اشترك بالحزمة الذهبية واحصل على وصول غير محدود شمرا أكاديميا
تسجيل مستخدم جديدParsl: Pervasive Parallel Programming in Python
84
0
0.0
(
0
)
اسأل ChatGPT حول البحث
ﻻ يوجد ملخص باللغة العربية
High-level programming languages such as Python are increasingly used to provide intuitive interfaces to libraries written in lower-level languages and for assembling applications from various components. This migration towards orchestration rather than implementation, coupled with the growing need for parallel computing (e.g., due to big data and the end of Moores law), necessitates rethinking how parallelism is expressed in programs. Here, we present Parsl, a parallel scripting library that augments Python with simple, scalable, and flexible constructs for encoding parallelism. These constructs allow Parsl to construct a dynamic dependency graph of components that it can then execute efficiently on one or many processors. Parsl is designed for scalability, with an extensible set of executors tailored to different use cases, such as low-latency, high-throughput, or extreme-scale execution. We show, via experiments on the Blue Waters supercomputer, that Parsl executors can allow Python scripts to execute components with as little as 5 ms of overhead, scale to more than 250 000 workers across more than 8000 nodes, and process upward of 1200 tasks per second. Other Parsl features simplify the construction and execution of composite programs by supporting elastic provisioning and scaling of infrastructure, fault-tolerant execution, and integrated wide-area data management. We show that these capabilities satisfy the needs of many-task, interactive, online, and machine learning applications in fields such as biology, cosmology, and materials science.
قيم البحث
اقرأ أيضاً
As an increasing number of leadership-class systems embrace GPU accelerators in the race towards exascale, efficient communication of GPU data is becoming one of the most critical components of high-performance computing. For developers of parallel p
rogramming models, implementing support for GPU-aware communication using native APIs for GPUs such as CUDA can be a daunting task as it requires considerable effort with little guarantee of performance. In this work, we demonstrate the capability of the Unified Communication X (UCX) framework to compose a GPU-aware communication layer that serves multiple parallel programming models of the Charm++ ecosystem: Charm++, Adaptive MPI (AMPI), and Charm4py. We demonstrate the performance impact of our designs with microbenchmarks adapted from the OSU benchmark suite, obtaining improvements in latency of up to 10.2x, 11.7x, and 17.4x in Charm++, AMPI, and Charm4py, respectively. We also observe increases in bandwidth of up to 9.6x in Charm++, 10x in AMPI, and 10.5x in Charm4py. We show the potential impact of our designs on real-world applications by evaluating a proxy application for the Jacobi iterative method, improving the communication performance by up to 12.4x in Charm++, 12.8x in AMPI, and 19.7x in Charm4py.
Computing has revolutionized the biological sciences over the past several decades, such that virtually all contemporary research in the biosciences utilizes computer programs. The computational advances have come on many fronts, spurred by fundament
al developments in hardware, software, and algorithms. These advances have influenced, and even engendered, a phenomenal array of bioscience fields, including molecular evolution and bioinformatics; genome-, proteome-, transcriptome- and metabolome-wide experimental studies; structural genomics; and atomistic simulations of cellular-scale molecular assemblies as large as ribosomes and intact viruses. In short, much of post-genomic biology is increasingly becoming a form of computational biology. The ability to design and write computer programs is among the most indispensable skills that a modern researcher can cultivate. Python has become a popular programming language in the biosciences, largely because (i) its straightforward semantics and clean syntax make it a readily accessible first language; (ii) it is expressive and well-suited to object-oriented programming, as well as other modern paradigms; and (iii) the many available libraries and third-party toolkits extend the functionality of the core language into virtually every biological domain (sequence and structure analyses, phylogenomics, workflow management systems, etc.). This primer offers a basic introduction to coding, via Python, and it includes concrete examples and exercises to illustrate the languages usage and capabilities; the main text culminates with a final project in structural bioinformatics. A suite of Supplemental Chapters is also provided. Starting with basic concepts, such as that of a variable, the Chapters methodically advance the reader to the point of writing a graphical user interface to compute the Hamming distance between two DNA sequences.
In recent years the computing landscape has seen an in- creasing shift towards specialized accelerators. Field pro- grammable gate arrays (FPGAs) are particularly promising as they offer significant performance and energy improvements compared to CPU
s for a wide class of applications and are far more flexible than fixed-function ASICs. However, FPGAs are difficult to program. Traditional programming models for reconfigurable logic use low-level hardware description languages like Verilog and VHDL, which have none of the pro- ductivity features of modern software development languages but produce very efficient designs, and low-level software lan- guages like C and OpenCL coupled with high-level synthesis (HLS) tools that typically produce designs that are far less efficient. Functional languages with parallel patterns are a better fit for hardware generation because they both provide high-level abstractions to programmers with little experience in hard- ware design and avoid many of the problems faced when gen- erating hardware from imperative languages. In this paper, we identify two optimizations that are important when using par- allel patterns to generate hardware: tiling and metapipelining. We present a general representation of tiled parallel patterns, and provide rules for automatically tiling patterns and gen- erating metapipelines. We demonstrate experimentally that these optimizations result in speedups up to 40x on a set of benchmarks from the data analytics domain.
This paper presents {scshape PaSh}, a system for parallelizing POSIX shell scripts. Given a script, {scshape PaSh} converts it to a dataflow graph, performs a series of semantics-preserving program transformations that expose parallelism, and then co
nverts the dataflow graph back into a script -- one that adds POSIX constructs to explicitly guide parallelism coupled with {scshape PaSh}-provided {scshape Unix}-aware runtime primitives for addressing performance- and correctness-related issues. A lightweight annotation language allows command developers to express key parallelizability properties about their commands. An accompanying parallelizability study of POSIX and GNU commands -- two large and commonly used groups -- guides the annotation language and optimized aggregator library that {scshape PaSh} uses. Finally, {scshape PaSh}s {scshape PaSh}s extensive evaluation over 44 unmodified {scshape Unix} scripts shows significant speedups ($0.89$--$61.1times$, avg: $6.7times$) stemming from the combination of its program transformations and runtime primitives.
Constraint Handling Rules (CHR) is a declarative rule-based formalism and language. Concurrency is inherent as rules can be applied to subsets of constraints in parallel. Parallel implementations of CHR, be it in software, be it in hardware, use diff
erent execution strategies for parallel execution of CHR programs depending on the implementation language. In this report, our goal is to analyze parallel execution of CHR programs from a more general conceptual perspective. We want to experimentally see what is possible when CHR programs are automatically parallelized. For this purpose, a sequential simulation of parallel CHR execution is used to systematically encode different parallel execution strategies. In exhaustive experiments on some typical examples from the literature, parallel and sequential execution can be compared to each other. The number of processors can be bounded or unbounded for a more theoretical analysis. As a result, some preliminary but indicative observations on the influence of the execution strategy can be made for the different problem classes and in general.
سجل دخول لتتمكن من نشر تعليقات
التعليقات
جاري جلب التعليقات
سجل دخول لتتمكن من متابعة معايير البحث التي قمت باختيارها
