Kaleidoscope : Graph Analytics on Evolving Graphs Steffen Maass, - - PowerPoint PPT Presentation

kaleidoscope graph analytics on evolving graphs
SMART_READER_LITE
LIVE PREVIEW

Kaleidoscope : Graph Analytics on Evolving Graphs Steffen Maass, - - PowerPoint PPT Presentation

Kaleidoscope : Graph Analytics on Evolving Graphs Steffen Maass, Taesoo Kim Georgia Institute of Technology April 23, 2018 Steffen Maass Kaleidoscope : Evolving Graph Analytics April 23, 2018 1 / 7 About me 4th year PhD Student at Georgia


slide-1
SLIDE 1

Kaleidoscope: Graph Analytics on Evolving Graphs

Steffen Maass, Taesoo Kim Georgia Institute of Technology April 23, 2018

Steffen Maass Kaleidoscope: Evolving Graph Analytics April 23, 2018 1 / 7

slide-2
SLIDE 2

About me

4th year PhD Student at Georgia Tech Advisor: Taesoo Kim Research Area: Systems

Operating Systems, Heterogeneous Systems, and Graph Processing

Thesis work: Processing of Evolving Graphs

Steffen Maass Kaleidoscope: Evolving Graph Analytics April 23, 2018 2 / 7

slide-3
SLIDE 3

Kaleidoscope- Overview

Problem: Low locality and high memory overhead for processing evolving graphs These problems hinder adoption of systems for evolving graphs, fallback: batch processing (large latency) We use a tiled representation of the evolving graph that mitigates memory overheads while allowing for higher processing performance Kaleidoscope can help with the execution of more complicated algorithms on larger graphs in less time.

Steffen Maass Kaleidoscope: Evolving Graph Analytics April 23, 2018 3 / 7

slide-4
SLIDE 4

Specific problem: Insertion performance

Inserting edges into Stinger in batches Observe performance of insertions over edges present in graph

0.0 0.5 1.0 1.5 2.0 0M 2M 4M 6M 8M 10M Insertion Cost per Batch 20k 40k 60k 80k 100k 120k 140k 0M 2M 4M 6M 8M 10M Throughput of Insertions Insertion cost (s) # Edges Insertions (edges/s) # Edges

⇒ Insertion performance collapses with > 1M edges

Steffen Maass Kaleidoscope: Evolving Graph Analytics April 23, 2018 4 / 7

slide-5
SLIDE 5

Specific problem: Memory overhead

Inserting edges into Stinger in batches Observe impact on execution time of evolving PageRank

0.0 0.5 1.0 1.5 2.0 2.5 0M 2M 4M 6M 8M 10M Used Memory 0.0 0.1 0.2 0.3 0.4 0.5 0M 2M 4M 6M 8M 10M Pagerank Time (per iteration) Memory (GB) # Edges Pagerank execution (s) # Edges

⇒ Execution time grows super-linearly due to insertion overhead

Steffen Maass Kaleidoscope: Evolving Graph Analytics April 23, 2018 5 / 7

slide-6
SLIDE 6

Goals for Kaleidoscope

Core design idea: Use tiled graph representation Allows for:

Lower memory overhead by using localized identifiers Asynchronous graph compaction Improvements in locality with space-filling curves

Also enables a straight-forward multi-core strategy by load-balancing tiles across processors

Steffen Maass Kaleidoscope: Evolving Graph Analytics April 23, 2018 6 / 7

slide-7
SLIDE 7

Conclusion

Kaleidoscope aims at addressing three problems when processing evolving graphs:

Large memory footprint Synchronous compaction Low locality

Kaleidoscope proposes a tiled data structure to address these problems:

Provides localized graphs Enables asynchronous compaction Exploits locality-optimizing space-filling curves

Steffen Maass Kaleidoscope: Evolving Graph Analytics April 23, 2018 7 / 7

slide-8
SLIDE 8

Conclusion

Kaleidoscope aims at addressing three problems when processing evolving graphs:

Large memory footprint Synchronous compaction Low locality

Kaleidoscope proposes a tiled data structure to address these problems:

Provides localized graphs Enables asynchronous compaction Exploits locality-optimizing space-filling curves

Thanks!

Steffen Maass Kaleidoscope: Evolving Graph Analytics April 23, 2018 7 / 7