Abstract: A data packet switching system comprises a plurality of network interfaces each adapted to be coupled to respective external networks for receiving and sending data packets to and from the external networks via a particular communication protocol. The data packet switching system further includes a plurality of symmetrical processors, including a first processor providing a control processor and remaining ones of said processors each providing data packet switching processors. The control processor is coupled to a corresponding one of the plurality of network interfaces and the data packet switching processors are coupled to each remaining one of the plurality of network interfaces. A switch is coupled to the control processor through the corresponding one of the network interfaces and is coupled to at least one of the switching processors through at least one other one of the network interfaces.

Abstract: A computer system housing where a vertical printed circuit board, e.g., a riser card, is inserted into a socket on a computer system motherboard. Some internal space within the housing may allow optimization of system memory capacity through packing of additional memory modules on the riser card. The additional memory may be mounted on the riser card and may reside in the vertical space created between the riser card and the directly-mounted memory on the motherboard. The computer system housing further includes a chassis that may be partitioned into two separate sub-chassis for proper positioning of one or more cooling fans as well as to accommodate changes in computer system configurations with minimized retooling of the chassis. The cooling fans may be mounted at such locations on the chassis that allow optimization of air circulation and, hence, cooling within the housing.

Abstract: A pending tag system and method to maintain data coherence in a processing node during pending transactions in a transaction pipeline. A pending tag storage unit may be coupled to a cache controller and configured to store pending tags each indicative of a coherence state for a data line corresponding to a pending transaction within the transaction pipeline. The pending tag storage unit includes a total amount of storage which is substantially less than an amount required to store tags contained in the full tag array for the cache memory. When a pending tag exists in the pending tag storage unit, the coherence state of the corresponding data line within the cache memory is dictated by the pending tag for snoop operations. Accordingly, data coherence is maintained during the period when transactions are pending, e.g., not yet presented to a processor and cache.

Abstract: A data packet switching and server load balancing device is provided by a general-purpose multiprocessor computer system. The general-purpose multiprocessor computer system comprises a plurality of symmetrical processors coupled together by a common data bus, a main memory shared by the processors, and a plurality of network interfaces each adapted to be coupled to respective external networks for receiving and sending data packets via a particular communication protocol, such as Transmission Control Protocol/Internet Protocol (TCP/IP). A first one of the processors is adapted to serve as a control processor and remaining ones of the processors are adapted to serve as data packet switching processors. The data packet switching processors are each coupled to at least one of the plurality of network interfaces. The control processor receives raw load status data from the external networks and generates load distribution configuration data therefrom.

Abstract: A mounting bracket forms a rack mount for a rack-mountable unit. The mounting bracket includes a planar body portion and a latching pivot for insertion into an aperture in a side wall of the rack-mountable unit. A head on the latching pivot is arranged to be insertable into a correspondingly shaped aperture, with securing of the mounting bracket to the rack-mountable unit being achieved by rotating the rack mount with respect to the rack-mountable unit with the latching pivot fully inserted into the aperture. On rotation, the head of the latching pivot is arranged to engage behind the side wall of the rack-mountable unit to secure the mounting bracket to the rack-mountable unit. Detent flanges on the mounting bracket prevent over-rotation of the bracket. A flange is provided for attaching the mounting bracket to the rack.

Abstract: An object-oriented interprise computing manager provides coordination between application programs by having each server program controlling the client executable program. In this manner, each client program communicates from the client to the server using a predefined protocol.

Abstract: A branch prediction scheme predicts whether a computer instruction will cause a branch to a non-sequential instruction. A prediction counter is selected by performing an exclusive or (XOR) operation between bits from an instruction address and a hybrid history. The hybrid history, in turn, is derived by concatenating bits from a global history register with bits from a local branch history table. The bits from the local branch history table are accessed by using bits from the instruction address.

Abstract: Event notification in a distributed system using an object maintained in serialized form, referred to as a marshalled object. For event notification, a machine registers with a device to receive notification of particular events within a network, and a marshalled object is transmitted with a registration request.

Abstract: An interprise computing manager in which an application is composed of a client (front end) program which communicates utilizing a network with a server (back end) program. The client and server programs are loosely coupled and exchange information using the network. The client program is composed of a User Interface (UI) and an object-oriented framework (Presentation Engine (PE) framework). The UI exchanges data messages with the framework. The framework is designed to handle two types of messages: (1) from the UI, and (2) from the server (back end) program via the network. The framework includes a component, the mediator which manages messages coming into and going out of the framework. A distributed computer system is presented with software for a client computer, a server computer and a network for connecting the client computer to the server computer which utilizes an execution framework code segment configured to couple the server computer and the client computer via the network.

Abstract: A method and apparatus for allowing a first thread to “share” its remaining time quantum with a second thread when the first thread is blocked. A thread may be blocked, for example, if it is waiting for a resource such as a data file or a lock. A thread may also be blocked if it is waiting for an event, such as a user keystroke. If there is a thread on the run queue that “owns” the resource needed by the consumer thread, the blocked consumer thread transfers its right to execute for a remaining time quantum to the owner thread, and the owner thread executes next. If the threads are in a same process, this transfer means that no process context switch is required, since the consumer thread and the owner thread are threads of the same process. In addition, this transfer means that the time before the resource becomes available to the blocked consumer thread will be short.

Abstract: A method and apparatus for operating a local server computer of a client-server network includes a technique to receive a request from a client computer of the client-server network. A determination is made whether the request requires dynamically generated information from a servlet object of the client-server network. If so, a specified servlet object corresponding to the request may be uploaded from a remote server computer of the client-server network. The specified servlet object is then executed to obtain dynamically generated information corresponding to the request.

Abstract: A fan control module is provided for a system unit. The fan control module includes power outputs for supplying power to a plurality of fan. It also includes a temperature sensor for giving a temperature signal. It further includes a control unit connected to receive the temperature signal and including preprogrammed control information for determining power signals to be supplied to each of the fan units for controlling the speed thereof. The fan control module can control the fan units in a coordinated manner enabling reliable and effective cooling of the system unit under widely varying parameters. It can mean that existing system components can be employed in harsher temperature environments that they were originally designed for, without needed a complete redesign thereof. The fan control module can be provided with electrical noise isolation circuitry to isolate other components from electrical noise generated by the fan units.

Abstract: A method and system for pruning slow multicast group members in a multicast group that includes a sending node and member nodes. The sending node and selected ones of the other nodes comprise repair heads of a repair tree. Each repair head has at least one child. Each of the member nodes generates a slowness metric. Each member node repair head aggregates its own slowness metric with the slowness metrics of their respective children in the tree along with a subtree flag that indicates whether the respective slowness metric is due to the reporting node or a node downstream of the reporting node. The member node repair heads propagates the largest of the aggregated slowness metrics upstream along with a subtree flag associated with the propagated slowness metric. Via this process the sending node receives the largest slowness metrics generated in respective branches of the repair tree along with corresponding subtree flags associated with the respective metrics.

Abstract: A method for creating a virtual device driver that runs under both Windows 3.x and Windows 95 operating systems is disclosed. There are two basic obstacles to be overcome in creating a virtual device driver VxD that will operate under both Windows 95 and Windows 3.x. The first obstacle, that of identificational incompatibility, is cured by disguising a Windows 95 compatible driver as a Windows 3.x compatible driver. This is done by renaming the Windows 95 driver with a file name having the three-character extension “386”. The version number within a Device Descriptor Block must also be changed in order to effect a total disguise. Once the identificational incompatibility has been cured through the aforementioned steps, Windows 3.x will load the Windows 95 driver. The second obstacle, that of partial functional incompatibility, is cured by appending additional logic and supplementary Windows 3.x emulation routines to the Windows 95 driver.

Abstract: A multi-level cache and method for operation of a multi-level cache generating multiple cache system accesses simultaneously. Each access request includes an address identifying a memory location having data that is a target of the access. A insertion pointer inserts each access request into an entry in a memory scheduling window. Each entry is marked as valid when that entry is ready to be applied to a first cache level. A picker picks valid entries from the memory scheduling window by pointing to the picked entry and applying the address therein to the first cache level. The picking occurs in a free-running mode regardless of whether the accesses hit in the first cache level. A second cache level, receives accesses that have missed in the first cache level. A resource monitor in the second cache level determines when a predetermined number of resources are committed to servicing the accesses that have missed in the first cache level.

Abstract: A user interface permits a programmer or other person to manage lock groups for classes. The programmer enters information through the user interface to define new lock groups, update defined lock groups, and delete lock groups. The programmer manages the lock groups in the classes, and an optional mapping tool maps the defined lock groups when converting data between an object model and a relational model.

Abstract: An apparatus and method for enabling remotely controlling power status of a remote device. The apparatus monitors information signals being transmitted to the remote device and from such information, determines whether to alter the power status of the remote device. The apparatus may include an uninterruptable power source to enable such remote control during an interrupt of main power to the apparatus.

Abstract: A method for routing conductive paths between a first datapaths and a second datapath in an integrated circuit is described. The method includes determining the degree of alignment between block one from the first datapath to block one from the second datapath, and determining the degree of alignment between block N from the first datapath to block N from the second datapath; Following the determination of the degree of alignment, the least aligned block pair to be routed is chosen from block one and block N. Next, a first horizontal track location to be used for routing the desired connection between said first datapath and said second datapath is chosen, and the corresponding conductive path is then routed using that track location. For each of the remaining unrouted block pairs, the next block pair to be routed is chosen to be the block pair immediately adjacent to the most recently routed block pair.

Abstract: An interprise computing manager in which an application is composed of a client (front end) program which communicates utilizing a network with a server (back end) program. The client and server programs are loosely coupled and exchange information using the network. The client program is composed of a User Interface (UI) and an object-oriented framework (Presentation Engine (PE) framework). The UI exchanges data messages with the framework. The framework is designed to handle two types of messages: (1) from the UI, and (2) from the server (back end) program via the network. The framework includes a component, the mediator which manages messages coming into and going out of the framework.

Abstract: A method and apparatus implementing a separate child context for each applet (or similar element) of a browser. A described embodiment of the present invention provides one or more child contexts that correspond to elements in the HTML for a web page displayed by a browser. For example, each applet executed by the browser has a corresponding and separate child context Each child context has an associated memory buffer. The browser also has a parent context, which each child context points to. When a graphic is displayed via a widget, the widget draws the graphic (such as a panel or a non-pressed button) in the child context of the applet and sets a “damage” flag in the child context. When the browser performs its main browser loop, it checks the status of the damaged flag for each element (including each applet). If the browser finds a damage flag that is set, this means that something was written into the child buffer and that the parent buffer needs updating.