Graph Processing Workloads Research Articles

Presto: A Decade of SQL Analytics at Meta

Presto is an open-source distributed SQL query engine that supports analytics workloads involving multiple exabyte-scale data sources. Presto is used for low-latency interactive use cases as well as long-running ETL jobs at Meta. It was originally launched at Meta in 2013 and donated to the Linux Foundation in 2019. Over the last ten years, upholding query latency and scalability with the hyper growth of data volume at Meta as well as new SQL analytics requirements have raised impressive challenges for Presto. A top priority has been ensuring query reliability does not regress with the shift towards smaller, more elastic container allocation, which requires queries to run with substantially smaller memory headroom and can be preempted at any time. Additionally, new demands from machine learning, privacy, and graph analytics have driven Presto maintainers to think beyond traditional data analytics. In this paper, we discuss several successful evolutions in recent years that have improved Presto latency as well as scalability by several orders of magnitude in production at Meta. Some of the notable ones are hierarchical caching, native vectorized execution engines, materialized views, and Presto on Spark. With these new capabilities, we have deprecated or are in the process of deprecating various legacy query engines so that Presto becomes the single piece to serve interactive, ad-hoc, ETL, and graph processing workloads for the entire data warehouse.

Practice of Streaming Processing of Dynamic Graphs: Concepts, Models, and Systems

Graph processing has become an important part of various areas of computing, including machine learning, medical applications, social network analysis, computational sciences, and others. A growing amount of the associated graph processing workloads are dynamic, with millions of edges added or removed per second. Graph streaming frameworks are specifically crafted to enable the processing of such highly dynamic workloads. Recent years have seen the development of many such frameworks. However, they differ in their general architectures (with key details such as the support for the concurrent execution of graph updates and queries, or the incorporated graph data organization), the types of updates and workloads allowed, and many others. To facilitate the understanding of this growing field, we provide the first analysis and taxonomy of dynamic and streaming graph processing. We focus on identifying the fundamental system designs and on understanding their support for concurrency, and for different graph updates as well as analytics workloads. We also crystallize the meaning of different concepts associated with streaming graph processing, such as dynamic, temporal, online, and time-evolving graphs, edge-centric processing, models for the maintenance of updates, and graph databases. Moreover, we provide a bridge with the very rich landscape of graph streaming theory by giving a broad overview of recent theoretical related advances, and by discussing which graph streaming models and settings could be helpful in developing more powerful streaming frameworks and designs. We also outline graph streaming workloads and research challenges.

The Case for Domain-Specialized Branch Predictors for Graph-Processing

Branch prediction is believed by many to be a solved problem, with state-of-the-art predictors achieving near-perfect prediction for many programs. In this article, we conduct a detailed simulation of graph-processing workloads in the GAPBS benchmark suite and show that branch mispredictions occur frequently and are still a large limitation on performance in key graph-processing applications. We provide a detailed analysis of which branches are mispredicting and show that a few key branches are the main source of performance degradation across the graph-processing benchmarks we looked at. We also propose a few ideas for future work to improve branch prediction accuracy on graph workloads.

GraphMap: scalable iterative graph processing using NoSQL

Despite having several distributed graph processing frameworks, scalable iterative processing of large graphs is a challenging problem since the graph and intermediate data need a global view of the graph topology in distributed memory. Although some systems support out-of-core iterative computations, they use a single machine and often require fast storage. In this paper, we present a new distributed iterative graph computation framework, called GraphMap, that utilizes a disk-based NoSQL database system for scalable graph processing while ensuring competitive performance. Extensive experiments on several real-world graphs show that GraphMap is more scalable and often faster than existing distributed memory-based systems for various graph processing workloads.

Multi-dimensional balanced graph partitioning via projected gradient descent

Motivated by performance optimization of large-scale graph processing systems that distribute the graph across multiple machines, we consider the balanced graph partitioning problem. Compared to most of the previous work, we study the multi-dimensional variant in which balance according to multiple weight functions is required. As we demonstrate by experimental evaluation, such multi-dimensional balance is essential for achieving performance improvements for typical distributed graph processing workloads. We propose a new scalable technique for the multidimensional balanced graph partitioning problem. It is based on applying randomized projected gradient descent to a non-convex continuous relaxation of the objective. We show how to implement the new algorithm efficiently in both theory and practice utilizing various approaches for the projection step. Experiments with large-scale graphs containing up to hundreds of billions of edges indicate that our algorithm has superior performance compared to the state of the art.

GARDENIA

This article presents the Graph Algorithm Repository for Designing Next-generation Accelerators (GARDENIA), a benchmark suite for studying irregular graph algorithms on massively parallel accelerators. Applications with limited control and data irregularity are the main focus of existing generic benchmarks for accelerators, while available graph processing benchmarks do not apply state-of-the-art algorithms and/or optimization techniques. GARDENIA includes emerging graph processing workloads from graph analytics, sparse linear algebra, and machine-learning domains, which mimic massively multithreaded commercial programs running on modern large-scale datacenters. Our characterization shows that GARDENIA exhibits irregular microarchitectural behavior, which is quite different from structured workloads and straightforward-implemented graph benchmarks.

Exploring Core and Cache Hierarchy Bottlenecks in Graph Processing Workloads

Graph processing is an important analysis technique for a wide range of big data problems. The ability to explicitly represent relationships between entities gives graph analytics significant performance advantage over traditional relational databases. In this paper, we perform an in-depth data-aware characterization of graph processing workloads on a simulated multi-core architecture, find bottlenecks in the core and the cache hierarchy that are not highlighted by previous characterization work, and analyze the behavior of the specific application data type causing the corresponding bottleneck. We find that load-load dependency chains involving different application data types form the primary bottleneck in achieving a high memory-level parallelism in graph processing workloads. We also observe that the private L2 cache has a negligible contribution to performance, whereas the shared L3 cache has higher performance sensitivity. In addition, we present a study on the effectiveness of several replacement policies. Finally, we study the relationship between different graph algorithms and the access volumes to the different data types. Overall, we provide useful insights and guidelines toward developing a more optimized CPU-based architecture for high performance graph processing.

Regression Prefetcher with Preprocessing for DRAM-PCM Hybrid Main Memory

This research is to design an effective hybrid main memory structure for graph processing applications, because it is quite expensive to use only high-speed DRAM for such applications. Thus, we propose a DRAM-PCM hybrid main memory structure to reduce the cost and energy consumption and design regression prefetch scheme to cope with irregular access patterns in large graph processing workloads. In addition, the prefetch includes preprocessing algorithm to maximize prefetching performance. Our experimental evaluation shows a performance improvement of 36 percent over a conventional DRAM model, 15 percent over existing prefetch models such as GHB/PC, SMS, and AMPM, and 6 percent over the latest model.

Distributed block formation and layout for disk-based management of large-scale graphs

We are witnessing an enormous growth in social networks as well as in the volume of data generated by them. An important portion of this data is in the form of graphs. In recent years, several graph processing and management systems emerged to handle large-scale graphs. The primary goal of these systems is to run graph algorithms and queries in an efficient and scalable manner. Unlike relational data, graphs are semi-structured in nature. Thus, storing and accessing graph data using secondary storage requires new solutions that can provide locality of access for graph processing workloads. In this work, we propose a scalable block formation and layout technique for graphs, which aims at reducing the I/O cost of disk-based graph processing algorithms. To achieve this, we designed a scalable MapReduce-style method called ICBL, which can divide the graph into a series of disk blocks that contain sub-graphs with high locality. Furthermore, ICBL can order the resulting blocks on disk to further reduce non-local accesses. We experimentally evaluated ICBL to showcase its scalability, layout quality, as well as the effectiveness of automatic parameter tuning for ICBL. We deployed the graph layouts generated by ICBL on the Neo4j open source graph database, http://www.neo4j.org/ (2015) graph database management system. Our results show that the layout generated by ICBL reduces the query running times over Neo4j more than $$2\times $$2× compared to the default layout.

A scalable processing-in-memory accelerator for parallel graph processing

The explosion of digital data and the ever-growing need for fast data analysis have made in-memory big-data processing in computer systems increasingly important. In particular, large-scale graph processing is gaining attention due to its broad applicability from social science to machine learning. However, scalable hardware design that can efficiently process large graphs in main memory is still an open problem. Ideally, cost-effective and scalable graph processing systems can be realized by building a system whose performance increases proportionally with the sizes of graphs that can be stored in the system, which is extremely challenging in conventional systems due to severe memory bandwidth limitations. In this work, we argue that the conventional concept of processing-in-memory (PIM) can be a viable solution to achieve such an objective. The key modern enabler for PIM is the recent advancement of the 3D integration technology that facilitates stacking logic and memory dies in a single package, which was not available when the PIM concept was originally examined. In order to take advantage of such a new technology to enable memory-capacity-proportional performance, we design a programmable PIM accelerator for large-scale graph processing called Tesseract. Tesseract is composed of (1) a new hardware architecture that fully utilizes the available memory bandwidth, (2) an efficient method of communication between different memory partitions, and (3) a programming interface that reflects and exploits the unique hardware design. It also includes two hardware prefetchers specialized for memory access patterns of graph processing, which operate based on the hints provided by our programming model. Our comprehensive evaluations using five state-of-the-art graph processing workloads with large real-world graphs show that the proposed architecture improves average system performance by a factor of ten and achieves 87% average energy reduction over conventional systems.