Darius
This presentation is the property of its rightful owner.
Sponsored Links
1 / 1

Varying the query staleness in TP-Grid PowerPoint PPT Presentation


  • 56 Views
  • Uploaded on
  • Presentation posted in: General

Darius Š idlauskas Aarhus University. Christian S. Jensen Aarhus University. Simonas Š altenis Aalborg University. Processing of Extreme Moving-Object Update and Query Workloads in Main Memory. Main Data Structures. Semantics. Timeslice. Freshness. Two-phase switching in TP-Grid.

Download Presentation

Varying the query staleness in TP-Grid

An Image/Link below is provided (as is) to download presentation

Download Policy: Content on the Website is provided to you AS IS for your information and personal use and may not be sold / licensed / shared on other websites without getting consent from its author.While downloading, if for some reason you are not able to download a presentation, the publisher may have deleted the file from their server.


- - - - - - - - - - - - - - - - - - - - - - - - - - E N D - - - - - - - - - - - - - - - - - - - - - - - - - -

Presentation Transcript


Varying the query staleness in tp grid

Darius ŠidlauskasAarhus University

Christian S. JensenAarhus University

Simonas ŠaltenisAalborg University

Processing of Extreme Moving-Object Update and Query Workloads in Main Memory

Main Data Structures

Semantics

Timeslice

Freshness

Two-phase switching in TP-Grid

Up-to-date

Query Results

Stale/delayed

  • Includes four diverse multi-core platforms

  • Studies eight grid-based index variants

  • Exercises the indexes under massive workloads containing tens of millions of moving vehicles simulated in a road network of Germany

  • All figures show results obtained on a 16-core Intel E5-2670 machine with 32 hardware threads in total

Optimal Grid Cell Size

Multi-threaded Scalability

Varying the query staleness in TwinGrid

Varying the query staleness in TP-Grid

Results from a micro-benchmark that measures CPU Cycles per 128-bit read/write using different synchronization methods.

Varying T0

Varying RQ Size

Varying #objects

Varying U/Q Ratio

MADALGO – Center for Massive Data Algorithmics, a Center of the Danish National Research Foundation


  • Login