Sökning: "work-stealing"

Hittade 5 avhandlingar innehållade ordet work-stealing.

  1. 1. Cooperative user- and system-level scheduling of task-centric parallel programs

    Författare :Georgios Varisteas; Mats Brorsson; Karl-Filip Faxén; Timothy Roscoe; KTH; []
    Nyckelord :TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY; parallel; workload; runtime; task; adaptive; resource management; load balancing; work-stealing; SRA - ICT; SRA - Informations- och kommunikationsteknik;

    Sammanfattning : Emerging architecture designs include tens of processing cores on a single chip die; it is believed that the number of cores will reach the hundreds in not so many years from now. However, most common workloads cannot expose fluctuating parallelism, insufficient to utilize such systems. LÄS MER

  3. 2. Effective cooperative scheduling of task-parallel applications on multiprogrammed parallel architectures

    Författare :Georgios Varisteas; Mats Brorsson; Avi Mendelson; KTH; []
    Nyckelord :TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY; multicore; parallel; scheduler; workload; runtime; task; adaptive; resource management; load balancing; work-stealing; Computer Science; Datalogi;

    Sammanfattning : Emerging architecture designs include tens of processing cores on a single chip die; it is believed that the number of cores will reach the hundreds in not so many years from now. However, most common parallel workloads cannot fully utilize such systems. LÄS MER

  4. 3. Runtime Management of Multiprocessor Systems for Fault Tolerance, Energy Efficiency and Load Balancing

    Författare :Stavros Tzilis; Chalmers tekniska högskola; []
    Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY; TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY; Fault Tolerance; Algorithms; Runtime Management; Multiprocessors; Performance; Adaptive Systems; Load Balancing; Energy Efficiency;

    Sammanfattning : Efficiency of modern multiprocessor systems is hurt by unpredictable events: aging causes permanent faults that disable components; application spawnings and terminations taking place at arbitrary times, affect energy proportionality, causing energy waste; load imbalances reduce resource utilization, penalizing performance. This thesis demonstrates how runtime management can mitigate the negative effects of unpredictable events, making decisions guided by a combination of static information known in advance and parameters that only become known at runtime. LÄS MER

  5. 4. On the Performance Analysis of Large Scale, Dynamic, Distributed and Parallel Systems

    Författare :John Ardelius; Seif Haridi; Supriya Krishnamurthy; Mark Jelasity; KTH; []
    Nyckelord :TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY; NATURVETENSKAP; NATURAL SCIENCES; Performance analysis distributed systems; SRA - ICT; SRA - Informations- och kommunikationsteknik;

    Sammanfattning : Evaluating the performance of large distributed applications is an important and non-trivial task. With the onset of Internet wide applications there is an increasing need to quantify reliability, dependability and performance of these systems, both as a guide in system design as well as a means to understand the fundamental properties of large-scale distributed systems. LÄS MER

  7. 5. Improving OpenMP Productivity with Data Locality Optimizations and High-resolution Performance Analysis

    Författare :Ananya Muddukrishna; Mats Brorsson; Nawal Copty; KTH; []
    Nyckelord :TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY; OpenMP; Performance Analysis; Scheduling; Locality Optimizations;

    Sammanfattning : The combination of high-performance parallel programming and multi-core processors is the dominant approach to meet the ever increasing demand for computing performance today. The thesis is centered around OpenMP, a popular parallel programming API standard that enables programmers to quickly get started with writing parallel programs. LÄS MER