PageRank Pipeline Benchmark: Proposal for a Holistic System Benchmark for Big-Data Platforms

@article{Dreher2016PageRankPB,
  title={PageRank Pipeline Benchmark: Proposal for a Holistic System Benchmark for Big-Data Platforms},
  author={Patrick Dreher and Chansup Byun and Chris Hill and Vijay N. Gadepally and Bradley C. Kuszmaul and Jeremy Kepner},
  journal={2016 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW)},
  year={2016},
  pages={929-937}
}
  • P. Dreher, C. Byun, J. Kepner
  • Published 6 March 2016
  • Computer Science
  • 2016 IEEE International Parallel and Distributed Processing Symposium Workshops (IPDPSW)
The rise of big data systems has created a need for benchmarks to measure and compare the capabilities of these systems. Big data benchmarks present unique scalability challenges. The supercomputing community has wrestled with these challenges for decades and developed methodologies for creating rigorous scalable benchmarks (e.g., HPC Challenge). The proposed PageRank pipeline benchmark employs supercomputing benchmarking methodologies to create a scalable benchmark that is reflective of many… 

Figures and Tables from this paper

Static graph challenge: Subgraph isomorphism

The proposed Subgraph Isomorphism Graph Challenge draws upon prior challenges from machine learning, high performance computing, and visual analytics to create a graph challenge that is reflective of many real-world graph analytics processing systems.

PageRank Acceleration for Large Graphs with Scalable Hardware and Two-Step SpMV

A 16nm ASIC based shared memory platform for PageRank implementation that fundamentally accelerates Sparse Matrix dense Vector multiplication (SpMV), the core kernel of PageRank, which is capable of handling very large graphs despite using significantly less fast random access memory than current solutions.

A CUDA implementation of the pagerank pipeline benchmark

The details of a CUDA implementation of the PageRank pipeline benchmark are presented, a new proposed benchmark aimed to compare and measure the capabilities of big data systems.

Benchmarking Big Data Systems: A Review

This paper attempts to fill the void by presenting a review of the state-of-the-art big data benchmarking efforts by giving an overview of popular open-source benchmarks from the point of view of big data systems.

Streaming graph challenge: Stochastic block partition

This paper describes a graph partition challenge with a baseline partition algorithm of sub-quadratic complexity that employs rigorous Bayesian inferential methods based on a statistical model that captures characteristics of the real-world graphs.

Sparse Deep Neural Network Graph Challenge

The proposed Sparse Deep Neural Network (DNN) Challenge draws upon prior challenges from machine learning, high performance computing, and visual analytics to create a challenge that is reflective of emerging sparse AI systems.

Stochastic Block Partition Graph Challenge-draft -

A graph partition challenge with a baseline partition algorithm that employs rigorous Bayesian inferential methods based on a statistical model that captures characteristics of the real-world graphs and enables the algorithm to address limitations of well-known graph partition approaches such as modularity maximization.

GraphChallenge.org Triangle Counting Performance

These submissions show that their state-of-the-art triangle counting execution time is a strong function of the number of edges in the graph, which improved significantly from 2017 to 2018 and remained comparable from 2018 to 2019.

GraphChallenge.org Sparse Deep Neural Network Performance

These submissions show that their state-of-the-art sparse DNN execution time, TDNN, is a strong function of the number of DNN operations performed, Nop, and underscores the need for new innovations to achieve high performance on very large sparseDNNs.

Data Prefetching and Eviction Mechanisms of In-Memory Storage Systems Based on Scheduling for Big Data Processing

This paper provides scheduling-aware data prefetching and eviction mechanisms based on Spark, Alluxio, and Hadoop that prefetch data and release memory resources based on the scheduling information and proposes a heuristic algorithm to reduce the computational time.

References

SHOWING 1-10 OF 60 REFERENCES

Spark: Cluster Computing with Working Sets

Spark can outperform Hadoop by 10x in iterative machine learning jobs, and can be used to interactively query a 39 GB dataset with sub-second response time.

Spinning Fast Iterative Data Flows

This work proposes a method to integrate incremental iterations, a form of workset iterations, with parallel dataflows and presents an extension to the programming model for incremental iterations that alleviates for the lack of mutable state in dataflow and allows for exploiting the sparse computational dependencies inherent in many iterative algorithms.

A cloud-based approach to big graphs

This work presents a Cloud-based approach that scales with Big Data while being fault-tolerant, applying it on the largest problem size in the Graph500 benchmark to traverse a Petabyte graph consisting of over 4 trillion vertices and 70 trillion edges.

Ligra: a lightweight graph processing framework for shared memory

This paper presents a lightweight graph processing framework that is specific for shared-memory parallel/multicore machines, which makes graph traversal algorithms easy to write and significantly more efficient than previously reported results using graph frameworks on machines with many more cores.

GraphX: Graph Processing in a Distributed Dataflow Framework

This paper introduces GraphX, an embedded graph processing framework built on top of Apache Spark, a widely used distributed dataflow system and demonstrates that GraphX achieves an order of magnitude performance gain over the base dataflow framework and matches the performance of specialized graph processing systems while enabling a wider range of computation.

A comparison of approaches to large-scale data analysis

A benchmark consisting of a collection of tasks that are run on an open source version of MR as well as on two parallel DBMSs shows a dramatic performance difference between the two paradigms.

Toward a New Metric for Ranking High Performance Computing Systems

A new high performance conjugate gradient (HPCG) benchmark is described, composed of computations and data access patterns more commonly found in applications that strive for a better correlation to real scientific application performance.

GraphChi: Large-Scale Graph Computation on Just a PC

This work presents GraphChi, a disk-based system for computing efficiently on graphs with billions of edges, and builds on the basis of Parallel Sliding Windows to propose a new data structure Partitioned Adjacency Lists, which is used to design an online graph database graphChi-DB.

Introducing the Graph 500

In the words of Lord Kelvin, “if you cannot measure it, you cannot improve it”. One of the longlasting successes of the Top 500 list is sustained, community-wide floating point performance

Achieving 100,000,000 database inserts per second using Accumulo and D4M

The Apache Accumulo database is an open source relaxed consistency database that is widely used for government applications and has a peak performance of over 100,000,000 database inserts per second which is 100× larger than the highest previously published value for any other database.
...