@article{fdi:010092358,
  title = {{I}ntegrating {HPC}, {AI}, and workflows for scientific data analysis},
  author = {{B}adia, {R}.{M}. and {B}erti-{E}quille, {L}aure and {F}erreira da {S}ilva, {R}. and {L}eser, {U}.},
  editor = {},
  language = {{ENG}},
  abstract = {{T}he {D}agstuhl {S}eminar 23352, titled '{I}ntegrating {HPC}, {AI}, and {W}orkflows for {S}cientific {D}ata {A}nalysis,' held from {A}ugust 27 to {S}eptember 1, 2023, was a significant event focusing on the


synergy between {H}igh-{P}erformance {C}omputing ({HPC}), {A}rtificial {I}ntelligence ({AI}), and scientific workflow technologies. {T}he seminar recognized that modern {B}ig {D}ata analysis in science rests on


three pillars: workflow technologies for reproducibility and steering, {AI} and {M}achine {L}earning ({ML}) for versatile analysis, and {HPC} for handling large data sets. {T}hese elements, while crucial,


have traditionally been researched separately, leading to gaps in their integration. {T}he seminar aimed to bridge these gaps, acknowledging the challenges and opportunities at the intersection of


these technologies. {T}he event highlighted the complex interplay between {HPC}, workflows, and {ML}, noting how {ML} has increasingly been integrated into scientific workflows, thereby enhancing


resource demands and bringing new requirements to {HPC} architectures, like support for {GPU}s and iterative computations. {T}he seminar also addressed the challenges in adapting {HPC} for


large-scale {ML} tasks, including in areas like deep learning, and the need for workflow systems to evolve to leverage {ML} in data analysis fully. {M}oreover, the seminar explored how {ML} could


optimize scientific workflow systems and {HPC} operations, such as through improved scheduling and fault tolerance. {A} key focus was on identifying prestigious use cases of {ML} in {HPC} and


understanding their unique, unmet requirements. {T}he stochastic nature of {ML} and its impact on the reproducibility of data analysis on {HPC} systems was also a topic of discussion.},
  keywords = {},
  booktitle = {},
  journal = {{D}agstuhl {R}eports},
  volume = {13},
  numero = {8},
  pages = {129--164},
  ISSN = {2192-5283},
  year = {2024},
  DOI = {10.4230/{D}ag{R}ep.13.8.129},
  URL = {https://www.documentation.ird.fr/hor/fdi:010092358},
}