Efficient integration of compiler-directed cache coherence and data prefetching

Cache coherence enforcement and memory latency reduction and hiding are very important and challenging problems in the design of large-scale distributed shared-memory (DSM) multiprocessors. We propose an integrated approach to solve these problems through a compiler-directed cache coherence scheme called the Cache Coherence with Data Prefetching (CCDP) scheme. The CCDP scheme enforces cache coherence by prefetching the potentially-stale references in a parallel program. It also prefetches the non-stale references to hide their memory latencies. To optimize the performance of the CCDP scheme, some prefetch hardware support is provided to efficiently handle these two forms of data prefetching operations. We also developed the compiler techniques utilized by the CCDP scheme for stale reference detection, prefetch target analysis and prefetch scheduling. We evaluated the performance of the CCDP scheme via execution-driven simulations of several applications from the SPEC CFP95 and CFP92 benchmark suites. The simulation results show that the CCDP scheme provides significant performance improvements for the benchmark programs studied.KeywordsCompiler-directed Cache CoherenceData PrefetchingMemory Latency HidingShared-memory Multiprocessors

Computer systems are extensively being used in today’s era and the advancement in computer systems has led to the evolution of various technologies. As the efficiency of the computer systems is to be enhanced, the usage of cache memory becomes a must. The cache memory problems occur when multiprocessor systems are used. When multiple processors are processors share a common memory pool, the problem of cache coherence occurs. Cache coherence is a state in which the cache memories of the processors must stay in coherence with each other. The data should be updated in all the cache systems. Various protocols are used to ensure cache coherence. This study delineates the cache memory architecture, cache coherence, and the issues that arise due to non-consistent data in the cache of multiprocessor systems. Moreover, this study also delineates the protocols of the cache coherence and also describes in detail the MISE protocol. This study will provide an in-depth review of cache, cache coherence, and the issues associated with cache coherence along with the solution.

Directory-based protocols are currently the method of choice to enforce cache coherence in large-scale shared-memory multiprocessors. The problems associated with these hardware schemes include their lack of scalability, although various suggestions have been made to ameliorate this drawback, and the loss of performance due to false sharing. Software controlled cache coherence (SCCC) is an alternative that solves the scalability problem at the possible expense of a serious loss in performance since many compile-time decisions on cacheability are conservative. The authors perform a comparative study of hardware and software cache coherence based on instruction-level simulations of two benchmarks. The studies do not shy away from realistic SCCC difficulties such as multi-word lines and DOAcross loops. The simplification in hardware and in protocols result in a slight performance loss for SCCC, a loss that becomes relatively smaller and negligible with larger memory latencies. >

Directory-based and software-assisted schemes are the two main approaches to solving the cache coherence problem in large scale shared-memory multiprocessors. Until now, the emphasis in software-assisted schemes has been on ascertaining consistency within parallel constructs such as DoAll or DoAcross loops. In this paper, we propose a timestamped-based approach which also allows caching within critical sections. This scheme combines the best features of software-assisted and directory-based cache coherence protocols. It is based on a compile time analysis of interactions among critical sections and execution time local detection of cache incoherence by comparing the times when a variable was last written and last updated in the cache. A quantitative evaluation based on synthetic traces shows that this scheme results in hit ratios almost as high as in directory-based solutions while significantly reducing the network traffic.

The emergence of chip multiprocessors is leading to rapid advances in hardware and software systems to provide distributed shared memory (DSM) programming models, so-called DSM systems. A DSM system provides programming advantages within a scalable and cost-effective hardware solution. This benefit derives from the fact that a DSM system creates a shared-memory abstraction on top of a distributed-memory machine by caching data replicas locally. In this respect, a coherence protocol is a vital component responsible for assuring data consistency across all replicas. The design of coherence protocols impacts a DSM system in terms of both performance and accuracy. Performance is often measured via simulation and various verification techniques have been proposed to deal with protocol accuracy. Nevertheless, integrating accuracy verification into a DSM cluster simulation to ensure correct simulation results is still an open issue. In this paper, we address three properties of a coherence protocol (safety, liveness, and inclusion) without which errors may occur in the simulation results. We propose a specification-based parameter—model interaction (SPMI) technique to detect these cases in a particular DSM cluster simulator called DSiMCluster. Our experimental results demonstrate that with SPMI, DSiMCluster can ensure the coherence protocol properties and provides a correct reflection of memory characteristics in shared-memory and DSM multiprocessors.

High speed networks and rapidly improving microprocessor performance make the network of workstations an extremely important tool for parallel computing in order to speedup the execution of scientific applications. Shared memory is an attractive programming model for designing parallel and distributed applications, where the programmer can focus on algorithmic development rather than data partition and communication. Based on this important characteristic, the design of systems to provide the shared memory abstraction on physically distributed memory machines has been developed, known as Distributed Shared Memory (DSM). DSM is built using specific software to combine a number of computer hardware resources into one computing environment. Such an environment not only provides an easy way to execute parallel applications, but also combines available computational resources with the purpose of speeding up execution of these applications. DSM systems need to maintain data consistency in memory, which usually leads to communication overhead. Therefore, there exists a number of strategies that can be used to overcome this overhead issue and improve overall performance. Strategies as prefetching have been proven to show great performance in DSM systems, since they can reduce data access communication latencies from remote nodes. On the other hand, these strategies also transfer unnecessary prefetching pages to remote nodes. In this research paper, we focus on the access pattern during execution of a parallel application, and then analyze the data type and behavior of parallel applications. We propose an adaptive data classification scheme to improve prefetching strategy with the goal to improve overall performance. Adaptive data classification scheme classifies data according to the accessing sequence of pages, so that the home node uses past history access patterns of remote nodes to decide whether it needs to transfer related pages to remote nodes. From experimental results, we can observe that our proposed method can increase the accuracy of data access in effective prefetch strategy by reducing the number of page faults and misprefetching. Experimental results using our proposed classification scheme show a performance improvement of about 9---25% over the same benchmark applications running on top of an original JIAJIA DSM system.

Parallel programming has been widely used in many scientific and technical areas to solve large problems. While general-purpose processors have rich infrastructure to support parallel programming on shared memory, such as coherent caches and synchronization libraries, parallel programming infrastructure for FPGAs is limited. Thus, development of FPGA-based parallel algorithms remains difficult. In this work, we seek to simplify parallel programming on FPGAs. We provide a set of easy-to-use declarative primitives to maintain coherency and consistency of accesses to shared memory resources. We propose a shared-memory service that automatically manages coherent caches on multiple FPGAs. Experimental results of a 2-dimensional heat transfer equation show that the shared memory service with our distributed coherent caches outperforms a centralized cache by 2.6x. To handle synchronization, we provide new lock and barrier primitives that leverage native FPGA communication capabilities and outperform traditional through-memory primitives by 1.8x.

The distributed shared memory (DSM) architecture is considered to be one of the most likely parallel computing environment candidate for the near future because of its ease of system scalability and facilitation for parallel programming. However, a naive program based on shared memory execution on a DSM machine often deteriorates performance, because of the overhead involved for maintaining cache coherency particularly with frequent remote memory accesses. We show that careful buffer management of parallel join processing on DSM can produce considerable performance improvements in comparison with a naive implementation. We propose four buffer management strategies for parallel hash join processing on the DSM architecture and actually implement them on the HP Exemplar SPP 1600. The basic strategy is to begin with the hash join algorithm for the shared everything architecture and then to consider the memory locality of DSM by distributing the hash table and data pool buffers among the nodes. The results of four buffering strategies are analyzed in detail. Consequently, we can conclude that, in order to achieve high performance on a DSM machine, our buffer management strategy in which the memory access pattern is extracted and buffers are allocated in the local memory of nodes to minimize memory access cost is very efficient.

Cache Coherence in Multiprocessors: A Survey

Nowadays clusters are one of the most used platforms in High Performance Computing and most programmers use the Message Passing Interface (MPI) library to program their applications in these distributed platforms getting their maximum performance, although it is a complex task. On the other side, OpenMP has been established as the de facto standard to program applications on shared memory platforms because it is easy to use and obtains good performance without too much effort. So, could it be possible to join both worlds? Could programmers use the easiness of OpenMP in distributed platforms? A lot of researchers think so. And one of the developed ideas is the distributed shared memory (DSM), a software layer on top of a distributed platform giving an abstract shared memory view to the applications. Even though it seems a good solution it also has some inconveniences. The memory coherence between the nodes in the platform is difficult to maintain (complex management, scalability issues, high overhead and others) and the latency of the remote-memory accesses which can be orders of magnitude greater than on a shared bus due to the interconnection network. Therefore this research improves the performance of OpenMP applications being executed on distributed memory platforms using a DSM with sequential consistency evaluating thoroughly the results from the NAS parallel benchmarks. The vast majority of designed DSMs use a relaxed consistency model because it avoids some major problems in the area. In contrast, we use a sequential consistency model because we think that showing these potential problems that otherwise are hidden may allow the finding of some solutions and, therefore, apply them to both models. The main idea behind this work is that both runtimes, the OpenMP and the DSM layer, should cooperate to achieve good performance, otherwise they interfere one each other trashing the final performance of applications. We develop three different contributions to improve the performance of these applications: (a) a technique to avoid false sharing at runtime, (b) a technique to mimic the MPI behaviour, where produced data is forwarded to their consumers and, finally, (c) a mechanism to avoid the network congestion due to the DSM coherence messages. The NAS Parallel Benchmarks are used to test the contributions. The results of this work shows that the false-sharing problem is a relative problem depending on each application. Another result is the importance to move the data flow outside of the critical path and to use techniques that forwards data as early as possible, similar to MPI, benefits the final application performance. Additionally, this data movement is usually concentrated at single points and affects the application performance due to the limited bandwidth of the network. Therefore it is necessary to provide mechanisms that allows the distribution of this data through the computation time using an otherwise idle network. Finally, results shows that the proposed contributions improve the performance of OpenMP applications on this kind of environments.

It is well known that memory latency is a major deterrent to achieving the maximum possible performance of a today's high speed RISC processors. Techniques to reduce or tolerate large memory latencies become essential for achieving high processor utilization. Many methods, ranging from software to hardware solutions, have been studied with varying amounts of success. Most techniques have concentrated on data prefetching. However, our simulations show that the CPU is stalled up to 50% of the time waiting for instructions. The instruction memory latency reduction technique typically used in CPU designs today is the one block look-ahead (OBL) method. In this thesis, I present a new hardware prefetching scheme based on dynamic interpretation of the instruction stream. This is done by adding a small pipeline to the cache that scans forward in the instruction stream interpreting each instruction and predicting the future execution path. It then prefetches what it predicts the CPU will be executing in the near future. The pipelined prefetching engine has been shown to be a very effective technique for decreasing the instruction stall cycles in typical on-chip cache memories used today. It performs well, yielding reductions in stall cycles up to 30% or more for both scientific and general purpose programs, and has been shown to reduce the number of instruction stall cycles as compared to the OBL technique as well. The idea of sub-line prefetching was also studied and presented. It was thought that prefetching full cache lines might present too much overhead in terms of bus bandwidth, so prefetches should only fill partial cache lines instead. However it was determined that prefetching partial cache lines does not show any benefit when dealing with cache lines smaller than 128 bytes.

Appropriate solution of the well-known cache coherence problem in shared memory multiprocessors is one of the key issues in improving the performance and scalability of these systems. Hardware methods are convenient because of their transparency for software. They also offer good performance since they deal with the problem dynamically. Hardware cache coherence schemes can be principally divided into two large groups: directory and snoopy protocols. This survey underlines their principles and summarizes a relatively large number of relevant representatives from both groups. The coherence problem in multilevel caches is also briefly considered. Special attention is devoted to cache coherence maintenance in large scalable shared memory multiprocessors. >

Efficiently maintaining cache coherence is a major problem in large-scale shared memory multiprocessors. Hardware directory coherence schemes have very high memory requirements, while software-directed schemes must rely on imprecise compile-time memory disambiguation. Recently proposed dynamically tagged directory schemes allocate pointers to blocks only as they are referenced, which significantly reduces their memory requirements, but they still allocate pointers to blocks that do not need them. The authors present two compiler optimizations that exploit the high-level sharing information available to the compiler to further reduce the size of a tagged directory by allocating pointers only when necessary. Trace-driven simulations are used to show that the performance of this combined hardware-software approach is comparable to other coherence schemes, but with significantly lower memory requirements. In addition, these simulations suggest that this approach is less sensitive to the quality of the memory disambiguation and interprocedural analysis performed by the compiler than software-only coherence schemes.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">&gt;</ETX>

Several mechanisms have been proposed for maintaining cache coherence in large-scale shared memory multiprocessors. Two important factors that distinguish these coherence mechanisms are: 1) the coherence enforcement strategy, such as updating or invalidating, that is used to prevent access to stale data; and 2) the coherence detection strategy, which is used to detect the existence of incoherent cached copies either at compile-time or at run-time. This paper examines the range of performance that can be realized by a compiler-directed coherence mechanism using three different levels of compiler ability. This performance is compared to the performance of the updating and the invalidating directory schemes. In addition, the performance of all three coherence schemes is compared with respect to different cache block sizes.

Integrating Fine-Grained Message Passing in Cache Coherent Shared Memory Multiprocessors