Heterogeneous many-cores are now an integral part of modern computing systems ranging from embedding systems to supercomputers. While heterogeneous many-core design offers the potential for energy-efficient high-performance, such potential can only be unlocked if the application programs are suitably parallel and can be made to match the underlying heterogeneous platform. In this article, we provide a comprehensive survey for parallel programming models for heterogeneous many-core architectures and review the compiling techniques of improving programmability and portability. We examine various software optimization techniques for minimizing the communicating overhead between heterogeneous computing devices. We provide a road map for a wide variety of different research areas. We conclude with a discussion on open issues in the area and potential research directions. This article provides both an accessible introduction to the fast-moving area of heterogeneous programming and a detailed bibliography of its main achievements.
We present a new programming paradigm which can be useful, in particular, for implementing window interfaces and parallel algorithms. This paradigm allows a user to define operators which can contain nested operators. The new paradigm is called operator-oriented. One of the goals of this paradigm is to escape the complexity of objects definitions inherent in many object-oriented languages and to move to transparent algorithms definitions.
We introduce process-oriented programming as a natural extension of object-oriented programming for parallel computing. It is based on the observation that every class of an object-oriented language can be instantiated as a process, accessible via a remote pointer. The introduction of process pointers requires no syntax extension, identifies processes with programming objects, and enables processes to exchange information simply by executing remote methods. Process-oriented programming is a high-level language alternative to multithreading, MPI and many other languages, environments and tools …
As the hardware industry moves towards using specialized heterogeneous many-cores to avoid the effects of the power wall, software developers are finding it hard to deal with the complexity of these systems. This article shares our experience when developing a programming model and its supporting compiler and libraries for Matrix-3000, which is designed for next-generation exascale supercomputers but has a complex memory hierarchy and processor organization. To assist its software development, we developed a software stack from scratch that includes a low-level programming interface and a high…
Local search is a successful approach for solving combinatorial optimization and constraint satisfaction problems. With the progressing move toward multi and many-core systems, GPUs and the quest for Exascale systems, parallelism has become mainstream as the number of cores continues to increase. New programming models are required and need to be better understood as well as data structures and algorithms. Such is the case for local search algorithms when run on hundreds or thousands of processing units. In this paper, we discuss some experiments we have been doing with Adaptive Search and pre…
Program correctness is one of the most difficult challenges in parallel programming. Message Passing Interface MPI is widely used in writing parallel applications. Since MPI is not a compiled language, the programmer will be enfaced with several programming bugs.This paper presents the most common programming bugs arise in MPI programs to help the programmer to compromise between the advantage of parallelism and the extra effort needed to detect and fix such bugs. An algebraic specification of an MPI-like programming language, called Simple MPI (SMPI), to be used in writing MPI programs specif…
Image convolution is widely used for sharpening, blurring and edge detection. In this paper, we review two common algorithms for convolving a 2D image by a separable kernel (filter). After optimising the naive codes using loop unrolling and SIMD vectorisation, we choose the algorithm with better performance as the baseline for parallelisation. We then compare the parallel performance of the optimised code using OpenMP, OpenCL and GPRM implementations on the Intel Xeon Phi. We also measure the effects of optimisation techniques and demonstrate how they affect both sequential and parallel perfor…
Hardware heterogeneity is here to stay for high-performance computing. Large-scale systems are currently equipped with multiple GPU accelerators per compute node and are expected to incorporate more specialized hardware in the future. This shift in the computing ecosystem offers many opportunities for performance improvement; however, it also increases the complexity of programming for such architectures. This work introduces a runtime framework that enables effortless programming for heterogeneous systems while efficiently utilizing hardware resources. The framework is integrated within a dis…
We present the Glasgow Parallel Reduction Machine (GPRM), a novel, flexible framework for parallel task-composition based many-core programming. We allow the programmer to structure programs into task code, written as C++ classes, and communication code, written in a restricted subset of C++ with functional semantics and parallel evaluation. In this paper we discuss the GPRM, the virtual machine framework that enables the parallel task composition approach. We focus the discussion on GPIR, the functional language used as the intermediate representation of the bytecode running on the GPRM. Usin…
A novel approach is presented to teach the parallel and distributed computing concepts of synchronization and remote memory access. The single program multiple data (SPMD) partitioned global address space (PGAS) model presented in this paper uses a procedural programming language appealing to undergraduate students. We propose that the amusing nature of the approach may engender creativity and interest using these concepts later in more sober environments. Specifically, we implement parallel extensions to LOLCODE within a source-to-source compiler sufficient for the development of parallel and…
This paper investigates session programming and typing of benchmark examples to compare productivity, safety and performance with other communications programming languages. Parallel algorithms are used to examine the above aspects due to their extensive use of message passing for interaction, and their increasing prominence in algorithmic research with the rising availability of hardware resources such as multicore machines and clusters. We contribute new benchmark results for SJ, an extension of Java for type-safe, binary session programming, against MPJ Express, a Java messaging system base…
Climbing Mont Blanc (CMB) is an open online judge used for training in energy efficient programming of state-of-the-art heterogeneous multicores. It uses an Odroid-XU3 board from Hardkernel with an Exynos Octa processor and integrated power sensors. This processor is three-way heterogeneous containing 14 different cores of three different types. The board currently accepts C and C++ programs, with support for OpenCL v1.1, OpenMP 4.0 and Pthreads. Programs submitted using the graphical user interface are evaluated with respect to time, energy used, and energy-efficiency (EDP). A small and varie…
We introduce SparkCL, an open source unified programming framework based on Java, OpenCL and the Apache Spark framework. The motivation behind this work is to bring unconventional compute cores such as FPGAs/GPUs/APUs/DSPs and future core types into mainstream programming use. The framework allows equal treatment of different computing devices under the Spark framework and introduces the ability to offload computations to acceleration devices. The new framework is seamlessly integrated into the standard Spark framework via a Java-OpenCL device programming layer which is based on Aparapi and a …
Heterogeneity is omnipresent in today's commodity computational systems, which comprise at least one multi-core Central Processing Unit (CPU) and one Graphics Processing Unit (GPU). Nonetheless, all this computing power is not being exploited in mainstream computing, as the programming of these systems entails many details of the underlying architecture and of its distinct execution models. Current research on parallel programming is addressing these issues but, still, the systems' heterogeneity is exposed at language level. This paper proposes a uniform framework, grounded on the Single Opera…
The complexity of heterogeneous computing architectures, as well as the demand for productive and portable parallel application development, have driven the evolution of parallel programming models to become more comprehensive and complex than before. Enhancing the conventional compilation technologies and software infrastructure to be parallelism-aware has become one of the main goals of recent compiler development. In this paper, we propose the design of unified parallel intermediate representation (UPIR) for multiple parallel programming models and for enabling unified compiler transformati…
In this paper, we discuss the educational value of a few mid-size and one large applied research projects at the Computer Science Department of Okanagan College (OC) and at the Universities of Paris East Creteil (LACL) and Orleans (LIFO) in France. We found, that some freshmen students are very active and eager to be involved in applied research projects starting from the second semester. They are actively participating in programming competitions and want to be involved in applied research projects to compete with sophomore and older students. Our observation is based on five NSERC Engage Col…
Pipeline is a fundamental parallel programming pattern. Mainstream pipeline programming frameworks count on data abstractions to perform pipeline scheduling. This design is convenient for data-centric pipeline applications but inefficient for algorithms that only exploit task parallelism in pipeline. As a result, we introduce a new task-parallel pipeline programming framework called Pipeflow. Pipeflow does not design yet another data abstraction but focuses on the pipeline scheduling itself, enabling more efficient implementation of task-parallel pipeline algorithms than existing frameworks. W…
Parametric linear programming is central in polyhedral computations and in certain control applications.We propose a task-based scheme for parallelizing it, with quasi-linear speedup over large problems.
High Performance Computing is notorious for its long and expensive software development cycle. To address this challenge, we present Bind: a "partitioned global workflow" parallel programming model for C++ applications that enables quick prototyping and agile development cycles for high performance computing software targeting heterogeneous distributed many-core architectures. We present applications of Bind to Linear Algebra and MapReduce algorithms alongside with performance results.
We discuss the use of both MPI and OpenMP in the teaching of senior undergraduate and junior graduate classes in parallel programming. We briefly introduce the OpenMP standard and discuss why we have chosen to use it in parallel programming classes. Advantages of using OpenMP over message passing methods are discussed. We also include a brief enumeration of some of the drawbacks of using OpenMP and how these drawbacks are being addressed by supplementing OpenMP with additional MPI codes and projects. Several projects given in my class are also described in this paper.
The current trend of multicore architectures on shared memory systems underscores the need of parallelism. While there are some programming model to express parallelism, thread programming model has become a standard to support these system such as OpenMP, and POSIX threads. MPI (Message Passing Interface) which remains the dominant model used in high-performance computing today faces this challenge. Previous version of MPI which is MPI-1 has no shared memory concept, and Current MPI version 2 which is MPI-2 has a limited support for shared memory systems. In this research, MPI-2 version of MP…
The pervasive adoption of Deep Learning (DL) and Graph Processing (GP) makes it a de facto requirement to build large-scale clusters of heterogeneous accelerators including GPUs and FPGAs. The OpenCL programming framework can be used on the individual nodes of such clusters but is not intended for deployment in a distributed manner. Fortunately, the original OpenCL semantics naturally fit into the programming environment of heterogeneous clusters. In this paper, we propose a heterogeneity-aware OpenCL-like (HaoCL) programming framework to facilitate the programming of a wide range of scientifi…
Real-time systems applications usually consist of a set of concurrent activities with timing-related properties. Developing these applications requires programming paradigms that can effectively handle the specification of concurrent activities and timing constraints, as well as controlling their execution on a particular platform. The prevailing trend for high-performance, and the use of fine-grained parallel execution makes this an even more challenging task. This paper provides an overview of the state-of-the-art and challenges for the development of real-time parallel applications, focusin…
Parsl is a parallel programming library for Python that aims to make it easy to specify parallelism in programs and to realize that parallelism on arbitrary parallel and distributed computing systems. Parsl relies on developers annotating Python functions-wrapping either Python or external applications-to indicate that these functions may be executed concurrently. Developers can then link together functions via the exchange of data. Parsl establishes a dynamic dependency graph and sends tasks for execution on connected resources when dependencies are resolved. Parsl's runtime system enables di…
Università di Udine（乌迪内大学）；GNCS-INdAM（意大利国家高等数学研究院-国家科学计算小组）；University of Texas at Dallas（德克萨斯大学达拉斯分校）；IMDEA Software Institute（IMDEA 软件研究所）；Universidad Politécnica de Madrid（马德里理工大学）；New Mexico State University（新墨西哥州立大学）；CRACS/INESC TEC（CRACS/INESC TEC 研究所）；University of Porto（波尔图大学）
Multi-core and highly-connected architectures have become ubiquitous, and this has brought renewed interest in language-based approaches to the exploitation of parallelism. Since its inception, logic programming has been recognized as a programming paradigm with great potential for automated exploitation of parallelism. The comprehensive survey of the first twenty years of research in parallel logic programming, published in 2001, has served since as a fundamental reference to researchers and developers. The contents are quite valid today, but at the same time the field has continued evolving …
This paper presents an overview of the "Applied Parallel Computing" course taught to final year Software Engineering undergraduate students in Spring 2014 at NUST, Pakistan. The main objective of the course was to introduce practical parallel programming tools and techniques for shared and distributed memory concurrent systems. A unique aspect of the course was that Java was used as the principle programming language. The course was divided into three sections. The first section covered parallel programming techniques for shared memory systems that include multicore and Symmetric Multi-Process…
In the past decade, high performance compute capabilities exhibited by heterogeneous GPGPU platforms have led to the popularity of data parallel programming languages such as CUDA and OpenCL. Such languages, however, involve a steep learning curve as well as developing an extensive understanding of the underlying architecture of the compute devices in heterogeneous platforms. This has led to the emergence of several High Performance Computing frameworks which provide high-level abstractions for easing the development of data-parallel applications on heterogeneous platforms. However, the schedu…
Current high-performance computer systems used for scientific computing typically combine shared memory computational nodes in a distributed memory environment. Extracting high performance from these complex systems requires tailored approaches. Task based parallel programming has been successful both in simplifying the programming and in exploiting the available hardware parallelism for shared memory systems. In this paper we focus on how to extend task parallel programming to distributed memory systems. We use a hierarchical decomposition of tasks and data in order to accommodate the differe…
Parametric linear programming is a central operation for polyhedral computations, as well as in certain control applications.Here we propose a task-based scheme for parallelizing it, with quasi-linear speedup over large problems.This type of parallel applications is challenging, because several tasks mightbe computing the same region. In this paper, we are presenting thealgorithm itself with a parallel redundancy elimination algorithm, andconducting a thorough performance analysis.
The advent of high performance computing (HPC) and graphics processing units (GPU), present an enormous computation resource for Large data transactions (big data) that require parallel processing for robust and prompt data analysis. While a number of HPC frameworks have been proposed, parallel programming models present a number of challenges, for instance, how to fully utilize features in the different programming models to implement and manage parallelism via multi-threading in both CPUs and GPUs. In this paper, we take an overview of three parallel programming models, CUDA, MapReduce, and …
This paper introduces an effort to incorporate reconfigurable logic (FPGA) components into a software programming model. For this purpose, we have implemented a hardware engine for remote memory communication between hardware computation nodes and CPUs. The hardware engine is compatible with the API of GASNet, a popular communication library used for parallel computing applications. We have further implemented our own x86 and ARMv7 software versions of the GASNet Core API, enabling us to write distributed applications with software and hardware GASNet components transparently communicating wit…
Embarrassingly parallel problems can be split in parts that are characterized by a really low (or sometime absent) exchange of information during their computation in parallel. As a consequence they can be effectively computed in parallel exploiting commodity hardware, hence without particularly sophisticated interconnection networks. Basically, this means Clusters, Networks of Workstations and Desktops as well as Computational Clouds. Despite the simplicity of this computational model, it can be exploited to compute a quite large range of problems. This paper describes JJPF, a tool for develo…
The processor accelerators are effective because they are working not (completely) on principles of stored program computers. They use some kind of parallelism, and it is rather hard to program them effectively: a parallel architecture by means of (and thinking in) sequential programming. The recently introduced EMPA architecture uses a new kind of parallelism, which offers the potential of reaching higher degree of parallelism, and also provides extra possibilities and challenges. It not only provides synchronization and inherent parallelization, but also takes over some duties typically offe…
Data-flow is a natural approach to parallelism. However, describing dependencies and control between fine-grained data-flow tasks can be complex and present unwanted overheads. TALM (TALM is an Architecture and Language for Multi-threading) introduces a user-defined coarse-grained parallel data-flow model, where programmers identify code blocks, called super-instructions, to be run in parallel and connect them in a data-flow graph. TALM has been implemented as a hybrid Von Neumann/data-flow execution system: the \emph{Trebuchet}. We have observed that TALM's usefulness largely depends on how p…
Interdisciplinary Centre for Security, Reliability and Trust (SnT)（安全、可靠性与信任跨学科中心（SnT））；University of Luxembourg（卢森堡大学）
The number of cores on graphical computing units (GPUs) is reaching thousands nowadays, whereas the clock speed of processors stagnates. Unfortunately, constraint programming solvers do not take advantage yet of GPU parallelism. One reason is that constraint solvers were primarily designed within the mental frame of sequential computation. To solve this issue, we take a step back and contribute to a simple, intrinsically parallel, lock-free and formally correct programming language based on concurrent constraint programming. We then re-examine parallel constraint solving on GPUs within this fo…
Heterogeneous clusters with nodes containing one or more accelerators, such as GPUs, have become common. While MPI provides inter-address space communication, and OpenCL provides a process with access to heterogeneous computational resources, programmers are forced to write hybrid programs that manage the interaction of both of these systems. This paper describes an array programming interface that provides users with automatic and manual distributions of data and work. Using work distribution and kernel def and use information, communication among processes and devices in a process is perform…
In this paper we present Ethane, a parallel search algorithm specifically designed for its execution on heterogeneous hardware environments. With Ethane we propose an algorithm inspired in the structure of the chemical compound of the same name, implementing a heterogeneous island model based in the structure of its chemical bonds. We also propose a schema for describing a family of parallel heterogeneous metaheuristics inspired by the structure of hydrocarbons in Nature, HydroCM (HydroCarbon inspired Metaheuristics), establishing a resem- blance between atoms and computers, and between chemic…
It has been shown that the parallel Lattice Linear Predicate (LLP) algorithm solves many combinatorial optimization problems such as the shortest path problem, the stable marriage problem and the market clearing price problem. In this paper, we give the parallel LLP algorithm for many dynamic programming problems. In particular, we show that the LLP algorithm solves the longest subsequence problem, the optimal binary search tree problem, and the knapsack problem. Furthermore, the algorithm can be used to solve the constrained versions of these problems so long as the constraints are lattice li…
Data layouts play a crucial role in determining the performance of a given application running on a given architecture. Existing parallel programming frameworks for both multicore and heterogeneous systems leave the onus of selecting a data layout to the programmer. Therefore, shifting the burden of data layout selection to optimizing compilers can greatly enhance programmer productivity and application performance. In this work, we introduce {\ADHA}: a two-level hierarchal formulation of the data layout problem for modern heterogeneous architectures. We have created a reference implementation…
Graphics processing units (GPU) had evolved from a specialized hardware capable to render high quality graphics in games to a commodity hardware for effective processing blocks of data in a parallel schema. This evolution is particularly interesting for scientific groups, which traditionally use mainly CPU as a work horse, and now can profit of the arrival of GPU hardware to HPC clusters. This new GPU hardware promises a boost in peak performance, but it is not trivial to use. In this article a programming platform designed to promote a direct use of this specialized hardware is presented. Thi…
This paper presents a parallel genetic algorithm for three dimensional bin packing with heterogeneous bins using Hadoop Map-Reduce framework. The most common three dimensional bin packing problem which packs given set of boxes into minimum number of equal sized bins is proven to be NP Hard. The variation of three dimensional bin packing problem that allows heterogeneous bin sizes and rotation of boxes is computationally more harder than common three dimensional bin packing problem. The proposed Map-Reduce implementation helps to run the genetic algorithm for three dimensional bin packing with …
Heterogeneous computing is emerging as a mandatory requirement for power-efficient system design. With this aim, modern heterogeneous platforms like Zynq All-Programmable SoC, that integrates ARM-based SMP and programmable logic, have been designed. However, those platforms introduce large design cycles consisting on hardware/software partitioning, decisions on granularity and number of hardware accelerators, hardware/software integration, bitstream generation, etc. This paper presents a performance parallel heterogeneous estimation for systems where hardware/software co-design and run-time he…
The development of Internet wide resources for general purpose parallel computing poses the challenging task of matching computation and communication complexity. A number of parallel computing models exist that address this for traditional parallel architectures, and there are a number of emerging models that attempt to do this for large scale Internet-based systems like computational grids. In this survey we cover the three fundamental aspects -- application, architecture and model, and we show how they have been developed over the last decade. We also cover programming tools that are curren…
The Adapteva Epiphany many-core architecture comprises a 2D tiled mesh Network-on-Chip (NoC) of low-power RISC cores with minimal uncore functionality. It offers high computational energy efficiency for both integer and floating point calculations as well as parallel scalability. Yet despite the interesting architectural features, a compelling programming model has not been presented to date. This paper demonstrates an efficient parallel programming model for the Epiphany architecture based on the Message Passing Interface (MPI) standard. Using MPI exploits the similarities between the Epiphan…
Many modern parallel computing systems are heterogeneous at their node level. Such nodes may comprise general purpose CPUs and accelerators (such as, GPU, or Intel Xeon Phi) that provide high performance with suitable energy-consumption characteristics. However, exploiting the available performance of heterogeneous architectures may be challenging. There are various parallel programming frameworks (such as, OpenMP, OpenCL, OpenACC, CUDA) and selecting the one that is suitable for a target context is not straightforward. In this paper, we study empirically the characteristics of OpenMP, OpenACC…
This paper presents HALO 1.0, an open-ended extensible multi-agent software framework that implements a set of proposed hardware-agnostic accelerator orchestration (HALO) principles. HALO implements a novel compute-centric message passing interface (C^2MPI) specification for enabling the performance portable execution of a hardware-agnostic host application across heterogeneous accelerators. The experiment results of evaluating eight widely used HPC subroutines based on Intel Xeon E5-2620 CPUs, Intel Arria 10 GX FPGAs, and NVIDIA GeForce RTX 2080 Ti GPUs show that HALO 1.0 allows for a unified…
This paper proposes a general formulation for temporal parallelisation of dynamic programming for optimal control problems. We derive the elements and associative operators to be able to use parallel scans to solve these problems with logarithmic time complexity rather than linear time complexity. We apply this methodology to problems with finite state and control spaces, linear quadratic tracking control problems, and to a class of nonlinear control problems. The computational benefits of the parallel methods are demonstrated via numerical simulations run on a graphics processing unit.
Task based parallel programming has shown competitive outcomes in many aspects of parallel programming such as efficiency, performance, productivity and scalability. Different approaches are used by different software development frameworks to provide these outcomes to the programmer, while making the underlying hardware architecture transparent to her. However, since programs are not portable between these frameworks, using one framework or the other is still a vital decision by the programmer whose concerns are expandability, adaptivity, maintainability and interoperability of the programs. …
