High-Level Support for Pipeline Parallelism on Many-Core Architectures

Benkner, Siegfried; Bajrovic, Enes; Marth, Erich; Sandrieser, Martin; Namyst, Raymond; Thibault, Samuel

doi:10.1007/978-3-642-32820-6_61

Cited by 9 publications

(8 citation statements)

References 22 publications

(20 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…During the training run, Qilin executes the program at different input sizes on CPUs and GPUs separately, and build performance models to determine workload partitioning between CPUs and GPUs. Peppher [25] employs component implementation variants of performance-critical parts of applications tailored to different architectures, and relies on the compiler and runtime system to select and schedule component tasks on available computing resources. PetaBricks [26], an implicitly parallel language and compiler, uses an empirical autotuning approach to search the space of possible implementations at installation time to construct poly-algorithms that combine many different algorithmic techniques to obtain better performance.…”

Section: Numerical Simulation Of Lid-driven Cavity Flowmentioning

confidence: 99%

Data Partitioning on Multicore and Multi-GPU Platforms Using Functional Performance Models

Zhong

Рычков

Lastovetsky

2015

IEEE Trans. Comput.

View full text Add to dashboard Cite

Heterogeneous multiprocessor systems, which are composed of a mix of processing elements, such as commodity multicore processors, graphics processing units (GPUs), and others, have been widely used in scientific computing community. Software applications incorporate the code designed and optimized for different types of processing elements in order to exploit the computing power of such heterogeneous computing systems. In this paper, we consider the problem of optimal distribution of the workload of data-parallel scientific applications between processing elements of such heterogeneous computing systems. We present a solution that uses functional performance models (FPMs) of processing elements and FPM-based data partitioning algorithms. Efficiency of this approach is demonstrated by experiments with parallel matrix multiplication and numerical simulation of lid-driven cavity flow on hybrid servers and clusters.

show abstract

Section: Numerical Simulation Of Lid-driven Cavity Flowmentioning

confidence: 99%

Data Partitioning on Multicore and Multi-GPU Platforms Using Functional Performance Models

Zhong

Рычков

Lastovetsky

2015

IEEE Trans. Comput.

View full text Add to dashboard Cite

show abstract

“…Benkner et al [31] propose high level constructs (in the form of pragmas) for modeling pipeline patterns in an application; underneath, they generate StarPU code for making decisions at runtime.…”

Section: Other Approaches For Gpu-based Systemsmentioning

confidence: 99%

Performance-aware component composition for GPU-based systems

Dastgeer¹

2014

View full text Add to dashboard Cite

This thesis adresses issues associated with efficiently programming modern heterogeneous GPU-based systems, containing multicore CPUs and one or more programmable Graphics Processing Units (GPUs). We use ideas from component-based programming to address programming, performance and portability issues of these heterogeneous systems. Specifically, we present three approaches that all use the idea of having multiple implementations for each computation; performance is achieved/retained either a) by selecting a suitable implementation for each computation on a given platform or b) by dividing the computation work across different implementations running on CPU and GPU devices in parallel.In the first approach, we work on a skeleton programming library (SkePU) that provides high-level abstraction while making intelligent implementation selection decisions underneath either before or during the actual program execution. In the second approach, we develop a composition tool that parses extra information (metadata) from XML files, makes certain decisions offline, and, in the end, generates code for making the final decisions at runtime. The third approach is a framework that uses source-code annotations and program analysis to generate code for the runtime library to make the selection decision at runtime. With a generic performance modeling API alongside program analysis capabilities, it supports online tuning as well as complex program transformations.These approaches differ in terms of genericity, intrusiveness, capabilities and knowledge about the program source-code; however, they all demonstrate usefulness of component programming techniques for programming GPU-based systems. With experimental evaluation, we demonstrate how all three approaches, although different in their own way, provide good performance on different GPU-based systems for a variety of applications.This work has been supported by two EU FP7 projects (PEP-PHER, EXCESS) and by SeRC. Populärvetenskaplig sammanfattningAtt få varje generation av datorer att fungera snabbareär viktigt för samhä-llets utveckling och tillväxt. Traditionellt hade de flesta datorer bara en general-purpose processor (den så kallade CPU:n) som bara kunde exekvera en beräkningsuppgift i taget. Under det senasteårtiondet har dock flerkärniga och mångkärniga processorer blivit vanliga, och datorer har också blivit mer heterogena. Ett modernt datorsystem innehåller vanligtvis flerän en CPU, tillsammans med specialprocessorer såsom grafikprocessorer (GPU:er) som ar anpassade för att kunna exekvera vissa typer av beräkningar effektivarë an CPU:er. Vi kallar ett sådant system med en eller flera GPU:er för ett GPU-baserat system. GPU:er i sådana system har sitt eget separata minne, och för att kunna köra en beräkning på en GPU så behöver man vanligtvis flytta all indata till GPU:ns minne och sedan hämta tillbaka resultatet när beräkningenär klar.Programmeringen av GPU-baserade systemär icke-trivialt av flera anledningar: (1) CPU:er och GPU:er kräver olika programmeringsexper...

show abstract

“…One established way to tackle the high programming complexity is the use of welldefined parallel programming patterns. This methodology has already been applied successfully by various libraries targeting accelerated parallel systems (e.g., Thrust [1], SkePU [2], PEP-PHER [3], HyPHI [4]). However, even though parallel pattern programming libraries may significantly improve programmability, an efficient and portable implementation of such libraries is challenging.…”

Section: Introductionmentioning

confidence: 99%

Automatic Tuning of a Parallel Pattern Library for Heterogeneous Systems with Intel Xeon Phi

Dokulil

Benkner

2014

2014 IEEE International Symposium on Parallel and Distributed Processing With Applications

Self Cite

View full text Add to dashboard Cite

Pattern libraries are important tools for high productivity application development. Their struggle for best performance is complicated by the fact that they are used to execute user-provided code, which is not known during their creation. This makes pattern libraries good candidate for automatic software tuning. In this paper, we deal with automatic online parameter tuning of the HyPHI hybrid pattern library for heterogeneous systems equipped with the Intel Xeon Phi coprocessors. We propose a framework that can be used to combine a pattern library with an existing tuning library in a practical and efficient way. Our experiments show that tuning can noticeably improve the performance of the library and it introduces very little overhead.

show abstract

High-Level Support for Pipeline Parallelism on Many-Core Architectures

Cited by 9 publications

References 22 publications

Data Partitioning on Multicore and Multi-GPU Platforms Using Functional Performance Models

Data Partitioning on Multicore and Multi-GPU Platforms Using Functional Performance Models

Performance-aware component composition for GPU-based systems

Automatic Tuning of a Parallel Pattern Library for Heterogeneous Systems with Intel Xeon Phi

Contact Info

Product

Resources

About