Proxy-Guided Load Balancing of Graph Processing Workloads on Heterogeneous Clusters

Song, Shuang; Li, Meng; Zheng, Xinnian; LeBeane, Michael; Ryoo, Jee Ho; Panda, Rutuparna; Gerstlauer, Andreas; John, Lizy K.

doi:10.1109/icpp.2016.16

Cited by 15 publications

(4 citation statements)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Schor et al [41] develop a framework for task scheduling of pipeline applications on heterogeneous platforms, which uses package transfer scheme for cross-device data transfer. Many other studies [11,24,27,43,44,53] work on task partition and task placement.…”

Section: Related Workmentioning

confidence: 99%

HiWayLib

Zheng

Zhai

et al. 2019

Proceedings of the Twenty-Fourth International Conference on Architectural Support for Programming Languages and Operating Syst

View full text Add to dashboard Cite

Pipeline is a parallel computing model underpinning a class of important applications running on CPU-GPU heterogeneous systems. A critical aspect for the efficiency of such applications is the support of communications among pipeline stages that may reside on CPU and different parts of a GPU. Existing libraries of concurrent data structures do not meet the needs, due to the massive parallelism on GPU and the complexities in CPU-GPU memory and connections. This work gives an in-depth study on the communication problem. It identifies three key issues, namely, slow and errorprone detection of the end of pipeline processing, intensive queue contentions on GPU, and cumbersome inter-device data movements. This work offers solutions to each of the issues, and integrates all together to form a unified library named HiWayLib. Experiments show that HiWayLib significantly boosts the efficiency of pipeline communications in CPU-GPU heterogeneous applications. For real-world applications, HiWayLib produces 1.22~2.13× speedups over the state-of-art implementations with little extra programming effort required. CCS Concepts • General and reference → Performance; • Computing methodologies → Parallel computing methodologies; • Computer systems organization → Heterogeneous (hybrid) systems.

show abstract

Section: Related Workmentioning

confidence: 99%

HiWayLib

Zheng

Zhai

et al. 2019

Proceedings of the Twenty-Fourth International Conference on Architectural Support for Programming Languages and Operating Syst

View full text Add to dashboard Cite

show abstract

“…Research by Song et al [28] and LeBeane et al [14] considers the important problem of partitioning on heterogeneous architectures and provides profiling to reduce runtime, improve load balance, and reduce energy consumption. Our framework instead focuses on shared memory packages.…”

Section: Related Workmentioning

confidence: 99%

A Comparison of Parallel Graph Processing Implementations

Pollard

Norris

2017

2017 IEEE International Conference on Cluster Computing (CLUSTER)

View full text Add to dashboard Cite

The rapidly growing number of large network analysis problems has led to the emergence of many parallel and distributed graph processing systems-one survey in 2014 identified over 80. Since then, the landscape has evolved; some packages have become inactive while more are being developed. Determining the best approach for a given problem is infeasible for most developers. To enable easy, rigorous, and repeatable comparison of the capabilities of such systems, we present an approach and associated software for analyzing the performance and scalability of parallel, open-source graph libraries. We demonstrate our approach on five graph processing packages: Graph-Mat, the Graph500, the Graph Algorithm Platform Benchmark Suite, GraphBIG, and PowerGraph using synthetic and real-world datasets. We examine previously overlooked aspects of parallel graph processing performance such as phases of execution and energy usage for three algorithms: breadth first search, single source shortest paths, and PageRank and compare our results to Graphalytics.

show abstract

“…There are several ways to perform graph processing. The distributed systems [10,22,30,36,57,67] leverage the ample computing resources to process large graphs. However, they inherently suffer from synchronization and fault tolerance overhead [27,50,69] and load imbalance [63].…”

Section: Introductionmentioning

confidence: 99%

GraphR: Accelerating Graph Processing Using ReRAM

Song

Zhuo

Qian

et al. 2018

2018 IEEE International Symposium on High Performance Computer Architecture (HPCA)

222

125

View full text Add to dashboard Cite

Graph processing recently received intensive interests in light of a wide range of needs to understand relationships. It is well-known for the poor locality and high memory bandwidth requirement. In conventional architectures, they incur a significant amount of data movements and energy consumption which motivates several hardware graph processing accelerators. The current graph processing accelerators rely on memory access optimizations or placing computation logics close to memory. Distinct from all existing approaches, we leverage an emerging memory technology to accelerate graph processing with analog computation.This paper presents GRAPHR, the first ReRAM-based graph processing accelerator. GRAPHR follows the principle of near-data processing and explores the opportunity of performing massive parallel analog operations with low hardware and energy cost. The analog computation is suitable for graph processing because: 1) The algorithms are iterative and could inherently tolerate the imprecision; 2) Both probability calculation (e.g., PageRank and Collaborative Filtering) and typical graph algorithms involving integers (e.g., BFS/SSSP) are resilient to errors. The key insight of GRAPHR is that if a vertex program of a graph algorithm can be expressed in sparse matrix vector multiplication (SpMV), it can be efficiently performed by ReRAM crossbar. We show that this assumption is generally true for a large set of graph algorithms.GRAPHR is a novel accelerator architecture consisting of two components: memory ReRAM and graph engine (GE). The core graph computations are performed in sparse matrix format in GEs (ReRAM crossbars). The vector/matrix-based graph computation is not new, but ReRAM offers the unique opportunity to realize the massive parallelism with unprecedented energy efficiency and low hardware cost. With small subgraphs processed by GEs, the gain of performing parallel operations overshadows the wastes due to sparsity. The experiment results show that GRAPHR achieves a 16.01× (up to 132.67×) speedup and a 33.82× energy saving on geometric mean compared to a CPU baseline system. Compared to GPU, GRAPHR achieves 1.69× to 2.19× speedup and consumes 4.77× to 8.91× less energy. GRAPHR gains a speedup of 1.16× to 4.12×, and is 3.67× to 10.96× more energy efficiency compared to PIM-based architecture.

show abstract

Proxy-Guided Load Balancing of Graph Processing Workloads on Heterogeneous Clusters

Cited by 15 publications

References 20 publications

HiWayLib

HiWayLib

A Comparison of Parallel Graph Processing Implementations

GraphR: Accelerating Graph Processing Using ReRAM

Contact Info

Product

Resources

About