Abstract: A method for remotely administering one or more nodes of a distributed data processing system to provide mirroring of operating system images, and/or designating of alternate volume groups for the one or more nodes. A new data class is defined in a system data repository (SDR) coupled to a control node of the distributed system. A set of commands are provided to initiate and discontinue mirroring from the control node on a nodal volume group, along with designating alternate volume groups for remote installation on one or more nodes of the system in parallel. An interface to add, delete, modify or display information about nodal volume groups is also provided.

Abstract: To generate an optimum communication schedule when data is transmitted or received between processors which constitute a parallel computer or a distributed multiprocessor system. Processors which each perform inter-processor communication are sorted into a plurality of groups. A communication graph is generated whose nodes correspond to the groups and edges correspond to the communications. Communication graphs are generated for distances between nodes from one through N−1. Each communication graph corresponds to a communication step of the inter-processor communication. Communication is grasped as a whole by the communication graph and the edge of the communication graph means the inter-processor communication which is performed in a certain communication step. In this way, the communication can be optimized.

Abstract: A technique for remotely administering one or more nodes of a distributed data processing system to provide mirroring of operating system images, and/or designating of alternate volume groups for the one or more nodes. A new data class is defined in a system data repository (SDR) coupled to a control node of the distributed system. A set of commands are provided to initiate and discontinue mirroring from the control node on a nodal volume group, along with designating alternate volume groups for remote installation on one or more nodes of the system in parallel. An interface to add, delete, modify or display information about nodal volume groups is also provided.

Abstract: An aligned Instruction cache (AIC) containing multiple instruction cache sectors in which may be recorded out-of-sequence blocks of instructions. Basic blocks of instructions are aligned in AIC sectors at program run time. An AIC directory uses the current instruction address to select an AIC directory entry and an associated row in the AIC containing multiple sectors. The AIC directory entry contains multiple “Sector S first address” fields respectively associated with the multiple AIC sectors, each of these directory fields containing the address of the first instruction in the associated AIC sector S when its contents are valid. A “fetch history table” (FHT) contains four FHT entries for each associated AIC row organized in FHT sets of four entries. Each valid FHT entry records a predicted sequence of instructions based on a prior actual execution of the sequence in the same program, which may repeat over and over again.

Abstract: A write-behind enablement approach is presented which allows writing data to multiple volumes of storage media associated with one or more server nodes in a distributed processing environment. A client application on a client node writes blocks of data to a first magnetic tape of a first server node until an end of physical storage of the first magnetic tape is reached, without having predetermined the size of the first magnetic storage. Thereafter, the writing of blocks of data is switched to a second magnetic tape, which may be on the first server node or a second server node in the system. The writing and switching process can repeat a number of times across multiple magnetic tapes. Data is written in a write-behind operation and the switching to a new magnetic tape occurs transparent to the client application, and without loss of data.

Abstract: A lock structure, which includes many entries, is partitioned into segments. A number of the segments are cleaned up in parallel, such that cleanup processing of the entire lock structure is optimized. The lock structure is maintained within a coupling facility, which provides access to the lock structure by one or more processors coupled to the coupling facility. The cleaning up of the lock structure is performed by commands driven by the one or more processors and executed within the coupling facility.

Abstract: A photolithographic process is provided for producing a blank storage disk which includes a reference track pattern. The track pattern provides two edges as reference lines from which distances are determinable for the purpose of laser writing multiple information tracks between adjacent reference track patterns which are preferably spirals (single or interlaced) or concentric circles. The photo-lithographic process is also used to create recording blanks having multiple layers.

Abstract: An efficient heat sink having a high density of fins and a large effective surface area is formed by coiling a flat strip of thermally conductive material in which teeth or millifins have been formed by a stamping operation, for example. A spacer may be employed to insure fin separation. In an alternate embodiment, the strips are stacked. The resulting heat sink is particularly effective in impingement flow cooling of electronic devices, chips, circuits or modules.

Abstract: A write-behind enablement approach is presented which allows writing data to multiple volumes of storage media associated with one or more server nodes in a distributed processing environment. A client application on a client node writes blocks of data to a first magnetic tape of a first server node until an end of physical storage of the first magnetic tape is reached, without having predetermined the size of the first magnetic storage. Thereafter, the writing of blocks of data is switched to a second magnetic tape, which may be on the first server node or a second server node in the system. The writing and switching process can repeat a number of times across multiple magnetic tapes. Data is written in a write-behind operation and the switching to a new magnetic tape occurs transparent to the client application, and without loss of data.

Abstract: An apparatus is provided for varying the direction which a control laser beam impinges on a rotatable storage medium. The reflected control beam is thus modulated by surfaces aspects of the medium such as by embedded reference tracks. This reflected light signal is converted to an electrical signal which is analyzable to determine vertical alignment particularly with respect to the orthognal direction. In one embodiment, the apparatus comprises a rotating cylinder in which a lens is disposed in a canted orientation so that the optical axis of the lens is not exactly aligned with the axis of the cylinder about which rotation occurs.

Abstract: In a direct lid attach structure incorporating thermally conductive material between a lid and an electronic circuit chip, there are provided a number of apertures in the lid. These apertures are provided directly opposite disks or pads disposed on the substrate to which the chip is attached. A hardenable adhesive such as an epoxy is disposed through the apertures and hardened in place so as to provide a bond between the lid and the underlying pad which has been previously affixed to the substrate to which the chip is attached with a compliant adhesive. There is thus provided an electronic chip assembly which allows bonded chip-to-lid thermal interfaces to be used with LGA interconnection techniques. The support structure mitigates the mechanical loads associated with LGA socketing which could otherwise damage the substrate and affect the integrity of the bonded thermal interface.

Abstract: A structure for reducing cross-talk in VLSI circuits is disclosed. By filling voltage and ground metal lines in free or unused channels of VLSI chips and connecting them efficiently to the regular power image of the chip, the line to line coupling through vertical layers is reduced almost to zero and in-layer line to line coupling is also drastically reduced.

Abstract: Tolerances in chip, substrate and hardware dimensions are accommodated by means of a floating sealing structure to insure that compliant thermally conductive paste disposed between the chip and its lid is as trim as possible in order to reduce thermal resistance of the paste so as to be able to run the chip at a cooler temperature. Standoffs are also preferably employed to insure proper paste gap thickness.

Abstract: When model statements in an origin language, model statements in a target language, and conversion rules for word (variable) sections are inputted from the screen of a conversion rule input means, a conversion rule generation means generates a conversion rule according to this input and stores it in the conversion rule database. The conversion rule is composed of a search key, a word conversion direction section, and a target language generation program. The search key is used when a conversion rule needed for the conversion of an unconverted origin program is searched for in a database and fetched, the word conversion direction section is used for calling the word conversion table or the word conversion program, and the target language generation program is used for generating a converted target program. The conversion rule input means, conversion rule generation means, and conversion rule drive means do not depend on the origin language and target language of the languages involved in conversion.

Abstract: Program product for an application programming interface that unifies a plurality of mechanisms into a single framework. The interface includes a mechanism for communicating between members of a process group of related processes, and a mechanism for synchronizing the related processes of the process group. Additionally, the application programming interface may include mechanisms for managing membership of the process group or a processor group of processors, and/or a mechanism for controlling a group state value for the process group.

Abstract: A write-behind computer program product is presented which allows writing data to multiple volumes of storage media associated with one or more server nodes in a distributed processing environment. A client application on a client node writes blocks of data to a first magnetic tape of a first server node until an end of physical storage of the first magnetic tape is reached, without having predetermined the size of the first magnetic storage. Thereafter, the writing of blocks of data is switched to a second magnetic tape, which may be on the first server node or a second server node in the system. The writing and switching process can repeat a number of times across multiple magnetic tapes. Data is written in a write-behind operation and the switching to a new magnetic tape occurs transparent to the client application, and without loss of data.

Abstract: A computer program product for use in a distributed processing system having a plurality of nodes wherein selected nodes are fenced or unfenced from selected ones of peripheral device server nodes in a fence/unfence operation. A common memory is provided for storing a fence map listing nodes fenced from server nodes. In the fence/unfence operation, a request processing node proposes changes to the fence map, and if no node fails during the fence/unfence operation, the proposed changes are changed into committed changes. If a node fails during the fence/unfence operation, the proposed changes are erased, the previous committed changes are restored, and the fence/unfence request is removed from the process queue for processing by the request processing node.

Abstract: A method for use in a distributed processing system having a plurality of nodes wherein selected nodes are fenced or unfenced from selected ones of peripheral device server nodes in a fence/unfence operation. A common memory is provided for storing a fence map listing nodes fenced from server nodes. In the fence/unfence operation, a request processing node proposes changes to the fence map, and if no node fails during the fence/unfence operation, the proposed changes are changed into committed changes. If a node fails during the fence/unfence operation, the proposed changes are erased, the previous committed changes are restored, and the fence/unfence request is removed from the process queue for processing by the request processing node.

Abstract: An indicator is provided in a Page Frame Table Entry to identify a page frame as “Permanently Non-Preferred” (PNP). The indicator is set for page frames in storage subincrements which have locations corresponding to page frames determined to be “bad” (permanent errors) during system IPL, when reconfiguring storage on-line, or when a storage-related error occurs for such a frame during system execution. Mechanisms are provided to convert even PNP page frames to preferred status when shortages of preferred pages exist; but the mechanism used for choosing PNP frames, and for determining which PNP frames to convert to preferred status when conversion is needed, increase the likelihood of locating a target subincrement to use in copying pages from a preferred storage subincrement when the preferred storage is taken off-line.

Abstract: A mechanism for handling processing errors in a computer system. The mechanism includes a first means for processing a stream of instructions, second means for detecting an error caused by a timing dependant defect and occurring during processing of the instruction by the first means and third means for varying the instruction processing cycle time of the first means in response to the detection of the error by the second means, and for causing the second means to retry at least a portion of the instruction subsequent to the varying. In a preferred embodiment, the mechanism uses the variable frequency oscillator, controlled by recovery code, to increase the system clock cycle time by a specified time (Textend) following what has been determined to be a critical fail and after normal retry has been unsuccessful. The increased cycle time extends the net slack and, thereby, provides tolerance to certain AC (path delay) defects which have developed in any cycle time dependant latch to latch segment.