A scalable processing-in-memory accelerator for parallel graph processing
13 Jun 2015-Vol. 43, Iss: 3, pp 105-117
TL;DR: This work argues that the conventional concept of processing-in-memory (PIM) can be a viable solution to achieve memory-capacity-proportional performance and designs a programmable PIM accelerator for large-scale graph processing called Tesseract.
Abstract: 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.
Citations
More filters
TL;DR: This work proposes a near-data processing and better-than-worst-case co-design methodology to efficiently move the instruction execution to the DRAM side and, at the same time, to allow the pipeline to operate at higher clock frequencies compared to the worst-case approach.
Abstract: Traditional processor architectures utilize an external DRAM for data storage, while they also operate under worst-case timing constraints. Such designs are heavily constrained by the delay costs of the data transfer between the core pipeline and the DRAM, and they are incapable of exploiting the timing variations of their pipeline stages. In this work, we focus on a near-data processing methodology combined with a novel timing analysis technique that enables the adaptive frequency scaling of the core clock and boosts the performance of low-power designs. We propose a near-data processing and better-than-worst-case co-design methodology to efficiently move the instruction execution to the DRAM side and, at the same time, to allow the pipeline to operate at higher clock frequencies compared to the worst-case approach. To this end, we develop a timing analysis technique, which evaluates the timing requirements of individual instructions and we dynamically scale the clock frequency, according to the instructions types that currently occupy the pipeline. We evaluate the proposed methodology on six different RISC-V post-layout implementations using an HMC DRAM to enable the processing-in-memory (PIM) process. Results indicate an average speedup factor of 1.96× with a 1.6× reduction in energy consumption compared to a standard RISC-V PIM baseline implementation.
1 citations
Posted Content•
TL;DR: IntersectX as discussed by the authors is a graph pattern mining accelerator with stream instruction set extension and architectural support based on a conventional processor, which can be considered as a natural extension to the traditional instructions that operate on scalar values.
Abstract: Graph pattern mining applications try to find all embeddings that match specific patterns. Compared to the traditional graph computation, graph mining applications are computation-intensive. The state-of-the-art method, pattern enumeration, constructs the embeddings that match the pattern. The key operation -- intersection -- of two edge lists, poses challenges to conventional architectures and requires substantial execution time. In this paper, we propose IntersectX, a vertically designed accelerator for pattern enumeration with stream instruction set extension and architectural supports based on conventional processor. The stream based ISA can be considered as a natural extension to the traditional instructions that operate on scalar values. We develop the IntersectX architecture composed of specialized mechanisms that efficiently implement the stream ISA extensions, including: (1) Stream Mapping Table (SMT) that records the mapping between stream ID and stream register; (2) the read-only Stream Cache (S-Cache) that enables efficient stream data movements; (3) tracking the dependency between streams with a property of intersection; (4) Stream Value Processing Unit (SVPU) that implements sparse value computations; and (5) the nested intersection translator that generates micro-op sequences for implementing nested intersections. We implement IntersectX ISA and architecture on zSim, and test it with seven popular graph mining applications (triangle/three-chain/tailed-traingle counting, 3-motif mining, 4/5-clique counting, and FSM) on ten real graphs. We develop our own implementation of AutoMine (InHouseAutomine). The results show that IntersectX significantly outperforms InHouseAutomine on CPU, on average 10.7 times and up to 83.9 times ; and GRAMER, a state-of-the-art graph pattern mining accelerator, based on exhaustive check, on average 40.1 times and up to 181.8 times.
1 citations
01 Jan 2018
TL;DR: This thesis proposes to utilize a novel moving computation to data model (MC) to overcome this synchronization bottleneck in a 1000-cores scale shared memory multicore processor and demonstrates the effectiveness of the model on workloads with wide range of synchronization requirements from graph analytics, machine learning and database domains.
Abstract: Single chip multicore processors are now prevalent and processors with hundreds of cores are being proposed and explored by both academia and industry. Shared memory cache coherence is the state–of–the–art technology for these processors to enable synchronization and communication between cores. However, since the synchronization of cores on shared data using hardware cache coherence suffers from instruction retries and cache line ping-pong overheads, it prevents performance scaling as core counts increase on a chip. This thesis proposes to utilize a novel moving computation to data model (MC) to overcome this synchronization bottleneck in a 1000-cores scale shared memory multicore processor. The proposed MC model pins shared data to dedicated cores called service cores. The execution of critical code sections is explicitly requested from worker cores to be performed at the service cores. In this way, the cache line bouncing between cores is prevented, hence data locality optimization is enabled. The proposed MC model utilizes auxiliary in-hardware explicit messaging for the critical section requests to enable efficient fine-grained blocking and non-blocking communication between communicating cores. To show the effectiveness of the proposed model, workloads with wide range of synchronization requirements from graph analytics, machine learning and database domains are Halit Dogan, University of Connecticut, 2018 implemented. The proposed model is then prototyped and exhaustively evaluated on a 72 core machine, Tilera R © Tile–Gx72TM multicore platform, as it incorporates in–hardware core–to–core messaging as an auxiliary capability to the shared memory cache coherence paradigm. Since the Tile-Gx72TM machine includes only 72 cores, it is deployed for evaluation at 8 to 64 core count scale. For further analysis at higher core count, a simulated RISC–V multicore environment is built and utilized, and the performance and dynamic energy scaling advantages of the MC model is evaluated against various baseline synchronization models up to 1024 cores. Accelerating Synchronization on Futuristic 1000-cores Multicore Processor with Moving Compute to Data Model
1 citations
01 Jun 2018
TL;DR: This paper examines different memory organizations that spread data across channels, ranks, and banks and identifies application features that benefit from different organizations and evaluates scheduling of OpenMP threads, finding up to 16 percent performance gains depending on workload.
Abstract: Advances in memory technologies including 3DDRAM memories (such as High Bandwidth Memory (HBM) and Hybrid Memory Cube (HMC) systems), wide I/O memory promise very large bandwidths at lower power consumption to address the needs of high-performance computing as well as emerging big data applications. However, in order to fully benefit from such bandwidths, it is necessary to understand how to optimally organize data across channels, ranks, banks or vaults of the memory structures, how to obtain large volumes of data with fewer accesses and how to schedule threads of multi threaded applications to benefit from these memory organizations. In this paper, we will examine different memory organizations that spread data across channels, ranks, and banks and identify application features that benefit from different organizations. Our study applies to generic DDR memory structures as well as 3DDRAMs. We will also evaluate scheduling of OpenMP threads (e.g., using static, dynamic and guided) but with emphasis on how different scheduling methods benefit from different memory organizations. Using the best scheduling for the application, proper memory organization, our experiments show, we can achieve up to 16 percent performance gains depending on workload.
1 citations
Cites background from "A scalable processing-in-memory acc..."
...[16] [17] [18] [19] [20] [21]) approaches whereby computation is moved closer to memory to overcome long memory latencies and utilize large bandwidths....
[...]
01 Jan 2016
TL;DR: RowCore is proposed, a row-oriented PNM architecture, which (pre)fetches and operates on entire memory rows to exploit BDMLs’ row-density and employs well-known MIMD execution to handle BDML’ irregularity, and sequential prefetch of input data to hide memory latency.
Abstract: The technology-push of die stacking and application-pull of Big Data machine learning (BDML) have created a unique opportunity for processing-near-memory (PNM). This paper makes four contributions: (1) While previous PNM work explores general MapReduce workloads, we identify three workload characteristics: (a) irregular-and-compute-light (i.e., perform only a few operations per input word which include data-dependent branches and indirect memory accesses); (b) compact (i.e., the computation has a small intermediate live data and uses only a small amount of contiguous input data); and (c) memory-row-dense (i.e., process the input data without skipping over many bytes). We show that BDMLs have or can be transformed to have these characteristics which, except for irregularity, are necessary for bandwidthand energyefficient PNM, irrespective of the architecture. (2) Based on these characteristics, we propose RowCore, a row-oriented PNM architecture, which (pre)fetches and operates on entire memory rows to exploit BDMLs’ row-density. Instead of this row-centric access and compute-schedule, traditional architectures opportunistically improve row locality while fetching and operating on cache blocks. (3) RowCore employs well-known MIMD execution to handle BDMLs’ irregularity, and sequential prefetch of input data to hide memory latency. In RowCore, however, one corelet prefetches a row for all the corelets which may stray far from each other due to their MIMD execution. Consequently, a leading corelet may prematurely evict the prefetched data before a lagging corelet has consumed the data. RowCore employs novel cross-corelet flow-control to prevent such eviction. (4) RowCore further exploits its flow-controlled prefetch for frequency scaling based on novel coarse-grain compute-memory rate-matching which decreases (increases) the processor clock speed when the prefetch buffers are empty (full). Using simulations, we show that RowCore improves performance and energy, by 135% and 20% over a GPGPU with prefetch, and by 35% and 34% over a multicore with prefetch, when all three architectures use the same resources (i.e., number of cores, and on-processor-die memory) and identical diestacking (i.e., GPGPUs/multicores/RowCore and DRAM).
1 citations
Cites background or methods from "A scalable processing-in-memory acc..."
...While Tesseract [10] targets graphanalysis workloads via MIMD processing and inter-core com-...
[...]
...While Tesseract [10] targets graphanalysis workloads via MIMD processing and inter-core communication, such workloads are not row-dense or compact, and Tesseract is not row-oriented and would incur row-locality problems similar to multicores....
[...]
...While processing-in-memory (PIM) has been around for decades [3, 4, 5, 6, 7, 8, 9, 10, 11, 12], there are three problems....
[...]
References
More filters
01 Apr 1998
TL;DR: This paper provides an in-depth description of Google, a prototype of a large-scale search engine which makes heavy use of the structure present in hypertext and looks at the problem of how to effectively deal with uncontrolled hypertext collections where anyone can publish anything they want.
Abstract: In this paper, we present Google, a prototype of a large-scale search engine which makes heavy use of the structure present in hypertext. Google is designed to crawl and index the Web efficiently and produce much more satisfying search results than existing systems. The prototype with a full text and hyperlink database of at least 24 million pages is available at http://google.stanford.edu/. To engineer a search engine is a challenging task. Search engines index tens to hundreds of millions of web pages involving a comparable number of distinct terms. They answer tens of millions of queries every day. Despite the importance of large-scale search engines on the web, very little academic research has been done on them. Furthermore, due to rapid advance in technology and web proliferation, creating a web search engine today is very different from three years ago. This paper provides an in-depth description of our large-scale web search engine -- the first such detailed public description we know of to date. Apart from the problems of scaling traditional search techniques to data of this magnitude, there are new technical challenges involved with using the additional information present in hypertext to produce better search results. This paper addresses this question of how to build a practical large-scale system which can exploit the additional information present in hypertext. Also we look at the problem of how to effectively deal with uncontrolled hypertext collections where anyone can publish anything they want.
14,696 citations
"A scalable processing-in-memory acc..." refers methods in this paper
...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....
[...]
Journal Article•
TL;DR: Google as discussed by the authors is a prototype of a large-scale search engine which makes heavy use of the structure present in hypertext and is designed to crawl and index the Web efficiently and produce much more satisfying search results than existing systems.
13,327 citations
TL;DR: This work presents a new coarsening heuristic (called heavy-edge heuristic) for which the size of the partition of the coarse graph is within a small factor of theSize of the final partition obtained after multilevel refinement, and presents a much faster variation of the Kernighan--Lin (KL) algorithm for refining during uncoarsening.
Abstract: Recently, a number of researchers have investigated a class of graph partitioning algorithms that reduce the size of the graph by collapsing vertices and edges, partition the smaller graph, and then uncoarsen it to construct a partition for the original graph [Bui and Jones, Proc. of the 6th SIAM Conference on Parallel Processing for Scientific Computing, 1993, 445--452; Hendrickson and Leland, A Multilevel Algorithm for Partitioning Graphs, Tech. report SAND 93-1301, Sandia National Laboratories, Albuquerque, NM, 1993]. From the early work it was clear that multilevel techniques held great promise; however, it was not known if they can be made to consistently produce high quality partitions for graphs arising in a wide range of application domains. We investigate the effectiveness of many different choices for all three phases: coarsening, partition of the coarsest graph, and refinement. In particular, we present a new coarsening heuristic (called heavy-edge heuristic) for which the size of the partition of the coarse graph is within a small factor of the size of the final partition obtained after multilevel refinement. We also present a much faster variation of the Kernighan--Lin (KL) algorithm for refining during uncoarsening. We test our scheme on a large number of graphs arising in various domains including finite element methods, linear programming, VLSI, and transportation. Our experiments show that our scheme produces partitions that are consistently better than those produced by spectral partitioning schemes in substantially smaller time. Also, when our scheme is used to compute fill-reducing orderings for sparse matrices, it produces orderings that have substantially smaller fill than the widely used multiple minimum degree algorithm.
5,629 citations
"A scalable processing-in-memory acc..." refers methods in this paper
...For this purpose, we use METIS [27] to perform 512-way multi-constraint partitioning to balance the number of vertices, outgoing edges, and incoming edges of each partition, as done in a recent previous work [51]....
[...]
...This is confirmed by the observation that Tesseract with METIS spends 59% of execution time waiting for synchronization barriers....
[...]
12 Jun 2005
TL;DR: The goals are to provide easy-to-use, portable, transparent, and efficient instrumentation, and to illustrate Pin's versatility, two Pintools in daily use to analyze production software are described.
Abstract: Robust and powerful software instrumentation tools are essential for program analysis tasks such as profiling, performance evaluation, and bug detection. To meet this need, we have developed a new instrumentation system called Pin. Our goals are to provide easy-to-use, portable, transparent, and efficient instrumentation. Instrumentation tools (called Pintools) are written in C/C++ using Pin's rich API. Pin follows the model of ATOM, allowing the tool writer to analyze an application at the instruction level without the need for detailed knowledge of the underlying instruction set. The API is designed to be architecture independent whenever possible, making Pintools source compatible across different architectures. However, a Pintool can access architecture-specific details when necessary. Instrumentation with Pin is mostly transparent as the application and Pintool observe the application's original, uninstrumented behavior. Pin uses dynamic compilation to instrument executables while they are running. For efficiency, Pin uses several techniques, including inlining, register re-allocation, liveness analysis, and instruction scheduling to optimize instrumentation. This fully automated approach delivers significantly better instrumentation performance than similar tools. For example, Pin is 3.3x faster than Valgrind and 2x faster than DynamoRIO for basic-block counting. To illustrate Pin's versatility, we describe two Pintools in daily use to analyze production software. Pin is publicly available for Linux platforms on four architectures: IA32 (32-bit x86), EM64T (64-bit x86), Itanium®, and ARM. In the ten months since Pin 2 was released in July 2004, there have been over 3000 downloads from its website.
4,019 citations
"A scalable processing-in-memory acc..." refers methods in this paper
...We evaluate our architecture using an in-house cycle-accurate x86-64 simulator whose frontend is Pin [38]....
[...]
06 Jun 2010
TL;DR: A model for processing large graphs that has been designed for efficient, scalable and fault-tolerant implementation on clusters of thousands of commodity computers, and its implied synchronicity makes reasoning about programs easier.
Abstract: Many practical computing problems concern large graphs. Standard examples include the Web graph and various social networks. The scale of these graphs - in some cases billions of vertices, trillions of edges - poses challenges to their efficient processing. In this paper we present a computational model suitable for this task. Programs are expressed as a sequence of iterations, in each of which a vertex can receive messages sent in the previous iteration, send messages to other vertices, and modify its own state and that of its outgoing edges or mutate graph topology. This vertex-centric approach is flexible enough to express a broad set of algorithms. The model has been designed for efficient, scalable and fault-tolerant implementation on clusters of thousands of commodity computers, and its implied synchronicity makes reasoning about programs easier. Distribution-related details are hidden behind an abstract API. The result is a framework for processing large graphs that is expressive and easy to program.
3,840 citations
"A scalable processing-in-memory acc..." refers methods in this paper
...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....
[...]
...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....
[...]