Abstract: Storage devices are presented which have some facility of error indication and error correction. The basic idea of the present invention is to double only the storing part inside the storing cell and share the environmental logic. Especially in case of multi-port cells this reduces the area penalty significantly because the read/write control within the cell is shared and only placed once. Writing the cell always writes both latches so that they hold the same data. A soft error can flip only one of the two latches. Then, a ‘XOR’ block detects that the data is no longer identical. While the data is read out the check bit indicates that the data is corrupted. The approach of doubling only the storing elements can be extended to implement a triple storing element (10, 12, 30) in the same cell. Then, with the help of a small and simple error correction logic (32) in the cell from a ‘majority vote’ can be seen which bit value is wrong in case of a soft error affecting one bit in the cell.

Abstract: In a mainframe class data processing system having multiple logical partitions and a port to a network, a host-network interface is established for reducing network overhead at the multiple partitions. The host-network interface includes, for example, a host channel connection coupling the multiple partitions of the host system to a communications adapter having a network device driver for each network coupled to the adapter. The adapter also includes an address resolution protocol (ARP) cache designed to hold predetermined media headers for the clients coupled to the network(s) for use in forwarding an internet protocol (IP) datagram across the network to one of the clients from a partition of the host system. Provision is also made for partition-to-partition communication of IP datagrams by storing IP addresses of the logical partitions as HOME addresses in the ARP cache of the adapter.

Abstract: A technique for transferring data between a first device and a second device using a shared line buffer connected to a system bus which couples the first device and the second device. The technique includes (i) transferring data between the line buffer and dedicated memory associated with the first device, wherein the first device includes a data controller coupled to the system bus through a bus interface. The transferring (i) includes using the data transfer controller to effectuate a multiword data transfer between the dedicated memory and the line buffer. The technique further includes multiword data (ii) transferring between the line buffer and the second device across the system bus. When the transferring (i) precedes the transferring (ii), data is read from the dedicated memory from output to the second device, and when the transferring (ii) precedes the transferring (i), data is written to dedicated memory from the second device.

Abstract: A cooling apparatus and method of fabrication are provided for cooling one or more heat generating components. The cooling apparatus includes a heat sink structure and an airflow tube assembly. In one embodiment, the heat sink structure has a first surface for coupling to one or more heat generating components, and a second surface having at least one fin extending therefrom. The airflow tube assembly has at least one airflow tube which is sized to at least partially receive the at least one fin of the heat sink structure, wherein an annular airflow can be established between the at least one airflow tube and the at least one fin of the heat sink structure, thereby enhancing heat transfer from the heat sink structure to the airflow and cooling of the heat generating component(s).

Abstract: A semiconductor device is presented which includes a self-aligned, planarized thin-film transistor which can be used in various integrated circuit devices, such as static random access memory (SRAM) cells. The semiconductor device has a first field-effect transistor and a second field-effect transistor. The second field-effect transistor overlies the first field-effect transistor, and the first field-effect transistor and the second field-effect transistor share a common gate. The second field-effect transistor includes a source and a drain which are self-aligned to the shared gate in a layer of planarized seminconductor material above the first field-effect transistor. In one embodiment, the second field-effect transistor is a thin-film transistor, and the shared gate has a U-shape wrap-around configuration at a body of the thin-film transistor.

Abstract: Asynchronous requests, such as input/output (I/O) requests, within a coprocessor of a computing environment are managed. The management of the asynchronous requests is based on priorities associated with the asynchronous requests. This management includes, for instance, selecting an asynchronous request to be processed using a priority scheme, and/or affording resources to the asynchronous requests using a priority scheme.

Abstract: In a distributed computing environment having a plurality of processing nodes, a technique is presented for referencing failure information representative of multiple related failures. A first failure report is created upon detection of an initial failure condition in a first program running in the distributed computing environment. The first program failure report is assigned a first identifier which uniquely identifies the report. Upon detecting a second program failure condition at a second node which is related to the first program failure condition, a second program failure report is created by recording information on the second program failure condition. A second identifier is assigned to the second program failure report which uniquely identifies the second program failure report, including a reference to the first identifier for the first program failure report.

Abstract: Assistive motion data processing and/or button data processing is performed in an adapter on user inputted variable data produced by a pointing device prior to communication to a computer. This processing may include one or more of processing to filter coordinate deviations from a desired path caused by unintended movements of the pointing device; removal of unintentional rapid button transitions of the pointing device; look-back processing to correct for unintentional pointer coordinate motion induced by operation of buttons on the pointing device; and detection of button double-clicks using relaxed requirements on motion and timing. The adapter's processing is transparent to the computer. Provision for user input of selected parameters is provided, as well as switching to allow for user deactivation of the adapter for conventional use of the pointing device.

Abstract: A dual work function semiconductor structure with borderless contact and method of fabricating the same are presented. The structure may include a field effect transistor (FET) having a substantially cap-free gate and a conductive contact to a diffusion adjacent to the cap-free gate, wherein the conductive contact is borderless to the gate. Because the structure is a dual work function structure, the conductive contact is allowed to extend over the cap-free gate without being electrically connected thereto.

Abstract: An on-screen display (OSD) processor, processing method and article of manufacture are provided having a color mapped mode, direct color mode, and 4:2:2 profile mode. The OSD processor implements both color mapped OSD region processing capability and direct color OSD region processing capability, along with an ability to store quantizer coefficients for the 4:2:2 profile mode of a video decoder coupled to the OSD processor. The capabilities of the OSD processor are implemented using a common embedded memory within the processor. During color mapped OSD region processing, color table data is temporarily stored within the embedded memory, while in direct color OSD region processing, direct color descriptions are stored within the embedded memory. When the video decoder is decoding a 4:2:2 formatted image, the embedded memory of the OSD processor is used to temporarily store inverse quantization data for the decode function.

Abstract: Throughput of a request (e.g., a write request) is enhanced by allowing a receiver of the request to reply to the request before fully receiving the entire request. This reduces the delay between the time that the receiver completes a request and the time that the sender sees that the request is finished, and allows other requests to be forwarded prior to completion of the first request. The other requests that are forwarded, however, are processed in the order of receipt. Additionally, any errors that occur in a request after the reply is sent is forwarded to the sender of the request, even though the reply has previously been sent.

Abstract: To enable a power to the computer to be shut down in a simple configuration and independently of the status of the computer. The power switch 46 is set at the normal position while the computer 10 is operating. Each of the power, reset, and function signals is thus on the high level (A). When the function key 42A is pressed in that status, the function signal can be shifted to a low level signal so as to validate only the key 42A (B). While the power switch 46 is shifted to a pointed position and the key 42A is not pressed, only the power signal is validated, thus a power-on or power-off command can be issued (C). If the power switch 46 is set at a pointed position and the key 42A is pressed, then the level of the reset signal becomes low, thereby the reset signal is validated with the key 42A (D). Consequently, the power to the computer can be shut down forcibly if the power switch 46 is set at a pointed position and the key 42A is pressed, regardless of the status of the computer 10 operation.

Abstract: Method, system and program product are provided implementing a technique for backprojecting an image from a projection data set. The technique includes splitting the projection data set into a plurality of multi-channel textures, with each multi-channel texture corresponding to a predetermined number of color channels of a multi-color rendering engine. The multi-color rendering engine is employed to simultaneously render the split projection data set and obtain intermediate results for each color channel. The intermediate results of each color channel are then accumulated to generate separate rendered images, wherein multiple images are simultaneously rendered from the projection data set using the separate color channels of the multi-color rendering engine.

Abstract: An electrically controllable, variable optical attenuator (VOA) is disclosed, in which polarization maintaining fiber is employed. The fiber is modified to expose the evanescent field of optical energy transmitted therein, by removing material therefrom in a direction parallel to either the fast or slow axis of the fiber, while preserving the polarization maintaining property of the fiber. A controllable material is formed over the modified portion, to remove optical energy in response to a changeable stimulus applied, which changes the refractive index of the material. Related packaging, material composition and system aspects of the attenuator are also disclosed.

Abstract: A central queue-based packet switch contains multiple input ports and multiple output ports coupled by a central queue path and a bypass path. The central queue has only shared memory and processing dynamically switches from transfer of message portions across the central queue path to the bypass path whenever a next message portion is identified by an output port as a critical portion. Upon transfer of message forwarding to the bypass path, subsequent message portions are forwarded across the bypass path unless the output port signals for transfer of the message portions back through the central queue path. Dynamic switching of message transfer from the central queue path to the bypass path is accomplished irrespective of whether contention exists for the output port.

Abstract: An integrated heat sink system is provided for internal cooling of a closed electronics container. The heat sink system includes a cold plate and a fin assembly thermally coupled to and extending from the cold plate. The cold plate has a surface for thermally coupling to one or more components within the container, such as a processor module. The heat sink system further includes at least one coolant carrier channel thermally coupled to and passing through the fins of the fin assembly. When the heat sink system is operational within the closed container, the cold plate thermally couples to and removes heat from the one or more components, the plurality of fins remove heat from air circulating within the closed container, and coolant within the coolant carrying channel(s) removes heat from the plurality of fins and from the cold plate thermally coupled thereto.

Abstract: Magnetoresistive devices are disclosed which include a changeable magnetic region within which at least two magnetic states can be imposed. Upon magnetoresistive electrical interaction with the device, the relative orientation of the magnetic states of the changeable magnetic region, and a proximate reference magnetic region, can be sensed thereby providing a binary data storage capability. The present invention limits the electrical interaction to only a preferred portion of the changeable magnetic region, e.g., the portion within which the two magnetic states can be dependably predicted to be substantially uniform, and opposite of one another. Structures for limiting the electrical interaction to this preferred portion of the changeable magnetic region are disclosed, and include smaller interaction regions, and alternating areas of insulation and conductive, interaction regions, disposed proximate the changeable magnetic region.

Abstract: A cooling system and method of fabrication are provided for cooling one or more heat-generating electronic elements within a portable computer. The cooling system includes a cold plate assembly thermally coupled to a heat-generating electronic element, and a heat exchange structure disposed within the cover of the portable computer. The heat exchange structure includes a hollow channel and an expansion chamber in fluid communication with the channel. A conduit carries coolant between the cold plate assembly and the hollow channel in the heat exchange structure, and a circulation pump circulates coolant through the conduit between the cold plate assembly and the heat exchange structure in a manner to remove heat from the heat-generating electronic component. The expansion chamber integrated within the heat exchange structure provides a reservoir for the circulation pump from which to draw coolant for circulation through the cold plate assembly.

Abstract: To provide a back light unit, a liquid display, and a method for manufacturing a light guide plate, in which the occurrence of bright lines can be diminished. An incoming surface 11a of a transparent light guide plate 11 is machined into a smooth surface S to correct a manufacturing tolerance during injection molding in order to form an edge portion E into a designed shape. To effectively reduce occurrence of bright lines, the edge portion E preferably has a curvature of radius or a chamfer dimension of 140 [&mgr;m] or smaller. The transparent light guide plate 11, a diffusion sheet 5, and a prism sheet 12 configure a back light unit 10 for a liquid crystal display.

Abstract: A heat exchanger using thermoelectric structures is provided for cooling a heat generating component of an electronic device. The heat exchanger includes a row of spaced passages, for example, formed by two or more separate tubes or a single coiled tube, for carrying a first cooling fluid. The heat exchanger further includes a thermoelectric structure disposed between adjacent spaced passages and exposed to a second cooling fluid. In one embodiment, the heat exchange also includes fins disposed between the same adjacent spaced passages so that the thermoelectric structure is disposed between the adjacent passages and the fins.