A copy of this work was available on the public web and has been preserved in the Wayback Machine. The capture dates from 2017; you can also visit the original URL.
The file type is application/pdf
.
Filters
Language-Centric Performance Analysis of OpenMP Programs with Aftermath
[chapter]
2016
Lecture Notes in Computer Science
We present a new set of tools for the language-centric performance analysis and debugging of OpenMP programs that allows programmers to relate dynamic information from parallel execution to OpenMP constructs ...
Our work is based on the Aftermath performance analysis tool and a ready-to-use, instrumented version of the LLVM/clang OpenMP runtime with negligible overhead for tracing. ...
Conclusion and Future Work We presented a synergistic language and hardware approach to the performance analysis of OpenMP programs. ...
doi:10.1007/978-3-319-45550-1_17
fatcat:x5v7z3j4v5evhcf3jvgdzisk4y
Accurate and Complete Hardware Profiling for OpenMP
[chapter]
2017
Lecture Notes in Computer Science
Analyzing the behavior of OpenMP programs and their interaction with the hardware is essential for locating performance bottlenecks and identifying performance optimization opportunities. ...
In this paper, we present an implementation of our technique for building a unique, coherent profile that contains all available hardware events from multiple executions of the same OpenMP program, each ...
Conclusion We presented a new approach for building accurate and complete hardware profiles of OpenMP programs that consists of combining information gathered from multiple executions of the same program ...
doi:10.1007/978-3-319-65578-9_18
fatcat:xr7r44qornablkjizxykpgfrmi
Characterizing Task-Based OpenMP Programs
2015
PLoS ONE
Programmers struggle to understand performance of task-based OpenMP programs since profiling tools only report thread-based performance. ...
We provide a cost-effective method to extract detailed taskbased performance information from OpenMP programs. ...
Aftermath [39] is a graphical tool to analyze performance problems in programs written using OpenStream, a streaming/data-flow task-based programming language. ...
doi:10.1371/journal.pone.0123545
pmid:25860023
pmcid:PMC4393318
fatcat:chk55wx4zbd2tocsfa6eaon4na
Copyright 20XX ACM X-XXXXX-XX-X/XX/XX ...$15.00. visualization and code-centric hotspots analysis. ...
There have been many languages (e.g., OpenMP, Cilk Plus) and libraries (e.g, Intel TBB, Qthreads, MassiveThreads) supporting task parallelism. ...
Aftermath [3] is a graphical tool that visualizes traces of an OpenStream [14] parallel program in timeline style. OpenStream is a dataflow, stream programming extension of OpenMP. ...
doi:10.1145/2835238.2835241
dblp:conf/sc/HuynhTPT15
fatcat:7vvcwyw4nfcivnnq5pzmye47ui
Application Analysis of the Ecological Economics Model of Parallel Accumulation Sorting and Dynamic Internet of Things in the Construction of Ecological Smart City
2022
Wireless Communications and Mobile Computing
In order to improve the effect of ecological smart city construction, this paper analyzes the application of the ecological economic model based on parallel accumulation sorting and dynamic Internet of ...
effect of the ecological smart city. ...
When OpenMP is used, the programmer needs to specify the part of the program that can be used for parallelism. ...
doi:10.1155/2022/8770859
fatcat:ok4t66nmjvgozbeaw2t3glc7b4
Topology-Aware and Dependence-Aware Scheduling and Memory Allocation for Task-Parallel Languages
2014
ACM Transactions on Architecture and Code Optimization (TACO)
By contrast, our solution makes no assumption on the structure of programs or on the layout of data in memory. ...
Experimental results, based on the Open-Stream language, show that locality of accesses to main memory of scientific applications can be increased significantly on a 64-core machine, resulting in a speedup ...
EMBEDDING INTO A TASK-PARALLEL LANGUAGE OpenStream [Pop and Cohen 2013] is a dataflow programming language designed as an incremental extension to OpenMP. ...
doi:10.1145/2641764
fatcat:tlu32qcxpnbsxpgikiw5blbg5e
GreenC5: An adaptive, energy-aware collection for green software development
2017
Sustainable Computing: Informatics and Systems
It was a pleasure working with two of them. ...
Our n-gram model can accurately predict the most energy efficient data structure sequence in 19 simulated and real-world programs-on average, with more than 50% accuracy and up to 98% using a bigram predictor ...
OpenMP is a standard for programming parallel shared memory systems without any support for power control. ...
doi:10.1016/j.suscom.2016.11.004
fatcat:mflbtcsmanfdlnao7kqoj6m3le
Enhancing the scalability of many-core systems towards utilizing fine-grain parallelism in task-based programming models
[article]
2018
New programming models emerged trying to bridge the gap between programming complexity and well-utilization of the multicore systems, with their various available resources. ...
In this era, a core's single performance is no longer the most important parameter, but the performance of the whole multicore system. ...
Other performance analysis, debugging, and visualization of dataflow task programming models include Paraver [36, 38] , Aftermath [51, 52] , DAGvis [77] , and TEMANEJO [24, 25, 74] . ...
doi:10.14279/depositonce-6636
fatcat:jzpbfvk6trfi7lur5vafenw5zm
CLIMATE CHANGE IMPACTS ON THE AQUACULTURE SECTOR FOR EUROPEAN ISLANDS
2020
Zenodo
Climate Change impacts and low carbon transition pathways in European islands and archipelagos for 2030-2100, complementing current available projections for Europe, and nourishing actual economic models with ...
According to the fifth Assessment Report of the Intergovernmental Panel on Climate Change, the warming of the climate system is unequivocal and continued emission of greenhouse gases will cause further ...
Acknowledgments The study has been carried out with the financial support of the Fondazione Cariplo under the project "Climatology for professional activities and adaptation to urban climate change in ...
doi:10.5281/zenodo.4775788
fatcat:oszlppnfnraw7oez4kpl2saidq