International Business Machines Corporation

Jacob Lorien Moilanen

Joel Howard Schopp

Michael Thomas Strosaker

Nathan Fontenot

Manish Ahuja

Mark Wayne VanderWiele

Travis M Grigsby

Michael Negley Abernethy, Jr

Nazgol Sedghi

Methods and arrangements to assign locks to threads are discussed. Embodiments include transformations, code, state machines or other logic to assign locks to threads. Embodiments may include setting a window of time at the end of a time slice of a thread. The embodiment may also involve prohibiting the thread from acquiring a lock during the window of time, based upon determining that the thread is within the window of time and determining that the thread does not hold any locks. Other embodiments include an apparatus to assign locks to threads and a computer program product to assign locks to threads.

Lock windows for reducing contention

A mechanism is provided for scheduling tasks across multiple processor units of differing capacity. In a multiple processor unit system with processor units of disparate speeds, it is advantageous to have the most processing-intensive tasks run on the processor units with the highest capacity. All tasks are initially scheduled on the lowest capacity processor units. Because processor units with higher capacity are more likely to have idle time, these higher capacity processor units may pull one or more tasks onto themselves from the same or lower capacity processor units. A processor unit will attempt to pull tasks that utilize a larger percentage of the timeslice. When a higher capacity processor unit is overloaded or near capacity, the higher capacity processor unit may push tasks to processor units with the same or lower capacity. A processor unit will attempt to push tasks that utilize a smaller percentage of the timeslice.

Pulling heavy tasks and pushing light tasks across multiple processor units of differing capacity

A computer implemented method, data processing system, and computer program product for dynamically scheduling algorithms in a pipeline which operate on a stream of data. The illustrative embodiments determine a computational cost of each algorithm in a plurality of algorithms in a pipeline. The plurality of algorithms in the pipeline processes an incoming data stream in a first sequential algorithm order. The illustrative embodiments reorder the plurality of algorithms in the pipeline to form a second sequential algorithm order based on the computational cost of each algorithm. The plurality of algorithms may then be executed in the second sequential algorithm order. When the illustrative embodiments assign a spare processing unit to an algorithm at an end of the pipeline, the computational cost of each algorithm in the plurality of algorithms in the pipeline is redetermined.

Horizontal scaling of stream processing

Provided is a method for displaying information such as lists of data, files and icons in a window of a graphical user interface (GUI). Unlike a typical display methodology, which arranges items in a 'machine-dependent' sorting order, the disclosed technology provides a 'natural' sorting order. The list, or names associated with the files or icons are incorporated into a query and the query is transmitted to a web service. The web service parses the query to determine a natural order appropriate to the material represented by the list, files, or icons rearranges the list, files or icons into the natural order and returns a response to the originator of the query. The operating system or GUI that originated the query receives the response, parses the response and displays the list, files or icons in the corresponding natural order.

Natural ordering in a graphical user interface

Partition migrations are scheduled between virtual partitions of a virtually partitioned data processing system. The virtually partitioned data processing system is a tickless system in which a periodic timer interrupt is not guaranteed to be sent to the processor at a defined time interval. A request is received for a partition migration. Gaps between scheduled timer interrupts are identified. The partition migration is then scheduled to occur within the largest gap.

Smart scheduling of automatic partition migration by the use of timers

A mechanism and functionality are provided for generating and using compiler optimized function variants. These variants may be used, for example, in situations where return values of functions called by code are not thereafter used by the code calling the functions. In particular, for a function called by computer code, at least two variants for the function may be generated. A function call, for calling the function, within original computer code may be analyzed to determine which variant of the at least two variants to use for the function call. The function call may be modified in the original computer code, to generate modified computer code, based on results of the analysis identifying which variant of the at least two variants to use for the function call.

Compiler optimized function variants for use when return codes are ignored

Methods and arrangements of assigning tasks to processors are discussed. Embodiments include transformations, code, state machines or other logic to detect an attempt to execute an instruction of a task on a processor not supporting the instruction (non-supporting processor). The method may involve selecting a processor supporting the instruction (supporting physical processor). In many embodiments, the method may include storing data about the attempt to execute the instruction and, based upon the data, making another assignment of the task to a physical processor supporting the instruction. In some embodiments, the method may include representing the instruction set of a virtual processor as the union of the instruction sets of the physical processors comprising the virtual processor and assigning a task to the virtual processor based upon the representing.

Assigning tasks to processors in heterogeneous multiprocessors

Illustrative embodiments provide a computer implemented method, a data processing system and a computer program product for lock contention reduction. In one illustrative embodiment, the computer implemented method provides a lock to an active thread, increments a lock counter, receives a request to de-schedule the active thread, and determines whether the lock is held by the active thread. The computer implemented method, responsive to a determination that the lock is held by the active thread, adds a first pre-determined amount to a time slice of the active thread.

Reducing lock contention by adding a time slice to an active thread holding a lock

A partitioned NUMA machine is managed to dynamically transform its partition layout state based on NUMA considerations. The NUMA machine includes two or more NUMA nodes that are operatively interconnected by one or more internodal communication links. Each node includes one or more CPUs and associated memory circuitry. Two or more logical partitions each comprise at a CPU and memory circuit allocation on at least one NUMA node. Each partition respectively runs at least one associated data processing application. The partitions are dynamically managed at runtime to transform the distributed data processing machine from a first partition layout state to a second partition layout state that is optimized for the data processing applications according to whether a given partition will most efficiently execute within a single NUMA node or by spanning across a node boundary. The optimization is based on access latency and bandwidth in the NUMA machine.

Dynamic logical partition management for NUMA machines and clusters

A method, system, and computer usable program product for energy conservation in multipath data communications are provided in the illustrative embodiments. A current utilization of each of several of I/O devices is determined. A violation determination is made whether an I/O device from the several I/O devices can be powered down without violating a rule. The I/O device is powered down responsive to the violation determination being false. A powering up determination may be made whether an additional I/O device is needed in a multipath I/O configuration. The I/O device may be located, powered up, and made available for multipath I/O configuration. A latency determination may be made whether a latency time of the I/O device can elapse before the time when the additional I/O device is needed. The powering on may occur no later than the latency time before the time the additional I/O device is needed.

Energy conservation in multipath data communications

Methods, apparatus, and products for determining thermal characteristics of instruction sets comprising one or more computer program instructions executed by a computer processor are disclosed that include tracking, in a performance counter, a number of classes of instructions run during execution of a plurality of instruction sets; identifying, for each instruction set, from the performance counter, a number of each class of instructions run during execution of the instruction set; and ranking the instruction sets in dependence upon the number of each class of instructions run during execution of each instruction set and a profile of thermal characteristics of classes of instructions.

Determining thermal characteristics of instruction sets

Methods, systems, and media are disclosed for autonomic system tuning of simultaneous multithreading ('SMT'). In one embodiment, the method for autonomic tuning of at least one SMT setting for an optimized processing, such as via throughput, latency, and power consumption, of a workload on a computer system includes calling, by a kernel, an SMT scheduler having at least one hook into a genetic library. Further, the method includes obtaining, by the SMT scheduler through the at least one hook, genetic data from the genetic library for the optimized processing of the workload. Further still, the method includes tuning, by the SMT scheduler and based on the obtaining, the at least one SMT setting for at least one cpu of the computer system.

Autonomic SMT System tuning

A computer implemented method, data processing system, and computer program product for reducing memory traffic via detection and tracking of temporally silent stores. When a memory store, comprising an address and a data value, to a cache is detected, a determination is made that a cache line in the cache contains a same address as the address in the memory store. A determination is then made that a tentative cache line invalidate signal for the cache line was previously sent to other data processing systems in the network to tentatively invalidate the cache line. If the memory store is a temporally silent store, a cache line revalidate signal is sent to the other data processing systems to clear the tentative invalidate signal for the cache line.

Reduced memory traffic via detection and tracking of temporally silent stores

Methods and computer program products for providing warnings and hints related to coding conventions using a coding style definition are provided. A source code is received, and a coding style definition is read. The source code is parsed to determine whether the source code adheres to the conventions in the coding style definition. Warnings are provided to indicate where the source code deviates from the coding style definition, if the source code fails to adhere to the conventions in the coding style definition. If the source code correctly adheres to the conventions in the coding style, hints can be provided to the compiler and linker so that they can optimize effectively using information that the compiler and linker would not normally have.

Methods and computer program product for optimizing binaries with coding style formalization

A computer implemented method in a data processing system for fingerprinting input/output workloads for input/output schedulers. Requests are identified in a workload for an input/output scheduler. Each request is classified to form a set of classifications. Whether an action is needed is determined based on the set of classifications. If the action is needed, the action is initiated.

Growing community of inventors

Austin, TX, United States of America

Jacob Lorien Moilanen