Offloading the Training of an I/O Access Pattern Detector to the Cloud

  • Cristiano A. Künas UFRGS
  • Matheus S. Serpa UFRGS
  • Jean Luca Bez Lawrence Berkeley National Laboratory
  • Edson L. Padoin UNIJUÍ
  • Philippe O. A. Navaux UFRGS

Resumo


I/O operations are a bottleneck for numerous applications, so optimizing the performance of these operations is of paramount importance. Many techniques explore and apply optimizations to different layers of the I/O stack to improve performance. The difficulty that arises is that the workload changes constantly. So detecting access patterns correctly, at runtime, becomes essential for systems that seek to self-adjust their parameters. Furthermore, the I/O pattern detection techniques should represent minimal overhead and should be able to perform detection as quickly as possible. This paper approaches a machine learning technique for detecting the I/O access patterns and proposes offloading the local training workload to the cloud using a TPU accelerator. Such an approach does not interfere with classifier accuracy (reaching up to 99% accuracy). Still, it allows the training to be asynchronous, enabling the local machine to allocate its computing resources to scientific applications while the model is trained or updated in the cloud.
Palavras-chave: Training, Runtime, High performance computing, Conferences, Computational modeling, Machine learning, Detectors, high-performance computing, access pattern detection, classification, TPU, cloud
Publicado
26/10/2021
KÜNAS, Cristiano A.; SERPA, Matheus S.; BEZ, Jean Luca; PADOIN, Edson L.; NAVAUX, Philippe O. A.. Offloading the Training of an I/O Access Pattern Detector to the Cloud. In: WORKSHOP ON CLOUD COMPUTING (WCC) - INTERNATIONAL SYMPOSIUM ON COMPUTER ARCHITECTURE AND HIGH PERFORMANCE COMPUTING (SBAC-PAD), 33. , 2021, Belo Horizonte. Anais [...]. Porto Alegre: Sociedade Brasileira de Computação, 2021 . p. 15-19.