DRAGON: breaking GPU memory capacity limits with direct NVM access
Heterogeneous computing with accelerators is growing in importance in high performance computing (HPC). Recently, application datasets have expanded beyond the memory capacity of these accelerators, and often beyond the capacity of their hosts. Meanwhile, nonvolatile memory (NVM) storage has emerged as a pervasive component in HPC systems because NVM provides massive amounts of memory capacity at affordable cost. Currently, for accelerator applications to use NVM, they must manually orchestrate data movement across multiple memories and this approach only performs well for applications with simple access behaviors. To address this issue, we developed DRAGON, a solution that enables all classes of GP-GPU applications to transparently compute on terabyte datasets residing in NVM. DRAGON leverages the page-faulting mechanism on the recent NVIDIA GPUs by extending capabilities of CUDA Unified Memory (UM). Our experimental results show that DRAGON transparently expands memory capacity and obtain additional speedups via automated I/O and data transfer overlapping.
- Research Organization:
- Oak Ridge National Lab. (ORNL), Oak Ridge, TN (United States)
- Sponsoring Organization:
- USDOE
- DOE Contract Number:
- AC05-00OR22725
- OSTI ID:
- 1489577
- Resource Relation:
- Conference: The International Conference for High Performance Computing, Networking, Storage, and Analysis - Dallas, Texas, United States of America - 11/11/2018 10:00:00 AM-11/16/2018 10:00:00 AM
- Country of Publication:
- United States
- Language:
- English
Similar Records
Distributed out-of-memory NMF on CPU/GPU architectures
GPU-Centric Communication on NVIDIA GPU Clusters with InfiniBand: A Case Study with OpenSHMEM