International Business Machines Corporation

Joseph M Rash

Edward Hau-chun Ku

Loren Blair Reiss

Douglas Ray Henderson

Thomas Eric Ryle

Dennis Albert Doidge

Brian Mitchell Bass

Jim Philip Ervin

Scott J Lemke

Pramod Narottambhai Patel

Joseph Kinman Lee

A multiported LAN switch comprised of legacy local area network ports and ATM ports. Each ATM port comprising a hardware forwarding engine for bridging LAN frames from the LAN ports to the ATM port. The hardware forwarding engine converts layerprotocols between the dissimilar ports expediently, without requiring intervention by a microprocessor. A substantial performance gain is attained compared to microprocessor controlled format converters. Both LAN emulation and virtual LANs are supported.

Method and apparatus for hardware forwarding of LAN frames over ATM networks

A multiported LAN switch comprised of legacy local area network ports and ATM ports. Each ATM port comprising a hardware forwarding engine for bridging LAN frames from the LAN ports to the ATM port. The hardware forwarding engine converts layer 2 protocols between the dissimilar ports expediently, without requiring intervention by a microprocessor. A substantial performance gain is attained compared to microprocessor controlled format converters. Both LAN emulation and virtual LANs are supported.

A method and system are provided for increasing processing efficiency associated with data frames transiting a network node having multiple ports. The method and system accomplish their objects via the following. A data frame having a header and data is received. An associated pointer for at least one portion of the received data frame is provided. The associated pointer is provided by segmenting each received data frame into parts, and associating with each segmented part a pointer. Thereafter, a portion of the received data frame is modified independent of other portions of the received data frame via utilization of given one or more of the associated pointers. Additionally, one or more copies of a portion (which can include the whole) of the received data frame is constructed by recalling each segmented part associated with one or more selected ones of the associated pointers. Furthermore, a determination is made as to whether the received header indicates unicast or multicast. In response to this determination, a number of data frames are constructed commensurate with protocols and destination addresses of one or more network nodes to which the constructed number of data frames is to be transmitted. The constructed data frames are transmitted from the node.

Multicast frame support in hardware routing assist

A system for coupling a local area network to a wide area network utilizes a PCI (Peripheral Component Interface) bus to couple a PCI interface to a PCI network interface card, which is coupled to the wide area network. The wide area network could be an asynchronous transfer mode network or a high bandwidth ethernet. If the PCI network interface card operates as a PCI master, then the PCI interface will operate as a PCI slave. If the PCI network interface card operates as a PCI slave, then the PCI interface of the invention will operate as a PCI master.

Protocol for using a PCI interface for connecting networks

A method and system are provided for enabling simultaneous cut-through and store-and-forward transmission of frames in high speed network devices. A Buffer Parameter Vector chains multiple frame buffers together. Frame Parameter Vectors created for each unique version of a frame are used to manage frames as they flow through the network device. Cut-through/store-and-forward decision logic determines whether frames can be transmitted by cut-through or store-and-forward. Multiple unique frames or copies of a frame that are to be transmitted store-and-forward have their Frame Parameter Vectors chained together by pointers. The cut-through/store-and-forward decision logic steps through the chain of Frame Parameter Vectors resulting in the frames associated with each Frame Parameter Vector being transmitted.

Simultaneous cut through and store-and-forward frame support in a

Method and apparatus for hardware forwarding of LAN frames over ATM

A method and system are provided for traffic shaping and bandwidth scaling in a high speed internetworking device. A slot time wheel mechanism is provided for traffic rate control and a credit/debit mechanism is provided for traffic shaping and scaling. The high speed traffic scaler and shaper incorporates a programmable slot time wheel, a traffic scaler state machine, a traffic shaper parameter table and a traffic scaler processor. The traffic scaler processor incorporates a traffic queue allocation manager, a queue priority arbiter, a port enable selector, a port priority arbiter and a DMA channel arbiter. The traffic queue allocation manager and the queue priority, port priority and DMA channel arbiters are each controlled by a corresponding state machine. The parameters in the traffic shaper parameter table are dynamically updated for each logical queue and are used to enable the credit/debit mechanism.

High speed internetworking traffic scaler and shaper

A memory interface for multi-port access to a memory unit, such as a static random-access memory (SRAM) device. The memory interface, which is generally adapted for a local area network (LAN) forwarding engine, provides single port read/write access to SRAM device, and arbitrates requests from the access interfaces to allocate bandwidth of the SRAM device among the requests. One embodiment allocates at least 50% of the bandwidth to a peripheral component interface (PCI) bus target interface and a PCI bus master interface, collectively. The arbitration logic may include a plurality of bandwidth control registers associated with respective access interfaces used to determine a permitted amount of bandwidth that an access interface is to have, wherein a request from an access interface is masked based on a value in its associated bandwidth control register. Arbitration can further allocate bandwidth using time division multiplexing.

Multi-port SRAM access control using time division multiplexed

A sequence in which two or more of the data units enter the network node, via a specific one of the multiple ports, is recorded. And, the two or more of the data units are transmitted from the network node according to the recorded sequence. The method and system achieve the recording of sequence via the following. In response to an insertion of one of the two or more data units into a specific one of the multiple processor subsystems, the specific one of the multiple processor subsystems is associated with a specific one of the multiple ports by which the one of the two or more data units entered the network node, and any other of the multiple processor subsystems that are currently processing on any other of the two or more data units that entered the network node through the specific one of the multiple ports is noted. Thereafter, any request to transmit by the specific one of the multiple processors is honored if it is determined that the data unit with the requesting processor is next according to the recorded sequence. The data unit is determined to be next in sequence if all of the multiple processors, that were processing on other data units which entered through the specific one of the multiple ports, have completed processing.

Growing community of inventors

Wake Forest, NC, United States of America

Joseph M Rash