Task (computing)

About: Task (computing) is a research topic. Over the lifetime, 9718 publications have been published within this topic receiving 129364 citations.

Layerwise Optimization by Gradient Decomposition for Continual Learning

Abstract: Deep neural networks achieve state-of-the-art and sometimes super-human performance across various domains. However, when learning tasks sequentially, the networks easily forget the knowledge of previous tasks, known as "catastrophic forgetting". To achieve the consistencies between the old tasks and the new task, one effective solution is to modify the gradient for update. Previous methods enforce independent gradient constraints for different tasks, while we consider these gradients contain complex information, and propose to leverage inter-task information by gradient decomposition. In particular, the gradient of an old task is decomposed into a part shared by all old tasks and a part specific to that task. The gradient for update should be close to the gradient of the new task, consistent with the gradients shared by all old tasks, and orthogonal to the space spanned by the gradients specific to the old tasks. In this way, our approach encourages common knowledge consolidation without impairing the task-specific knowledge. Furthermore, the optimization is performed for the gradients of each layer separately rather than the concatenation of all gradients as in previous works. This effectively avoids the influence of the magnitude variation of the gradients in different layers. Extensive experiments validate the effectiveness of both gradient-decomposed optimization and layer-wise updates. Our proposed method achieves state-of-the-art results on various benchmarks of continual learning.

Information processing system and power saving method for the system

Abstract: PROBLEM TO BE SOLVED: To effectively suppress the power consumption of the whole system by positively generating inactive processors even in a state where the number of tasks is over that of processors. SOLUTION: In this information processing system, OS previously knows the resource request quantity of the processors 11 and 12 of the processing unit of each task including OS itself to centralize the group of tasks to the specific processor 11 within a range in which the resources of the processors 11 and 12 are not short (a range in which the sum of the request quantity of the processor resources is not over 100). Thereby, the other processor 12 is brought into an inactive state so that power source supply for the inactive processor is stopped or a clock frequency is lowered. Thereby the power consumption of the whole system is effectively suppressed. COPYRIGHT: (C)1997,JPO

Chunks and Tasks: A programming model for parallelization of dynamic algorithms

Abstract: We propose Chunks and Tasks, a parallel programming model built on abstractions for both data and work. The application programmer specifies how data and work can be split into smaller pieces, chunks and tasks, respectively. The Chunks and Tasks library maps the chunks and tasks to physical resources. In this way we seek to combine user friendliness with high performance. An application programmer can express a parallel algorithm using a few simple building blocks, defining data and work objects and their relationships. No explicit communication calls are needed; the distribution of both work and data is handled by the Chunks and Tasks library. This makes efficient implementation of complex applications that require dynamic distribution of work and data easier. At the same time, Chunks and Tasks imposes restrictions on data access and task dependencies that facilitate the development of high performance parallel back ends. We discuss the fundamental abstractions underlying the programming model, as well as performance, determinism, and fault resilience considerations. We also present a pilot C++ library implementation for clusters of multicore machines and demonstrate its performance for irregular block-sparse matrix-matrix multiplication.

Energy Efficiency for Clustered Heterogeneous Multicores

Abstract: Heterogeneous multicore systems clustered in multiple Voltage Frequency Islands (VFIs) are the next-generation solution for power and energy efficient computing systems. Due to the heterogeneity, the power consumption and execution time of a task changes not only with Dynamic Voltage and Frequency Scaling (DVFS), but also according to the task-to-island assignment, presenting major challenges for power management and energy minimization techniques. This paper focuses on energy minimization of periodic real-time tasks (or performance-constrained tasks) on such systems, in which the cores in an island are homogeneous and share the same voltage and frequency, but different islands have different types and numbers of cores and can be executed at other voltages and frequencies. We present an efficient algorithm to minimize the total energy consumption while satisfying the timing constraints of all tasks. Our technique consists of the coordinated selection of the voltage and frequency levels for each island, together with a task partitioning strategy that considers the energy consumption of the task executing on different islands and at different frequencies, as well as the impact of the frequency and the underlying core architecture to the resulting execution time. Every task is then mapped to the most energy efficient island for the selected voltage and frequency levels, and to a core inside the island such that the workloads of the cores in a VFI are balanced. We experimentally evaluate our technique and compare it to state-of-the-art solutions, resulting in average in 25 percent less energy consumption (and up to 87 percent for some cases), while guaranteeing that all tasks meet their deadlines.

Method of linking devices to gaming machines

Abstract: A method of dynamically linking abstracted hardware devices, which are used in association with gaining machines, to gaming software is disclosed. The game machine has a central processing unit (“CPU”), a resource manager, driver pools, and a communication link that connect a plurality of intelligent Input/Output controller boards (“IOCB”) to hardware devices interfaced to the game. The resource manager's functional blocks are: a resource manager control task, a plurality of Input/Output (“I/O”) communication drivers to connect to the IOCBs, a low level and high level driver manager, a low level and high level driver pool, and a plurality of resource repositories that interface to the gaming software. The resource manager starts an I/O communication driver to scan for the primary IOCB on the I/O memory bus, Universal Serial Bus, or Firewire. Once the primary IOCB is found, the resource control task will load more I/O communication drivers for any secondary IOCBs. The resource control task starts the driver managers, and requests the IOCB(s) to send the list of attached hardware. The driver managers load the drivers required for the type and version of hardware attached to the game. The gaming software interfaces to the hardware through the high level drivers loaded in the resource repositories. The high level drivers can be software or hardware drivers. Software drivers can simulate hardware, connect to other parts of the gaming software, or combine functions by calling other software and hardware drivers. New drivers can be added easily, allowing gaming software to use new hardware with little or no changes.