Sökning: "parallel computer"

Visar resultat 1 - 5 av 439 avhandlingar innehållade orden parallel computer.

  1. 1. Adaptiveness and Lock-free Synchronization in Parallel Stochastic Gradient Descent

    Författare :Karl Bäckström; Chalmers tekniska högskola; []
    Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; NATURVETENSKAP; NATURAL SCIENCES; TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY; parallelism; machine learning; Stochastic gradient descent;

    Sammanfattning : The emergence of big data in recent years due to the vast societal digitalization and large-scale sensor deployment has entailed significant interest in machine learning methods to enable automatic data analytics. In a majority of the learning algorithms used in industrial as well as academic settings, the first-order iterative optimization procedure Stochastic gradient descent (SGD), is the backbone. LÄS MER

  2. 2. Automated CNN pipeline generation for heterogeneous architectures

    Författare :Pirah Noor Soomro; Chalmers tekniska högskola; []
    Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; NATURVETENSKAP; NATURAL SCIENCES; TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY; Online tuning; CNN parallel pipelines; Heterogeneous computing units; Processing on chiplets; Design space exploration;

    Sammanfattning : Heterogeneity is a vital feature in emerging processor chip designing. Asymmetric multicore-clusters such as high-performance cluster and power efficient cluster are common in modern edge devices. One example is Intel's Alder Lake featuring Golden Cove high-performance cores and Gracemont power-efficient cores. LÄS MER

  3. 3. Clustering in the Big Data Era: methods for efficient approximation, distribution, and parallelization

    Författare :Amir Keramatian; Chalmers tekniska högskola; []
    Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; NATURVETENSKAP; NATURAL SCIENCES; TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY; NATURVETENSKAP; NATURAL SCIENCES; TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY; Clustering; Approximation-based synopsis; Distributed and Parallel Processing; Applied ML;

    Sammanfattning : Data clustering is an unsupervised machine learning task whose objective is to group together similar items. As a versatile data mining tool, data clustering has numerous applications, such as object detection and localization using data from 3D laser-based sensors, finding popular routes using geolocation data, and finding similar patterns of electricity consumption using smart meters. LÄS MER

  4. 4. Throughput and energy efficiency of lock-free data structures: Execution Models and Analyses

    Författare :Aras Atalar; Chalmers tekniska högskola; []
    Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; NATURVETENSKAP; NATURAL SCIENCES; NATURVETENSKAP; NATURAL SCIENCES; Modeling; Data Structures; Throughput; Concurrency; Energy Efficiency; Parallel Computing; Analysis; Performance; Lock-free;

    Sammanfattning : Concurrent data structures are key program components to harness the available parallelism in multi-core processors. Lock-free algorithmic implementations of concurrent data structures offer high scalability and possess desirable properties such as immunity to deadlocks, convoying and priority inversion. LÄS MER

  5. 5. Design of Energy-Efficient High-Performance ASIP-DSP Platforms

    Författare :Andréas Karlsson; Dake Liu; Andreas Ehliar; Jarmo Takala; Linköpings universitet; []
    Nyckelord :NATURVETENSKAP; NATURAL SCIENCES; TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY; NATURVETENSKAP; NATURAL SCIENCES; TEKNIK OCH TEKNOLOGIER; ENGINEERING AND TECHNOLOGY;

    Sammanfattning : In the last ten years, limited clock frequency scaling and increasing power density has shifted IC design focus towards parallelism, heterogeneity and energy efficiency. Improving energy efficiency is by no means simple and it calls for a reevaluation of old design choices in processor architecture, and perhaps more importantly, development of new programming methodologies that exploit the features of modern architectures. LÄS MER