Filters








74,300 Hits in 4.3 sec

Estimation of MPI Application Performance on Volunteer Environments [chapter]

Girish Nandagudi, Jaspal Subhlok, Edgar Gabriel, Judit Gimenez
2012 Lecture Notes in Computer Science  
Goal if this study • To simulate the performance of parallel applications on desktop grids -To estimate the effects of bandwidth, latency on the performance -To estimate the effects of occurrence  ...  Edgar Gabriel VolpexMPI • MPI library for execution of parallel application on volatile nodes • Key features: -controlled redundancy: each MPI process can have multiple replicas -Receiver based  ... 
doi:10.1007/978-3-642-29737-3_56 fatcat:l4xd4eeeendldcnc62ihzudsda

Dynamic scheduling techniques for heterogeneous computing systems

Babak Hamidzadeh, Yacine Atif, David J. Lilja
1995 Concurrency Practice and Experience  
There has been a recent increase of interest in heterogeneous computing systems, due partly to the fact that a single parallel architecture may not be adequate for exploiting all of a program'savailable  ...  These algorithms execute a noveloptimization technique to dynamically compute schedules based on the potentially non-uniform computation and communication costs on the processors of a heterogeneous system  ...  Static scheduling with imprecise estimates can lead to large computational load imbalances at run-time, which produce significantly longer execution times.  ... 
doi:10.1002/cpe.4330070705 fatcat:qp4bpmd675e4fj5sglnxrg47qy

Tiling and Scheduling of Three-level Perfectly Nested Loops with Dependencies on Heterogeneous Systems

Ebrahim Zarei Zefreh, Shahriar Lotfi, Leyli Mohammad Khanli, Jaber Karimpour
2016 Scalable Computing : Practice and Experience  
We develop and evaluate a theoretical model to estimate the parallel execution time of tilled nested loops.  ...  A heterogeneous computing system is a set of multiple computing nodes connected via a high-speed network interconnection, used for executing parallel and distributed scientific applications [5, 6, 7] .  ...  They would also like to thanks Nasrin Nasrabadi and Fateme Karimi, PhD Students, for all very valuable comments.  ... 
doi:10.12694/scpe.v17i4.1205 fatcat:tvbrsukttvct5fky2g7tsz3j5e

Adaptive parallel computing on heterogeneous networks with mpC

Alexey Lastovetsky
2002 Parallel Computing  
The language was designed specially for programming high-performance parallel computations on heterogeneous networks of computers.  ...  program to this network in such a way that leads to its better execution time.  ...  It has been carried out by Alexey Lastovetsky (design and run-time  ... 
doi:10.1016/s0167-8191(02)00159-x fatcat:bbubscz6k5cmvciy6qwrjc45ja

FuPerMod: A Framework for Optimal Data Partitioning for Parallel Scientific Applications on Dedicated Heterogeneous HPC Platforms [chapter]

David Clarke, Ziming Zhong, Vladimir Rychkov, Alexey Lastovetsky
2013 Lecture Notes in Computer Science  
We demonstrate how it can be used to optimise data-parallel applications for modern heterogeneous HPC platforms.  ...  Optimisation of data-parallel scientific applications for modern HPC platforms is challenging in terms of efficient use of heterogeneous hardware and software.  ...  Our software framework is designed to help in construction of computation performance models for any data-parallel application with given accuracy and cost-effectiveness.  ... 
doi:10.1007/978-3-642-39958-9_16 fatcat:hvj6pjvvsza7fmom3oml6s6icu

MPIBlib: Benchmarking MPI Communications for Parallel Computing on Homogeneous and Heterogeneous Clusters [chapter]

Alexey Lastovetsky, Vladimir Rychkov, Maureen O'Flynn
2008 Lecture Notes in Computer Science  
It is important to note that the definition assumes that we estimate the execution time for a single isolated operation.  ...  Practically, the execution time of the communication operation is estimated from the results of an experiment that, in addition to the operation, includes other communications and computations.  ...  Introduction Accurate estimation of the execution time of MPI communication operations plays an important role in optimization of parallel applications.  ... 
doi:10.1007/978-3-540-87475-1_32 fatcat:6t4ys5oszffcnabppkjotsosgm

Heterogeneous placement optimization for database query processing

Tomas Karnagel, Dirk Habich
2017 it - Information Technology  
In this paper, we summarize our efforts to use hardware heterogeneity efficiently for query processing.  ...  The current hardware trend is heterogeneity, where multiple computing units like CPUs and GPUs are used together in one system.  ...  Funding: This work is funded by the German Research Foundation (DFG) within the Cluster of Excellence "Center for Advancing Electronics Dresden" (Orchestration Path).  ... 
doi:10.1515/itit-2016-0048 fatcat:accqkgmvl5eshc2hkyfvleh73u

FuPerMod: a software tool for the optimization of data-parallel applications on heterogeneous platforms

David Clarke, Ziming Zhong, Vladimir Rychkov, Alexey Lastovetsky
2014 Journal of Supercomputing  
Optimization of data-parallel applications for modern HPC platforms requires partitioning the computations between the heterogeneous computing devices in proportion to their speed.  ...  Heterogeneous data partitioning algorithms are based on computation performance models of the executing platforms.  ...  The important requirement is that it does not vary during the execution of the application. This model can be estimated in the same way for any data-parallel application.  ... 
doi:10.1007/s11227-014-1207-9 fatcat:7xskswgmindbjih3ppoaq5f7be

Efficiency Measurement for Effective Stress Management in Heterogeneous 2-D Mesh Processor

Arashdeep Singh, Sunny Behal, Ankit Arora
2013 International Journal of Computer Applications  
Parallel schedulers are implemented in cluster technology for job assignment and placement. Further, core processor technology will provide a greater endeavor for load balancing.  ...  This research covers heterogeneous multiprocessors with 2-D mesh interconnection mapped to cube oriented memory mesh for job allocation and distribution.  ...  The Parallel workload analyzer interpret this job for parallel behavior, if the job having parallel modules can be executed simultaneously, then such parallel modules can be distributed to other processors  ... 
doi:10.5120/14066-2330 fatcat:ca4fmkpao5ee5g4fp27yeahqhu

Distributed Data Partitioning for Heterogeneous Processors Based on Partial Estimation of Their Functional Performance Models [chapter]

Alexey Lastovetsky, Ravi Reddy
2010 Lecture Notes in Computer Science  
The paper presents a new data partitioning algorithm for parallel computing on heterogeneous processors.  ...  Instead, it uses a computational kernel to estimate the speed functions of the processors for different problem sizes during its execution.  ...  Using experimental results for parallel matrix multiplication on a local heterogeneous computational cluster, we demonstrate that the execution time of the proposed distributed partitioning algorithm is  ... 
doi:10.1007/978-3-642-14122-5_13 fatcat:yxjqszm4dzg2dlseztslzcbf3u

Design and Implementation of a Parallel Heterogeneous Algorithm for Hyperspectral Image Analysis Using HeteroMPI

David Valencia, Alexey Lastovetsky, Antonio Plaza
2006 2006 Fifth International Symposium on Parallel and Distributed Computing  
Although most available parallel processing strategies for hyperspectral image analysis assume homogeneity in the computing platform, heterogeneous networks of computers represent a promising cost-effective  ...  To address the need for cost-effective parallel hyperspectral imaging algorithms, this paper develops an innovative heterogeneous parallel algorithm for spatial/spectral morphological analysis of hyperspectral  ...  Before reporting the timing results, we emphasize that the relative speeds of the heterogeneous processors were first estimated for different problem sizes (i.e., number of iterations ranging from 1 =  ... 
doi:10.1109/ispdc.2006.18 dblp:conf/ispdc/ValenciaLP06 fatcat:yc5ndjdjpzbo7gh7s4u6qp5kxq

GPU Computing Pipeline Inefficiencies and Optimization Opportunities in Heterogeneous CPU-GPU Processors

Joel Hestness, Stephen W. Keckler, David A. Wood
2015 2015 IEEE International Symposium on Workload Characterization  
For heterogeneous processors, the results indicate increased opportunity for techniques that provide flexible compute and data granularities, and support for efficient producer-consumer data handling and  ...  This paper quantifies opportunities for applications and architectures to evolve to leverage the new capabilities of heterogeneous processors.  ...  This optimistic migrated-compute estimate assumes that all benchmark compute phases can be effectively distributed across CPU and GPU cores.  ... 
doi:10.1109/iiswc.2015.15 dblp:conf/iiswc/HestnessKW15 fatcat:rfgukt3qkrfvfodutm37qerc5a

Power capping of CPU-GPU heterogeneous systems through coordinating DVFS and task mapping

Toshiya Komoda, Shingo Hayashi, Takashi Nakada, Shinobu Miwa, Hiroshi Nakamura
2013 2013 IEEE 31st International Conference on Computer Design (ICCD)  
To guide the settings of DVFS and task mapping for avoiding power violation and the load imbalance, we develop new empirical models of the performance and the maximum power consumption of a CPU-GPU heterogeneous  ...  We evaluate the proposed technique with five data-parallel applications on a machine equipped with a single CPU and a single GPU.  ...  ACKNOWLEDGMENT This work was supported by JST, CREST and the Grantin-Aid for JSPS Fellow (23 8062).  ... 
doi:10.1109/iccd.2013.6657064 dblp:conf/iccd/KomodaHNMN13 fatcat:wxflzexp25abjehe4ej4wdda2e

Adaptive Processor Allocation for Moldable Jobs in Computational Grid

Kuo-Chan Huang, Po-Chi Shih, Yeh-Ching Chung
2009 International Journal of Grid and High Performance Computing  
This article develops adaptive processor allocation policies based on the moldable property of parallel jobs to deal with such situations in a heterogeneous computational grid environment.  ...  In a computational grid environment, a common practice is try to allocate an entire parallel job onto a single participating site.  ...  Job scheduling for parallel computers has been subject to research for a long time. As for grid computing, previous works discussed several strategies for a grid scheduler.  ... 
doi:10.4018/jghpc.2009010102 fatcat:t4yu64w72bg4tktocshui7vzdm

Heterogeneous computing: challenges and opportunities

A.A. Khokhar, V.K. Prasanna, M.E. Shaaban, C.-L. Wang
1993 Computer  
Heterogeneous computing (HC) is the well-orchestrated and coordinated effective use of a suite of diverse high-performance machines (including parallel machines) to provide superspeed processing for computationally  ...  Most of the current parallel machines are suited only for homogeneous computing.  ...  Code-type profiling: A code-specific function to identify various types of parallelism present in code and to estimate the execution times of each code type.  ... 
doi:10.1109/2.214439 fatcat:a5wzxmuxfvhcthbx5jtxl4xj5i
« Previous Showing results 1 — 15 out of 74,300 results