Cisco Technology, Inc.

Emc IP Holding Company LLC

Netronome Systems Incorporated

Cisco Systems Inc.

Emc Corporation

Bruce Alexander Wilford

Mark Himelstein

Vikram Venkataraghavan

Vishwas Durai

Rick Carlson

Richard Van Gaasbeck

Todd Wilde

Blair Barnett

David R Emberson

Kevin J Rowett

David J Tsiang

Yie-Fong Dan

James Yarbrough

Dan Arai

Gavin J Stark

Hon Wah Chin

Thomas Dejanovic

Robert M Broberg

Anthony J Bates

Grace Ho

Frederic Roy Carlson, Jr

Bill Katz

Jan Medved

Anthony Joseph Li

Daniel Arai

Sonny N Tran

Rich Van Gaasbeck

Stephan Crandall

Robert O'Grady

Bruce Sherry

A system has a collection of central processing units. Each central processing unit is connected to at least one other central processing unit and has a path into flash memory resources. A central processing unit supports a mapping from a data address space, to a flash memory virtual address space, to a flash memory virtual page number to a flash memory physical address space.

Multiprocessor system with independent direct access to bulk solid state memory resources

According to one embodiment, a data processing system includes a plurality of processing units, each processing unit having one or more processor cores. The system further includes a plurality of memory roots, each memory root being associated with one of the processing units. Each memory root includes one or more branches and a plurality of memory leaves to store data. Each of the branches is associated with one or more of the memory leaves and to provide access to the data stored therein. The system further includes a memory fabric coupled to each of the branches of each memory root to allow each branch to access data stored in any of the memory leaves associated with any one of remaining branches.

Exabyte-scale data processing system

Data processing system with a scalable architecture over ethernet

According to one embodiment, a data processing system includes a plurality of processors, each of the processors being coupled to each of remaining processors via a processor interconnect, a plurality of memory controllers, each memory controller corresponding to one of the processors, a plurality of memory targets, each memory target includes one or more branches and a plurality of memory leaves for storing data, and an Ethernet switch fabric coupled to the memory controllers and the memory targets. When a first of the memory controllers writes data to a first of the memory leaves, the first memory controller sends a cache coherence message to remaining ones of the memory controllers to indicate that the data stored in the first memory leaf has been updated, such that any of the remaining memory controllers can update its cache by fetching the data from the first memory leaf.

Non-uniform memory access (NUMA) mechanism for accessing memory with cache coherence

According to one embodiment, a data processing system includes a plurality of central processing unit (CPU) subsystems, each CPU subsystem having a plurality of CPUs and a plurality of memory controllers, each memory controller corresponding to one of the CPUs, a plurality of memory complexes, each memory complex being associated with one of the CPU subsystems, wherein each memory complex comprises one or more branches, a plurality of memory leaves to store data, wherein each of the branches is coupled to one or more of the memory leaves and to provide access to the data stored in the memory leaves, and a replication interface to automatically replicate data received from one of the CPU subsystems to another one of the memory complexes, wherein the received data is to be stored in one of the memory leaves.

Flash memory complex with a replication interface to replicate data to another flash memory complex of a data processing system

A page virtualization table (PVT) and one or more block virtualization tables (BVTs) are maintained. The PVT includes PVT entries, each mapping a logical page number (LPN) to a virtual page number (VPN). Each BVT includes BVT entries, each mapping a virtual block number (VBN) to a physical block number (PBN). A request is received for accessing data stored in one of flash memory devices, the request including a first LPN. A search is performed in the PVT based on the first LPN to locate a first PVT entry to obtain a first VPN from the first PVT entry. A search is performed in a first BVT to locate a first BVT entry based on the VPN to obtain a first PBN from the first BVT entry. An input and output (IO) request is issued based on the first PBN to a flash controller associated with a first flash memory device that stores data corresponding to the first PBN.

Software-implemented flash translation layer policies in a data processing system

A system includes a plurality of processors, each being coupled to each of remaining processors via a cluster of processor interconnects. The cluster of processor interconnects form a data distribution network. The system further includes a plurality of roots coupled to the processors, each root corresponding to one of the processors. Each root comprises a memory controller, one or more branches coupled to the memory controller, and a plurality of memory leaves coupled to the branches, each memory leaf having one or more solid state memory devices. Each of the branches is associated with one or more of the memory leaves and provides access to the associated memory leaves. Each of the processors can access any one of the memory leaves via a corresponding branch of any one of the roots over the data distribution network.

A hardware trie structure includes a tree of internal node circuits and leaf node circuits. Each internal node is configured by a corresponding multi-bit node control value (NCV). Each leaf node can output a corresponding result value (RV). An input value (IV) supplied onto input leads of the trie causes signals to propagate through the trie such that one of the leaf nodes outputs one of the RVs onto output leads of the trie. In a transactional memory, a memory stores a set of NCVs and RVs. In response to a lookup command, the NCVs and RVs are read out of memory and are used to configure the trie. The IV of the lookup is supplied to the input leads, and the trie looks up an RV. A non-final RV initiates another lookup in a recursive fashion, whereas a final RV is returned as the result of the lookup command.

Recursive lookup with a hardware trie structure that has no sequential logic elements

A system includes a collection of central processing units, where each central processing unit is connected to at least one other central processing unit and a root path into at least 10 Tera Bytes of solid state memory resources. Each central processing unit directly accesses solid state memory resources without swapping solid state memory contents into main memory.

A linecard architecture for high speed routing of data in a communications device. This architecture provides low latency routing based on packet priority: packet routing and processing occurs at line rate (wire speed) for most operations. A packet data stream is input to the inbound receiver, which uses a small packet FIFO to rapidly accumulate packet bytes. Once the header portion of the packet is received, the header alone is used to perform a high speed routing lookup and packet header modification. The queue manager then uses the class of service information in the packet header to enqueue the packet according to the required priority. Enqueued packets are buffered in a large memory space holding multiple packets prior to transmission across the device's switch fabric to the outbound linecard. On arrival at the outbound linecard, the packet is enqueued in the outbound transmitter portion of the linecard architecture. Another large, multi-packet memory structure, as employed in the inbound queue manager, provides buffering prior to transmission onto the network.

Architecture for high speed class of service enabled linecard

A system and method for locally determining a fair allocated bandwidth for a network node configured to send and receive packets in an upstream direction and a downstream direction is disclosed. A local allocated bandwidth is allocated for locally generated network packets sent in the downstream direction. A minimum downstream available network bandwidth is determined from information received in the upstream direction. The local allocated bandwidth is adjusted based on the minimum downstream available network bandwidth and the local allocated bandwidth is used to govern whether a class of locally generated network packets are sent in the downstream direction.

Method and apparatus for distributed bandwidth allocation for a bi-directional ring media with spatial and local reuse

The invention provides a method and system for routing information lookup for packets using a routing protocol such as IP. Routing information which has been determined responsive to the packet header, which includes a destination address, a source address, and an input interface for the packet. Routing lookup is performed in response to at least one set of selected routing information, using a lookup table which includes tags both for the routing information and for a bitmask length (thus indicating the generality or scope of the routing information for the routing lookup). The lookup table is structured so that addresses having the most common bitmask length are addressed first, but that more specific addresses are still considered when they are present. It has been discovered that most internet addresses can be found by reference to 24-bit or 21-bit IP addresses, after which 16-bit, 12-bit, and finally 32-bit IP addresses are considered. Lookup flags indicate when a relatively uncommon but more specific 32-bit IP address match is available. A memory controller pipelines the lookup requests to a hash table memory, flushes superfluous requests when a lookup result is found, and handles cases relating to 32-bit IP address matches.

Multiple parallel packet routing lookup

An apparatus and method that provides improved statistics collection for high bandwidth interfaces supporting multiple connections. Statistics are counted for a plurality of connections. A determination is made to determine if a count value for each of the connections is greater than or equal to a threshold. Statistics are collected for connections having a determined count value greater than or equal to the threshold before connections having a count value below the threshold. The apparatus and method can thus avoid data loss and reduce wasted processing time in maintaining reliable and accurate statistics for multiple connection supported by a network switch or interface.

Growing community of inventors

Los Altos, CA, United States of America

Bruce Alexander Wilford