Abstract: A computer-implemented method, carried out by one or more processors, for consolidating an index entry of a dictionary. In an embodiment, the method comprises the steps of receiving, by one or more processors, a set of parameters, wherein the set of parameters indicates at least a length of prefix and a length of hash value; receiving, by one or more processors, a first term for entry into an index; converting, by one or more processors, the first term for entry into the index according to the set of parameters; and responsive to determining the converted first term is not present in the index, storing, by one or more processors, the first converted term into the index.

Abstract: In accordance with some embodiments of the present invention, a composite material is prepared by blending a flame retardant modified cellulosic nanomaterial (FR-CN) filler into a polymer, wherein the FR-CN filler comprises a cellulosic nanomaterial (e.g., cellulose nanocrystals (CNCs) and/or cellulose nanofibrils (CNFs)) having a surface functionalized to incorporate a phosphorus-containing moiety. In some embodiments, the FR-CN filler is prepared by reacting hydroxyl groups on the surface of the cellulosic nanomaterial and a halogenated phosphorous-containing monomer (e.g., diphenyl phosphoryl chloride). In some embodiments, the surface of the cellulosic nanomaterial is further functionalized to incorporate an orthogonal functionality selected to enhance the compatibility of the FR-CN filler with the polymer by reacting hydroxyl groups on the surface of the cellulosic nanomaterial and a monomer (e.g., epichlorohydrin when the polymer is an epoxy-based polymer).

Abstract: In one embodiment, a system includes a switch having logic configured to receive an overlay packet via an overlay tunnel, the overlay packet including an overlay tunnel header having Quality of Service (QoS) attributes stored therein and a packet, remove the QoS attributes from the overlay tunnel header, decapsulate the packet from the overlay packet to remove the overlay tunnel header, determine a destination port from the packet, and forward the packet to the destination port. In another embodiment, a method includes receiving a packet on a source port, determining a virtual network associated with the source port, encapsulating the packet with at least one overlay tunnel header to form an overlay packet, storing QoS attributes with the at least one overlay tunnel header, the QoS attributes being determined in part by the virtual network, and sending the overlay packet via an overlay tunnel.

Abstract: Embodiments relate to a control area for managing multiple threads in a computer. An aspect is a computer system that includes a virtual machine (VM) configuration with one or more cores. Each core is enabled to operate in a single thread (ST) mode or a multithreading (MT) mode. The ST mode consists of a single thread and the MT mode consists of a plurality of threads on shared resources of a respective core. The computer system includes a core-oriented system control area (COSCA) having a common area representing all of the cores of the VM configuration and separate core description areas for each of the cores in the VM configuration. Each core description area indicates a location of one or more thread description areas each representing a thread within the respective core, and each thread description area indicates a location of a state description of the respective thread.

Abstract: Effecting reissue in a data processing system of a cryptographic credential certifying a set of attributes, the credential being initially bound to a first secret key stored in a first processing device. A backup token is produced using the first device and comprises a commitment to said set of attributes and first proof data permitting verification that the set of attributes in said commitment corresponds to the set of attributes certified by said credential. At a second processing device, a second secret key is stored and blinded to produce a blinded key. A credential template token produced from the backup token and the blinded key is sent to a credential issuer where said verification is performed using the first proof data and the credential template token is used to provide a reissued credential, certifying said set of attributes, to the second device, the reissued credential being bound to the second secret key.

Abstract: The present invention provides ART techniques with reduced LER. In one aspect, a method of ART with reduced LER is provided which includes the steps of: providing a silicon layer separated from a substrate by a dielectric layer; patterning one or more ART lines in the silicon layer selective to the dielectric layer; contacting the silicon layer with an inert gas at a temperature, pressure and for a duration sufficient to cause re-distribution of silicon along sidewalls of the ART lines patterned in the silicon layer; using the resulting smoothened, patterned silicon layer to pattern ART trenches in the dielectric layer; and epitaxially growing a semiconductor material up from the substrate at the bottom of each of the ART trenches, to form fins in the ART trenches.

Abstract: A computer-implemented method for storing a conversation as a record in a records management server is provided. The computer-implemented method comprises, capturing one or more instant messages exchanged among a plurality of participants as a conversation. The computer-implemented method further comprises, storing the conversation as a record in a records management system, in response to a determination that the conversation meets a predetermined criteria.

Abstract: According to embodiments of the disclosure, methods, systems and computer program products for memory power management and data consolidation are disclosed. The method may include selecting a first real memory portion and a second real memory portion from a plurality of real memory portions coupled to a memory controller in a computer system by a memory bus. The first real memory portion may be connected to a first buffer and the second real memory portion may be connected to a second buffer. The first and second real memory portions may be selected by the memory controller. The method may include migrating data from the first real memory portion to the second real memory portion on a migration bus through the first and second buffers. The method may also include placing the first real memory portion into a reduced power mode.

Abstract: A memory controller enters a memory mode, allocating memory address space within a pair of DIMMs such that each DIMM of the pair contains unallocated memory address space corresponding to allocated memory space in the other DIMM. The memory controller enters another memory mode, modifying the allocation of the memory address space from a first DIMM of the pair of DIMMs to a second DIMM of the pair of DIMMs. The data is moved from allocated memory address space of the first DIMM to unallocated memory address space in the second DIMM.

Abstract: A partition mobility facility in which a partition that is executing one or more applications that have optimized code with one or more extended features is to be moved from a source system to a target system. If the target system does not support the extended mode features, then action is taken to remove the code having those features to facilitate migration.

Abstract: Disclosed are structures with an optical waveguide having a first segment at a first level and a second segment extending between the first level and a higher second level and further extending along the second level. Specifically, the waveguide comprises a first segment between first and second dielectric layers. The second dielectric layer has a trench, which extends through to the first dielectric layer and which has one side positioned laterally adjacent to an end of the first segment. The waveguide also comprises a second segment extending from the bottom of the trench on the side adjacent to the first segment up to and along the top surface of the second dielectric layer on the opposite side of the trench. A third dielectric layer covers the second segment in the trench and on the top surface of the second dielectric layer. Also disclosed are methods of forming such optoelectronic structures.

Abstract: Detecting remote operation of a computer by another computer by receiving pointing device movement event information associated with multiple pointing device movement events in a sequence of pointing device movement events detected at a first computer, determining a frequency of the pointing device movement events from the pointing device movement event information, and determining that the frequency is consistent with a frequency of pointing device movement events that are sent to the first computer, thereby detecting that the first computer is operated by a computer other than the first computer.

Abstract: Methods, systems, and articles of manufacture for automatically fixing inaccessible widgets during mobile application execution are provided herein. A method includes identifying an image element from a set of one or more user interface elements of an application that are inaccessible to a given set of users; generating a text description associated with the image element; extracting a portion of the text description related to an accessibility property of the image element; and adjusting the accessibility property of the image element to render the image element accessible to the given set of users.

Abstract: A method, system and computer program product are provided for implementing enhanced reliability of memory subsystems utilizing a dual port Dynamic Random Access Memory (DRAM) configuration. The DRAM configuration includes a first buffer and a second buffer, each buffer including a validity counter. The validity counter for a receiving buffer is incremented as each respective data row from a transferring buffer is validated through Error Correction Code (ECC), Reliability, Availability, and Serviceability (RAS) logic and transferred to the receiving buffer, while the validity counter for the transferring buffer is decremented. Data are read from or written to either the first buffer or the second buffer based upon a respective count value of the validity counters.

Abstract: For efficient handing of semi-asynchronous RAID write failures using a processor device in a computing environment, a write operation is committed on a primary copy of data on a primary entity while sending the data to a secondary entity while awaiting an acknowledgment by the secondary entity. The acknowledgment indicates to the primary entity that metadata for the write operation has arrived at the secondary entity without necessarily indicating the data has arrived at the secondary entity. The acknowledgment is sent from the secondary entity regardless of a write failure and allowing the secondary entity to perform a recovery operation if a write failure occurs.

Abstract: A battery pack includes a plurality of cells. Two or more fuel gauges are associated with a voltage adjustable set of the plurality of cells. Each of the two or more fuel gauges is associated with one cell in the voltage adjustable set. Each of the two or more fuel gauges is configured to communicate cell capacity of the associated cell to a master controller. Two or more charge voltage controllers are associated with the voltage adjustable set. Each of the two or more charge voltage controllers is associated with one or more cells in the voltage adjustable set. Each of the two or more charge voltage controllers is configured to receive a signal from the master controller. Each of the two or more charge voltage controllers is configured to increase charge voltage on the associated one or more cells in response to receiving the signal.

Abstract: A variable declaration is identified in a source code file. A variable is identified that is associated with a variable declaration. A location of first use of the variable in the source code is determined. The variable declaration is moved to a first location preceding the location of first use of the variable to optimize the source code.

Abstract: According to embodiments of the present invention, one or more computer processors determine that a predetermined workload threshold associated with an invalidated object is not exceeded and transmits an invalidation command associated with the invalidated object to the owner of the invalidated object. The one or more computer processors instruct the modifier of the invalidated object to retain possession of a first lock on the object beyond the transaction. The one or more computer processors determine that a usage pattern associated with the invalidated object matches a predetermined usage pattern for selecting a lock that can be retained beyond an associated transaction and transmits a second lock a requestor. The one or more computer processors instruct the modifier to release possession of the first lock to the owner and transmit a first image of the current version of the invalidated object to the owner for subsequent transmission to the requestor.

Abstract: A method of forming an active matrix pixel that includes forming a driver device including contact regions deposited using a low temperature deposition process on a first portion of an insulating substrate. An electrode of an organic light emitting diode is formed on a second portion of the insulating substrate. The electrode is in electrical communication to receive an output from the driver device. At least one passivation layer is formed over the driver device. A switching device comprising at least one amorphous semiconductor layer is formed on the at least one passivation layer over the driver device.

Abstract: An optimizer identifies application code to be modified and modifies that code, such that the application includes unmodified code and modified code. Based on generating the modified code, the optimizer sets one or more controls to selectively enable use of extended mode features by the application. The extended mode features include one or more features at an instruction set level different from an instruction set level available to the application. The controls may be set in a control register or entries of address translation structures, as examples.

Abstract: A memory access operand of an instruction that accesses memory may be treated as a transaction atomic access. The processor may execute one or more processor state setting instructions, causing state information to be set in the processor. Upon executing a transaction policy override instruction, the default conflict detection policy is overridden for one or more subsequent memory accessing instructions.

Abstract: Extension patterns are deployed to core deployment patterns stored in a first software repository. An event relating to registration of a component is detected. In response to detecting the event, a tool registry can be queried to identify one or more extension deployment patterns for use with one or more core deployment patterns. Based upon the query, one or more extension deployment components can be retrieved from a second software repository. The one or more extension deployment components can be deployed on top of one or more instances of the one or more core deployment patterns.

Abstract: A mechanism that provides a source of reliability concern is leveraged to establish a non-volatile memory element. A memory cell may be programmed to have a longer retention time or a shorter retention time. Such mechanisms include, but are not limited to, threshold voltage modulation by charge trapping in the gate dielectric of an access transistor of a dynamic random access memory (DRAM) cell. A memory cell is programmed with a voltage pulse into a long retention time mode or into a short retention time mode. The programmed mode of each memory cell may be read by storing electrical charges in the DRAM cells, and by measuring whether the electrical charges remain after a threshold retention time. Further, a dual mode memory cell may be operated as a conventional DRAM cell, or as a non-volatile memory storing retention time as data.

Abstract: A wavy line interconnect structure that accommodates small metal lines and large vias is disclosed. A lithography mask design used to pattern metal line trenches uses optical proximity correction (OPC) techniques to approximate wavy lines using rectangular opaque features. The large vias can be formed using a self-aligned dual damascene process without the need for a separate via lithography mask. Instead, a sacrificial layer allows etching of an underlying thick dielectric block, while protecting narrow features of the trenches that correspond to the metal line interconnects. The resulting vias have an aspect ratio that is relatively easy to fill, while the larger via footprint provides low via resistance. By lifting the shrink constraint for vias, thereby allowing the via footprint to exceed the minimum size of the metal line width, a path is cleared for further process generations to continue shrinking metal lines to dimensions below 10 nm.

Abstract: Code to be modified is identified and modified by a dynamic code optimizer (DCO) or other optimizer executing in the same or different address space as the application being modified. The modified code is stored in memory regions separate from the memory regions of the unmodified or pre-existing code. This allows instruction fetches by the application to access the modified code, while data accesses by the application access the unmodified code. An optimizer may also access the code, but accesses by the optimizer are considered data accesses, and therefore, such accesses would be to the unmodified code, instead of the modified code. Thus, an address mapping capability is provided in which the optimizer may access the modified code by having multiple addresses point to the same physical memory location. One address is used by the application in an instruction fetch and the other address is used by the optimizer in a data access to access the modified code.

Abstract: In a method for sending a teleconference notification to one or more client devices connected to a teleconference an indication is received to send a teleconference notification to one or more client devices connected to a teleconference. One or more processors determine that a first client device of the one or more client devices is not an audio only device. In response to determining that the first client device of the one or more client devices is not an audio only device, one or more processors cause a non-audio notification of the teleconference notification to be sent to the first client device.

Abstract: A technique includes providing a nanodevice. A gate electrode structure has nanochannels with a first end connected to a first common trench and a second end connected to a second common trench. A gate electrode extends laterally as a continuous line on the gate electrode structure and is formed in each of the nanochannels. The gate electrode forms a separate nano-ring electrode around a partial circumference inside each of the nanochannels. The gate electrode is parallel to the first and second common trenches and is perpendicular to the nanochannels.

Abstract: According to embodiments of the disclosure, methods, systems, and computer program products for initializing a streaming application are disclosed. The method may include compiling code on a compiler system, the compiling of the code including establishing an operator graph having a plurality of processing elements including a first processing element and a second processing element. The compiling of code including receiving a first compiler directive specifying an operator sub-graph included in the operator graph, the operator sub-graph containing one or more processing elements from the plurality of processing elements. The compiling of code including receiving a second compiler directive identifying the first processing element, the first processing element configured to bypass the operator sub-graph by transmitting a predicted output tuple to the second processing element in response to determining that a processing condition exists in the operator graph.

Abstract: A computing device receives session description protocol (SDP) information including network parameters, from a plurality of client devices participating in an audio-video conference hosted by a primary conference host. The computing device selects a secondary conference host from the plurality of client devices. In response to receiving the SDP information from the plurality of client devices, the computing device sends a reply, including network parameter information identifying the secondary conference host, to the plurality of client devices of the audio-video conference. The computing device determines a failure of the primary conference host, wherein the failure is based, at least in part, on a violation of a threshold limit of a transmission rate of the primary conference host, and in response to determining the failure, the computing device sends information to activate the secondary conference host as the audio-video conference host, to the plurality of client devices.

Abstract: Embodiments of the present invention disclose an approach for inserting code into a running thread of execution. A computer sets a first set of bits to a first value, wherein the first value indicates that a first set of instructions should be inserted onto a stack. The computer executes a second set of instructions associated with a first safepoint, wherein the second set of instructions comprises one or more instructions to determine if the first set of bits is set to the first value. The computer determines that the first set of bits is set to the first value, and the computer inserts the first set of instructions onto the stack.

Abstract: A technique is provided for controlling biomolecules in a nanodevice. A membrane has two reservoirs at opposing ends of the membrane. A nanochannel is formed in the membrane connecting the two reservoirs. A gate electrode is formed on the membrane such that the gate electrode extends laterally in a region of the nanochannel. A biomolecule is trapped in the nanochannel by applying a first voltage to the gate electrode. In response to trapping the biomolecule, the biomolecule is stretched in the nanochannel by applying a second voltage to the gate electrode. The biomolecule is stretched based on changing from the first voltage to the second voltage applied to the gate electrode.

Abstract: A data set is stored in a linear data structure. A memory manager receives multiple change requests for the data set. In response to receiving, for example, a read request for the data set, the memory manager batch processes the change requests by first moving the data set into a non-linear data structure. The non-linear data structure consumes more memory resources than the linear data structure but may provide for faster processing of the change requests while eliminating duplicate data elements. The updated data set is then returned to the more memory-efficient linear data structure.

Abstract: A digital work of literature is vocalized using enhanced text-to-speech (TTS) controls by analyzing a digital work of literature using natural language processing to identify speaking character voice characteristics associated with context of each quote as extracted from the first work of literature; converting the character voice characteristics to audio metadata to control text-to-speech audio synthesis for each quote; transforming the audio metadata into text-to-speech engine commands, each quote being associated with audio synthesis control parameters for the TTS in the context of each the quotes in the work of literature; and inputting the commands to a text-to-speech engine to cause vocalization of the work of literature according to the words of each quote, character voice characteristics of corresponding to each quote, and context corresponding to each quote.

Abstract: The present invention relates generally to forming interconnects over contacts and more particularly, to a method and structure for filling interconnect trenches with a sacrificial filler material before removal of a hard mask layer to protect the liners of the contacts from damage during the removal process. A method is disclosed that may include: filling an opening in a dielectric layer above a contact and a contact liner with a sacrificial filler material, such that the contact liner is completely covered by the sacrificial filler material; removing a hard mask layer used to pattern and form the opening; and removing the sacrificial filler material from the opening selective to the dielectric layer, the contact liner, and the contact to form an interconnect trench.

Abstract: Various embodiments manage service issues within a wireless communication network. In one embodiment, a one or more call detail records associated with a set of wireless communication devices of a wireless communication network is received. A set of information within each of the one or more call detail records is compared to a baseline statistical model. The baseline statistical model identifies a normal operating state of the wireless communication network. At least one outlier call detail record in the one or more call detail records is identified based on the comparison. The at least one outlier call detail record indicates that at least one wireless communication device associated with the at least one outlier call detail record experienced one or more service issues.

Abstract: Embodiments relate to thread context restoration. One aspect is a multithreading computer system including a configuration with a core configurable between a single thread (ST) mode and a multithreading (MT) mode. The ST mode addresses a primary thread and the MT mode addresses the primary thread and one or more secondary threads on shared resources of the core. A multithreading facility is configured to control utilization of the configuration to perform a method including disabling one or more secondary threads based on switching from MT mode to ST mode. A thread context of secondary threads is made unavailable to programs. Based on a last-set program-specified maximum thread-id indicating MT, the thread context is obtained by a) executing a set MT instruction to resume the MT mode, and b) based on being in the resumed MT mode, accessing the thread context.

Abstract: According to embodiments of the disclosure, methods, systems, and computer program products for initializing a streaming application are disclosed. The method may include compiling code on a compiler system, the compiling of the code including establishing an operator graph having a plurality of processing elements including a first processing element and a second processing element. The compiling of code including receiving a first compiler directive specifying an operator sub-graph included in the operator graph, the operator sub-graph containing one or more processing elements from the plurality of processing elements. The compiling of code including receiving a second compiler directive identifying the first processing element, the first processing element configured to bypass the operator sub-graph by transmitting a predicted output tuple to the second processing element in response to determining that a processing condition exists in the operator graph.

Abstract: A wireless packet switch and methods for controlling the same include a multiple port controllers, each in communication with a respective wireless transceiver, configured to analyze data streams to and from the respective wireless transceiver; a cross-connect switch in communication with all of the port controllers, configured to provide connections between respective port controllers; an arbiter, in communication with all of the port controllers and with the cross-connect switch, configured to control the cross-connect switch, such that the cross-connect switch connects data streams of the port controllers in accordance with packet destination information and scheduling information from the port controllers.

Abstract: A sensing apparatus includes a device containing microwells and a switched capacitor circuit in which at least one of the sensing/storage capacitors is a capacitor that extends perpendicularly with respect to a semiconductor device layer containing field effect transistors. Capacitor structures extend into microwells or within a doped layer on a handle substrate. Ion generation within the microwells is sensed using the circuit.

Abstract: Crawling computer-based documents by performing static analysis on a computer-based document to identify within the computer-based document one or more execution vectors, where each execution vector includes a computer program segment including a call to an entity that is external to the computer-based document, and one or more additional computer program segments whose execution precedes and leads ultimately to execution of the computer program segment that includes the call to the entity, and causing any of the computer program segments in any of the execution vectors to be executed during a crawling of the computer-based document, and any computer program segment within the computer-based document that is excluded from the execution vectors to be excluded from execution during the crawling of the computer-based document.

Abstract: A method for scheduling a crossbar using distributed request-grant-accept arbitration between input group arbiters and output group arbiters in a switch unit is provided. Each input group arbiter and output group arbiter maintains an ordered queue of links in an input group or an output group. The ordered queue prioritizes links in the output group or output group that was least recently selected. To satisfy an arbitration slot won on the group-level, the input group arbiter or output group arbiter starts a search from the oldest link that was selected and maintains fairness among links in the group.

Abstract: A thin film inductor with top and bottom pole pieces that are mechanically connected to each other at at least two via zones, to create a magnetically permeable yoke that defines at least one interior space. Enclosed portion(s) of a winding member pass through the interior space(s) of the yoke. The enclosed portion(s) of the winding member define an axial direction and a transverse direction. The pole pieces extend beyond the via zones in the axial and/or transverse direction. The extended pole pieces improve magnetic performance of the thin film inductor, by effectively moving pole piece edges away from locations of high magnetic flux density.

Abstract: A database table is monitored to automatically determine its volatility, and at least one volatility attribute expressing volatility state is saved. The volatility attribute is used to manage the database, e.g., to determine an optimum query execution strategy for a query involving data in the table, and/or for determining whether to re-optimize a previously saved query execution strategy and/or for managing storage and retrieval of table data. Preferably, parameters of the database table are captured at regular sampling intervals and a figure of merit representing volatility is computed from the parameter values. Preferably, the database supports the SQL database language, and the volatility attribute is or includes the SQL VOLATILE attribute. In an additional embodiment, the database manager may express volatility of a database table as a value within a range.

Abstract: In a method for displaying content corresponding to a character, symbol or shape drawn by a user on a touch screen. In response to the user drawing the character, symbol or shape on the touch screen, a processor determines (a) a size of the character, symbol or shape based on one or more geometric measurements made by the processor of the character, symbol or shape, and (b) content corresponding to the character, symbol or shape. The processor displays on the touch screen the content with a size based in part on the size of the character, symbol or shape drawn by the user.

Abstract: A method for transferring and storing a data set associated with an in-memory data grid (IMDG) is provided. The method may include identifying at least two data object instances associated with the data set based on a determined relationship between the at least two data object instances. The method may also include performing a field relation analysis on the identified at least two data object instances and recording the field relation analysis. The method may include receiving a request for a data object associated with the data set. The method may include determining if an optimization can be performed on the data object. The method may include omitting a field value associated with the data object based on the determined optimization. The method may include inflating the omitted field value into the data set associated with the data object request and returning the data set with the inflated field value.

Abstract: Hierarchical address translation structures providing separate translations for instruction fetches and data accesses. An address is to be translated from the address to another address using a hierarchy of address translation structures. The hierarchy of address translation structures includes a plurality of levels, and a determination is made as to which level of the plurality of levels it is indicated that translation through the hierarchy of address translation structures is to split into a plurality of translation paths. The hierarchy of address translation structures is traversed to obtain information to be used to translate the address to the another address, in which the traversing selects, based on a determination of the level that indicates the split and based on an attribute of the address to be translated, one translation path of the plurality of translation paths to obtain the information to be used to translate the address to the another address.

Abstract: A self-organizing internet protocol television (IPTV) grid system that: establishes an internet protocol television grid including an IPTV server, a plurality of grid nodes, a first end user device and a second end user device; communicates an IPTV channel signal over a first communication path that begins at the IPTV server and ends at the first end user device; communicates the IPTV channel signal over a second communication path that begins at the IPTV server and ends at the second end user device; determines that a quality issue condition exists for the channel signal as communicated to the second end user device; and responsive to the determination of the quality issue condition, communicates the IPTV channel signal over a third communication path that begins at the first end user device and ends at the second end user device.

Abstract: A streams manager monitors performance of a streaming application, and when the performance needs to be improved, the streams manager requests a cloud manager provision one or more VMs on a server that has a specified hardware type, and optionally has specified available hardware capacity. In response, the cloud manager determines which available servers have the specified hardware type, and when available hardware capacity is specified, further determines which of the available servers with the specified hardware type have the specified available capacity. When there are multiple servers that satisfy the request from the streams manager, the cloud manager determines from historical performance logs for the servers which is preferred. The cloud manager then provisions the requested VM(s) on the specified hardware type and returns the requested VM(s) to the streams manager. The streams manager then deploys a portion of the streaming application to the VM(s).

Abstract: In a method for visualizing motion of an object in an image, at least two images, including a first image and a second image, wherein each of the at least two images includes an object are received. One or more processors determine a first distance value for the object in the first image and a second distance value for the object in the second image, wherein each distance value is based on a distance between the object and an image capturing device. One or more processors compare the first distance value to the second distance value to determine a difference between the first distance value and the second distance value. One or more processors generate an indication based on the determined difference between the first distance value and the second distance value.

Abstract: Profile data for streaming operators is collected and classified according to the function and relationship of operators, and split rules are constructed for the operators. A streams manager monitors performance of a streaming application, and when the performance needs to be improved, the streams manager determines from the split rules how to split the flow graph for the streaming application. The streams manager requests virtual machines from a cloud manager. In response, the cloud manager provisions one or more virtual machines in a cloud. The streams manager then modifies the flow graph so a portion of the flow graph is deployed to the one or more virtual machines in the cloud. In this manner a streaming application can dynamically evolve to increase its performance as needed.