Software Distributed Shared Memory System Research Articles

Consistency Model and Synchronization Primitives in SDSMS

Abstract —consistency model like Strict Consistency, Sequential Consistency, Processor Consistency, Weak Consistency etc. Then the techniques for implementing distributed shared memory Systems and Synchronization Primitives in Software Distributed Shared Memory Systems are discussed. The analysis involves the performance measurement of the protocol concerned that is Multiple Writer Protocol. Each protocol has pros and cons. So, the problems that are associated with each protocol is discussed and other related things are explored. Keywords — Distributed System, Single owner protocol, Multiple owner protocolI. I NTRODUCTION distributed system is an application that executes a collection of protocols to coordinate the actions of multiple processes on a network, such that all components cooperate together to perform a single or small set of related tasks. II. M EMORY C ONSISTENCY M ODEL A memory consistency model is a contract between programmers and shared memory which specifies how the memory operations of a program will be executed. Computer scientists have proposed different memory models to enhance distributed shared memory systems. In this section, we will give an introduction to those memory models and some terminology used in this paper.

Integrating coordinated checkpointing and recovery mechanisms into DSM synchronization barriers

Distributed shared memory (DSM) creates an abstraction of a physical shared memory that parallel programmers can access. Most recent software DSM systems provide relaxed-memory models that guarantee consistency only at synchronization operations, such as locks and barriers. As the main goal of DSM systems is to provide support for long-term computation-intensive applications, checkpointing and recovery mechanisms are highly desirable. This article presents and evaluates the integration of a coordinated checkpointing mechanism to the barrier primitive that is usually provided with many DSM systems. Our results on some popular benchmarks and a real parallel application show that the overhead introduced during the failure-free execution is often small.

Towards a more efficient implementation of OpenMP for clusters via translation to global arrays

This paper discusses a novel approach to implementing OpenMP on clusters. Traditional approaches to do so rely on Software Distributed Shared Memory systems to handle shared data. We discuss these and then introduce an alternative approach that translates OpenMP to Global Arrays (GA), explaining the basic strategy. GA requires a data distribution. We do not expect the user to supply this; rather, we show how we perform data distribution and work distribution according to the user-supplied OpenMP static loop schedules. An inspector–executor strategy is employed for irregular applications in order to gather information on accesses to potentially non-local data, group non-local data transfers and overlap communications with local computations. Furthermore, a new directive INVARIANT is proposed to provide information about the dynamic scope of data access patterns. This directive can help us generate efficient codes for irregular applications using the inspector–executor approach. We also illustrate how to deal with some hard cases containing reshaping and strided accesses during the translation. Our experiments show promising results for the corresponding regular and irregular GA codes.

Running OpenMP applications efficiently on an everything-shared SDSM

Traditional software distributed shared memory (SDSM) systems modify the semantics of a real hardware shared memory system by relaxing the coherence semantic and by limiting the memory regions that are actually shared. These semantic modifications are done to improve performance of the applications using it. In this paper, we will show that a SDSM system that behaves like a real shared memory system (without the afore-mentioned relaxations) can also be used to execute OpenMP applications and achieve similar speedups as the ones obtained by traditional SDSM systems. This performance can be achieved by encouraging the cooperation between the SDSM and the OpenMP runtime instead of relaxing the semantics of the shared memory. In addition, techniques like boundaries alignment and page presend are demonstrated as very useful to overcome the limitations of the current SDSM systems.

JIACKPT: A Recoverable Software Distributed Shared Memory System

Software distributed shared memory (DSM) system has constructed a virtual shared memory abstract on cluster, which combines the programmability of shared memory and fine scalability of cluster. So it is widely studied. Software DSM system is easy to fail because it is a distributed system, some kinds of fault tolerance are necessary for it to be more practical. A recoverable and portable software DSM system, JIACKPT (JIAjia with ChecKPoinTing), has been designed and implemented to tolerate the fault of system. JIACKPT, based on JIAJIA, has adopted the checkpointing technology. By maintaining the strict global consistent state and using some optimization techniques, JIACKPT has gotten high performance. The experimental results on an 8-node PC cluster show that the checkpoint overhead is less than 10% of the whole execution time when checkpoint is done once per minute. JIACKPT also has good portability and can run on several operating systems, such as Linux, Solaris, etc.

An Effective Logical Cache for a Clustered LRC-Based DSM System

As local-area workstation networks are widely available, the idea of offering a software distributed shared memory (SDSM) system across interconnects of clusters is quite an attractive alternative for compute-intensive applications. However, the higher cost of sending a message over an inter-cluster link compared to an intra-cluster one can limit applications' performance on a multi-cluster SDSM system. In this paper, we present the extensions that we have added to the SDSM TreadMarks, which provides the i>lazy release consistency (LRC) memory model, in order to adapt it to a loosely-coupled cluster-based platform. We have implemented a logical per-cluster cache that exploits cluster locality. By accessing the cache of its cluster, a processor can share data previously requested by a second processor of its cluster, thereby, minimizing, the cost of inter-cluster communication.

Accurate data redistribution cost estimation in software distributed shared memory systems

Distributing data is one of the key problems in implementing efficient distributed-memory parallel programs. The problem becomes more difficult in programs where data redistribution between computational phases is considered. The global data distribution problem is to find the optimal distribution in multi-phase parallel programs. Solving this problem requires accurate knowledge of data redistribution cost. We are investigating this problem in the context of a software distributed shared memory (SDSM) system, in which obtaining accurate redistribution cost estimates is difficult. This is because SDSM communication is implicit: It depends on access patterns, page locations, and the SDSM consistency protocol. We have developed integrated compile- and run-time analysis for SDSM systems to determine accurate redistribution cost estimates with low overhead. Our resulting system, SUIF-Adapt, can efficiently and accurately estimate execution time, including redistribution, to within 5% of the actual time in all of our test cases and is often much closer. These precise costs enable SUIF-Adapt to find efficient global data distributions in multiple-phase programs.

Efficient Support for Pipelining in Software Distributed Shared Memory Systems

Though more difficult to program, distributed-memory parallel machines provide greater scalability than their shared-memory counterparts. Software Distributed Shared Memory (SDSM) systems provide the abstraction of shared memory on a distributed machine. While SDSMs provide an attractive programming model, they currently cannot efficiently support all classes of scientific application. One such class are those with recurrences that cause dependencies across processors or nodes. A popular solution to such problems is to use pipelining which breaks the computation into blocks; each processor performs the computation of a block, which enables the next processor in the pipeline to compute its corresponding block. Once the pipeline is filled, the computation of blocks proceeds in parallel. While pipelining is useful, it is not efficiently supported by current SDSM systems. This paper presents an approach to integrating pipelining into SDSM systems. We describe our design and implementation of one-way pipelining in a SDSM. The key idea is to retain the shared-memory model, but design the extensions such that the execution will mimic what would be done in an explicit message-passing program. We show that one-way pipelining is superior to the two most common ways to program pipelined applications, which are distributed locks and explicit matrix transposition. Finally, we show that one-way pipelining is competitive with a hand-coded, explicit message-passing program.

OpenMP for Networks of SMPs

In this paper, we present the first system that implements OpenMP on a network of shared-memory multiprocessors. This system enables the programmer to rely on a single, standard, shared-memory API for parallelization within a multiprocessor and between multiprocessors. It is implemented via a translator that converts OpenMP directives to appropriate calls to a modified version of the TreadMarks software distributed shared-memory (SDSM) system. In contrast to previous SDSM systems for SMPs, the modified TreadMarks system uses POSIX threads for parallelism within an SMP node. This approach greatly simplifies the changes required to the SDSM in order to exploit the intranode hardware shared memory. We present performance results for seven applications (Barnes-Hut, CLU, and Water from SPLASH-2, 3D-FFT from NAS, Red-Black SOR, TSP, and MGS) running on an SP2 with four four-processor SMP nodes. A comparison between the thread implementation and the original implementation of TreadMarks shows that using the hardware shared memory within an SMP node significantly reduces the amount of data and the number of messages transmitted between nodes and consequently achieves speedups that are up to 30% better than the original versions. We also compare SDSM against message passing. Overall, the speedups of multithreaded TreadMarks programs are within 7–30% of the MPI versions.

Limited multiple-writer: An approach to dealing with false sharing in software DSMs

False sharing is one of the most important factors impacting the performance of DSM (distributed shared memory) systems. The single-writer approach is simple, but it cannot avoid the ping-pong effect of the data page thrashing, while the multiple-writer approach is effective for false sharing but with high cost. This paper proposes a new approach, called limited multiple-writer (LMW) to handling multiple writers in software DSM. It distinguishes two kinds of multiple-writer as lock-based form and barrier-based form, and handles them with different policies. It discards theTwin andDiff in traditional multiple-writer approach, and simplifies the implementation of multiple-writer in software DSM systems. The implementation of LMW in a CVM (Coherent Virtual Machine) software DSM system, which is based on a network of workstations, is introduced. Evaluation results show that for some applications such as SOR (Successive Over-Relaxation), LU (Lower triangular and Upper triangular), FFT (Fast Fourier Transformation), and IS (Integer Sorting), LMW provides a significant reduction in execution time (11%, 16%, 33% and 46%) compared with the traditional multiple-writer approach on the platform.

IMPROVING THE EXECUTION EFFICIENCY OF BARRIER SYNCHRONIZATION IN SOFTWARE DSM THROUGH STATIC ANALYSIS

In software Distributed Shared Memory (SDSM) systems, the large coherence granularity imposed by virtual memory page size tends to induce false sharing, which may lead to heavy network traffic or useless page misses on barrier operations. In this paper, we propose a method to alleviate the coherence overhead of barrier synchronization in the SDSM systems. It performs static analysis on a shared-memory program to examine data dependency between processors across global barriers, and then special primitives are inserted into the program in order to exploit the dependency information at run time. If the data modified before a barrier will be accessed by some of the other processors after the barrier, coherence messages are transferred only to the processors through the inserted primitives. Furthermore, if the modified data will not be used by any other processors, the primitives enforce the coherence messages to be delivered only to master process after the parallel execution of the program completes. We implemented the static analysis with SUIF parallelizing compiler and then evaluated the execution performance of modified programs in a 16-node SDSM system supporting AURC protocol. The experimental results show that our method is very effective at reducing the useless coherence messages, and also can improve the execution time substantially by reducing false sharing misses.

Using confidence interval to summarize the evaluating results of DSM systems

Distributed Shared Memory (DSM) systems have gained popular acceptance by combining the scalability and low cost of distributed system with the ease of use of single address space. Many new hardware DSM and software DSM systems have been proposed in recent years. In general, benchmarking is widely used to demonstrate the performance advantages of new systems. However, the common method used to summarize the measured results is the arithmetic mean of ratios, which is incorrect in some cases. Furthermore, many published papers list a lot of data only, and do not summarize them effectively, which confuse users greatly. In fact, many users want to get a single number as conclusion, which is not provided in old summarizing techniques. Therefore, a new data-summarizing technique based on confidence interval is proposed in this paper. The new technique includes two data-summarizing methods: (1) paired confidence interval method; (2) unpaired confidence interval method. With this new technique, it is concluded that at some confidence one system is better than others. Four examples are shown to demonstrate the advantages of this new technique. Furthermore, with the help of confidence level, it is proposed to standardize the benchmarks used for evaluating DSM systems so that a convincing result can be got. In addition, the new summarizing technique fits not only for evaluating DSM systems, but also for evaluating other systems, such as memory system and communication systems.

Improving the performance of distributed shared memory systems via parallel file input/output

File accesses in page-based software Distributed Shared Memory (DSM) systems are usually performed by a single node, which may lead to a poor overall performance because a large amount of network traffic is generated to transfer data between this file handling node and the other nodes. To reduce the file-related network traffic in the DSM systems, we have designed a parallel file I/O system, that is independent of the memory consistency models, for the page-based software DSM systems built on a network of workstations. The two main features in our design are the adaptive data distribution scheme and the delayed file access mechanism. The former distributes file blocks among the nodes according to the access pattern of the application, while the latter ensures that the data are transferred to the consumer node instead of the request node by exploiting the memory mapping features of the virtual shared address space of the DSM systems. Our first prototype is built on Cohesion, a page-based software DSM system also developed by our research group, and this implementation requires very little modification on Cohesion. The performance result of our prototype is quite encouraging: the total execution time of the 2048 × 1024 20-iterations Successive Over Relaxation program on eight nodes was reduced from 196 s with sequential I/O to 108 s with parallel I/O, while it was reduced in the 512 × 512 Matrix Multiplication program on eight nodes from 100 s with sequential I/O to 84 s with parallel I/O.

An interaction of coherence protocols and memory consistency models in DSM systems

Coherence protocols and memory consistency models are two improtant issues in hardware coherent shared memory multiprocessors and softare distributed shared memory(DSM) systems. Over the years, many researchers have made extensive study on these two issues repectively. However, the interaction between them has not been studied in the literature. In this paper, we study the coherence protocols and memory consistency models used by hardware and software DSM systems in detail. Based on our analysis, we draw a general definition for memory consistency model, i.e., memory consistency model is the logical sum of the ordering of events in each processor and coherence protocol. We also point that in hardware DSM system the emphasis of memory consistency model is relaxing the restriction of event ordering, while in software DSM system, memory consistency model focuses mainly on relaxing coherence protocol. Taking Lazy Release Consistency(LRC) as an example, we analyze the relationship between coherence protocols and memory consistency models in software DSM systems, and find that whether the advantages of LRC can be exploited or not depends greatly on it's corresponding protocol. We draw the conclusion that the more relaxed consistency model is, the more relaxed coherence protocol needed to support it. This conclusion is very useful when we design a new consistency model. Furthermore, we make some improvements on traditional multiple writer protocol, and as far as we aware, we describe the complex state transition for multiple writer protocol for the first time. In the end, we list the main research directions for memory consistency models in hardware and software DSM systems.

Techniques for reducing consistency-related communication in distributed shared-memory systems

Distributed shared memory (DSM) is an abstraction of shared memory on a distributed-memory machine. Hardware DSM systems support this abstraction at the architecture level; software DSM systems support the abstraction within the runtime system. One of the key problems in building an efficient software DSM system is to reduce the amount of communication needed to keep the distributed memories consistent. In this article we present four techniques for doing so: software release consistency; multiple consistency protocols; write-shared protocols; and an update-with-timeout mechanism. These techniques have been implemented in the Munin DSM system. We compare the performance of seven Munin application programs: first to their performance when implemented using message passing, and then to their performance when running on a conventional software DSM system that does not embody the preceding techniques. On a 16-processor cluster of workstations, Munin's performance is within 5% of message passing for four out of the seven applications. For the other three, performance is within 29 to 33%. Detailed analysis of two of these three applications indicates that the addition of a function-shipping capability would bring their performance to within 7% of the message-passing performance. Compared to a conventional DSM system, Munin achieves performance improvements ranging from a few to several hundred percent, depending on the application.