HPC the easy way: new technologies for high performance application development and deployment

We consider the application of parallel programming environments to develop portable and efficient high performance data mining (DM) tools. We first assess the need of parallel and distributed DM applications, by pointing out the problems of scalability of some mining techniques and the need to mine large, eventually geographically distributed databases. We discuss the main issues of exploiting parallel and distributed computation for DM algorithms. A high-level programming language enhances the software engineering aspects of parallel DM, and it simplifies the problems of integration with existing sequential and parallel data management systems, thus leading to programming-efficient and high-performance implementations of applications. We describe a programming environment we have implemented that is based on the parallel skeleton model, and we examine the addition of object-like interfaces toward external libraries and system software layers. This kind of abstractions will be included in the forthcoming programming environment ASSIST. In the main part of the chapter, as a proof-of-concept we describe three well-known DM algorithms, Apriori, C4.5, and DBSCAN. For each problem, we explain the sequential algorithm and a structured parallel version, which is discussed and compared to parallel solutions found in the literature. We also discuss the potential gain in performance and expressiveness from the addition of external objects on the basis of the experiments we performed so far. We evaluate the approach with respect to performance results, design, and implementation considerations.

Genericity of parallel programming environments, enabling development of portable parallel programs, is expected to result in performance penalties. Furthermore, programmability and tool support of programming environments are important issues if a choice between programming environments has to be made. In this paper we propose a methodology to compare native and generic parallel programming environments, taking into account such competing issues as portability and performance. As a case study, this paper compares the Iserver-Occam, Parix, Express and PVM parallel programming environments on a 512-node Parasytec GCel. Furthermore, we apply our methodology to compare Parix and PVM on a new architecture, a 32-node Parsytec PowerXplorer, which is based on the PowerPC chip. In our approach we start with a representative application and isolate the basic (environment)-dependent building blocks. These basic building blocks, which depend on floating-point performance and communication capabilities of the environments, are analysed independently. We have measured point-to-point communication times, global communication times and floating-point performance. All information is combined into a time complexity analysis, allowing comparison of the environments on different degrees of functionality. Together with demands for portability of the code and development time (i.e. programmability), an overall judgement of the environments is given.

Smart environments demand novel paradigms offering easy configuration, programming and deployment of pervasive applications. To this purpose, different solutions have been proposed ranging from visual paradigms based on mashups to formal languages. However, most of the paradigms proposed in the literature require further external tools to turn application description code into an executable program before the deployment on target devices. Source code generation, runtime upgrades and recovery, and online debugging and inspection are often cumbersome in these programming environments. In this work we describe a methodology for real-time and on-line programming in smart environments that is compact and efficient enough to run on resource-constrained devices. The pillar of the proposed approach is real-time exchange of executable symbolic code in heterogeneous networks. The methodology is supported by an inference engine that is able to generate symbolic code starting from knowledge about hardware devices and their placement in the environment, and about the application domain. Interoperability with existing smart applications and Internet of Things (IoT) deployments is reached through a symbolic Transmission Control Protocol (TCP) client, and Message Queue Telemetry Transport (MQTT) client.

Today, security is recognized as an absolute need in application development. Programming environments offer mechanisms and concepts allowing an easy integration of security mechanisms into the application. However, this often has to be done by hand, resulting in extra effort that has to be made during the development cycle. Furthermore, the code is popped up with statements that enforce application or site-specific security requirements, having negative impact on the reusability and maintainability of the code. The goal of This work is to promote the usage of declarative security mechanisms which allow the decoupling of security logic completely from the application logic. Furthermore, the framework GAMMA is presented, that offers several declarative authentication, access control, and auditing mechanisms that can be transparently integrated into software applications.

<sec><title>Objective</title> Design brief is the main basis for determining capital construction projects and preparing design documents, whose preparation entails strict compliance with scientific and rigorous processes and methods. In the current construction process of landscape architecture projects in China, the preparation of design brief relies more on the experience of practitioners than on reliable evidence, and it is difficult to control the scientificity and rationality of the design basis. If landscape architectural programming is incorporated in the construction process of landscape architecture projects by designers and building owners to demonstrate the scale, nature, positioning and design requirements of such projects, and the preparation process and content of design brief as the basis for design are controlled before the design is carried out, it may be an effective way to promote scientific decision-making in landscape design. Landscape architectural programming is precisely a set of theories and methods for studying the process of design basis formation. As a matter of fact, the use of programming to enhance the scientificity of design decision-making has received considerable attention in the field of urban design and architecture. However, the current research on landscape architectural programming is still in its infancy, and there is an urgent need to clarify the connotations and attributes and develop the research methods of landscape architectural programming. </sec><sec><title>Methods/process</title> This research firstly traces and comparatively analyzes the development process of programming in the fields of urban design, architectural design and landscape architecture, and comparatively analyzes the design programming in the three human settlement environment disciplines in terms of the chronological position of programming in practice, the connotation of programming and the purpose of implementing programming, so as to put forward the broad and narrow connotations of landscape architectural programming, and point out the specific definitions and essential attributes of landscape planning. Secondly, from the perspective of scientific research, according to the process and hierarchy of scientific research, landscape architectural programming is reviewed as an independent research topic, and the research framework of landscape architectural programming in line with the characteristics and needs of the landscape architecture specialty is explored. </sec><sec><title>Results/conclusion</title> The research shows that design programming has two layers of connotation: Design programming in the broad sense is the programming of the whole cycle of project practice, covering the whole process of project planning, approval, design, construction, use, etc. Design programming in the narrow sense is the study of design basis and its formation process, which is positioned after project approval and before design. The current landscape architectural programming should prioritize the connotation in the narrow sense. As to the definition of the concept, landscape architectural programming refers to the research work in which landscape architects propose a combination of qualitative and quantitative design bases through various methods and procedures, which requires landscape architects to, following the target of a landscape architecture construction project, make rational and objective analysis of the social context and other relevant factors of the project by multidimensional investigation methods based on field investigation in combination with personal experience and technical specifications, and to justify the construction target as appropriate. Landscape architectural programming is evidence-based, which advocates evidence-based science rather than experience, and can thus contribute to scientific decision-making of design. The research framework of landscape architectural programming contains epistemology, theoretical perspective, programming methodology, programming procedure, programming methodology, and programming technology. The relationship between these 5 parts is as follows: Programming methodology is a complete set of action plans necessary for programming and a systematic collection of multiple methods and approaches, which links epistemology and theoretical perspective upward, and coordinates the three aspects of programming procedure, programming methodology and programming technology downward; programming procedure serves as an operation program for the modes and steps of programming practice, involving a variety of specific planning methods; programming methodology depends on the support of various techniques or tools in data collection, processing and analysis. In addition, this research integrates the author’s research and practical experience, and initially proposes a six-phase programming procedure: Goal presetting, field investigation and analysis, concept and spatial conception, goal justification, programming expression, and post-programming evaluation. This research also proposes 6 alternative programming methods including the survey research method, content analysis method, hierarchical analysis method, semantic analysis method, importance-satisfaction analysis method, and card analysis method, as well as 4 alternative programming techniques including the programming information matrix, programming periodic table, public participation model, and design competition model. </sec>

In designing a programming language, programming environment, or programming methodology there are a whole lot of both implicit and explicit “shoulds.” By a “should” we mean the claim that the appropriate use of language/environment/methodology X will lead to good habits and result in good products. For example, ADA's commitment to strong typing and mechanisms for constructing data types implies that these components are good and should result in more effective programming. The top-down design methodology implies that designers should start at the specifications and refine downward; this process will result in a good design. Etectera. The problem is that it is not clear that the current crop of languages/environments/methodologies (L/E/M's) do result in more productive programming and design, and that the “shoulds” implied by them are really all that good ([7]).

Demand for programming environments to exploit clusters of symmetric multiprocessors (SMPs) is increasing. In this paper, we present a new programming environment, called ParADE, to enable easy, portable, and high-performance programming on SMP clusters. It is an OpenMP programming environment on top of a multi-threaded software distributed shared memory (SDSM) system with a variant of home-based lazy release consistency protocol. To boost performance, the runtime system provides explicit message-passing primitives to make it a hybrid-programming environment. Collective communication primitives are used for the synchronization and work-sharing directives associated with small data structures, lessening the synchronization overhead and avoiding the implicit barriers of work-sharing directives. The OpenMP translator bridges the gap between the OpenMP abstraction and the hybrid programming interfaces of the runtime system. The experiments with several NAS benchmarks and applications on a Linux-based cluster show promising results that ParADE overcomes the performance problem of the conventional SDSM-based OpenMP environment.

Programming models and environments play the essential roles in high performance computing of enabling the conception, design, implementation and execution of science and engineering application codes. Programmer productivity is strongly influenced by the effectiveness of our programming models and environments, as is software sustainability since our codes have lifespans measured in decades, so the advent of new computing architectures, increased concurrency, concerns for resilience, and the increasing demands for high-fidelity, multi-physics, multi-scale and data-intensive computations mean that we have new challenges to address as part of our fundamental R&D requirements. Fortunately, we also have new tools and environments that make design, prototyping and delivery of new programming models easier than ever. The combination of new and challenging requirements and new, powerful toolsets enables significant synergies for the next generation of programming models and environments R&D. This report presents the topics discussed and results from the 2014 DOE Office of Science Advanced Scientific Computing Research (ASCR) Programming Models & Environments Summit, and subsequent discussions among the summit participants and contributors to topics in this report.

PALLAS is an independent German software company specializing in High Performance Computing. Apart from consulting and training services, a programming environment for developing, porting and tuning of parallel applications is available. It consists of VAMPIR: versatile performance analysis of MPI programs TotalView: parallel debugger for MPI/PARMACS/PVM programs HPF: High Performance Fortran from The Portland Group and provides quality and functionality across a wide range of parallel platforms from workstations to MPP systems.

The authors discuss a concurrent programming environment and its application to a two-arm cooperative manipulation experiment on RIPS (robot instruction processing system). RIPS is a hierarchical multiprocessor architecture in which various custom and general-purpose processors are applied to a partitioning of the robot control problem. The system provides hardware support for synchronization and communication primitives, making it easier to write concurrent programs for RIPS' heterogeneous processors. The experiment demonstrated the viability of RIPS in supporting computationally intensive robot control methodologies, and as a byproduct has helped to develop a parallel programming environment for RIPS, called USE RIPS (user software environment for RIPS). By building USE RIPS on Unix and using a layered approach, it is possible to adapt or make use of various existing programs and utilities, such as the GNU and C++ compilers. >

This paper presents a performance estimator, a prototype of which is implemented within the parallel programming environment PCASE. The estimation is based on static performance prediction, using not only the design information of target machines but also benchmarking results. Additionally, communication costs are estimated based on a hierarchical memory machine model, which enables users to understand all the underlying communication costs on distributed memory machines for each parallel loop. With this performance suggestion, it is possible to interactively optimize data distribution and appropriately select vectorized or parallelized loops. Moreover, the skeleton profiling method is presented. It makes high speed trace (execution count of each statement) generation possible by deleting statements which do not affect the execution path of a program.KeywordsExecution PathExecution CostTarget MachineMemory MachineVector InstructionThese keywords were added by machine and not by the authors. This process is experimental and the keywords may be updated as the learning algorithm improves.

High level performance metrics for FPGA-based multiprocessor systems

Exploring children's learning experience in constructionism-based coding activities through design-based research

The MIT/IEEE/Amazon GraphChallenge.org encourages community approaches to developing new solutions for analyzing graphs and sparse data. Sparse AI analytics present unique scalability difficulties. The Sparse Deep Neural Network (DNN) Challenge draws upon prior challenges from machine learning, high performance computing, and visual analytics to create a challenge that is reflective of emerging sparse AI systems. The sparse DNN challenge is based on a mathematically well-defined DNN inference computation and can be implemented in any programming environment. In 2019 several sparse DNN challenge submissions were received from a wide range of authors and organizations. This paper presents a performance analysis of the best performers of these submissions. These submissions show that their state-of-the-art sparse DNN execution time, $T_{\rm DNN}$, is a strong function of the number of DNN operations performed, $N_{\rm op}$. The sparse DNN challenge provides a clear picture of current sparse DNN systems and underscores the need for new innovations to achieve high performance on very large sparse DNNs.

Key issues in high speed computing are identified and discussed. They include technology trends and impediments to industrial use of supercomputers. Other topics are: parallel programming tools and environments, automatic parallelization and algorithms.