NDC: Analyzing the impact of 3D-stacked memory+logic devices on MapReduce workloads
23 Mar 2014-pp 190-200
TL;DR: A number of key elements necessary in realizing efficient NDC operation are described and evaluated, including low-EPI cores, long daisy chains of memory devices, and the dynamic activation of cores and SerDes links.
Abstract: While Processing-in-Memory has been investigated for decades, it has not been embraced commercially. A number of emerging technologies have renewed interest in this topic. In particular, the emergence of 3D stacking and the imminent release of Micron's Hybrid Memory Cube device have made it more practical to move computation near memory. However, the literature is missing a detailed analysis of a killer application that can leverage a Near Data Computing (NDC) architecture. This paper focuses on in-memory MapReduce workloads that are commercially important and are especially suitable for NDC because of their embarrassing parallelism and largely localized memory accesses. The NDC architecture incorporates several simple processing cores on a separate, non-memory die in a 3D-stacked memory package; these cores can perform Map operations with efficient memory access and without hitting the bandwidth wall. This paper describes and evaluates a number of key elements necessary in realizing efficient NDC operation: (i) low-EPI cores, (ii) long daisy chains of memory devices, (iii) the dynamic activation of cores and SerDes links. Compared to a baseline that is heavily optimized for MapReduce execution, the NDC design yields up to 15X reduction in execution time and 18X reduction in system energy.
Citations
More filters
18 Jun 2016
TL;DR: This work proposes a novel PIM architecture, called PRIME, to accelerate NN applications in ReRAM based main memory, and distinguishes itself from prior work on NN acceleration, with significant performance improvement and energy saving.
Abstract: Processing-in-memory (PIM) is a promising solution to address the "memory wall" challenges for future computer systems. Prior proposed PIM architectures put additional computation logic in or near memory. The emerging metal-oxide resistive random access memory (ReRAM) has showed its potential to be used for main memory. Moreover, with its crossbar array structure, ReRAM can perform matrix-vector multiplication efficiently, and has been widely studied to accelerate neural network (NN) applications. In this work, we propose a novel PIM architecture, called PRIME, to accelerate NN applications in ReRAM based main memory. In PRIME, a portion of ReRAM crossbar arrays can be configured as accelerators for NN applications or as normal memory for a larger memory space. We provide microarchitecture and circuit designs to enable the morphable functions with an insignificant area overhead. We also design a software/hardware interface for software developers to implement various NNs on PRIME. Benefiting from both the PIM architecture and the efficiency of using ReRAM for NN computation, PRIME distinguishes itself from prior work on NN acceleration, with significant performance improvement and energy saving. Our experimental results show that, compared with a state-of-the-art neural processing unit design, PRIME improves the performance by ~2360× and the energy consumption by ~895×, across the evaluated machine learning benchmarks.
1,197 citations
Cites background from "NDC: Analyzing the impact of 3D-sta..."
...Recent efforts [2], [3], [4], [5], [58] decouple logic and memory designs in different dies, adopting 3D stacked memories with a logic layer that encapsulates processing units to perform computation, as shown in Figure 3(b)....
[...]
...Also, while previous work focused on database and graph processing applications [3], [5], PRIME aims at accelerating NN applications....
[...]
...introduce promising solutions to the challenges [2], [3], [4], [5], by leveraging 3D memory technologies [6] to integrate computation logic with the memory....
[...]
13 Jun 2015
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.
718 citations
04 Apr 2017
TL;DR: The hardware architecture and software scheduling and partitioning techniques for TETRIS, a scalable NN accelerator using 3D memory, are presented and it is shown that despite the use of small SRAM buffers, the presence of3D memory simplifies dataflow scheduling for NN computations.
Abstract: The high accuracy of deep neural networks (NNs) has led to the development of NN accelerators that improve performance by two orders of magnitude. However, scaling these accelerators for higher performance with increasingly larger NNs exacerbates the cost and energy overheads of their memory systems, including the on-chip SRAM buffers and the off-chip DRAM channels.This paper presents the hardware architecture and software scheduling and partitioning techniques for TETRIS, a scalable NN accelerator using 3D memory. First, we show that the high throughput and low energy characteristics of 3D memory allow us to rebalance the NN accelerator design, using more area for processing elements and less area for SRAM buffers. Second, we move portions of the NN computations close to the DRAM banks to decrease bandwidth pressure and increase performance and energy efficiency. Third, we show that despite the use of small SRAM buffers, the presence of 3D memory simplifies dataflow scheduling for NN computations. We present an analytical scheduling scheme that matches the efficiency of schedules derived through exhaustive search. Finally, we develop a hybrid partitioning scheme that parallelizes the NN computations over multiple accelerators. Overall, we show that TETRIS improves mthe performance by 4.1x and reduces the energy by 1.5x over NN accelerators with conventional, low-power DRAM memory systems.
453 citations
13 Jun 2015
TL;DR: In this article, the authors propose a new PIM architecture that does not change the existing sequential programming models and automatically decides whether to execute PIM operations in memory or processors depending on the locality of data.
Abstract: Processing-in-memory (PIM) is rapidly rising as a viable solution for the memory wall crisis, rebounding from its unsuccessful attempts in 1990s due to practicality concerns, which are alleviated with recent advances in 3D stacking technologies. However, it is still challenging to integrate the PIM architectures with existing systems in a seamless manner due to two common characteristics: unconventional programming models for in-memory computation units and lack of ability to utilize large on-chip caches. In this paper, we propose a new PIM architecture that (1) does not change the existing sequential programming models and (2) automatically decides whether to execute PIM operations in memory or processors depending on the locality of data. The key idea is to implement simple in-memory computation using compute-capable memory commands and use specialized instructions, which we call PIM-enabled instructions, to invoke in-memory computation. This allows PIM operations to be interoperable with existing programming models, cache coherence protocols, and virtual memory mechanisms with no modification. In addition, we introduce a simple hardware structure that monitors the locality of data accessed by a PIM-enabled instruction at runtime to adaptively execute the instruction at the host processor (instead of in memory) when the instruction can benefit from large on-chip caches. Consequently, our architecture provides the illusion that PIM operations are executed as if they were host processor instructions. We provide a case study of how ten emerging data-intensive workloads can benefit from our new PIM abstraction and its hardware implementation. Evaluations show that our architecture significantly improves system performance and, more importantly, combines the best parts of conventional and PIM architectures by adapting to data locality of applications.
395 citations
23 Jun 2014
TL;DR: This work explores the use of 3D die stacking to move memory-intensive computations closer to memory and introduces a methodology for rapid design space exploration by analytically predicting performance and energy of in-memory processors based on metrics obtained from execution on today's GPU hardware.
Abstract: As computation becomes increasingly limited by data movement and energy consumption, exploiting locality throughout the memory hierarchy becomes critical to continued performance scaling. Moving computation closer to memory presents an opportunity to reduce both energy and data movement overheads. We explore the use of 3D die stacking to move memory-intensive computations closer to memory. This approach to processing in memory addresses some drawbacks of prior research on in-memory computing and is commercially viable in the foreseeable future.Because 3D stacking provides increased bandwidth, we study throughput-oriented computing using programmable GPU compute units across a broad range of benchmarks, including graph and HPC applications. We also introduce a methodology for rapid design space exploration by analytically predicting performance and energy of in-memory processors based on metrics obtained from execution on today's GPU hardware. Our results show that, on average, viable PIM configurations show moderate performance losses (27%) in return for significant energy efficiency improvements (76\% reduction in EDP) relative to a representative mainstream GPU at 22nm technology. At 16nm technology, on average, viable PIM configurations are performance competitive with a representative mainstream GPU (7% speedup) and provide even greater energy efficiency improvements (85\% reduction in EDP).
338 citations
References
More filters
TL;DR: This presentation explains how the underlying runtime system automatically parallelizes the computation across large-scale clusters of machines, handles machine failures, and schedules inter-machine communication to make efficient use of the network and disks.
Abstract: MapReduce is a programming model and an associated implementation for processing and generating large datasets that is amenable to a broad variety of real-world tasks. Users specify the computation in terms of a map and a reduce function, and the underlying runtime system automatically parallelizes the computation across large-scale clusters of machines, handles machine failures, and schedules inter-machine communication to make efficient use of the network and disks. Programmers find the system easy to use: more than ten thousand distinct MapReduce programs have been implemented internally at Google over the past four years, and an average of one hundred thousand MapReduce jobs are executed on Google's clusters every day, processing a total of more than twenty petabytes of data per day.
17,663 citations
Proceedings Article•
22 Jun 2010TL;DR: 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.
Abstract: MapReduce and its variants have been highly successful in implementing large-scale data-intensive applications on commodity clusters. However, most of these systems are built around an acyclic data flow model that is not suitable for other popular applications. This paper focuses on one such class of applications: those that reuse a working set of data across multiple parallel operations. This includes many iterative machine learning algorithms, as well as interactive data analysis tools. We propose a new framework called Spark that supports these applications while retaining the scalability and fault tolerance of MapReduce. To achieve these goals, Spark introduces an abstraction called resilient distributed datasets (RDDs). An RDD is a read-only collection of objects partitioned across a set of machines that can be rebuilt if a partition is lost. 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.
4,959 citations
"NDC: Analyzing the impact of 3D-sta..." refers background in this paper
...This paper focuses on in-memory MapReduce workloads that are commercially important and are especially suitable for NDC because of their embarrassing parallelism and largely localized memory accesses....
[...]
10 Feb 2007
TL;DR: It is established that, given a careful implementation, MapReduce is a promising model for scalable performance on shared-memory systems with simple parallel code.
Abstract: This paper evaluates the suitability of the MapReduce model for multi-core and multi-processor systems. MapReduce was created by Google for application development on data-centers with thousands of servers. It allows programmers to write functional-style code that is automatically parallelized and scheduled in a distributed system. We describe Phoenix, an implementation of MapReduce for shared-memory systems that includes a programming API and an efficient runtime system. The Phoenix runtime automatically manages thread creation, dynamic task scheduling, data partitioning, and fault tolerance across processor nodes. We study Phoenix with multi-core and symmetric multiprocessor systems and evaluate its performance potential and error recovery features. We also compare MapReduce code to code written in lower-level APIs such as P-threads. Overall, we establish that, given a careful implementation, MapReduce is a promising model for scalable performance on shared-memory systems with simple parallel code
1,058 citations
"NDC: Analyzing the impact of 3D-sta..." refers methods in this paper
...Phoenix [53] is a programming API and runtime that implements MapReduce for shared-memory systems....
[...]
25 Oct 2008
TL;DR: Mars hides the programming complexity of the GPU behind the simple and familiar MapReduce interface, and is up to 16 times faster than its CPU-based counterpart for six common web applications on a quad-core machine.
Abstract: We design and implement Mars, a MapReduce framework, on graphics processors (GPUs). MapReduce is a distributed programming framework originally proposed by Google for the ease of development of web search applications on a large number of commodity CPUs. Compared with CPUs, GPUs have an order of magnitude higher computation power and memory bandwidth, but are harder to program since their architectures are designed as a special-purpose co-processor and their programming interfaces are typically for graphics applications. As the first attempt to harness GPU's power for MapReduce, we developed Mars on an NVIDIA G80 GPU, which contains over one hundred processors, and evaluated it in comparison with Phoenix, the state-of-the-art MapReduce framework on multi-core CPUs. Mars hides the programming complexity of the GPU behind the simple and familiar MapReduce interface. It is up to 16 times faster than its CPU-based counterpart for six common web applications on a quad-core machine.
793 citations
"NDC: Analyzing the impact of 3D-sta..." refers background in this paper
...The Mars framework does the same for GPUs [33]....
[...]
01 Jun 2008
TL;DR: This work explores more aggressive 3D DRAM organizations that make better use of the additional die-to-die bandwidth provided by 3D stacking, as well as the additional transistor count, to achieve a 1.75x speedup over previously proposed 3D-DRAM approaches on memory-intensive multi-programmed workloads on a quad-core processor.
Abstract: Three-dimensional integration enables stacking memory directly on top of a microprocessor, thereby significantly reducing wire delay between the two. Previous studies have examined the performance benefits of such an approach, but all of these works only consider commodity 2D DRAM organizations. In this work, we explore more aggressive 3D DRAM organizations that make better use of the additional die-to-die bandwidth provided by 3D stacking, as well as the additional transistor count. Our simulation results show that with a few simple changes to the 3D-DRAM organization, we can achieve a 1.75x speedup over previously proposed 3D-DRAM approaches on our memory-intensive multi-programmed workloads on a quad-core processor. The significant increase in memory system performance makes the L2 miss handling architecture (MHA) a new bottleneck, which we address by combining a novel data structure called the Vector Bloom Filter with dynamic MSHR capacity tuning. Our scalable L2 MHA yields an additional 17.8% performance improvement over our 3D-stacked memory architecture.
679 citations
"NDC: Analyzing the impact of 3D-sta..." refers methods in this paper
...Loh [44] describes various design strategies if the memory chips were t o be used as main memory....
[...]