ACAT 2017
The 18th International Workshop on Advanced Computing and Analysis Techniques in Physics Research (ACAT) took place in Seattle this week. We presented our work on integrating the dynamic web federation into HEP computing as a poster.
The conference focused on the use of machine learning algorithm in physics research with contributions from industry offering effective computing technology to execute workflows employing deep neural nets.
These technologies offer solutions to the computing issues the field is facing in light of a great increase in data with a constant computing budget. When the LHC experiments were planned it was assumed that Dennard Scaling would solve this problem for us, it has become clear that this is not the case.
It was shown that generative adversarial neural nets may be used to do do simulation, and that supervised learning may provide options for triggering and reconstruction. In some places these technologies are already used. nVidia, Microsoft, and DWave presented technology options to train, test, and deploy computing well suited to executing the workflows required by these algorithms.
The content presented at the conference were feasibility studies, next we need to perform systematic comparisons between these new techniques and our established and well proven workflows. Whatever happens, HEP computing seems to be evolving into a direction that requires more heterogeneous computing resources than what the grid allows. Leveraging IaaS cloud technology in a well suited way to execute scientific workflows will become more important rather than less. With that our addition of the dynamic data federation to cloud scheduler was certainly received as a useful addition.
The talk on the Rocet scheduler on Thursday afternoon presented a tool that functions in a very similar fashion to cloud scheduler. The KIT group seemed very interested in shoal and the dynafed, since they started bumping into similar problems as us. Hopefully here we found future collaborators. Clearly a tool like this is needed in the HEP community.
The conference focused on the use of machine learning algorithm in physics research with contributions from industry offering effective computing technology to execute workflows employing deep neural nets.
These technologies offer solutions to the computing issues the field is facing in light of a great increase in data with a constant computing budget. When the LHC experiments were planned it was assumed that Dennard Scaling would solve this problem for us, it has become clear that this is not the case.
It was shown that generative adversarial neural nets may be used to do do simulation, and that supervised learning may provide options for triggering and reconstruction. In some places these technologies are already used. nVidia, Microsoft, and DWave presented technology options to train, test, and deploy computing well suited to executing the workflows required by these algorithms.
The content presented at the conference were feasibility studies, next we need to perform systematic comparisons between these new techniques and our established and well proven workflows. Whatever happens, HEP computing seems to be evolving into a direction that requires more heterogeneous computing resources than what the grid allows. Leveraging IaaS cloud technology in a well suited way to execute scientific workflows will become more important rather than less. With that our addition of the dynamic data federation to cloud scheduler was certainly received as a useful addition.
The talk on the Rocet scheduler on Thursday afternoon presented a tool that functions in a very similar fashion to cloud scheduler. The KIT group seemed very interested in shoal and the dynafed, since they started bumping into similar problems as us. Hopefully here we found future collaborators. Clearly a tool like this is needed in the HEP community.
Comments
Post a Comment