01-17 2013-06-08 Offload processor modules for connection to system memory, and corresponding methods and systems

Applications Claiming Priority (10)

Application Number Priority Date Filing Date Title
US201361753903P 2013-01-17 2013-01-17
US201361753892P 2013-01-17 2013-01-17
US201361753910P 2013-01-17 2013-01-17
US201361753901P 2013-01-17 2013-01-17
US201361753907P 2013-01-17 2013-01-17
US201361753906P 2013-01-17 2013-01-17
US201361753899P 2013-01-17 2013-01-17
US201361753895P 2013-01-17 2013-01-17
US201361753904P 2013-01-17 2013-01-17
US13/913,409 US20140201409A1 (en) 2013-01-17 2013-06-08 Offload processor modules for connection to system memory, and corresponding methods and systems

Publications (1)

Publication Number Publication Date
US20140201409A1 true US20140201409A1 (en) 2014-07-17

Family

ID=51165034

Family Applications (25)

Application Number Title Priority Date Filing Date
US13/913,411 Active - Reinstated 2034-04-01 US9250954B2 (en) 2013-01-17 2013-06-08 Offload processor modules for connection to system memory, and corresponding methods and systems
US13/913,405 Abandoned US20140201408A1 (en) 2013-01-17 2013-06-08 Offload processor modules for connection to system memory, and corresponding methods and systems
US13/913,407 Abandoned US20140201416A1 (en) 2013-01-17 2013-06-08 Offload processor modules for connection to system memory, and corresponding methods and systems
US13/913,409 Abandoned US20140201409A1 (en) 2013-01-17 2013-06-08 Offload processor modules for connection to system memory, and corresponding methods and systems
US13/913,410 Expired - Fee Related US9348638B2 (en) 2013-01-17 2013-06-08 Offload processor modules for connection to system memory, and corresponding methods and systems
US13/921,071 Abandoned US20140201310A1 (en) 2013-01-17 2013-06-18 Network Overlay System and Method Using Offload Processors
US13/921,047 Abandoned US20140201390A1 (en) 2013-01-17 2013-06-18 Network Overlay System and Method Using Offload Processors
US13/921,059 Abandoned US20140201309A1 (en) 2013-01-17 2013-06-18 Network Overlay System and Method Using Offload Processors
US13/924,558 Abandoned US20140198653A1 (en) 2013-01-17 2013-06-22 Scheduling and Traffic Management with Offload Processors
US13/924,560 Abandoned US20140198799A1 (en) 2013-01-17 2013-06-22 Scheduling and Traffic Management with Offload Processors
US13/924,559 Abandoned US20140198803A1 (en) 2013-01-17 2013-06-22 Scheduling and Traffic Management with Offload Processors
US13/924,557 Abandoned US20140198652A1 (en) 2013-01-17 2013-06-22 Scheduling and Traffic Management with Offload Processors
US13/924,621 Abandoned US20140201305A1 (en) 2013-01-17 2013-06-24 Network Overlay System and Method Using Offload Processors
US13/924,619 Abandoned US20140201304A1 (en) 2013-01-17 2013-06-24 Network Overlay System and Method Using Offload Processors
US13/924,618 Abandoned US20140201303A1 (en) 2013-01-17 2013-06-24 Network Overlay System and Method Using Offload Processors
US13/928,336 Abandoned US20140201461A1 (en) 2013-01-17 2013-06-26 Context Switching with Offload Processors
US13/928,339 Abandoned US20140201761A1 (en) 2013-01-17 2013-06-26 Context Switching with Offload Processors
US13/928,335 Abandoned US20140201453A1 (en) 2013-01-17 2013-06-26 Context Switching with Offload Processors
US13/928,337 Abandoned US20140201402A1 (en) 2013-01-17 2013-06-26 Context Switching with Offload Processors
US13/931,914 Active - Reinstated 2033-12-20 US9288101B1 (en) 2013-01-17 2013-06-29 Full bandwidth packet handling with server systems including offload processors
US13/931,907 Active - Reinstated 2034-06-15 US9436639B1 (en) 2013-01-17 2013-06-29 Full bandwidth packet handling with server systems including offload processors
US13/931,905 Active - Reinstated 2034-09-05 US9436638B1 (en) 2013-01-17 2013-06-29 Full bandwidth packet handling with server systems including offload processors
US13/931,913 Active - Reinstated 2034-07-09 US9460031B1 (en) 2013-01-17 2013-06-29 Full bandwidth packet handling with server systems including offload processors
US13/931,910 Active - Reinstated 2034-09-05 US9436640B1 (en) 2013-01-17 2013-06-29 Full bandwidth packet handling with server systems including offload processors
US15/396,323 Active 2033-10-11 US10649924B2 (en) 2013-01-17 2016-12-30 Network overlay systems and methods using offload processors

Family Applications Before (3)

Application Number Title Priority Date Filing Date
US13/913,411 Active - Reinstated 2034-04-01 US9250954B2 (en) 2013-01-17 2013-06-08 Offload processor modules for connection to system memory, and corresponding methods and systems
US13/913,405 Abandoned US20140201408A1 (en) 2013-01-17 2013-06-08 Offload processor modules for connection to system memory, and corresponding methods and systems
US13/913,407 Abandoned US20140201416A1 (en) 2013-01-17 2013-06-08 Offload processor modules for connection to system memory, and corresponding methods and systems

Family Applications After (21)

Application Number Title Priority Date Filing Date
US13/913,410 Expired - Fee Related US9348638B2 (en) 2013-01-17 2013-06-08 Offload processor modules for connection to system memory, and corresponding methods and systems
US13/921,071 Abandoned US20140201310A1 (en) 2013-01-17 2013-06-18 Network Overlay System and Method Using Offload Processors
US13/921,047 Abandoned US20140201390A1 (en) 2013-01-17 2013-06-18 Network Overlay System and Method Using Offload Processors
US13/921,059 Abandoned US20140201309A1 (en) 2013-01-17 2013-06-18 Network Overlay System and Method Using Offload Processors
US13/924,558 Abandoned US20140198653A1 (en) 2013-01-17 2013-06-22 Scheduling and Traffic Management with Offload Processors
US13/924,560 Abandoned US20140198799A1 (en) 2013-01-17 2013-06-22 Scheduling and Traffic Management with Offload Processors
US13/924,559 Abandoned US20140198803A1 (en) 2013-01-17 2013-06-22 Scheduling and Traffic Management with Offload Processors
US13/924,557 Abandoned US20140198652A1 (en) 2013-01-17 2013-06-22 Scheduling and Traffic Management with Offload Processors
US13/924,621 Abandoned US20140201305A1 (en) 2013-01-17 2013-06-24 Network Overlay System and Method Using Offload Processors
US13/924,619 Abandoned US20140201304A1 (en) 2013-01-17 2013-06-24 Network Overlay System and Method Using Offload Processors
US13/924,618 Abandoned US20140201303A1 (en) 2013-01-17 2013-06-24 Network Overlay System and Method Using Offload Processors
US13/928,336 Abandoned US20140201461A1 (en) 2013-01-17 2013-06-26 Context Switching with Offload Processors
US13/928,339 Abandoned US20140201761A1 (en) 2013-01-17 2013-06-26 Context Switching with Offload Processors
US13/928,335 Abandoned US20140201453A1 (en) 2013-01-17 2013-06-26 Context Switching with Offload Processors
US13/928,337 Abandoned US20140201402A1 (en) 2013-01-17 2013-06-26 Context Switching with Offload Processors
US13/931,914 Active - Reinstated 2033-12-20 US9288101B1 (en) 2013-01-17 2013-06-29 Full bandwidth packet handling with server systems including offload processors
US13/931,907 Active - Reinstated 2034-06-15 US9436639B1 (en) 2013-01-17 2013-06-29 Full bandwidth packet handling with server systems including offload processors
US13/931,905 Active - Reinstated 2034-09-05 US9436638B1 (en) 2013-01-17 2013-06-29 Full bandwidth packet handling with server systems including offload processors
US13/931,913 Active - Reinstated 2034-07-09 US9460031B1 (en) 2013-01-17 2013-06-29 Full bandwidth packet handling with server systems including offload processors
US13/931,910 Active - Reinstated 2034-09-05 US9436640B1 (en) 2013-01-17 2013-06-29 Full bandwidth packet handling with server systems including offload processors
US15/396,323 Active 2033-10-11 US10649924B2 (en) 2013-01-17 2016-12-30 Network overlay systems and methods using offload processors

Country Status (6)

Country Link
US (25) US9250954B2 (en)
EP (3) EP2946296A4 (en)
JP (2) JP2016503933A (en)
KR (3) KR20160037827A (en)
CN (2) CN105765910A (en)
WO (6) WO2014113056A1 (en)

Cited By (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20170192921A1 (en) * 2016-01-04 2017-07-06 Ren Wang Multi-core communication acceleration using hardware queue device
CN109426556A (en) * 2017-08-31 2019-03-05 大唐移动通信设备有限公司 A kind of process scheduling method and device
US10942824B2 (en) 2018-10-08 2021-03-09 Hewlett Packard Enterprise Development Lp Programming model and framework for providing resilient parallel tasks

Families Citing this family (127)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US8271980B2 (en) 2004-11-08 2012-09-18 Adaptive Computing Enterprises, Inc. System and method of providing system jobs within a compute environment
US9231886B2 (en) 2005-03-16 2016-01-05 Adaptive Computing Enterprises, Inc. Simple integration of an on-demand compute environment
EP3203374B1 (en) 2005-04-07 2021-11-24 III Holdings 12, LLC On-demand access to compute resources
US11720290B2 (en) 2009-10-30 2023-08-08 Iii Holdings 2, Llc Memcached server functionality in a cluster of data processing nodes
US9432298B1 (en) * 2011-12-09 2016-08-30 P4tents1, LLC System, method, and computer program product for improving memory systems
CN103377161A (en) * 2012-04-24 2013-10-30 鸿富锦精密工业(深圳)有限公司 Main board and data processing method applied to same
WO2013177316A2 (en) 2012-05-22 2013-11-28 Xockets IP, LLC Efficient packet handling, redirection, and inspection using offload processors
US9558351B2 (en) 2012-05-22 2017-01-31 Xockets, Inc. Processing structured and unstructured data using offload processors
US10311014B2 (en) * 2012-12-28 2019-06-04 Iii Holdings 2, Llc System, method and computer readable medium for offloaded computation of distributed application protocols within a cluster of data processing nodes
WO2014113056A1 (en) 2013-01-17 2014-07-24 Xockets IP, LLC Offload processor modules for connection to system memory
US9569223B2 (en) * 2013-02-13 2017-02-14 Red Hat Israel, Ltd. Mixed shared/non-shared memory transport for virtual machines
US10084718B1 (en) 2013-03-15 2018-09-25 Google Llc Bi-Connected hierarchical data center network based on multi-ported network interface controllers (NICs)
US9288163B2 (en) * 2013-03-15 2016-03-15 Avago Technologies General Ip (Singapore) Pte. Ltd. Low-latency packet receive method for networking devices
US9460024B2 (en) * 2013-03-15 2016-10-04 Vmware, Inc. Latency reduction for direct memory access operations involving address translation
US9462088B2 (en) 2013-04-02 2016-10-04 Cisco Technology, Inc. Offload operations for overlay networks
US9606842B2 (en) * 2013-05-08 2017-03-28 National Science Foundation Resource and core scaling for improving performance of power-constrained multi-core processors
US9143403B2 (en) * 2013-06-19 2015-09-22 Hewlett-Packard Development Company, L.P. Autonomous metric tracking and adjustment
US9331868B2 (en) * 2013-10-15 2016-05-03 At&T Intellectual Property I, L.P. Method of bus virtualization in computing machine intercommunications
US9785558B2 (en) * 2013-10-29 2017-10-10 Hua Zhong University Of Science Technology Mixed cache management
US9454394B2 (en) * 2013-11-22 2016-09-27 Red Hat Israel, Ltd. Hypervisor dynamically assigned input/output resources for virtual devices
US10254987B2 (en) * 2013-12-12 2019-04-09 Samsung Electronics Co., Ltd. Disaggregated memory appliance having a management processor that accepts request from a plurality of hosts for management, configuration and provisioning of memory
KR101572689B1 (en) * 2014-01-06 2015-11-27 (주)구름네트웍스 Apparatus for Virtualizing a Network Interface and Method thereof
US9705798B1 (en) * 2014-01-07 2017-07-11 Google Inc. Systems and methods for routing data through data centers using an indirect generalized hypercube network
JP2015143945A (en) * 2014-01-31 2015-08-06 富士通株式会社 Storage control device, storage device and control program
CN103905337B (en) * 2014-03-31 2018-01-23 华为技术有限公司 A kind of processing unit of Internet resources, method and system
US9467389B2 (en) 2014-04-28 2016-10-11 International Business Machines Corporation Handling large frames in a virtualized fibre channel over ethernet (FCoE) data forwarder
US9491031B2 (en) * 2014-05-06 2016-11-08 At&T Intellectual Property I, L.P. Devices, methods, and computer readable storage devices for collecting information and sharing information associated with session flows between communication devices and servers
US9742881B2 (en) * 2014-06-30 2017-08-22 Nicira, Inc. Network virtualization using just-in-time distributed capability for classification encoding
US10140827B2 (en) 2014-07-07 2018-11-27 Google Llc Method and system for processing motion event notifications
US9420331B2 (en) 2014-07-07 2016-08-16 Google Inc. Method and system for categorizing detected motion events
US10127783B2 (en) 2014-07-07 2018-11-13 Google Llc Method and device for processing motion events
US9449229B1 (en) 2014-07-07 2016-09-20 Google Inc. Systems and methods for categorizing motion event candidates
US9354794B2 (en) 2014-07-07 2016-05-31 Google Inc. Method and system for performing client-side zooming of a remote video feed
US9501915B1 (en) 2014-07-07 2016-11-22 Google Inc. Systems and methods for analyzing a video stream
WO2016013024A1 (en) * 2014-07-25 2016-01-28 StorNetware Systems Pvt. Ltd. Unified converged network, storage and computer system
US9892079B2 (en) * 2014-07-25 2018-02-13 Rajiv Ganth Unified converged network, storage and compute system
US10261817B2 (en) * 2014-07-29 2019-04-16 Nxp Usa, Inc. System on a chip and method for a controller supported virtual machine monitor
US9922000B2 (en) * 2014-08-25 2018-03-20 Marvell World Trade Ltd. Packet buffer with dynamic bypass
US10313683B2 (en) * 2014-08-30 2019-06-04 Apple Inc. Video encoder with context switching
US9703951B2 (en) 2014-09-30 2017-07-11 Amazon Technologies, Inc. Allocation of shared system resources
USD782495S1 (en) 2014-10-07 2017-03-28 Google Inc. Display screen or portion thereof with graphical user interface
US9378363B1 (en) 2014-10-08 2016-06-28 Amazon Technologies, Inc. Noise injected virtual timer
US9754103B1 (en) 2014-10-08 2017-09-05 Amazon Technologies, Inc. Micro-architecturally delayed timer
US9864636B1 (en) * 2014-12-10 2018-01-09 Amazon Technologies, Inc. Allocating processor resources based on a service-level agreement
US9491112B1 (en) 2014-12-10 2016-11-08 Amazon Technologies, Inc. Allocating processor resources based on a task identifier
US20160188529A1 (en) * 2014-12-25 2016-06-30 Intel Corporation Guaranteed quality of service in system-on-a-chip uncore fabric
US20160197834A1 (en) * 2015-01-02 2016-07-07 Siegfried Luft Architecture and method for traffic engineering between diverse cloud providers
US9952979B1 (en) * 2015-01-14 2018-04-24 Cavium, Inc. Methods and systems for direct memory access operations
US10310998B2 (en) 2015-06-30 2019-06-04 Microsoft Technology Licensing, Llc Direct memory access with filtering
CN111708717A (en) * 2015-06-30 2020-09-25 华为技术有限公司 Data copying method, direct memory access controller and computer system
KR102402672B1 (en) * 2015-09-01 2022-05-26 삼성전자주식회사 Computing system and method for processing operations thereof
US9491765B1 (en) * 2015-09-21 2016-11-08 Dell Products L.P. Beam forming communication system
US20170142234A1 (en) * 2015-11-13 2017-05-18 Microsoft Technology Licensing, Llc Scalable addressing mechanism for virtual machines
US10817456B2 (en) 2015-11-18 2020-10-27 Oracle International Corporation Separation of control and data plane functions in SoC virtualized I/O device
US10853303B2 (en) 2015-11-18 2020-12-01 Oracle International Corporation Separation of control and data plane functions in SoC virtualized I/O device
US10031801B2 (en) 2015-12-01 2018-07-24 Microsoft Technology Licensing, Llc Configurable reliability for memory devices
US10048977B2 (en) * 2015-12-22 2018-08-14 Intel Corporation Methods and apparatus for multi-stage VM virtual network function and virtual service function chain acceleration for NFV and needs-based hardware acceleration
US9985890B2 (en) 2016-03-14 2018-05-29 International Business Machines Corporation Identifying a local congestion control algorithm of a virtual machine
US10802998B2 (en) * 2016-03-29 2020-10-13 Intel Corporation Technologies for processor core soft-offlining
US20200301747A1 (en) 2016-03-31 2020-09-24 Nec Corporation Control method, control apparatus and server in network system
US10045252B2 (en) * 2016-06-02 2018-08-07 International Business Machines Corporation Virtual switch-based congestion control for multiple TCP flows
KR102548599B1 (en) 2016-06-17 2023-06-29 삼성전자주식회사 Memory device including buffer-memory and memory module including the same
US11671382B2 (en) 2016-06-17 2023-06-06 Intel Corporation Technologies for coordinating access to data packets in a memory
US10091904B2 (en) * 2016-07-22 2018-10-02 Intel Corporation Storage sled for data center
US10148576B2 (en) * 2016-07-28 2018-12-04 Fortinet, Inc. Network processing unit (NPU) integrated layer 2 network device for layer 3 offloading
WO2018049235A1 (en) * 2016-09-08 2018-03-15 Macnica Americas, Inc. Fpga offload module and processes for seamless frame-level switching of media streams in real-time
US10552212B2 (en) * 2016-11-28 2020-02-04 Arm Limited Data processing
US20180150256A1 (en) 2016-11-29 2018-05-31 Intel Corporation Technologies for data deduplication in disaggregated architectures
US10715424B2 (en) 2016-12-06 2020-07-14 Microsoft Technology Licensing, Llc Network traffic management with queues affinitized to one or more cores
US10826841B2 (en) 2016-12-06 2020-11-03 Microsoft Technology Licensing, Llc Modification of queue affinity to cores based on utilization
US10554554B2 (en) * 2016-12-06 2020-02-04 Microsoft Technology Licensing, Llc Hybrid network processing load distribution in computing systems
CN106656711B (en) * 2016-12-26 2019-06-18 中核控制系统工程有限公司 A kind of predefined method of token bus time slot
US11853244B2 (en) * 2017-01-26 2023-12-26 Wisconsin Alumni Research Foundation Reconfigurable computer accelerator providing stream processor and dataflow processor
US10949427B2 (en) 2017-01-31 2021-03-16 Microsoft Technology Licensing, Llc Stream data processing on multiple application timelines
JP6859755B2 (en) * 2017-03-02 2021-04-14 富士通株式会社 Information processing device, control method of information processing device, and control program of information processing device
WO2018183542A1 (en) 2017-03-29 2018-10-04 Fungible, Inc. Non-blocking any-to-any data center network with packet spraying over multiple alternate data paths
US10257033B2 (en) * 2017-04-12 2019-04-09 Cisco Technology, Inc. Virtualized network functions and service chaining in serverless computing infrastructure
US20180330288A1 (en) * 2017-05-15 2018-11-15 Alteryx, Inc. Method of data aggregation for cache optimization and efficient processing
US10331445B2 (en) * 2017-05-24 2019-06-25 Microsoft Technology Licensing, Llc Multifunction vector processor circuits
US20180341494A1 (en) * 2017-05-26 2018-11-29 Intel Corporation Accelerating network security monitoring
US10990291B2 (en) * 2017-06-12 2021-04-27 Dell Products, L.P. Software assist memory module hardware architecture
US10838902B2 (en) 2017-06-23 2020-11-17 Facebook, Inc. Apparatus, system, and method for performing hardware acceleration via expansion cards
CN109213268A (en) * 2017-07-04 2019-01-15 佛山市顺德区顺达电脑厂有限公司 Server cabinet system and its signal transmission frequency method of adjustment
US10659254B2 (en) * 2017-07-10 2020-05-19 Fungible, Inc. Access node integrated circuit for data centers which includes a networking unit, a plurality of host units, processing clusters, a data network fabric, and a control network fabric
CN117348976A (en) 2017-07-10 2024-01-05 微软技术许可有限责任公司 Data processing unit for stream processing
CN107741867B (en) * 2017-09-30 2020-03-10 Oppo广东移动通信有限公司 Application program management method and device, storage medium and electronic equipment
US10496437B2 (en) * 2017-11-14 2019-12-03 International Business Machines Corporation Context switch by changing memory pointers
US10592164B2 (en) 2017-11-14 2020-03-17 International Business Machines Corporation Portions of configuration state registers in-memory
US20190171601A1 (en) * 2017-12-03 2019-06-06 Intel Corporation Mechanisms for fpga chaining and unified fpga views to composed system hosts
US10812315B2 (en) 2018-06-07 2020-10-20 Cisco Technology, Inc. Cross-domain network assurance
KR20200013461A (en) 2018-07-30 2020-02-07 삼성전자주식회사 Performing internal processing operations of memory device
US10795612B2 (en) * 2018-07-31 2020-10-06 EMC IP Holding Company LLC Offload processing using storage device slots
US10862805B1 (en) 2018-07-31 2020-12-08 Juniper Networks, Inc. Intelligent offloading of services for a network device
US10649927B2 (en) * 2018-08-20 2020-05-12 Intel Corporation Dual in-line memory module (DIMM) programmable accelerator card
TW202026873A (en) 2018-08-23 2020-07-16 美商阿爾克斯股份有限公司 Single node and multiple node datastore architecture in a network routing environment
US10979542B2 (en) * 2018-08-28 2021-04-13 Vmware, Inc. Flow cache support for crypto operations and offload
US10705762B2 (en) * 2018-08-30 2020-07-07 Micron Technology, Inc. Forward caching application programming interface systems and methods
CN109358953B (en) * 2018-09-20 2020-09-08 中南大学 Multitask application unloading method in micro cloud
US11204819B2 (en) 2018-12-21 2021-12-21 Samsung Electronics Co., Ltd. System and method for offloading application functions to a device
US10606775B1 (en) 2018-12-28 2020-03-31 Micron Technology, Inc. Computing tile
US11003539B2 (en) * 2019-01-15 2021-05-11 EMC IP Holding Company LLC Offload processing using a storage slot
CN109714217A (en) * 2019-02-28 2019-05-03 苏州浪潮智能科技有限公司 A kind of cabinet and rack room communication means
US10929310B2 (en) 2019-03-01 2021-02-23 Cisco Technology, Inc. Adaptive address translation caches
JP2020184690A (en) * 2019-05-08 2020-11-12 富士通株式会社 Packet categorization program, packet categorization method, and information processing unit
US11374879B2 (en) * 2019-06-17 2022-06-28 Cyxtera Data Centers, Inc. Network configuration of top-of-rack switches across multiple racks in a data center
US11374880B2 (en) * 2019-06-17 2022-06-28 Cyxtera Data Centers, Inc. Automated deployment of internet connectivity to rack switches in a data center
CN110181928B (en) * 2019-07-09 2021-09-21 苏州微影激光技术有限公司 Plate making device and plate making method of screen printing plate
US11275111B2 (en) 2019-09-20 2022-03-15 Micron Technology, Inc. Plurality of edge through-silicon vias and related systems, methods, and devices
WO2021084309A1 (en) * 2019-10-30 2021-05-06 Telefonaktiebolaget Lm Ericsson (Publ) In-band protocol-based in-network computation offload framework
US11232049B2 (en) * 2019-12-13 2022-01-25 Micron Technology, Inc. Memory module with computation capability
US20210349820A1 (en) * 2020-05-08 2021-11-11 Intel Corporation Memory allocation for distributed processing devices
JP2022048644A (en) * 2020-09-15 2022-03-28 富士通株式会社 Semiconductor device and transfer method
US11736566B2 (en) 2020-09-28 2023-08-22 Vmware, Inc. Using a NIC as a network accelerator to allow VM access to an external storage via a PF module, bus, and VF module
US11792134B2 (en) 2020-09-28 2023-10-17 Vmware, Inc. Configuring PNIC to perform flow processing offload using virtual port identifiers
US11593278B2 (en) 2020-09-28 2023-02-28 Vmware, Inc. Using machine executing on a NIC to access a third party storage not supported by a NIC or host
US11829793B2 (en) 2020-09-28 2023-11-28 Vmware, Inc. Unified management of virtual machines and bare metal computers
US20220103488A1 (en) * 2020-09-28 2022-03-31 Vmware, Inc. Packet processing with hardware offload units
US11636053B2 (en) 2020-09-28 2023-04-25 Vmware, Inc. Emulating a local storage by accessing an external storage through a shared port of a NIC
US11418597B2 (en) * 2020-10-08 2022-08-16 Toyota Motor Engineering & Manufacturing North America, Inc. System and method for value-anticipating task offloading
US11301410B1 (en) * 2020-12-13 2022-04-12 Advanced Mciro Devices, Inc. Tags for request packets on a network communication link
US11451493B2 (en) * 2021-01-06 2022-09-20 Mellanox Technologies, Ltd. Connection management in a network adapter
US11822675B2 (en) * 2021-06-24 2023-11-21 International Business Machines Corporation Securing customer data and internal register data during hardware checkstops in a multi-tenant environment
US20230066513A1 (en) * 2021-08-30 2023-03-02 EMC IP Holding Company LLC Asynchronous Reservation of Storage Volumes with Persistent Storage of Reservation Data
US11863376B2 (en) 2021-12-22 2024-01-02 Vmware, Inc. Smart NIC leader election
US20230221874A1 (en) * 2022-01-12 2023-07-13 Vmware, Inc. Method of efficiently receiving files over a network with a receive file command
US11899594B2 (en) 2022-06-21 2024-02-13 VMware LLC Maintenance of data message classification cache on smart NIC
US20220327061A1 (en) * 2022-06-23 2022-10-13 Daniel Christian Biederman Packet processing device to determine memory to store data in a server architecture and computing system including same

Citations (15)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US4894768A (en) * 1986-03-17 1990-01-16 Hitachi, Ltd. Data processing system with coprocessor
US5923887A (en) * 1996-05-20 1999-07-13 Advanced Micro Devices, Inc. Interrupt request that defines resource usage
US6446163B1 (en) * 1999-01-04 2002-09-03 International Business Machines Corporation Memory card with signal processing element
US20020159353A1 (en) * 2001-04-25 2002-10-31 Yoshiyuki Sasaki Data storage apparatus that either certifies a recording medium in the background or verifies data written in the recording medium
US20030091187A1 (en) * 2001-10-12 2003-05-15 Fontijn Wilhelmus Fransiscus Johannes Apparatus and method for reading or writing user data
US20040160446A1 (en) * 2003-02-18 2004-08-19 Gosalia Anuj B. Multithreaded kernel for graphics processing unit
US20040187122A1 (en) * 2003-02-18 2004-09-23 Microsoft Corporation Systems and methods for enhancing performance of a coprocessor
US20050283546A1 (en) * 1997-12-17 2005-12-22 Huppenthal Jon M Switch/network adapter port coupling a reconfigurable processing element to one or more microprocessors for use with interleaved memory controllers
US20070150671A1 (en) * 2005-12-23 2007-06-28 Boston Circuits, Inc. Supporting macro memory instructions
US20070255776A1 (en) * 2006-05-01 2007-11-01 Daisuke Iwai Processor system including processor and coprocessor
US20090063792A1 (en) * 2007-09-05 2009-03-05 Nec Electronics Corporation Memory control circuit, semiconductor integrated circuit, and verification method of nonvolatile memory
US20100064099A1 (en) * 2008-09-08 2010-03-11 Satyanarayana Nishtala Input-output module, processing platform and method for extending a memory interface for input-output operations
US20110208900A1 (en) * 2010-02-23 2011-08-25 Ocz Technology Group, Inc. Methods and systems utilizing nonvolatile memory in a computer system main memory
US8447957B1 (en) * 2006-11-14 2013-05-21 Xilinx, Inc. Coprocessor interface architecture and methods of operating the same
US20140204099A1 (en) * 2011-12-26 2014-07-24 Minjiao Ye Direct link synchronization communication between co-processors

Family Cites Families (231)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP2514954B2 (en) * 1987-03-13 1996-07-10 三菱電機株式会社 IC card
EP0422310A1 (en) * 1989-10-10 1991-04-17 International Business Machines Corporation Distributed mechanism for the fast scheduling of shared objects
US5237662A (en) 1991-06-27 1993-08-17 Digital Equipment Corporation System and method with a procedure oriented input/output mechanism
US5247675A (en) 1991-08-09 1993-09-21 International Business Machines Corporation Preemptive and non-preemptive scheduling and execution of program threads in a multitasking operating system
US5577213A (en) 1994-06-03 1996-11-19 At&T Global Information Solutions Company Multi-device adapter card for computer
US5913028A (en) * 1995-10-06 1999-06-15 Xpoint Technologies, Inc. Client/server data traffic delivery system and method
US6179489B1 (en) * 1997-04-04 2001-01-30 Texas Instruments Incorporated Devices, methods, systems and software products for coordination of computer main microprocessor and second microprocessor coupled thereto
US6085307A (en) 1996-11-27 2000-07-04 Vlsi Technology, Inc. Multiple native instruction set master/slave processor arrangement and method thereof
US6791947B2 (en) * 1996-12-16 2004-09-14 Juniper Networks In-line packet processing
US5930256A (en) * 1997-03-28 1999-07-27 Xerox Corporation Self-arbitrating crossbar switch
US6374330B1 (en) * 1997-04-14 2002-04-16 International Business Machines Corporation Cache-coherency protocol with upstream undefined state
US5870350A (en) 1997-05-21 1999-02-09 International Business Machines Corporation High performance, high bandwidth memory bus architecture utilizing SDRAMs
US6128642A (en) * 1997-07-22 2000-10-03 At&T Corporation Load balancing based on queue length, in a network of processor stations
US6092146A (en) 1997-07-31 2000-07-18 Ibm Dynamically configurable memory adapter using electronic presence detects
US6157955A (en) 1998-06-15 2000-12-05 Intel Corporation Packet processing system including a policy engine having a classification unit
US20060117274A1 (en) 1998-08-31 2006-06-01 Tseng Ping-Sheng Behavior processor system and method
US6370622B1 (en) * 1998-11-20 2002-04-09 Massachusetts Institute Of Technology Method and apparatus for curious and column caching
US20020107990A1 (en) * 2000-03-03 2002-08-08 Surgient Networks, Inc. Network connected computing system including network switch
US6625685B1 (en) 2000-09-20 2003-09-23 Broadcom Corporation Memory controller with programmable configuration
US7120155B2 (en) 2000-10-03 2006-10-10 Broadcom Corporation Switch having virtual shared memory
US6665495B1 (en) * 2000-10-27 2003-12-16 Yotta Networks, Inc. Non-blocking, scalable optical router architecture and method for routing optical traffic
US20020107971A1 (en) * 2000-11-07 2002-08-08 Bailey Brian W. Network transport accelerator
US7274706B1 (en) * 2001-04-24 2007-09-25 Syrus Ziai Methods and systems for processing network data
TWI240864B (en) 2001-06-13 2005-10-01 Hitachi Ltd Memory device
US20030078749A1 (en) * 2001-10-18 2003-04-24 Hans Eberle Memory module with integrated radio transmitter
US6889294B1 (en) * 2001-10-29 2005-05-03 Lsi Logic Corporation Virtual shared volume via proxy data transfer
AU2003217370A1 (en) * 2002-02-08 2003-09-02 Bermai, Inc. Medium access control in a wireless network
US6751113B2 (en) 2002-03-07 2004-06-15 Netlist, Inc. Arrangement of integrated circuits in a memory module
US7472205B2 (en) 2002-04-24 2008-12-30 Nec Corporation Communication control apparatus which has descriptor cache controller that builds list of descriptors
US7415723B2 (en) * 2002-06-11 2008-08-19 Pandya Ashish A Distributed network security system and a hardware processor therefor
US7698338B2 (en) 2002-09-18 2010-04-13 Netezza Corporation Field oriented pipeline architecture for a programmable data streaming processor
US7454749B2 (en) 2002-11-12 2008-11-18 Engineered Intelligence Corporation Scalable parallel processing on shared memory computers
US20040133720A1 (en) * 2002-12-31 2004-07-08 Steven Slupsky Embeddable single board computer
JP2004220070A (en) * 2003-01-09 2004-08-05 Japan Science & Technology Agency Context switching method and device, central processing unit, context switching program and computer-readable storage medium storing it
US7089412B2 (en) 2003-01-17 2006-08-08 Wintec Industries, Inc. Adaptive memory module
US7155379B2 (en) 2003-02-25 2006-12-26 Microsoft Corporation Simulation of a PCI device's memory-mapped I/O registers
US7337314B2 (en) 2003-04-12 2008-02-26 Cavium Networks, Inc. Apparatus and method for allocating resources within a security processor
US7657933B2 (en) * 2003-04-12 2010-02-02 Cavium Networks, Inc. Apparatus and method for allocating resources within a security processing architecture using multiple groups
US6794896B1 (en) * 2003-04-21 2004-09-21 Xilinx, Inc. Method and apparatus for multithreading
US7320083B2 (en) * 2003-04-23 2008-01-15 Dot Hill Systems Corporation Apparatus and method for storage controller to deterministically kill one of redundant servers integrated within the storage controller chassis
US6982892B2 (en) 2003-05-08 2006-01-03 Micron Technology, Inc. Apparatus and methods for a physical layout of simultaneously sub-accessible memory modules
US8560627B2 (en) * 2003-05-23 2013-10-15 Alcatel Lucent Virtual switch for use in fibre channel applications
US20050038946A1 (en) 2003-08-12 2005-02-17 Tadpole Computer, Inc. System and method using a high speed interface in a system having co-processors
US20050114700A1 (en) * 2003-08-13 2005-05-26 Sensory Networks, Inc. Integrated circuit apparatus and method for high throughput signature based network applications
US8776050B2 (en) 2003-08-20 2014-07-08 Oracle International Corporation Distributed virtual machine monitor for managing multiple virtual resources across multiple physical nodes
US20050078708A1 (en) * 2003-10-14 2005-04-14 International Business Machines Corporation Formatting packet headers in a communications adapter
US7787471B2 (en) * 2003-11-10 2010-08-31 Broadcom Corporation Field processor for a network device
US7657706B2 (en) 2003-12-18 2010-02-02 Cisco Technology, Inc. High speed memory and input/output processor subsystem for efficiently allocating and using high-speed memory and slower-speed memory
US7493621B2 (en) * 2003-12-18 2009-02-17 International Business Machines Corporation Context switch data prefetching in multithreaded computer
US7558890B1 (en) * 2003-12-19 2009-07-07 Applied Micro Circuits Corporation Instruction set for programmable queuing
US7213126B1 (en) * 2004-01-12 2007-05-01 Advanced Micro Devices, Inc. Method and processor including logic for storing traces within a trace cache
US20050018495A1 (en) 2004-01-29 2005-01-27 Netlist, Inc. Arrangement of integrated circuits in a memory module
US7286436B2 (en) 2004-03-05 2007-10-23 Netlist, Inc. High-density memory module utilizing low-density memory components
US7289386B2 (en) 2004-03-05 2007-10-30 Netlist, Inc. Memory module decoder
US7916574B1 (en) 2004-03-05 2011-03-29 Netlist, Inc. Circuit providing load isolation and memory domain translation for memory module
US7532537B2 (en) 2004-03-05 2009-05-12 Netlist, Inc. Memory module with a circuit providing load isolation and memory domain translation
US7668165B2 (en) 2004-03-31 2010-02-23 Intel Corporation Hardware-based multi-threading for packet processing
US7254036B2 (en) 2004-04-09 2007-08-07 Netlist, Inc. High density memory module using stacked printed circuit boards
US7502474B2 (en) * 2004-05-06 2009-03-10 Advanced Micro Devices, Inc. Network interface with security association data prefetch for high speed offloaded security processing
US7480611B2 (en) 2004-05-13 2009-01-20 International Business Machines Corporation Method and apparatus to increase the usable memory capacity of a logic simulation hardware emulator/accelerator
US7831745B1 (en) * 2004-05-25 2010-11-09 Chelsio Communications, Inc. Scalable direct memory access using validation of host and scatter gather engine (SGE) generation indications
US7436845B1 (en) * 2004-06-08 2008-10-14 Sun Microsystems, Inc. Input and output buffering
US20060004965A1 (en) 2004-06-30 2006-01-05 Tu Steven J Direct processor cache access within a system having a coherent multi-processor protocol
US7930422B2 (en) * 2004-07-14 2011-04-19 International Business Machines Corporation Apparatus and method for supporting memory management in an offload of network protocol processing
EP1622009A1 (en) * 2004-07-27 2006-02-01 Texas Instruments Incorporated JSM architecture and systems
US7895431B2 (en) * 2004-09-10 2011-02-22 Cavium Networks, Inc. Packet queuing, scheduling and ordering
US7305574B2 (en) 2004-10-29 2007-12-04 International Business Machines Corporation System, method and storage medium for bus calibration in a memory subsystem
KR100666169B1 (en) 2004-12-17 2007-01-09 삼성전자주식회사 Flash memory data storing device
US8010682B2 (en) * 2004-12-28 2011-08-30 International Business Machines Corporation Early coherency indication for return data in shared memory architecture
US8281031B2 (en) * 2005-01-28 2012-10-02 Standard Microsystems Corporation High speed ethernet MAC and PHY apparatus with a filter based ethernet packet router with priority queuing and single or multiple transport stream interfaces
US8072887B1 (en) * 2005-02-07 2011-12-06 Extreme Networks, Inc. Methods, systems, and computer program products for controlling enqueuing of packets in an aggregated queue including a plurality of virtual queues using backpressure messages from downstream queues
US20060215649A1 (en) * 2005-03-08 2006-09-28 Chris Morrall Network address converting apparatus using SSW tree
EP1872192B1 (en) 2005-04-21 2012-09-12 Violin Memory, Inc. Interconnection system
JP4322232B2 (en) * 2005-06-14 2009-08-26 株式会社ソニー・コンピュータエンタテインメント Information processing apparatus, process control method, and computer program
US8438328B2 (en) 2008-02-21 2013-05-07 Google Inc. Emulation of abstracted DIMMs using abstracted DRAMs
US8244971B2 (en) 2006-07-31 2012-08-14 Google Inc. Memory circuit system and method
US20080304481A1 (en) 2005-07-12 2008-12-11 Paul Thomas Gurney System and Method of Offloading Protocol Functions
US20070016906A1 (en) * 2005-07-18 2007-01-18 Mistletoe Technologies, Inc. Efficient hardware allocation of processes to processors
US7543131B2 (en) * 2005-08-12 2009-06-02 Advanced Micro Devices, Inc. Controlling an I/O MMU
US7500083B2 (en) * 2005-08-15 2009-03-03 Silicon Informatics Accelerated processing with scheduling to configured coprocessor for molecular data type by service and control coprocessor upon analysis of software code
US7442050B1 (en) 2005-08-29 2008-10-28 Netlist, Inc. Circuit card with flexible connection for memory module with heat spreader
US7650557B2 (en) * 2005-09-19 2010-01-19 Network Appliance, Inc. Memory scrubbing of expanded memory
US7620746B2 (en) * 2005-09-29 2009-11-17 Apple Inc. Functional DMA performing operation on DMA data and writing result of operation
US8862783B2 (en) * 2005-10-25 2014-10-14 Broadbus Technologies, Inc. Methods and system to offload data processing tasks
US7899864B2 (en) 2005-11-01 2011-03-01 Microsoft Corporation Multi-user terminal services accelerator
US7773630B2 (en) * 2005-11-12 2010-08-10 Liquid Computing Corportation High performance memory based communications interface
US8225297B2 (en) 2005-12-07 2012-07-17 Microsoft Corporation Cache metadata identifiers for isolation and sharing
US7904688B1 (en) 2005-12-21 2011-03-08 Trend Micro Inc Memory management unit for field programmable gate array boards
WO2007084422A2 (en) 2006-01-13 2007-07-26 Sun Microsystems, Inc. Modular blade server
US7619893B1 (en) 2006-02-17 2009-11-17 Netlist, Inc. Heat spreader for electronic modules
US20070226745A1 (en) 2006-02-28 2007-09-27 International Business Machines Corporation Method and system for processing a service request
JP2007233903A (en) * 2006-03-03 2007-09-13 Hitachi Ltd Storage controller and data recovery method for storage controller
US7421552B2 (en) 2006-03-17 2008-09-02 Emc Corporation Techniques for managing data within a data storage system utilizing a flash-based memory vault
US7434002B1 (en) 2006-04-24 2008-10-07 Vmware, Inc. Utilizing cache information to manage memory access and cache utilization
US8869147B2 (en) * 2006-05-31 2014-10-21 Qualcomm Incorporated Multi-threaded processor with deferred thread output control
US7716411B2 (en) 2006-06-07 2010-05-11 Microsoft Corporation Hybrid memory device with single interface
US8948166B2 (en) 2006-06-14 2015-02-03 Hewlett-Packard Development Company, Lp. System of implementing switch devices in a server system
US7957280B2 (en) 2006-06-16 2011-06-07 Bittorrent, Inc. Classification and verification of static file transfer protocols
US7636800B2 (en) 2006-06-27 2009-12-22 International Business Machines Corporation Method and system for memory address translation and pinning
US8599716B2 (en) * 2006-06-30 2013-12-03 Cisco Technolgy, Inc. Method and system to configure quality of service in a network
US7291032B1 (en) * 2006-07-05 2007-11-06 International Business Machines Corporation Connector for adjacent devices
KR100823734B1 (en) * 2006-07-07 2008-04-21 한국전자통신연구원 Data acceleration apparatus for iSCSI and iSCSI storage system using the same
US7624118B2 (en) 2006-07-26 2009-11-24 Microsoft Corporation Data processing over very large databases
US7760715B1 (en) 2006-08-04 2010-07-20 Parin B. Dalal Circuit and method for rate-limiting a scheduler
US8116320B2 (en) * 2006-08-07 2012-02-14 Adc Telecommunications, Inc. Mapping external port using virtual local area network
US8943245B2 (en) 2006-09-28 2015-01-27 Virident Systems, Inc. Non-volatile type memory modules for main memory
US8074022B2 (en) 2006-09-28 2011-12-06 Virident Systems, Inc. Programmable heterogeneous memory controllers for main memory with different memory modules
US20080082750A1 (en) 2006-09-28 2008-04-03 Okin Kenneth A Methods of communicating to, memory modules in a memory channel
US8189328B2 (en) 2006-10-23 2012-05-29 Virident Systems, Inc. Methods and apparatus of dual inline memory modules for flash memory
WO2008055272A2 (en) 2006-11-04 2008-05-08 Virident Systems, Inc. Integrating data from symmetric and asymmetric memory
US8149834B1 (en) * 2007-01-25 2012-04-03 World Wide Packets, Inc. Forwarding a packet to a port from which the packet is received and transmitting modified, duplicated packets on a single port
US20080222351A1 (en) * 2007-03-07 2008-09-11 Aprius Inc. High-speed optical connection between central processing unit and remotely located random access memory
US20080229049A1 (en) 2007-03-16 2008-09-18 Ashwini Kumar Nanda Processor card for blade server and process.
EP3923287B1 (en) 2007-04-12 2023-01-11 Rambus Inc. Memory system with point-to-point request interconnect
US8935406B1 (en) * 2007-04-16 2015-01-13 Chelsio Communications, Inc. Network adaptor configured for connection establishment offload
US20080271030A1 (en) * 2007-04-30 2008-10-30 Dan Herington Kernel-Based Workload Management
US8904098B2 (en) 2007-06-01 2014-12-02 Netlist, Inc. Redundant backup using non-volatile memory
US8301833B1 (en) 2007-06-01 2012-10-30 Netlist, Inc. Non-volatile memory module
US8874831B2 (en) 2007-06-01 2014-10-28 Netlist, Inc. Flash-DRAM hybrid memory module
US8347005B2 (en) 2007-07-31 2013-01-01 Hewlett-Packard Development Company, L.P. Memory controller with multi-protocol interface
US7743196B2 (en) * 2007-08-15 2010-06-22 Agere Systems Inc. Interface with multiple packet preemption based on start indicators of different types
US9141670B2 (en) 2007-08-27 2015-09-22 Teradata Us, Inc. Methods and systems for hardware acceleration of streamed database operations and queries based on multiple hardware accelerators
US7840748B2 (en) 2007-08-31 2010-11-23 International Business Machines Corporation Buffered memory module with multiple memory device data interface ports supporting double the memory capacity
US8503465B2 (en) * 2007-09-17 2013-08-06 Qualcomm Incorporated Priority scheduling and admission control in a communication network
US7949683B2 (en) 2007-11-27 2011-05-24 Cavium Networks, Inc. Method and apparatus for traversing a compressed deterministic finite automata (DFA) graph
US20090158276A1 (en) * 2007-12-12 2009-06-18 Eric Lawrence Barsness Dynamic distribution of nodes on a multi-node computer system
US8862706B2 (en) * 2007-12-14 2014-10-14 Nant Holdings Ip, Llc Hybrid transport—application network fabric apparatus
US8990799B1 (en) * 2008-01-30 2015-03-24 Emc Corporation Direct memory access through virtual switch in device driver
US8856464B2 (en) * 2008-02-12 2014-10-07 Virident Systems, Inc. Systems for two-dimensional main memory including memory modules with read-writeable non-volatile memory devices
US20090249330A1 (en) * 2008-03-31 2009-10-01 Abercrombie David K Method and apparatus for hypervisor security code
JP5186982B2 (en) 2008-04-02 2013-04-24 富士通株式会社 Data management method and switch device
US20110235260A1 (en) 2008-04-09 2011-09-29 Apacer Technology Inc. Dram module with solid state disk
US8516185B2 (en) 2009-07-16 2013-08-20 Netlist, Inc. System and method utilizing distributed byte-wise buffers on a memory module
US8001434B1 (en) 2008-04-14 2011-08-16 Netlist, Inc. Memory board with self-testing capability
US8787060B2 (en) 2010-11-03 2014-07-22 Netlist, Inc. Method and apparatus for optimizing driver load in a memory package
US8417870B2 (en) 2009-07-16 2013-04-09 Netlist, Inc. System and method of increasing addressable memory space on a memory board
US8154901B1 (en) 2008-04-14 2012-04-10 Netlist, Inc. Circuit providing load isolation and noise reduction
CA2719841C (en) 2008-05-22 2016-03-22 Nokia Siemens Networks Oy Adaptive scheduler for communication systems apparatus, system and method
TWI469055B (en) * 2008-06-27 2015-01-11 Realtek Semiconductor Corp Network task offload apparatus and method thereof
US8190699B2 (en) 2008-07-28 2012-05-29 Crossfield Technology LLC System and method of multi-path data communications
US20100031235A1 (en) 2008-08-01 2010-02-04 Modular Mining Systems, Inc. Resource Double Lookup Framework
US20100032820A1 (en) * 2008-08-06 2010-02-11 Michael Bruennert Stacked Memory Module
US8452934B2 (en) * 2008-12-16 2013-05-28 Sandisk Technologies Inc. Controlled data access to non-volatile memory
US7930519B2 (en) * 2008-12-17 2011-04-19 Advanced Micro Devices, Inc. Processor with coprocessor interfacing functional unit for forwarding result from coprocessor to retirement unit
GB2466289A (en) * 2008-12-18 2010-06-23 Veda Technology Ltd Executing a service application on a cluster by registering a class and storing subscription information of generated objects at an interconnect
US7870309B2 (en) * 2008-12-23 2011-01-11 International Business Machines Corporation Multithreaded programmable direct memory access engine
US8054832B1 (en) 2008-12-30 2011-11-08 Juniper Networks, Inc. Methods and apparatus for routing between virtual resources based on a routing location policy
GB2466984B (en) * 2009-01-16 2011-07-27 Imagination Tech Ltd Multi-threaded data processing system
US8352710B2 (en) * 2009-01-19 2013-01-08 International Business Machines Corporation Off-loading of processing from a processor blade to storage blades
US20100183033A1 (en) 2009-01-20 2010-07-22 Nokia Corporation Method and apparatus for encapsulation of scalable media
US8498349B2 (en) 2009-03-11 2013-07-30 Texas Instruments Incorporated Demodulation and decoding for frequency modulation (FM) receivers with radio data system (RDS) or radio broadcast data system (RBDS)
US8949838B2 (en) * 2009-04-27 2015-02-03 Lsi Corporation Multi-threaded processing with hardware accelerators
US8869150B2 (en) * 2010-05-18 2014-10-21 Lsi Corporation Local messaging in a scheduling hierarchy in a traffic manager of a network processor
US8009682B2 (en) * 2009-05-05 2011-08-30 Citrix Systems, Inc. Systems and methods for packet steering in a multi-core architecture
US8264903B1 (en) 2009-05-05 2012-09-11 Netlist, Inc. Systems and methods for refreshing a memory module
US8489837B1 (en) 2009-06-12 2013-07-16 Netlist, Inc. Systems and methods for handshaking with a memory module
US8892783B2 (en) * 2009-06-22 2014-11-18 Citrix Systems, Inc. Systems and methods for initialization and link management of NICS in a multi-core environment
US8205057B2 (en) * 2009-06-30 2012-06-19 Texas Instruments Incorporated Method and system for integrated pipeline write hazard handling using memory attributes
US9128632B2 (en) 2009-07-16 2015-09-08 Netlist, Inc. Memory module with distributed data buffers and method of operation
US9535849B2 (en) 2009-07-24 2017-01-03 Advanced Micro Devices, Inc. IOMMU using two-level address translation for I/O and computation offload devices on a peripheral interconnect
US8085801B2 (en) * 2009-08-08 2011-12-27 Hewlett-Packard Development Company, L.P. Resource arbitration
US20110035540A1 (en) 2009-08-10 2011-02-10 Adtron, Inc. Flash blade system architecture and method
US8479216B2 (en) * 2009-08-18 2013-07-02 International Business Machines Corporation Method for decentralized load distribution in an event-driven system using localized migration between physically connected nodes and load exchange protocol preventing simultaneous migration of plurality of tasks to or from a same node
US8848513B2 (en) 2009-09-02 2014-09-30 Qualcomm Incorporated Seamless overlay connectivity using multi-homed overlay neighborhoods
US8972627B2 (en) * 2009-09-09 2015-03-03 Fusion-Io, Inc. Apparatus, system, and method for managing operations for data storage media
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
US20110083175A1 (en) * 2009-10-06 2011-04-07 Sonus Networks, Inc. Methods and Apparatuses for Policing and Prioritizing of Data Services
US8442048B2 (en) * 2009-11-04 2013-05-14 Juniper Networks, Inc. Methods and apparatus for configuring a virtual network switch
EP2512168B1 (en) * 2009-12-08 2019-12-25 Nec Corporation Bandwidth control device, bandwidth control method, and wireless network system
US9389895B2 (en) 2009-12-17 2016-07-12 Microsoft Technology Licensing, Llc Virtual storage target offload techniques
US8743877B2 (en) * 2009-12-21 2014-06-03 Steven L. Pope Header processing engine
WO2011087820A2 (en) 2009-12-21 2011-07-21 Sanmina-Sci Corporation Method and apparatus for supporting storage modules in standard memory and/or hybrid memory bus architectures
US8473695B2 (en) * 2011-03-31 2013-06-25 Mosys, Inc. Memory system including variable write command scheduling
US20110197004A1 (en) * 2010-02-05 2011-08-11 Serebrin Benjamin C Processor Configured to Virtualize Guest Local Interrupt Controller
EP2363812B1 (en) 2010-03-04 2018-02-28 Karlsruher Institut für Technologie Reconfigurable processor architecture
CN102906696A (en) 2010-03-26 2013-01-30 维尔图尔梅特里克斯公司 Fine grain performance resource management of computer systems
CN101794271B (en) * 2010-03-31 2012-05-23 华为技术有限公司 Implementation method and device of consistency of multi-core internal memory
JP5336423B2 (en) * 2010-05-14 2013-11-06 パナソニック株式会社 Computer system
US8601498B2 (en) 2010-05-28 2013-12-03 Security First Corp. Accelerator system for use with secure data storage
US8631271B2 (en) 2010-06-24 2014-01-14 International Business Machines Corporation Heterogeneous recovery in a redundant memory system
US9118591B2 (en) 2010-07-30 2015-08-25 Broadcom Corporation Distributed switch domain of heterogeneous components
US9658877B2 (en) * 2010-08-23 2017-05-23 Empire Technology Development Llc Context switching using a context controller and on-chip context cache
TW201214082A (en) * 2010-09-17 2012-04-01 Hon Hai Prec Ind Co Ltd Mother board
GB2513551B (en) 2010-09-24 2018-01-10 Ibm High-speed memory system
US8904115B2 (en) * 2010-09-28 2014-12-02 Texas Instruments Incorporated Cache with multiple access pipelines
US8483046B2 (en) 2010-09-29 2013-07-09 International Business Machines Corporation Virtual switch interconnect for hybrid enterprise servers
US8405668B2 (en) * 2010-11-19 2013-03-26 Apple Inc. Streaming translation in display pipe
US8996644B2 (en) * 2010-12-09 2015-03-31 Solarflare Communications, Inc. Encapsulated accelerator
US8566831B2 (en) * 2011-01-26 2013-10-22 International Business Machines Corporation Execution of work units in a heterogeneous computing environment
US20120239874A1 (en) 2011-03-02 2012-09-20 Netlist, Inc. Method and system for resolving interoperability of multiple types of dual in-line memory modules
US8885334B1 (en) * 2011-03-10 2014-11-11 Xilinx, Inc. Computing system with network attached processors
US8774213B2 (en) 2011-03-30 2014-07-08 Amazon Technologies, Inc. Frameworks and interfaces for offload device-based packet processing
US8825900B1 (en) * 2011-04-05 2014-09-02 Nicira, Inc. Method and apparatus for stateless transport layer tunneling
US8930647B1 (en) 2011-04-06 2015-01-06 P4tents1, LLC Multiple class memory systems
WO2012141694A1 (en) 2011-04-13 2012-10-18 Hewlett-Packard Development Company, L.P. Input/output processing
US8442056B2 (en) 2011-06-28 2013-05-14 Marvell International Ltd. Scheduling packets in a packet-processing pipeline
US8547825B2 (en) * 2011-07-07 2013-10-01 International Business Machines Corporation Switch fabric management
US20130019057A1 (en) 2011-07-15 2013-01-17 Violin Memory, Inc. Flash disk array and controller
CA2843320A1 (en) 2011-07-25 2013-01-31 Servergy, Inc. Method and system for building a low power computer system
CN103875214B (en) * 2011-08-10 2017-05-03 马维尔国际贸易有限公司 Intelligent phy with security detection for ethernet networks
US8767463B2 (en) 2011-08-11 2014-07-01 Smart Modular Technologies, Inc. Non-volatile dynamic random access memory system with non-delay-lock-loop mechanism and method of operation thereof
US9021146B2 (en) * 2011-08-30 2015-04-28 Apple Inc. High priority command queue for peripheral component
US9223618B2 (en) * 2011-09-20 2015-12-29 Intel Corporation Multi-threaded queuing system for pattern matching
US9094333B1 (en) * 2011-10-26 2015-07-28 Qlogic, Corporation Systems and methods for sending and receiving information via a network device
US8966457B2 (en) * 2011-11-15 2015-02-24 Global Supercomputing Corporation Method and system for converting a single-threaded software program into an application-specific supercomputer
US9424188B2 (en) 2011-11-23 2016-08-23 Smart Modular Technologies, Inc. Non-volatile memory packaging system with caching and method of operation thereof
US20140325183A1 (en) * 2011-11-28 2014-10-30 Freescale Semiconductor, Inc. Integrated circuit device, asymmetric multi-core processing module, electronic device and method of managing execution of computer program code therefor
US10203881B2 (en) * 2011-12-19 2019-02-12 Apple Inc. Optimized execution of interleaved write operations in solid state drives
US9170947B2 (en) * 2011-12-29 2015-10-27 Intel Corporation Recovering from data errors using implicit redundancy
US9542437B2 (en) 2012-01-06 2017-01-10 Sap Se Layout-driven data selection and reporting
US8918634B2 (en) 2012-02-21 2014-12-23 International Business Machines Corporation Network node with network-attached stateless security offload device employing out-of-band processing
JP5565425B2 (en) * 2012-02-29 2014-08-06 富士通株式会社 Arithmetic apparatus, information processing apparatus and arithmetic method
US8924606B2 (en) 2012-03-02 2014-12-30 Hitachi, Ltd. Storage system and data transfer control method
US20130254457A1 (en) * 2012-03-21 2013-09-26 Lsi Corporation Methods and structure for rapid offloading of cached data in a volatile cache memory of a storage controller to a nonvolatile memory
US9513845B2 (en) 2012-03-30 2016-12-06 Violin Memory Inc. Memory module virtualization
US10019371B2 (en) 2012-04-27 2018-07-10 Hewlett Packard Enterprise Development Lp Data caching using local and remote memory
WO2013177316A2 (en) 2012-05-22 2013-11-28 Xockets IP, LLC Efficient packet handling, redirection, and inspection using offload processors
US9558351B2 (en) 2012-05-22 2017-01-31 Xockets, Inc. Processing structured and unstructured data using offload processors
WO2013180691A1 (en) * 2012-05-29 2013-12-05 Intel Corporation Peer-to-peer interrupt signaling between devices coupled via interconnects
US20130347103A1 (en) * 2012-06-21 2013-12-26 Mark Veteikis Packet capture for error tracking
US20140089609A1 (en) * 2012-09-26 2014-03-27 Advanced Micro Devices, Inc. Interposer having embedded memory controller circuitry
US9170968B2 (en) * 2012-09-27 2015-10-27 Intel Corporation Device, system and method of multi-channel processing
US20140101370A1 (en) * 2012-10-08 2014-04-10 HGST Netherlands B.V. Apparatus and method for low power low latency high capacity storage class memory
US9268716B2 (en) * 2012-10-19 2016-02-23 Yahoo! Inc. Writing data from hadoop to off grid storage
US20140157287A1 (en) * 2012-11-30 2014-06-05 Advanced Micro Devices, Inc Optimized Context Switching for Long-Running Processes
WO2014105650A1 (en) * 2012-12-26 2014-07-03 Cortina Systems, Inc. Communication traffic processing architectures and methods
WO2014113056A1 (en) 2013-01-17 2014-07-24 Xockets IP, LLC Offload processor modules for connection to system memory
US10031820B2 (en) 2013-01-17 2018-07-24 Lenovo Enterprise Solutions (Singapore) Pte. Ltd. Mirroring high performance and high availablity applications across server computers
US9378161B1 (en) 2013-01-17 2016-06-28 Xockets, Inc. Full bandwidth packet handling with server systems including offload processors
US10372551B2 (en) 2013-03-15 2019-08-06 Netlist, Inc. Hybrid memory system with configurable error thresholds and failure analysis capability
US9792154B2 (en) 2015-04-17 2017-10-17 Microsoft Technology Licensing, Llc Data processing system having a hardware acceleration plane and a software plane

Patent Citations (18)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US4894768A (en) * 1986-03-17 1990-01-16 Hitachi, Ltd. Data processing system with coprocessor
US5923887A (en) * 1996-05-20 1999-07-13 Advanced Micro Devices, Inc. Interrupt request that defines resource usage
US7565461B2 (en) * 1997-12-17 2009-07-21 Src Computers, Inc. Switch/network adapter port coupling a reconfigurable processing element to one or more microprocessors for use with interleaved memory controllers
US20050283546A1 (en) * 1997-12-17 2005-12-22 Huppenthal Jon M Switch/network adapter port coupling a reconfigurable processing element to one or more microprocessors for use with interleaved memory controllers
US6446163B1 (en) * 1999-01-04 2002-09-03 International Business Machines Corporation Memory card with signal processing element
US20020159353A1 (en) * 2001-04-25 2002-10-31 Yoshiyuki Sasaki Data storage apparatus that either certifies a recording medium in the background or verifies data written in the recording medium
US20030091187A1 (en) * 2001-10-12 2003-05-15 Fontijn Wilhelmus Fransiscus Johannes Apparatus and method for reading or writing user data
US20040160446A1 (en) * 2003-02-18 2004-08-19 Gosalia Anuj B. Multithreaded kernel for graphics processing unit
US20040187122A1 (en) * 2003-02-18 2004-09-23 Microsoft Corporation Systems and methods for enhancing performance of a coprocessor
US20070150671A1 (en) * 2005-12-23 2007-06-28 Boston Circuits, Inc. Supporting macro memory instructions
US20070255776A1 (en) * 2006-05-01 2007-11-01 Daisuke Iwai Processor system including processor and coprocessor
US8447957B1 (en) * 2006-11-14 2013-05-21 Xilinx, Inc. Coprocessor interface architecture and methods of operating the same
US20090063792A1 (en) * 2007-09-05 2009-03-05 Nec Electronics Corporation Memory control circuit, semiconductor integrated circuit, and verification method of nonvolatile memory
US20100064099A1 (en) * 2008-09-08 2010-03-11 Satyanarayana Nishtala Input-output module, processing platform and method for extending a memory interface for input-output operations
US7886103B2 (en) * 2008-09-08 2011-02-08 Cisco Technology, Inc. Input-output module, processing platform and method for extending a memory interface for input-output operations
US20110099317A1 (en) * 2008-09-08 2011-04-28 Cisco Technology, Inc. Input-output module for operation in memory module socket and method for extending a memory interface for input-output operations
US20110208900A1 (en) * 2010-02-23 2011-08-25 Ocz Technology Group, Inc. Methods and systems utilizing nonvolatile memory in a computer system main memory
US20140204099A1 (en) * 2011-12-26 2014-07-24 Minjiao Ye Direct link synchronization communication between co-processors

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
A.C. Verschueren, M. Verhappen, B.D. Theelen, M.P.J. Stevens, Arbitration in a multi-processor to multi-coprocessor connection switch, in: J.P. Veen (Ed.), Proceedings of ProRISC'99, Mierlo, The Netherlands, 24-26 November, STW Technology Foundation, Utrecht, The Netherlands, 1999, pp. 563-568. *

Cited By (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20170192921A1 (en) * 2016-01-04 2017-07-06 Ren Wang Multi-core communication acceleration using hardware queue device
CN108292239A (en) * 2016-01-04 2018-07-17 英特尔公司 It is communicated and is accelerated using the multi-core of hardware queue equipment
US10445271B2 (en) * 2016-01-04 2019-10-15 Intel Corporation Multi-core communication acceleration using hardware queue device
US10929323B2 (en) 2016-01-04 2021-02-23 Intel Corporation Multi-core communication acceleration using hardware queue device
CN109426556A (en) * 2017-08-31 2019-03-05 大唐移动通信设备有限公司 A kind of process scheduling method and device
US10942824B2 (en) 2018-10-08 2021-03-09 Hewlett Packard Enterprise Development Lp Programming model and framework for providing resilient parallel tasks

Also Published As

Publication number Publication date
KR20160040439A (en) 2016-04-14
WO2014113061A2 (en) 2014-07-24
KR20160037828A (en) 2016-04-06
WO2014113062A3 (en) 2015-06-25
US9250954B2 (en) 2016-02-02
US9460031B1 (en) 2016-10-04
CN105765910A (en) 2016-07-13
US9348638B2 (en) 2016-05-24
US10649924B2 (en) 2020-05-12
US9288101B1 (en) 2016-03-15
EP2946296A1 (en) 2015-11-25
US9436638B1 (en) 2016-09-06
EP2946298A1 (en) 2015-11-25
US20140198799A1 (en) 2014-07-17
EP2946296A4 (en) 2016-11-16
KR20160037827A (en) 2016-04-06
US20140201309A1 (en) 2014-07-17
US20140201303A1 (en) 2014-07-17
WO2014113055A1 (en) 2014-07-24
US20140198652A1 (en) 2014-07-17
US20140201453A1 (en) 2014-07-17
US20140201461A1 (en) 2014-07-17
US20140201417A1 (en) 2014-07-17
WO2014113061A3 (en) 2015-06-18
US20140201310A1 (en) 2014-07-17
WO2014113062A2 (en) 2014-07-24
US20140201404A1 (en) 2014-07-17
US20140201305A1 (en) 2014-07-17
JP2016503934A (en) 2016-02-08
WO2014113056A1 (en) 2014-07-24
US20140201416A1 (en) 2014-07-17
US20140201408A1 (en) 2014-07-17
US20140201304A1 (en) 2014-07-17
US20140198803A1 (en) 2014-07-17
US20140201402A1 (en) 2014-07-17
US9436640B1 (en) 2016-09-06
EP2946528A4 (en) 2016-08-24
US20140198653A1 (en) 2014-07-17
US20170237703A1 (en) 2017-08-17
EP2946298A4 (en) 2016-11-16
CN105874441A (en) 2016-08-17
WO2014113063A1 (en) 2014-07-24
WO2014113059A1 (en) 2014-07-24
JP2016503933A (en) 2016-02-08
EP2946528A2 (en) 2015-11-25
US20140201761A1 (en) 2014-07-17
US9436639B1 (en) 2016-09-06
US20140201390A1 (en) 2014-07-17

Similar Documents

Publication Publication Date Title
US9250954B2 (en) Offload processor modules for connection to system memory, and corresponding methods and systems
US10212092B2 (en) Architectures and methods for processing data in parallel using offload processing modules insertable into servers
US9378161B1 (en) Full bandwidth packet handling with server systems including offload processors

Legal Events

Date Code Title Description
AS Assignment

Owner name: XOCKETS IP, LLC, DELAWARE

Free format text: NUNC PRO TUNC ASSIGNMENT;ASSIGNORS:DALAL, PARIN BHADRIK;BELAIR, STEPHEN PAUL;REEL/FRAME:037669/0912

Effective date: 20160204

Owner name: XOCKETS, INC., CALIFORNIA

Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNOR:XOCKETS IP, LLC;REEL/FRAME:037670/0001

Effective date: 20150719

STCB Information on status: application discontinuation

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