Global ETD Search

Search theses and dissertations gathered from participating repositories worldwide. Every result links back to the library that holds it. No account is needed.

Results

Showing 1 to 20 of 29 for “"Scale-out"”.

  1. JUST-IN-TIME SCALE-OUT OF SHELL PROGRAMS, CORRECTLY

    … parallelization for scaling out on multicore CPUs and distribution to support processing of data that does not fit on a single machine. This unfortunate state of affairs is due to three fundamental challenges inherent to the shell: (1) shell programs compose arbitrary …

    penn Repository record for JUST-IN-TIME SCALE-OUT OF SHELL PROGRAMS, CORRECTLY (opens in a new tab)

  2. Investigating Opportunities and Challenges in Modeling and Designing Scale-Out DNN Accelerators

    … is presented and described in detail named SCALE-Sim (Systolic CNN Accelerator Simulator). The simulator is available as an open-sourced repository and has 2 primary use-cases in which computer architects can extract significant results. The first use-case is for system designers who would …

    gatech Repository record for Investigating Opportunities and Challenges in Modeling and Designing Scale-Out DNN Accelerators (opens in a new tab)

  3. Look-up tables : the benefit of enabling fine-grained routing and load balancing

    … tuples. Fine-grained partitioning can fix the scale out problem introduced by simplistic partitioning schemes. In this thesis, I introduce a design of a distributed query execution system that handles fine-grained partitioning using look-up tables. I introduce look-up tables, which is a mapping …

    mit Repository record for Look-up tables : the benefit of enabling fine-grained routing and load balancing (opens in a new tab)

  4. Stela: on-demand elasticity in distributed data stream processing systems

    … stream processing systems lack the ability to scale out and scale in (i.e., increase or decrease the number of machines or VMs allocated to the application) efficiently and unintrusively when requested by the user on demand. In order to scale out/in, a critical problem that needs to be solved …

    uiuc Repository record for Stela: on-demand elasticity in distributed data stream processing systems (opens in a new tab)

  5. Dynamic re-optimization techniques for stream processing engines and object stores

    <p>Large scale data storage and processing systems are strongly motivated by the need to store and analyze massive datasets. The complexity of a large class of these systems is rooted in their distributed nature, extreme scale, need for real-time response, and streaming nature. The use of these …

    purdue-thes Repository record for Dynamic re-optimization techniques for stream processing engines and object stores (opens in a new tab)

  6. Squeezing the most benefit from network parallelism in datacenters

    … Moore's law begins to wane, using parallelism to scale out processing units, vs. scale them up, is becoming exceedingly popular. The one-big-switch abstraction, for example, is typically implemented via leveraging massive degrees of parallelism behind the scene. In particular, in today's …

    uiuc Repository record for Squeezing the most benefit from network parallelism in datacenters (opens in a new tab)

  7. On the Design and Analysis of Cloud Data Center Network Architectures

    … Commodity-Off-The-Shelf (COTS) cheap switches to scale out data centers to large sizes, instead of using high-end switches to scale up data centers. Based on this scale-out principle, a large number of novel DCN architectures have been proposed. These DCN architectures are classified into two …

    temple Repository record for On the Design and Analysis of Cloud Data Center Network Architectures (opens in a new tab)

  8. Microreactor technology : scale-up of multiphase continuous flow chemistries

    … compounds and kinetic studies at the laboratory scale. High heat and mass transfer rates, rapid mixing, and higher selectivities and conversions can be achieved in these microdevices thanks to the small characteristic dimensions, enabling the synthesis of compounds that cannot be synthesized in …

    mit Repository record for Microreactor technology : scale-up of multiphase continuous flow chemistries (opens in a new tab)

  9. On Optimizing and Leveraging Distributed Shared Memory for High Performance, Resource Aggregation, and Cache-coherent Heterogeneous-ISA Processors

    … To transparently migrate a vCPU at runtime without incurring a significant downtime, the dissertation presents a suite of techniques including leveraging thread migration, loading/restoring vCPU in KVM states, maintaining a global vCPU location table, and creating a DSM kernel thread for …

    vt Repository record for On Optimizing and Leveraging Distributed Shared Memory for High Performance, Resource Aggregation, and Cache-coherent Heterogeneous-ISA Processors (opens in a new tab)

  10. Search for rare events in [the square root of sigma nu nu] = 200 GeV Au+Au PHOBOS data

    … matrix in the analysis, which is used to scale out correlations between difference pseduorapidity (n) regions. In the end we produce a value of x2 per degree of freedom (X2v ) for each event, which reflects how well the event agrees with the ensemble average. We compare this distribution …

    mit Repository record for Search for rare events in [the square root of sigma nu nu] = 200 GeV Au+Au PHOBOS data (opens in a new tab)

  11. CRIU-RTX: Remote Thread eXecution using Checkpoint/Restore in Userspace

    … prior work has addressed this problem by scaling-out application threads across multiple nodes to exploit resources outside the single machine boundary. Prior works have also leveraged heterogeneous instruction set architecture (ISA) systems to improve application performance as well as …

    vt Repository record for CRIU-RTX: Remote Thread eXecution using Checkpoint/Restore in Userspace (opens in a new tab)

  12. Mitigating the Cost, Performance, and Power Overheads Induced by Load Variations in Multicore Cloud Servers

    … is a common technique to partition data among scale-out servers. Unfortunately, skewed popularity of data-elements can cause significant load imbalance among shard servers, leading to response time degradation. I design an augmented variant of a well-known memory-caching system to identify and …

    purdue-thes Repository record for Mitigating the Cost, Performance, and Power Overheads Induced by Load Variations in Multicore Cloud Servers (opens in a new tab)

  13. OneSwitch Data Center Architecture

    … flows. The Three-Tier architecture and current routing schemes are no longer sufficient for achieving high bandwidth utilization. Data center networks should be built in a way where they can adequately support virtualization and cloud computing technologies. Data center networks should provide …

    vt Repository record for OneSwitch Data Center Architecture (opens in a new tab)

  14. Jet physics at ATLAS

    … fits is only significant if the jet energy scale (JES) can be constrained to ~1% at high pT. Uncertainties in the theoretical prediction of the inclusive-jet cross-section such as PDFs and fixed-order (scale) uncertainties were studied and compared with experimental errors arising from jet …

    glasgow Repository record for Jet physics at ATLAS (opens in a new tab)

  15. Higher moment models for risk and portfolio management

    … of time varying higher moments. A comprehensive out-of- sample risk and portfolio management application provides strong evidence of the improvement over non time varying higher moments. Finally, in Chapter 4, I consider the benefits of active investing when the benchmark index is not optimally …

    city-london Repository record for Higher moment models for risk and portfolio management (opens in a new tab)

  16. Metrics, Models and Methodologies for Energy-Proportional Computing

    … are often over-provisioned to avoid costly outages associated with the potential overloading of electrical circuitry. However, such over provisioning is often unnecessary since a data center rarely operates at its maximum capacity. It is imperative that we realize effective strategies to …

    vt Repository record for Metrics, Models and Methodologies for Energy-Proportional Computing (opens in a new tab)

  17. The thermal and metamorphic evolution of the Northern Highlands Terrane, Scotland

    … in a variety of structural settings throughout the NHT. Our data show that the ductile thrust nappes of northernmost Scotland preserve a record of Scandian (435-410 Ma) orogenesis. High grade metamorphism in the hinterland Naver nappe likely resulted from the widespread infiltration of …

    vt Repository record for The thermal and metamorphic evolution of the Northern Highlands Terrane, Scotland (opens in a new tab)

  18. A cross-stack, network-centric architectural design for next-generation datacenters

    This thesis proposes a full-stack, cross-layer datacenter architecture based on in-network computing and near-memory processing paradigms. The proposed datacenter architecture is built atop two principles: (1) utilizing commodity, off-the-shelf hardware (i.e., processor, DRAM, and network devices) …

    uiuc Repository record for A cross-stack, network-centric architectural design for next-generation datacenters (opens in a new tab)

  19. Participation Of Pharmacists In Diabetes Self Management Education And Training (DSME/T) Programs In United States - A Mixed Methods Research Study

    … beneficial to patients (Median: 95 of 100 point scale) when asked to rate pharmacist how beneficial pharmacists were on semantic differential scale. Out of the 342 program coordinators reporting no pharmacist involvement, 56% think pharmacists bring additional benefit to the patient, and 25% plan …

    creighton Repository record for Participation Of Pharmacists In Diabetes Self Management Education And Training (DSME/T) Programs In United States - A Mixed Methods Research Study (opens in a new tab)

  20. Improving Cloud Middlebox Infrastructure for Online Services

    … an example, this thesis shows that the prevalent scale-out middlebox designs using commodity servers are plagued with three fundamental problems: (1) The server-based layer-4 middleboxes are costly and inflate round-trip-time as much as 2x by processing the packets in software. (2) The middlebox …

    purdue-thes Repository record for Improving Cloud Middlebox Infrastructure for Online Services (opens in a new tab)

Page 1 of 2