Search

The Unified Parallel C (UPC) language from the Partitioned Global Address Space (PGAS) family unifies the advantages of shared and local memory spaces and offers a relatively straightforward code parallelisation with the Central Processing Unit (CPU). In contrast, the Computer Unified Device Architecture (CUDA) development kit gives a tool to make use of the Graphics Processing Unit (GPU). We provide a detailed comparison between these novel techniques through the parallelisation of a two-dimensional lattice Boltzmann method based fluid flow solver. Our comparison between the CUDA and UPC parallelisation takes into account the required conceptual effort, the performance gain, and the limitations of the approaches from the application oriented developers’ point of view. We demonstrated that UPC led to competitive efficiency with the local memory implementation. However, the performance of the shared memory code fell behind our expectations, and we concluded that the investigated UPC compilers could not efficiently treat the shared memory space. The CUDA implementation proved to be more complex compared to the UPC approach mainly because of the complicated memory structure of the graphics card which also makes GPUs suitable for the parallelisation of the lattice Boltzmann method.

In this study, we exploit the advantages of Berkeley's Unified Parallel C (UPC) programming model to optimize the speedup performance of computational hydrodynamic (CHD) simulations, which constitute an important class of modelling tool for hydraulic engineering applications. A two-dimensional (2D) numerical model, termed UPC-CHD, is developed using the conservative forms of the Navier-Stokes (NS) continuity, momentum, and energy equations for viscous, incompressible, and adiabatic flow cases with the UPC model. The following numerical schemes are adopted for discretization in UPC-CHD: (1) a 2-step Lax-Wendroff explicit scheme for the temporal term; (2) a Roe linear approximation with a 3rd-order upwind biased algorithm for the convective fluxes; and (3) a central-differencing scheme for the viscous fluxes. The obtained speedup results demonstrate that UPC-CHD with the affinity principle achieves good speedup performance when compared to the serial algorithm, with an average value of 0.8 per unit core (thread) until 100 processor cores when simulating the Couette, Blasius boundary layer, and Poiseuille flows on a 2D domain of 100 million grids. Finally, we also investigate the effects of varying domain size on the speedup performances of UPC-CHD for the same flow conditions. Nanyang Technological University This research study is funded by the internal core funding from the Nanyang Environment and Water Research Institute (NEWRI),Nanyang Technological University (NTU), Singapore.

Various partitioned global address space (PGAS) languages capable of providing global-view programming environments on multi-node computer systems have been proposed to improve programming productivity in high-performance computing. However, several PGAS languages often require a detailed description of the remote data access, similar to descriptions used in message passing interface one-sided communications. Some PGAS languages have limitations pertaining to remote data access and recommend their local-view programming models, rather than the global-view ones, due to performance-related reasons. In this study, we propose SMint, which is an application programming interface that provides a global-view programming model with a software distributed shared memory mSMS as the runtime. Using stencil computation as a typical processing method, the performance and programmability of SMint have been compared with those of XcalableMP and Unified Parallel C, which are well-known examples of PGAS languages based on the C language. It was found that SMint achieved the best performance under the ideal global-view programming model.

In this paper we evaluate the performance of Unified Parallel C (which implements the partitioned global address space programming model) using a numerical method that is widely used in fluid dynamics. In order to evaluate the incremental approach to parallelization (which is possible with UPC) and its performance characteristics, we implement different levels of optimization of the UPC code and compare it with an MPI parallelization on four different clusters of the Austrian HPC infrastructure (LEO3, LEO3E, VSC2, VSC3) and on an Intel Xeon Phi. We find that UPC is significantly easier to develop in compared to MPI and that the performance achieved is comparable to MPI in most situations. The obtained results show worse performance (on VSC2), competitive performance (on LEO3, LEO3E and VSC3), and superior performance (on the Intel Xeon Phi)., Comment: Parallel Computing 2016

We improve performance of fine-grain UPC applications by orders of magnitude.We introduce a novel shared-data localization transformation.We present a thorough performance analysis and evaluation.We show that reducing run-time calls is crucial for performance.We achieve performance comparable to C and MPI using the UPC programming model. Programs written in the Unified Parallel C (UPC) language can access any location of the entire local and remote address space via read/write operations. However, UPC programs that contain fine-grained shared accesses can exhibit performance degradation. One solution is to use the inspector-executor technique to coalesce fine-grained shared accesses to larger remote access operations. A straightforward implementation of the inspector-executor transformation results in excessive instrumentation that hinders performance.This paper addresses this issue and introduces various techniques that aim at reducing the generated instrumentation code: a shared-data localization transformation based on Constant-Stride Linear Memory Descriptors (CSLMADs) S. Aarseth, Gravitational N-Body Simulations: Tools and Algorithms, Cambridge Monographs on Mathematical Physics, Cambridge University Press, 2003., the inlining of data locality checks and the usage of an index vector to aggregate the data. Finally, the paper introduces a lightweight loop code motion transformation to privatize shared scalars that were propagated through the loop body.A performance evaluation, using up to 2048 cores of a POWER 775, explores the impact of each optimization and characterizes the overheads of UPC programs. It also shows that the presented optimizations increase performance of UPC programs up to 1.8 × their UPC hand-optimized counterpart for applications with regular accesses and up to 6.3 × for applications with irregular accesses.

Fortran Coarrays are a well known data structure in High Performance Computing (HPC) applications. There have been various attempts to port the concept to other programming languages that have a wider user base outside of scientific computing. While a popular implementation of the partitioned global address space (PGAS) model is Unified Parallel C (UPC), there is currently no portable implementation of Coarrays for C++. In this paper a portable version is presented, which is closely based on the Coarray C++ implementation of the Cray Compiling Environment. In this work we focus on a common subset of all proposed features by Cray. Our implementation utilizes the distributed data structures provided by the DASH library, demonstrating their universal applicability. Finally, a performance evaluation shows that our proposed Coarray abstraction adds negligible overhead and even outperforms native Coarray Fortran.

The Partitioned Global Address Space (PGAS) programming model strikes a balance between the locality-aware, but explicit, message-passing model (e.g. MPI) and the easy-to-use, but locality-agnostic, shared memory model (e.g. OpenMP). However, the PGAS rich memory model comes at a performance cost which can hinder its potential for scalability and performance. To contain this overhead and achieve full performance, compiler optimizations may not be sufficient and manual optimizations are typically added. This, however, can severely limit the productivity advantage. Such optimizations are usually targeted at reducing address translation overheads for shared data structures. This paper proposes a hardware architectural support for PGAS, which allows the processor to efficiently handle shared addresses. This eliminates the need for such hand-tuning, while maintaining the performance and productivity of PGAS languages. We propose to avail this hardware support to compilers by introducing new instructions to efficiently access and traverse the PGAS memory space. A prototype compiler is realized by extending the Berkeley Unified Parallel C (UPC) compiler. It allows unmodified code to use the new instructions without the user intervention, thereby creating a real productive programming environment. Two different implementations of the system are realized: the first is implemented using the full system simulator Gem5, which allows the evaluation of the performance gain. The second is implemented using a soft core processor Leon3 on an FPGA to verify the implement ability and to parameterize the cost of the new hardware and its instructions. The new instructions show promising results for the NAS Parallel Benchmarks implemented in UPC. A speedup of up to 5.5x is demonstrated for unmodified codes. Unmodified code performance using this hardware was shown to also surpass the performance of manually optimized code by up to 10%.

Summary Accelerators have revolutionised the high performance computing (HPC) community. Despite their advantages, their very specific programming models and limited communication capabilities have kept them in a supporting role of the main processors. With the introduction of Xeon Phi, this is no longer true, as it can be programmed as the main processor and has direct access to the InfiniBand network adapter. Collective operations play a key role in many HPC applications. Therefore, studying its behaviour in the context of manycore coprocessors has great importance. This work analyses the performance of different algorithms for broadcast, scatter and gather, in a large-scale Xeon Phi supercomputer. The algorithms evaluated are those available in the reference message passing interface (MPI) implementation for Xeon Phi (Intel MPI), the default algorithm in an optimised MPI implementation (MVAPICH2-MIC), and a new set of algorithms, developed by the authors of this work, designed with modern processors and new communication features in mind. The latter are implemented in Unified Parallel C (UPC), a partitioned global address space language, leveraging one-sided communications, hierarchical trees and message pipelining. This study scales the experiments to 15360 cores in the Stampede supercomputer and compares the results to Xeon and hybrid Xeon + Xeon Phi experiments, with up to 19456 cores. Copyright © 2015 John Wiley & Sons, Ltd.

[Abstract] Detecting epistasis, such as 2-SNP interactions, in genome-wide association studies (GWAS) is an important but time consuming operation. Consequently, GPUs have already been used to accelerate these studies, reducing the runtime for moderately-sized datasets to less than 1 hour. However, single-GPU approaches cannot perform large-scale GWAS in reasonable time. In this work we present multiEpistSearch, a tool to detect epistasis that works on GPU clusters. While CUDA is used for parallelization within each GPU, the workload distribution among GPUs is performed with Unified Parallel C++ (UPC++), a novel extension of C++ that follows the Partitioned Global Address Space (PGAS) model. multiEpistSearch is able to analyze large-scale datasets with 5 million SNPs from 10,000 individuals in less than 3 hours using 24 NVIDIA GTX Titans. London. Wellcome Trust; 076113 London. Wellcome Trust; 085475

In this paper, we developed a computational hydrodynamics (CHD) numerical model based on the Unified Parallel C (UPC) computing architecture. UPC is the extension of ISO C following the Partitioned Global Address Space (PGAS) architecture which harnesses the ease of programming of the shared memory paradigm while enabling the exploitation of data locality. UPC computing stores the data having the affinity with the corresponding computing thread in the local memory section which significantly improves the computational speedup. UPC requires a unique arrangement to achieve the optimal combination of programmability, portability, and performance scalability. The UPC-CHD model is currently governed by the unsteady, laminar, and incompressible Navier–Stokes (NS) equations with domain decomposition. The temporal term is discretized with the two-step explicit scheme from the Lax-Wendroff family of predictor–correctors. The convective fluxes are computed by the ROE scheme with the third-order upwind-biased algorithm, and the viscous terms are discretized with the second-order central differencing scheme. The calculations of the flux predictor and corrector are then distributed using a UPC work-sharing function, which is based on the single-program multiple-data approach (SPMD). The data structure together with the discretization is uniquely arranged for UPC architecture using blocked-cyclic techniques and affinity calculation algorithms. Three reference cases of laminar Blasius boundary layer, Poiseuille’s flow and Couette’s flow were simulated with UPC-CHD. The accuracy of these reference cases was first validated using the respective analytical solution, which was followed by evaluating the model’s computational performance with an SGI UV-2000 server of 100 cores. The speedup results confirm the high efficiency of the proposed computer architecture as compared to other existing ones. With proper optimization, the speed up of the UPC-CHD model is almost 56 times and 5 times faster than the sequential version and sole-UPC version without optimization, respectively.

Although MPI is commonly used for parallel programming on distributed-memory systems, Partitioned Global Address Space (PGAS) approaches are gaining attention for programming modern multi-core CPU clusters. They feature a hybrid memory abstraction: distributed memory is viewed as a shared memory that is partitioned among nodes in order to simplify programming. In this chapter you will learn about Unified Parallel C++ (UPC++), a library-based extension of C++ that gathers the advantages of both PGAS and Object Oriented paradigms. The examples included in this chapter will help you to understand the main features of PGAS languages and how they can simplify the task of programming parallel source code for clusters and supercomputers. In particular, we study UPC++ examples addressing the topics of memory affinity, privatization, remote memory accesses, asynchronous copies, and locks.

This GASNet specification describes a network-independent and language-independent high-performance communication interface intended for use in implementing the runtime system for global address space languages (such as UPC or Titanium).

The Particle-in-Cell (PIC) method is a Particle-Mesh technique that allows to efficiently simulate kinetic models. Among others applications, space weather simulations could be tackled by massively parallel Particle-in-Cell codes, to model the dynamics of space plasma disturbances. However, realistic Particle-Mesh plasma simulations require huge data sets and are computationally expensive. This is why high scalability must be achieved in order to perform the massively parallel plasma simulations required for space weather purposes. In Particle-Mesh techniques such as PIC simulations, computational particles are free to move on a fixed grid mesh and can show important inhomogeneity during computation. This results in an imbalanced work load between different threads that must be tackled. This paper reports on a 2D electrostatic PIC code in Unified Parallel C, developed for both plasma and gravitational simulations. The algorithm includes dynamic load-balancing capabilities. We compare different load-balancing strategies: one based on the particle distribution, and one based on computation time. We also present results of the simulation of the classical two-stream instability, and a simulation of a gravitational clustering experiment triggered by the Jeans instability. It is shown that both dynamic load-balancing based on computation time or on the number of particles are efficient for Particle-Mesh simulations where high particle inhomogeneities occur.

This is a post-peer-review, pre-copyedit version of an article published in The Journal of Supercomputing. The final authenticated version is available online at: https://doi.org/10.1007/s11227-012-0843-1 [Abstract] The simulation of particle dynamics is an essential method to analyze and predict the behavior of molecules in a given medium. This work presents the design and implementation of a parallel simulation of Brownian dynamics with hydrodynamic interactions for shared memory systems using two approaches: (1) OpenMP directives and (2) the Partitioned Global Address Space (PGAS) paradigm with the Unified Parallel C (UPC) language. The structure of the code is described, and different techniques for work distribution are analyzed in terms of efficiency, in order to select the most suitable strategy for each part of the simulation. Additionally, performance results have been collected from two representative NUMA systems, and they are studied and compared against the original sequential code. Ministerio de Ciencia e Innovación; TIN2010-16735 Spanish network CAPAP-H3; TIN2010-12011-E Xunta de Galicia; 2010/6

Constantly increasing hardware parallelism poses more and more challenges to programmers and language designers. One approach to harness the massive parallelism is to move to task-based programming models that rely on runtime systems for dependency analysis and scheduling. Such models generally benefit from the existence of a global address space. This paper presents the parallel memory allocator of the Myrmics runtime system, in which multiple allocator instances organized in a tree hierarchy cooperate to implement a global address space with dynamic region support on distributed memory machines. The Myrmics hierarchical memory allocator is step towards improved productivity and performance in parallel programming. Productivity is improved through the use of dynamic regions in a global address space, which provide a convenient shared memory abstraction for dynamic and irregular data structures. Performance is improved through scaling on manycore systems without system-wide cache coherency. We evaluate the stand-alone allocator on an MPI-based x86 cluster and find that it scales well for up to 512 worker cores, while it can outperform Unified Parallel C by a factor of 3.7-10.7x.

Unified Parallel C (UPC) is a language used to write parallel programs for distributed memory parallel computers. UPC-CHECK ( http://hpcgroup.public.iastate.edu/UPC-CHECK/ ) is a scalable tool developed to automatically detect argument errors in UPC functions and deadlocks in UPC programs at run-time and issue high quality error messages to help programmers quickly fix those errors. The run-time complexity of all detection techniques used are optimal, i.e. O(1) except for deadlocks involving locks where it is theoretically known to be linear in the number of threads. The tool is easy to use, and involves merely replacing the compiler command with upc-check. Error messages issued by UPC-CHECK were evaluated using the UPC RTED test suite for argument errors in UPC functions and deadlocks. Results of these tests show that the error messages issued by UPC-CHECK for these tests are excellent.

The popularity of Partitioned Global Address Space (PGAS) languages has increased during the last years thanks to their high programmability and performance through an efficient exploitation of data locality, especially on hierarchical architectures such as multicore clusters. This paper describes UPCBLAS, a parallel numerical library for dense matrix computations using the PGAS Unified Parallel C language. The routines developed in UPCBLAS are built on top of sequential basic linear algebra subprograms functions and exploit the particularities of the PGAS paradigm, taking into account data locality in order to achieve a good performance. Furthermore, the routines implement other optimization techniques, several of them by automatically taking into account the hardware characteristics of the underlying systems on which they are executed. The library has been experimentally evaluated on a multicore supercomputer and compared with a message-passing-based parallel numerical library, demonstrating good scalability and efficiency. Copyright © 2012 John Wiley & Sons, Ltd.

The popularity of Partitioned Global Address Space (PGAS) languages has increased during the last years thanks to their high programmability and performance through an effcient exploitation of data locality. This paper describes the implementation of effcient parallel dense triangular solvers in the PGAS language Unified Parallel C (UPC). The solvers are built on top of sequential BLAS functions and exploit the particularities of the PGAS paradigm. Furthermore, the numerical routines developed implement an automatic process that adapts the algorithms to the characteristics of the system where they are executed. The triangular solvers have been experimentally evaluated in two different multicore clusters and compared to message-passing based counterparts, demonstrating good scalability and effciency.

An increasing number of supercomputers adopt a heterogeneous architecture, consisting of both general purpose CPUs and specialized accelerators. Such design is beneficial for scalability and power, but on the other hand, heterogeneity brings new challenges in communication systems to connect heterogeneous components and provide support for programming. The communication system of the Dawning 6000 connects two kinds of heterogeneous processors, Loongson and AMD, and adopts a three layer architecture with an intranode layer between heterogeneous components. To efficiently connect heterogeneous components, the system forms a global address space and provides a mechanism for message transmission via an in-node global store; and employing Infiniband network, provides an OS-bypassing virtualization method to share an Infiniband card between nodes. To facilitate programming on heterogeneous processors, it supports unified parallel C (UPC), with a modified complier based on global address space. Also, a special collective network is implemented for collective operations. Results obtained from a prototype system prove these features to be both feasible and efficient.

Proton exchange membrane fuel cells (PEMFCs) have aroused great interest in recent years, in particular for transportation applications. However, fuel cell (FC) technology is not yet ready for large-scale commercial use, as it requires more understanding and intensive development, in particular in the thermal behavior area. Such understanding of the FC requires many large-scale simulations that can take unacceptably large execution time. This is especially true when using traditional models that are governed by heat equations and based on computational tools that derive approximate solutions to partial differential equations. Such multimodel systems also require synchronization that results in overhead. Instead, in this paper, a new fully integrated modeling approach that lends itself to parallelism is introduced. This approach can benefit from advances in parallel computing, and thus dramatically reduce time and enable multiple large simulations. This is called the global nodal method, which is intended to analyze and simulate the thermal behavior of PEMFCs. Parallel simulations are implemented with the message passing interface (MPI) and using the unified parallel C (UPC) language on parallel systems. It will be shown that computation time to conduct thermal behavior in large-scale simulation using MPI and UPC is significantly reduced compared to sequential simulations, and obtained data are highly precise and accurate.

The Partitioned Global Address Space (PGAS) model of Unified Parallel C (UPC) can help users express and manage application data locality on non-uniform memory access (NUMA) multi-core shared-memory systems to get good performance. First, we describe several UPC program optimization techniques that are important to achieving good performance on NUMA multi-core computers with examples and quantitative performance results. Second, we use two numerical computing kernels, parallel matrix–matrix multiplication and parallel 3-D FFT, to demonstrate the end-to-end development and optimization for UPC applications. Our results show that the optimized UPC programs achieve very good and scalable performance on current multi-core systems and can even outperform vendor-optimized libraries in some cases.

De novo whole genome assembly reconstructs genomic sequences from short, overlapping, and potentially erroneous DNA segments and is one of the most important computations in modern genomics. This work presents HipMer, the first high-quality end-to-end de novo assembler designed for extreme scale analysis, via efficient parallelization of the Meraculous code. First, we significantly improve scalability of parallel k-mer analysis for complex repetitive genomes that exhibit skewed frequency distributions. Next, we optimize the traversal of the de Bruijn graph of k-mers by employing a novel communication-avoiding parallel algorithm in a variety of use-case scenarios. Finally, we parallelize the Meraculous scaffolding modules by leveraging the one-sided communication capabilities of the Unified Parallel C while effectively mitigating load imbalance. Large-scale results on a Cray XC30 using grand-challenge genomes demonstrate efficient performance and scalability on thousands of cores. Overall, our pipeline accelerates Meraculous performance by orders of magnitude, enabling the complete assembly of the human genome in just 8.4 minutes on 15K cores of the Cray XC30, and creating unprecedented capability for extreme-scale genomic analysis.

The main motivation of this work is the evaluation of the Unified Parallel C (UPC) model, for Boltzmann-fluid simulations. UPC is one of the current models in the so-called Partitioned Global Address Space paradigm. This paradigm attempts to increase the simplicity of codes and achieve a better efficiency and scalability. Two different UPC-based implementations, explicit and implicit, are presented and evaluated. We compare the fundamental features of our UPC implementations with other parallel programming model, MPI-OpenMP. In particular each of the major steps of any LBM code, i.e., Boundary Conditions, Communication, and LBM solver, are analyzed.

© 2015 IEEE. Aligning a set of query sequences to a set of target sequences is an important task in bioinformatics. In this work we present merAligner, a highly parallel sequence aligner that implements a seed-and-extend algorithm and employs parallelism in all of its components. MerAligner relies on a high performance distributed hash table (seed index) and uses onesided communication capabilities of the Unified Parallel C to facilitate a fine-grained parallelism. We leverage communication optimizations at the construction of the distributed hash table and software caching schemes to reduce communication during the aligning phase. Additionally, merAligner preprocesses the target sequences to extract properties enabling exact sequence matching with minimal communication. Finally, we efficiently parallelize the I/O intensive phases and implement an effective load balancing scheme. Results show that merAligner exhibits efficient scaling up to thousands of cores on a Cray XC30 supercomputer using real human and wheat genome data while significantly outperforming existing parallel alignment tools.

The Partitioned Global Address Space (PGAS) approach is a promising programming model in high performance parallel computing that combines the advantages of distributed memory systems and shared memory systems. The PGAS model has been used on a variety of hardware platforms in the form of PGAS programming languages like Unified Parallel C (UPC), Chapel and Fortress. However, in spite of the increasing adoption in distributed and shared memory systems, the extension of the PGAS model to accelerator platforms is still not well supported. To exploit the immense computational power of multi-GPU systems, this work is concerned with the design and implementation of a Partitioned Global Address Space model for multi-GPU systems. Several issues related to the combination of logically separate GPU memories on multiple graphic cards are addressed. Furthermore, the execution model of modern GPU architectures is studied and a task creation mechanism with load balancing is proposed. Our work is implemented in the context of the DASH project, a C++ template library that realizes PGAS semantics through operator overloading. Experimental results suggest promising performance of the design and its implementation.

Unified Parallel C (UPC) is an explicit parallel extension to ISO C which follows the Partitioned Global Address Space (PGAS) programming model. UPC, therefore, combines the ability to express parallelism while exploiting locality. To do so, compilers must embody effective UPC-specific optimizations. In this paper we present a strategy for evaluating the performance of PGAS compilers. It is based on emulating possible optimizations and comparing the performance to the raw compiler performance. It will be shown that this technique uncovers missed optimization opportunities. The results also demonstrate that, with such automatic optimizations, the UPC performance will be compared favorably with other paradigms.

It is now well established that the device scaling predicted by Moore's Law is no longer a viable option for increasing the clock frequency of future uniprocessor systems at the rate that had been sustained during the last two decades. As a result, future systems are rapidly moving from uniprocessor to multiprocessor configurations, so as to use parallelism instead of frequency scaling as the foundation for increased compute capacity. The dominant emerging multiprocessor structure for the future is a Non-Uniform Cluster Computing (NUCC) system with nodes that are built out of multi-core SMP chips with non-uniform memory hierarchies, and interconnected in horizontally scalable cluster configurations such as blade servers. Unlike previous generations of hardware evolution, this shift will have a major impact on existing software. Current OO language facilities for concurrent and distributed programming are inadequate for addressing the needs of NUCC systems because they do not support the notions of non-uniform data access within a node, or of tight coupling of distributed nodes.We have designed a modern object-oriented programming language, X10, for high performance, high productivity programming of NUCC systems. A member of the partitioned global address space family of languages, X10 highlights the explicit reification of locality in the form of places }; lightweight activities embodied in async , future , foreach , and ateach constructs; a construct for termination detection ( finish ); the use of lock-free synchronization ( atomic blocks ); and the manipulation of cluster-wide global data structures. We present an overview of the X10 programming model and language, experience with our reference implementation, and results from some initial productivity comparisons between the X10 and Java™ languages.

The aim of this paper is to present a qualitative evaluation of three state-of-the-art parallel languages: OpenMP, Unified Parallel C (UPC) and Co-Array Fortran (CAF). OpenMP and UPC are explicit parallel programming languages based on the ANSI standard. CAF is an implicit programming language. On the one hand, OpenMP designs for shared-memory architectures and extends the base-language by using compiler directives that annotate the original source-code. On the other hand, UPC and CAF designs for distribute-shared memory architectures and extends the base-language by new parallel constructs. We deconstruct each language into its basic components, show examples, make a detailed analysis, compare them, and finally draw some conclusions.

Partitioned Global Address Space (PGAS) languages are a popular alternative when building applications to run on large scale parallel machines. Unified Parallel C (UPC) is a well known PGAS language that is available on most high performance computing systems. Good performance of UPC applications is often one important requirement for a system acquisition. This paper presents the memory management techniques employed by the IBM XL UPC compiler to achieve optimal performance on systems with Remote Direct Memory Access (RDMA). Additionally we describe a novel technique employed by the UPC runtime for transforming remote memory accesses on a same shared memory node into local memory accesses, to further improve performance. We evaluate the proposed memory allocation policies for various UPC benchmarks and using the IBM® Power® 775 supercomputer [1].

We are proposing a novel framework that amelio-rates locality-aware parallel programming models, by defining a hierarchical data locality model extension. We also propose two hierarchical thread partitioning algorithms. These algorithms synthesize hierarchical thread placement layouts that targets minimizing the program's overall communication costs. We demonstrate the effectiveness of our approach using the NAS Parallel Benchmarks implemented in Unified Parallel C (UPC) using a modified Berkeley UPC Compiler and runtime system. We achieved performance gains of up to 88% in performance by applying the placement layouts our algorithms suggest.

De novo whole genome assembly reconstructs genomic sequence from short, overlapping, and potentially erroneous fragments called reads. We study optimized parallelization of the most time-consuming phases of Meraculous, a state of-the-art production assembler. First, we present a new parallel algorithm for k-mer analysis, characterized by intensive communication and I/O requirements, and reduce the memory requirements by 6.93×. Second, we efficiently parallelize de Bruijn graph construction and traversal, which necessitates a distributed hash table and is a key component of most de novo assemblers. We provide a novel algorithm that leverages one-sided communication capabilities of the Unified Parallel C (UPC) to facilitate the requisite fine-grained parallelism and avoidance of data hazards, while analytically proving its scalability properties. Overall results show unprecedented performance and efficient scaling on up to 15,360 cores of a Cray XC30, on human genome as well as the challenging wheat genome, with performance improvement from days to seconds.

Programs written in Partitioned Global Address Space (PGAS) languages can access any location of the entire address space via standard read/write operations. However, the compiler have to create the communication mechanisms and the runtime system to use synchronization primitives to ensure the correct execution of the programs. However, PGAS programs may have fine-grained shared accesses that lead to performance degradation. One solution is to use the inspector-executor technique to determine which accesses are indeed remote and which accesses may be coalesced in larger remote access operations. A straightforward implementation of the inspector-executor in a PGAS system may result in excessive instrumentation that hinders performance. This paper introduces a shared-data localization transformation based on linear memory descriptors (LMADs) that reduces the amount of instrumentation introduced by the compiler into programs written in the UPC language and describes a prototype implementation of the proposed transformation. A performance evaluation, using up to 2048 cores of a POWER 775 supercomputer, allows for a prediction that applications with regular accesses can achieve up to 180% of the performance of handoptimized versions while applications with irregular accesses yield performance gain from 1.12X up to 6.3X speedup.

We are proposing a novel framework that ameliorates locality-aware parallel programming models, by defining hierarchical data locality model extension. We also propose a hierarchical thread partitioning algorithm. This algorithm synthesizes hierarchical thread placement layouts that targets minimizing the program's overall communication costs. We demonstrated the effectiveness of our approach using NAS Parallel Benchmarks implemented in Unified Parallel C (UPC) language using a modified Berkeley UPC Compiler and runtime system. We demonstrated an up to 85% improvement in performance by applying the placement layout suggested by our algorithm.

This paper presents the application of the PCJ library for the parallelization of the selected HPC applications implemented in Java language. The library is motivated by partitioned global address space (PGAS) model represented by Co-Array Fortran, Unified Parallel C, X10 or Titanium. In the PCJ, each task has its own local memory and stores and access variables locally. Variables can be shared between tasks and can be accessed, read and modified by other tasks. The library provides methods to perform basic operations like synchronization of tasks, get and put values in asynchronous onesided way. Additionally the library offers methods for creating groups of tasks, broadcasting and monitoring variables. The PCJ has ability to work on the multinode multicore systems hiding details of interand intranode communication. The PCJ library fully complies with Java standards therefore the programmer does not have to use additional libraries, which are not part of the standard Java distribution. In this paper the PCJ library has been used to run example HPC applications on the multicore nodes. In particular we present performance results for parallel raytracing, matrix multiplication and map-reduce calculations. The detailed information on performance of the reduction operation is also presented. The results show good performance and scalability compared to native implementations of the same algorithms. In particular, MPI C++ and Java 8 parallel streams have been used as a reference. It is noteworthy that the PCJ library due to its performance and ability to create simple code has great promise to be successful for parallelization of the HPC applications.

InfiniBand is widely used for low-latency, high-throughput cluster computing. Saving the state of the InfiniBand network as part of distributed checkpointing has been a long-standing challenge for researchers. Because of a lack of a solution, typical MPI implementations have included custom checkpoint-restart services that "tear down" the network, checkpoint each node as if the node were a standalone computer, and then re-connect the network again. We present the first example of transparent, system-initiated checkpoint-restart that directly supports InfiniBand. The new approach is independent of any particular Linux kernel, thus simplifying the current practice of using a kernel-based module, such as BLCR. This direct approach results in checkpoints that are found to be faster than with the use of a checkpoint-restart service. The generality of this approach is shown not only by checkpointing an MPI computation, but also a native UPC computation (Berkeley Unified Parallel C), which does not use MPI. Scalability is shown by checkpointing 2,048 MPI processes across 128 nodes (with 16 cores per node). In addition, a cost-effective debugging approach is also enabled, in which a checkpoint image from an InfiniBand-based production cluster is copied to a local Ethernet-based cluster, where it can be restarted and an interactive debugger can be attached to it. This work is based on a plugin that extends the DMTCP (Distributed MultiThreaded CheckPointing) checkpoint-restart package., Comment: 22 pages, 2 figures, 9 tables

The past decade has seen the advent of a number of parallel programming models such as Coarray Fortran (CAF), Unified Parallel C, X10, and Chapel. Despite the productivity gains promised by these models, most parallel scientific applications still rely on MPI as their data movement model. One reason for this trend is that it is hard for users to incrementally adopt these new programming models in existing MPI applications. Because each model use its own runtime system, they duplicate resources and are potentially error-prone. Such independent runtime systems were deemed necessary because MPI was considered insufficient in the past to play this role for these languages.The recently released MPI-3, however, adds several new capabilities that now provide all of the functionality needed to act as a runtime, including a much more comprehensive one-sided communication framework. In this paper, we investigate how MPI-3 can form a runtime system for one example programming model, CAF, with a broader goal of enabling a single application to use both MPI and CAF with the highest level of interoperability.