J. McClure, Hao Wang, J. Prins, Cass T. Miller, Wu-chun Feng
Large-scale simulation can provide a wide range of information needed to develop and validate theoretical models for multiphase flow in porous medium systems. In this paper, we consider a coupled solution in which a multiphase flow simulator is coupled to an analysis approach used to extract the interfacial geometries as the flow evolves. This has been implemented using MPI to target heterogeneous nodes equipped with GPUs. The GPUs evolve the multiphase flow solution using the lattice Boltzmann method while the CPUs compute up scaled measures of the morphology and topology of the phase distributions and their rate of evolution. Our approach is demonstrated to scale to 4,096 GPUs and 65,536 CPU cores to achieve a maximum performance of 244,754 million-lattice-node updates per second (MLUPS) in double precision execution on Titan. In turn, this approach increases the size of systems that can be considered by an order of magnitude compared with previous work and enables detailed in situ tracking of averaged flow quantities at temporal resolutions that were previously impossible. Furthermore, it virtually eliminates the need for post-processing and intensive I/O and mitigates the potential loss of data associated with node failures.
{"title":"Petascale Application of a Coupled CPU-GPU Algorithm for Simulation and Analysis of Multiphase Flow Solutions in Porous Medium Systems","authors":"J. McClure, Hao Wang, J. Prins, Cass T. Miller, Wu-chun Feng","doi":"10.1109/IPDPS.2014.67","DOIUrl":"https://doi.org/10.1109/IPDPS.2014.67","url":null,"abstract":"Large-scale simulation can provide a wide range of information needed to develop and validate theoretical models for multiphase flow in porous medium systems. In this paper, we consider a coupled solution in which a multiphase flow simulator is coupled to an analysis approach used to extract the interfacial geometries as the flow evolves. This has been implemented using MPI to target heterogeneous nodes equipped with GPUs. The GPUs evolve the multiphase flow solution using the lattice Boltzmann method while the CPUs compute up scaled measures of the morphology and topology of the phase distributions and their rate of evolution. Our approach is demonstrated to scale to 4,096 GPUs and 65,536 CPU cores to achieve a maximum performance of 244,754 million-lattice-node updates per second (MLUPS) in double precision execution on Titan. In turn, this approach increases the size of systems that can be considered by an order of magnitude compared with previous work and enables detailed in situ tracking of averaged flow quantities at temporal resolutions that were previously impossible. Furthermore, it virtually eliminates the need for post-processing and intensive I/O and mitigates the potential loss of data associated with node failures.","PeriodicalId":309291,"journal":{"name":"2014 IEEE 28th International Parallel and Distributed Processing Symposium","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-05-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128734712","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Computing systems are being designed with an increasing number of hardware cores. To effectively use these cores, applications need to maximize the amount of parallel processing and minimize the time spent in sequential execution. In this work, we aim to exploit fine-grained parallelism beyond the parallelism already encoded in an application. We define an execution model using a primary core and some number of secondary cores that collaborate to speed up the execution of sequential code regions. This execution model relies on cores that are physically close to each other and have fast communication paths between them. For this purpose, we introduce dedicated hardware queues for low-latency transfer of values between cores, and define special "enque" and "deque" instructions to use the queues. Further, we develop compiler analyses and transformations to automatically derive fine-grained parallel code from sequential code regions. We implemented this model for exploiting fine-grained parallelization in the IBM XL compiler framework and in a simulator for the Blue Gene/Q system. We also studied the Sequoia benchmarks to determine code sections where our techniques are applicable. We evaluated our work using these code sections, and observed an average speedup of 1.32 on 2 cores, and an average speedup of 2.05 on 4 cores. Since these code sections are otherwise sequentially executed, we conclude that our approach is useful for accelerating single thread performance.
{"title":"Using Multiple Threads to Accelerate Single Thread Performance","authors":"Zehra Sura, K. O'Brien, J. Brunheroto","doi":"10.1109/IPDPS.2014.104","DOIUrl":"https://doi.org/10.1109/IPDPS.2014.104","url":null,"abstract":"Computing systems are being designed with an increasing number of hardware cores. To effectively use these cores, applications need to maximize the amount of parallel processing and minimize the time spent in sequential execution. In this work, we aim to exploit fine-grained parallelism beyond the parallelism already encoded in an application. We define an execution model using a primary core and some number of secondary cores that collaborate to speed up the execution of sequential code regions. This execution model relies on cores that are physically close to each other and have fast communication paths between them. For this purpose, we introduce dedicated hardware queues for low-latency transfer of values between cores, and define special \"enque\" and \"deque\" instructions to use the queues. Further, we develop compiler analyses and transformations to automatically derive fine-grained parallel code from sequential code regions. We implemented this model for exploiting fine-grained parallelization in the IBM XL compiler framework and in a simulator for the Blue Gene/Q system. We also studied the Sequoia benchmarks to determine code sections where our techniques are applicable. We evaluated our work using these code sections, and observed an average speedup of 1.32 on 2 cores, and an average speedup of 2.05 on 4 cores. Since these code sections are otherwise sequentially executed, we conclude that our approach is useful for accelerating single thread performance.","PeriodicalId":309291,"journal":{"name":"2014 IEEE 28th International Parallel and Distributed Processing Symposium","volume":"38 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-05-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116530275","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Data migration schemes are critical to balance the load in storage clusters for performance improvement. However, as NAND flash based SSDs are widely deployed in storage systems, extending the lifespan of SSD storage clusters becomes a new challenge for data migration. Prior approaches designed for HDD storage clusters, however, are inefficient due to excessive write amplification during data migration, which significantly decrease the lifespan of SSD storage clusters. To overcome this problem, we propose EDM, an endurance aware data migration scheme with careful data placement and movement to minimize the data migrated, so as to limit the worn-out of SSDs while improving the performance. Based on the observation that performance degradation is dominated by the wear speed of an SSD, which is affected by both the storage utilization and the write intensity, two complementary data migration policies are designed to explore the trade-offs among throughput, response time during migration, and lifetime of SSD storage clusters. Moreover, we design an SSD wear model and quantitatively calculate the amount of data migrated as well as the sources and destinations of the migration, so as to reduce the write amplification caused by migration. Results on a real storage cluster using real-world traces show that EDM performs favorably versus existing HDD based migration techniques, reducing cluster-wide aggregate erase count by up to 40%. In the meantime, it improves the performance by 25% on average compared to the baseline system which achieves almost the same effectiveness of performance improvement as previous migration techniques.
{"title":"EDM: An Endurance-Aware Data Migration Scheme for Load Balancing in SSD Storage Clusters","authors":"Jiaxin Ou, J. Shu, Youyou Lu, Letian Yi, Wei Wang","doi":"10.1109/IPDPS.2014.86","DOIUrl":"https://doi.org/10.1109/IPDPS.2014.86","url":null,"abstract":"Data migration schemes are critical to balance the load in storage clusters for performance improvement. However, as NAND flash based SSDs are widely deployed in storage systems, extending the lifespan of SSD storage clusters becomes a new challenge for data migration. Prior approaches designed for HDD storage clusters, however, are inefficient due to excessive write amplification during data migration, which significantly decrease the lifespan of SSD storage clusters. To overcome this problem, we propose EDM, an endurance aware data migration scheme with careful data placement and movement to minimize the data migrated, so as to limit the worn-out of SSDs while improving the performance. Based on the observation that performance degradation is dominated by the wear speed of an SSD, which is affected by both the storage utilization and the write intensity, two complementary data migration policies are designed to explore the trade-offs among throughput, response time during migration, and lifetime of SSD storage clusters. Moreover, we design an SSD wear model and quantitatively calculate the amount of data migrated as well as the sources and destinations of the migration, so as to reduce the write amplification caused by migration. Results on a real storage cluster using real-world traces show that EDM performs favorably versus existing HDD based migration techniques, reducing cluster-wide aggregate erase count by up to 40%. In the meantime, it improves the performance by 25% on average compared to the baseline system which achieves almost the same effectiveness of performance improvement as previous migration techniques.","PeriodicalId":309291,"journal":{"name":"2014 IEEE 28th International Parallel and Distributed Processing Symposium","volume":"113 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-05-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126999138","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
S. Di, M. Bouguerra, L. Bautista-Gomez, F. Cappello
HPC community projects that future extreme scale systems will be much less stable than current Petascale systems, thus requiring sophisticated fault tolerance to guarantee the completion of large scale numerical computations. Execution failures may occur due to multiple factors with different scales, from transient uncorrectable memory errors localized in processes to massive system outages. Multi-level checkpoint/restart is a promising model that provides an elastic response to tolerate different types of failures. It stores checkpoints at different levels: e.g., local memory, remote memory, using a software RAID, local SSD, remote file system. In this paper, we respond to two open questions: 1) how to optimize the selection of checkpoint levels based on failure distributions observed in a system, 2) how to compute the optimal checkpoint intervals for each of these levels. The contribution is three-fold. (1) We build a mathematical model to fit the multi-level checkpoint/restart mechanism with large scale applications regarding various types of failures. (2) We theoretically optimize the entire execution performance for each parallel application by selecting the best checkpoint level combination and corresponding checkpoint intervals. (3) We characterize checkpoint overheads on different checkpoint levels in a real cluster environment, and evaluate our optimal solutions using both simulation with millions of cores and real environment with real-world MPI programs running on hundreds of cores. Experiments show that optimized selections of levels associated with optimal checkpoint intervals at each level outperforms other state-of-the-art solutions by 5-50 percent.
{"title":"Optimization of Multi-level Checkpoint Model for Large Scale HPC Applications","authors":"S. Di, M. Bouguerra, L. Bautista-Gomez, F. Cappello","doi":"10.1109/IPDPS.2014.122","DOIUrl":"https://doi.org/10.1109/IPDPS.2014.122","url":null,"abstract":"HPC community projects that future extreme scale systems will be much less stable than current Petascale systems, thus requiring sophisticated fault tolerance to guarantee the completion of large scale numerical computations. Execution failures may occur due to multiple factors with different scales, from transient uncorrectable memory errors localized in processes to massive system outages. Multi-level checkpoint/restart is a promising model that provides an elastic response to tolerate different types of failures. It stores checkpoints at different levels: e.g., local memory, remote memory, using a software RAID, local SSD, remote file system. In this paper, we respond to two open questions: 1) how to optimize the selection of checkpoint levels based on failure distributions observed in a system, 2) how to compute the optimal checkpoint intervals for each of these levels. The contribution is three-fold. (1) We build a mathematical model to fit the multi-level checkpoint/restart mechanism with large scale applications regarding various types of failures. (2) We theoretically optimize the entire execution performance for each parallel application by selecting the best checkpoint level combination and corresponding checkpoint intervals. (3) We characterize checkpoint overheads on different checkpoint levels in a real cluster environment, and evaluate our optimal solutions using both simulation with millions of cores and real environment with real-world MPI programs running on hundreds of cores. Experiments show that optimized selections of levels associated with optimal checkpoint intervals at each level outperforms other state-of-the-art solutions by 5-50 percent.","PeriodicalId":309291,"journal":{"name":"2014 IEEE 28th International Parallel and Distributed Processing Symposium","volume":"80 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-05-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130637900","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Bit-reproducibility has many advantages in the context of high-performance computing. Besides simplifying and making more accurate the process of debugging and testing the code, it can allow the deployment of applications on heterogeneous systems, maintaining the consistency of the computations. In this work we analyze the basic operations performed by scientific applications and identify the possible sources of non-reproducibility. In particular, we consider the tasks of evaluating transcendental functions and performing reductions using non-associative operators. We present a set of techniques to achieve reproducibility and we propose improvements over existing algorithms to perform reproducible computations in a portable way, at the same time obtaining good performance and accuracy. By applying these techniques to more complex tasks we show that bit-reproducibility can be achieved on a broad range of scientific applications.
{"title":"Designing Bit-Reproducible Portable High-Performance Applications","authors":"Andrea Arteaga, O. Fuhrer, T. Hoefler","doi":"10.1109/IPDPS.2014.127","DOIUrl":"https://doi.org/10.1109/IPDPS.2014.127","url":null,"abstract":"Bit-reproducibility has many advantages in the context of high-performance computing. Besides simplifying and making more accurate the process of debugging and testing the code, it can allow the deployment of applications on heterogeneous systems, maintaining the consistency of the computations. In this work we analyze the basic operations performed by scientific applications and identify the possible sources of non-reproducibility. In particular, we consider the tasks of evaluating transcendental functions and performing reductions using non-associative operators. We present a set of techniques to achieve reproducibility and we propose improvements over existing algorithms to perform reproducible computations in a portable way, at the same time obtaining good performance and accuracy. By applying these techniques to more complex tasks we show that bit-reproducibility can be achieved on a broad range of scientific applications.","PeriodicalId":309291,"journal":{"name":"2014 IEEE 28th International Parallel and Distributed Processing Symposium","volume":"10 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-05-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131269544","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Emerging task-based parallel programming models shield programmers from the daunting task of parallelism management by delegating the responsibility of mapping and scheduling of individual tasks to the runtime system. The runtime system can use semantic information about task dependencies supplied by the programmer and the mapping information of tasks to enable optimizations like data-flow based execution and locality-aware scheduling of tasks. However, should the cache coherence substrate have access to this information from the runtime system, it would enable aggressive optimizations of prevailing access patterns such as one-to-many producer-consumer sharing and migratory sharing. Such linkage has however not been studied before. We present a family of runtime guided cache coherence optimizations enabled by linking dependency and mapping information from the runtime system to the cache coherence substrate. By making this information available to the cache coherence substrate, we show that optimizations, such as downgrading and self-invalidation, that help reducing overheads associated with producer-consumer and migratory sharing can be supported with reasonable extensions to the baseline cache coherence protocol. Our experimental results establish that each optimization provides significant performance gain in isolation and can provide additional gains when combined. Finally, we evaluate these optimizations in the context of earlier proposed runtime-guided prefetching schemes and show that they can have synergistic effects.
{"title":"Runtime-Guided Cache Coherence Optimizations in Multi-core Architectures","authors":"M. Manivannan, P. Stenström","doi":"10.1109/IPDPS.2014.71","DOIUrl":"https://doi.org/10.1109/IPDPS.2014.71","url":null,"abstract":"Emerging task-based parallel programming models shield programmers from the daunting task of parallelism management by delegating the responsibility of mapping and scheduling of individual tasks to the runtime system. The runtime system can use semantic information about task dependencies supplied by the programmer and the mapping information of tasks to enable optimizations like data-flow based execution and locality-aware scheduling of tasks. However, should the cache coherence substrate have access to this information from the runtime system, it would enable aggressive optimizations of prevailing access patterns such as one-to-many producer-consumer sharing and migratory sharing. Such linkage has however not been studied before. We present a family of runtime guided cache coherence optimizations enabled by linking dependency and mapping information from the runtime system to the cache coherence substrate. By making this information available to the cache coherence substrate, we show that optimizations, such as downgrading and self-invalidation, that help reducing overheads associated with producer-consumer and migratory sharing can be supported with reasonable extensions to the baseline cache coherence protocol. Our experimental results establish that each optimization provides significant performance gain in isolation and can provide additional gains when combined. Finally, we evaluate these optimizations in the context of earlier proposed runtime-guided prefetching schemes and show that they can have synergistic effects.","PeriodicalId":309291,"journal":{"name":"2014 IEEE 28th International Parallel and Distributed Processing Symposium","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-05-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132388028","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Saurav Muralidharan, Manu Shantharam, Mary W. Hall, M. Garland, Bryan Catanzaro
Autotuning systems intelligently navigate a search space of possible implementations of a computation to find the implementation(s) that best meets a specific optimization criteria, usually performance. This paper describes Nitro, a programmer-directed auto tuning framework that facilitates tuning of code variants, or alternative implementations of the same computation. Nitro provides a library interface that permits programmers to express code variants along with meta-information that aids the system in selecting among the set of variants at run time. Machine learning is employed to build a model through training on this meta-information, so that when a new input is presented, Nitro can consult the model to select the appropriate variant. In experiments with five real-world irregular GPU benchmarks from sparse numerical methods, graph computations and sorting, Nitro-tuned variants achieve over 93% of the performance of variants selected through exhaustive search. Further, we describe optimizations and heuristics in Nitro that substantially reduce training time and other overheads.
{"title":"Nitro: A Framework for Adaptive Code Variant Tuning","authors":"Saurav Muralidharan, Manu Shantharam, Mary W. Hall, M. Garland, Bryan Catanzaro","doi":"10.1109/IPDPS.2014.59","DOIUrl":"https://doi.org/10.1109/IPDPS.2014.59","url":null,"abstract":"Autotuning systems intelligently navigate a search space of possible implementations of a computation to find the implementation(s) that best meets a specific optimization criteria, usually performance. This paper describes Nitro, a programmer-directed auto tuning framework that facilitates tuning of code variants, or alternative implementations of the same computation. Nitro provides a library interface that permits programmers to express code variants along with meta-information that aids the system in selecting among the set of variants at run time. Machine learning is employed to build a model through training on this meta-information, so that when a new input is presented, Nitro can consult the model to select the appropriate variant. In experiments with five real-world irregular GPU benchmarks from sparse numerical methods, graph computations and sorting, Nitro-tuned variants achieve over 93% of the performance of variants selected through exhaustive search. Further, we describe optimizations and heuristics in Nitro that substantially reduce training time and other overheads.","PeriodicalId":309291,"journal":{"name":"2014 IEEE 28th International Parallel and Distributed Processing Symposium","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-05-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122310475","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Adam Fidel, S. A. Jacobs, Shishir Sharma, N. Amato, Lawrence Rauchwerger
Motion planning, which is the problem of computing feasible paths in an environment for a movable object, has applications in many domains ranging from robotics, to intelligent CAD, to protein folding. The best methods for solving this PSPACE-hard problem are so-called sampling-based planners. Recent work introduced uniform spatial subdivision techniques for parallelizing sampling-based motion planning algorithms that scaled well. However, such methods are prone to load imbalance, as planning time depends on region characteristics and, for most problems, the heterogeneity of the sub problems increases as the number of processors increases. In this work, we introduce two techniques to address load imbalance in the parallelization of sampling-based motion planning algorithms: an adaptive work stealing approach and bulk-synchronous redistribution. We show that applying these techniques to representatives of the two major classes of parallel sampling-based motion planning algorithms, probabilistic roadmaps and rapidly-exploring random trees, results in a more scalable and load-balanced computation on more than 3,000 cores.
{"title":"Using Load Balancing to Scalably Parallelize Sampling-Based Motion Planning Algorithms","authors":"Adam Fidel, S. A. Jacobs, Shishir Sharma, N. Amato, Lawrence Rauchwerger","doi":"10.1109/IPDPS.2014.66","DOIUrl":"https://doi.org/10.1109/IPDPS.2014.66","url":null,"abstract":"Motion planning, which is the problem of computing feasible paths in an environment for a movable object, has applications in many domains ranging from robotics, to intelligent CAD, to protein folding. The best methods for solving this PSPACE-hard problem are so-called sampling-based planners. Recent work introduced uniform spatial subdivision techniques for parallelizing sampling-based motion planning algorithms that scaled well. However, such methods are prone to load imbalance, as planning time depends on region characteristics and, for most problems, the heterogeneity of the sub problems increases as the number of processors increases. In this work, we introduce two techniques to address load imbalance in the parallelization of sampling-based motion planning algorithms: an adaptive work stealing approach and bulk-synchronous redistribution. We show that applying these techniques to representatives of the two major classes of parallel sampling-based motion planning algorithms, probabilistic roadmaps and rapidly-exploring random trees, results in a more scalable and load-balanced computation on more than 3,000 cores.","PeriodicalId":309291,"journal":{"name":"2014 IEEE 28th International Parallel and Distributed Processing Symposium","volume":"33 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-05-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"124127420","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Korbinian Molitorisz, Thomas Karcher, Alexander Biele, W. Tichy
The free lunch of ever increasing single-processor performance is over. Software engineers have to parallelize software to gain performance improvements. But not every software engineer is a parallel expert and with millions of lines of code that have not been developed with multicore in mind, we have to find ways to assist in identifying parallelization potential. This paper makes three contributions: 1) An empirical study of more than 900,000 lines of code reveals five use cases in the runtime profile of object-oriented data structures that carry parallelization potential. 2) The study also points out frequently used data structures in realistic software in which these use cases can be found. 3) We developed DSspy, an automatic dynamic profiler that locates these use cases and makes recommendations on how to parallelize them. Our evaluation shows that DSspy reduces the search space for parallelization by up to 77% and engineers only need to consider 23% of all data structure instances for parallelization.
{"title":"Locating Parallelization Potential in Object-Oriented Data Structures","authors":"Korbinian Molitorisz, Thomas Karcher, Alexander Biele, W. Tichy","doi":"10.1109/IPDPS.2014.106","DOIUrl":"https://doi.org/10.1109/IPDPS.2014.106","url":null,"abstract":"The free lunch of ever increasing single-processor performance is over. Software engineers have to parallelize software to gain performance improvements. But not every software engineer is a parallel expert and with millions of lines of code that have not been developed with multicore in mind, we have to find ways to assist in identifying parallelization potential. This paper makes three contributions: 1) An empirical study of more than 900,000 lines of code reveals five use cases in the runtime profile of object-oriented data structures that carry parallelization potential. 2) The study also points out frequently used data structures in realistic software in which these use cases can be found. 3) We developed DSspy, an automatic dynamic profiler that locates these use cases and makes recommendations on how to parallelize them. Our evaluation shows that DSspy reduces the search space for parallelization by up to 77% and engineers only need to consider 23% of all data structure instances for parallelization.","PeriodicalId":309291,"journal":{"name":"2014 IEEE 28th International Parallel and Distributed Processing Symposium","volume":"162 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-05-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"123948782","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Yang You, S. Song, H. Fu, A. Márquez, M. Dehnavi, K. Barker, K. Cameron, A. Randles, Guangwen Yang
Support Vector Machine (SVM) has been widely used in data-mining and Big Data applications as modern commercial databases start to attach an increasing importance to the analytic capabilities. In recent years, SVM was adapted to the field of High Performance Computing for power/performance prediction, auto-tuning, and runtime scheduling. However, even at the risk of losing prediction accuracy due to insufficient runtime information, researchers can only afford to apply offline model training to avoid significant runtime training overhead. Advanced multi- and many-core architectures offer massive parallelism with complex memory hierarchies which can make runtime training possible, but form a barrier to efficient parallel SVM design. To address the challenges above, we designed and implemented MIC-SVM, a highly efficient parallel SVM for x86 based multi-core and many-core architectures, such as the Intel Ivy Bridge CPUs and Intel Xeon Phi co-processor (MIC). We propose various novel analysis methods and optimization techniques to fully utilize the multilevel parallelism provided by these architectures and serve as general optimization methods for other machine learning tools. MIC-SVM achieves 4.4-84x and 18-47x speedups against the popular LIBSVM, on MIC and Ivy Bridge CPUs respectively, for several real-world data-mining datasets. Even compared with GPUSVM, run on a top of the line NVIDIA k20x GPU, the performance of our MIC-SVM is competitive. We also conduct a cross-platform performance comparison analysis, focusing on Ivy Bridge CPUs, MIC and GPUs, and provide insights on how to select the most suitable advanced architectures for specific algorithms and input data patterns.
{"title":"MIC-SVM: Designing a Highly Efficient Support Vector Machine for Advanced Modern Multi-core and Many-Core Architectures","authors":"Yang You, S. Song, H. Fu, A. Márquez, M. Dehnavi, K. Barker, K. Cameron, A. Randles, Guangwen Yang","doi":"10.1109/IPDPS.2014.88","DOIUrl":"https://doi.org/10.1109/IPDPS.2014.88","url":null,"abstract":"Support Vector Machine (SVM) has been widely used in data-mining and Big Data applications as modern commercial databases start to attach an increasing importance to the analytic capabilities. In recent years, SVM was adapted to the field of High Performance Computing for power/performance prediction, auto-tuning, and runtime scheduling. However, even at the risk of losing prediction accuracy due to insufficient runtime information, researchers can only afford to apply offline model training to avoid significant runtime training overhead. Advanced multi- and many-core architectures offer massive parallelism with complex memory hierarchies which can make runtime training possible, but form a barrier to efficient parallel SVM design. To address the challenges above, we designed and implemented MIC-SVM, a highly efficient parallel SVM for x86 based multi-core and many-core architectures, such as the Intel Ivy Bridge CPUs and Intel Xeon Phi co-processor (MIC). We propose various novel analysis methods and optimization techniques to fully utilize the multilevel parallelism provided by these architectures and serve as general optimization methods for other machine learning tools. MIC-SVM achieves 4.4-84x and 18-47x speedups against the popular LIBSVM, on MIC and Ivy Bridge CPUs respectively, for several real-world data-mining datasets. Even compared with GPUSVM, run on a top of the line NVIDIA k20x GPU, the performance of our MIC-SVM is competitive. We also conduct a cross-platform performance comparison analysis, focusing on Ivy Bridge CPUs, MIC and GPUs, and provide insights on how to select the most suitable advanced architectures for specific algorithms and input data patterns.","PeriodicalId":309291,"journal":{"name":"2014 IEEE 28th International Parallel and Distributed Processing Symposium","volume":"71 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2014-05-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115045055","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：