A case study: Holistic performance analysis on heterogeneous architectures using the vampir toolchain. Dietrich, R.; Winkler, F.; William, T.; Stolle, J.; Henschel, R.; and Berry, D., K. Advances in Parallel Computing, 25:793-802, IOS Press BV, 2014.
A case study: Holistic performance analysis on heterogeneous architectures using the vampir toolchain [link]Website  abstract   bibtex   
State-of-the-art high performance computing (HPC) applications have to scale over an increasing number of processing elements, meanwhile application developers recently have to face the programming of special accelerator hardware. Although computing languages like CUDA and programming standards like OpenACC provide a fairly easy way to exploit the computational power of general purpose graphics processing units (GPGPUs), their programming is still challenging. Performance analysis is a vital procedure to efficiently use the available hardware and programming models. This paper presents the Vampir performance analysis capabilities by taking the example of a molecular dynamics code, which uses message passing (MPI), threading (OpenMP) and offloading to accelerators (OpenACC and CUDA). It is shown that the Vampir tool-set allows a holistic view on the combined usage of all commonly utilized programming paradigms in heterogeneous HPC applications. © 2014 The authors and IOS Press.
@article{
 title = {A case study: Holistic performance analysis on heterogeneous architectures using the vampir toolchain},
 type = {article},
 year = {2014},
 identifiers = {[object Object]},
 pages = {793-802},
 volume = {25},
 websites = {https://www.scopus.com/inward/record.uri?eid=2-s2.0-84902282377&doi=10.3233%2F978-1-61499-381-0-793&partnerID=40&md5=79fc3b36d0e75edf5b7e2975868eecc2},
 publisher = {IOS Press BV},
 id = {0d225d36-a9d5-320a-a77d-fa9bef73046b},
 created = {2019-10-01T17:21:27.660Z},
 file_attached = {false},
 profile_id = {42d295c0-0737-38d6-8b43-508cab6ea85d},
 last_modified = {2019-10-01T17:26:32.871Z},
 read = {false},
 starred = {false},
 authored = {true},
 confirmed = {true},
 hidden = {false},
 citation_key = {Dietrich2014793},
 source_type = {article},
 notes = {cited By 1},
 folder_uuids = {22c3b665-9e84-4884-8172-710aa9082eaf},
 private_publication = {false},
 abstract = {State-of-the-art high performance computing (HPC) applications have to scale over an increasing number of processing elements, meanwhile application developers recently have to face the programming of special accelerator hardware. Although computing languages like CUDA and programming standards like OpenACC provide a fairly easy way to exploit the computational power of general purpose graphics processing units (GPGPUs), their programming is still challenging. Performance analysis is a vital procedure to efficiently use the available hardware and programming models. This paper presents the Vampir performance analysis capabilities by taking the example of a molecular dynamics code, which uses message passing (MPI), threading (OpenMP) and offloading to accelerators (OpenACC and CUDA). It is shown that the Vampir tool-set allows a holistic view on the combined usage of all commonly utilized programming paradigms in heterogeneous HPC applications. © 2014 The authors and IOS Press.},
 bibtype = {article},
 author = {Dietrich, R and Winkler, F and William, T and Stolle, J and Henschel, R and Berry, D K},
 journal = {Advances in Parallel Computing}
}
Downloads: 0