Implicitly Parallel Programming Models for Thousand-Core Microprocessors

Hwu, Wen-mei W.; Ryoo, Shane; Ueng, Sain-Zee; Kelm, John H.; Gelado, Isaac; Stone, Sam S.; Kidd, Robert E.; Baghsorkhi, Sara S.; Mahesri, Aqeel; Tsao, Stephanie C.; Navarro, Nacho; Lumetta, Steve; Frank, Matthew I.; Patel, Sanjay J.

doi:10.1109/dac.2007.375265

Cited by 16 publications

(17 citation statements)

References 0 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The parallel computing landscape seems too complex for any single solution to be a panacea. Parallel libraries [16,40], domain specific languages [58], parallel computing toolboxes [46,54], implicit and interactive parallelization [5,32], and automatic parallelization [25] are some promising directions that can might be easily adoptable by scientists due to higher level abstractions provided.…”

Section: Analysis Of Resultsmentioning

confidence: 99%

A survey of the practice of computational science

Prabhu

Kim

et al. 2011

State of the Practice Reports

View full text Add to dashboard Cite

Computing plays an indispensable role in scientific research. Presently, researchers in science have different problems, needs, and beliefs about computation than professional programmers. In order to accelerate the progress of science, computer scientists must understand these problems, needs, and beliefs. To this end, this paper presents a survey of scientists from diverse disciplines, practicing computational science at a doctoral-granting university with very high research activity. The survey covers many things, among them, prevalent programming practices within this scientific community, the importance of computational power in different fields, use of tools to enhance performance and software productivity, computational resources leveraged, and prevalence of parallel computation. The results reveal several patterns that suggest interesting avenues to bridge the gap between scientific researchers and programming tools developers.

show abstract

Section: Analysis Of Resultsmentioning

confidence: 99%

A survey of the practice of computational science

Prabhu

Kim

et al. 2011

State of the Practice Reports

View full text Add to dashboard Cite

show abstract

“…Although active research on new programming models [1], [2] may simplify explicit parallelization of many applications, transparent or semi-transparent parallelization assisted by hardware, compilers, or runtime systems would significantly improve the applicability of many-core systems to existing sequential programs and better enable parallel commercial applications [3], [4]. However, automatic parallelization remains an elusive goal, despite much work to parallelize general-purpose programming languages transparently [4], [5], [6]. Alternatively, automatic parallelization of scripting languages [7], [8] would alleviate the application developers' parallel programming burden while avoiding many of the difficulties of parallelizing compilers.…”

Section: Introductionmentioning

confidence: 99%

Machine learning based online performance prediction for runtime parallelization and task scheduling

Singh

et al. 2009

2009 IEEE International Symposium on Performance Analysis of Systems and Software

View full text Add to dashboard Cite

Abstract-With the emerging many-core paradigm, parallel programming must extend beyond its traditional realm of scientific applications. Converting existing sequential applications as well as developing next-generation software requires assistance from hardware, compilers and runtime systems to exploit parallelism transparently within applications. These systems must decompose applications into tasks that can be executed in parallel and then schedule those tasks to minimize load imbalance. However, many systems lack a priori knowledge about the execution time of all tasks to perform effective load balancing with low scheduling overhead.In this paper, we approach this fundamental problem using machine learning techniques first to generate performance models for all tasks and then applying those models to perform automatic performance prediction across program executions. We also extend an existing scheduling algorithm to use generated task cost estimates for online task partitioning and scheduling. We implement the above techniques in the pR framework, which transparently parallelizes scripts in the popular R language, and evaluate their performance and overhead with both a realworld application and a large number of synthetic representative test scripts. Our experimental results show that our proposed approach significantly improves task partitioning and scheduling, with maximum improvements of 21.8%, 40.3% and 22.1% and average improvements of 15.9%, 16.9% and 4.2% for LMM (a real R application) and synthetic test cases with independent and dependent tasks, respectively.

show abstract

“…The outlined issues become especially pronounced when systems with many cores are considered [4,18]. Manufacturing general purpose processors with hundreds or thousands of cores may be feasible soon, and specialized manycore processors already exist in graphic processing units (GPUs).…”

Section: Hardware Layermentioning

confidence: 99%

“…Modeling software running on thousands of cores requires rethinking of existing approaches [4]. While techniques and tools for parallelizing software are evolving [5], novel methods and tools need to be created to assist software architects in designing systems that can exploit the capabilities for parallel execution but do not overburden software developers during implementation [6].…”

Section: Introductionmentioning

confidence: 99%