اشترك بالحزمة الذهبية واحصل على وصول غير محدود شمرا أكاديميا
تسجيل مستخدم جديدProductivity, Portability, Performance: Data-Centric Python
340
0
0.0
(
0
)
نشر من قبل
Alexandros Nikolaos Ziogas
تاريخ النشر
2021
مجال البحث
الهندسة المعلوماتية
والبحث باللغة
English
اسأل ChatGPT حول البحث
ﻻ يوجد ملخص باللغة العربية
Python has become the de facto language for scientific computing. Programming in Python is highly productive, mainly due to its rich science-oriented software ecosystem built around the NumPy module. As a result, the demand for Python support in High Performance Computing (HPC) has skyrocketed. However, the Python language itself does not necessarily offer high performance. In this work, we present a workflow that retains Pythons high productivity while achieving portable performance across different architectures. The workflows key features are HPC-oriented language extensions and a set of automatic optimizations powered by a data-centric intermediate representation. We show performance results and scaling across CPU, GPU, FPGA, and the Piz Daint supercomputer (up to 23,328 cores), with 2.47x and 3.75x speedups over previous-best solutions, first-ever Xilinx and Intel FPGA results of annotated Python, and up to 93.16% scaling efficiency on 512 nodes.
قيم البحث
اقرأ أيضاً
There has been a significant amount of work in the literature proposing semantic relaxation of concurrent data structures for improving scalability and performance. By relaxing the semantics of a data structure, a bigger design space, that allows wea
ker synchronization and more useful parallelism, is unveiled. Investigating new data structure designs, capable of trading semantics for achieving better performance in a monotonic way, is a major challenge in the area. We algorithmically address this challenge in this paper. We present an efficient, lock-free, concurrent data structure design framework for out-of-order semantic relaxation. Our framework introduces a new two dimensional algorithmic design, that uses multiple instances of a given data structure. The first dimension of our design is the number of data structure instances operations are spread to, in order to benefit from parallelism through disjoint memory access. The second dimension is the number of consecutive operations that try to use the same data structure instance in order to benefit from data locality. Our design can flexibly explore this two-dimensional space to achieve the property of monotonically relaxing concurrent data structure semantics for achieving better throughput performance within a tight deterministic relaxation bound, as we prove in the paper. We show how our framework can instantiate lock-free out-of-order queues, stacks, counters and dequeues. We provide implementations of these relaxed data structures and evaluate their performance and behaviour on two parallel architectures. Experimental evaluation shows that our two-dimensional data structures significantly outperform the respected previous proposed ones with respect to scalability and throughput performance. Moreover, their throughput increases monotonically as relaxation increases.
Based on the two observations that diverse applications perform better on different multicore architectures, and that different phases of an application may have vastly different resource requirements, Pal et al. proposed a novel reconfigurable hardw
are approach for executing multithreaded programs. Instead of mapping a concurrent program to a fixed architecture, the architecture adaptively reconfigures itself to meet the applications concurrency and communication requirements, yielding significant improvements in performance. Based on our earlier abstract operational framework for multicore execution with hierarchical memory structures, we describe execution of multithreaded programs on reconfigurable architectures that support a variety of clustered configurations. Such reconfiguration may not preserve the semantics of programs due to the possible introduction of race conditions arising from concurrent accesses to shared memory by threads running on the different cores. We present an intuitive partial ordering notion on the cluster configurations, and show that the semantics of multithreaded programs is always preserved for reconfigurations upward in that ordering, whereas semantics preservation for arbitrary reconfigurations can be guaranteed for well-synchronised programs. We further show that a simple approximate notion of efficiency of execution on the different configurations can be obtained using the notion of amortised bisimulations, and extend it to dynamic reconfiguration.
In this paper we present CARMA, a language recently defined to support specification and analysis of collective adaptive systems. CARMA is a stochastic process algebra equipped with linguistic constructs specifically developed for modelling and progr
amming systems that can operate in open-ended and unpredictable environments. This class of systems is typically composed of a huge number of interacting agents that dynamically adjust and combine their behaviour to achieve specific goals. A CARMA model, termed a collective, consists of a set of components, each of which exhibits a set of attributes. To model dynamic aggregations, which are sometimes referred to as ensembles, CARMA provides communication primitives that are based on predicates over the exhibited attributes. These predicates are used to select the participants in a communication. Two communication mechanisms are provided in the CARMA language: multicast-based and unicast-based. In this paper, we first introduce the basic principles of CARMA and then we show how our language can be used to support specification with a simple but illustrative example of a socio-technical collective adaptive system.
Data engineering is becoming an increasingly important part of scientific discoveries with the adoption of deep learning and machine learning. Data engineering deals with a variety of data formats, storage, data extraction, transformation, and data m
ovements. One goal of data engineering is to transform data from original data to vector/matrix/tensor formats accepted by deep learning and machine learning applications. There are many structures such as tables, graphs, and trees to represent data in these data engineering phases. Among them, tables are a versatile and commonly used format to load and process data. In this paper, we present a distributed Python API based on table abstraction for representing and processing data. Unlike existing state-of-the-art data engineering tools written purely in Python, our solution adopts high performance compute kernels in C++, with an in-memory table representation with Cython-based Python bindings. In the core system, we use MPI for distributed memory computations with a data-parallel approach for processing large datasets in HPC clusters.
The last improvements in programming languages, programming models, and frameworks have focused on abstracting the users from many programming issues. Among others, recent programming frameworks include simpler syntax, automatic memory management and
garbage collection, which simplifies code re-usage through library packages, and easily configurable tools for deployment. For instance, Python has risen to the top of the list of the programming languages due to the simplicity of its syntax, while still achieving a good performance even being an interpreted language. Moreover, the community has helped to develop a large number of libraries and modules, tuning them to obtain great performance. However, there is still room for improvement when preventing users from dealing directly with distributed and parallel computing issues. This paper proposes and evaluates AutoParallel, a Python module to automatically find an appropriate task-based parallelization of affine loop nests to execute them in parallel in a distributed computing infrastructure. This parallelization can also include the building of data blocks to increase task granularity in order to achieve a good execution performance. Moreover, AutoParallel is based on sequential programming and only contains a small annotation in the form of a Python decorator so that anyone with little programming skills can scale up an application to hundreds of cores.
سجل دخول لتتمكن من نشر تعليقات
التعليقات
جاري جلب التعليقات
سجل دخول لتتمكن من متابعة معايير البحث التي قمت باختيارها
