Software Support for Heterogeneous Memories in HPC
- funded by: LANL
- funding level: $315,429
- duration: 11/09/2018 - 09/30/2021
This project proposes to explore different solutions of software support for
heterogeneous memory architectures for future supercomputers. Its
primary aim will be to seamlessly integrate the new memory
technologies in to the existing architecture support while taking full
advantage of its characteristics for existing HPC applications and
making the programmers job easier for developing new applications for
the future systems.
Publications:
-
"Performance characterization of a DRAM-NVM
hybrid memory architecture for HPC applications
using Intel Optane DC Persistent Memory Modules"
by Onkar Patil, Latchesar Ionkov, Jason Lee, Frank Mueller, Michael Lang,
in International Symposium on Memory Systems (MEMSYS), Sep/Oct 2019, pages.
- Using Non-Volatile
Memory in High Performance Computing to Shrink the Size of
Clusters by Onkar Patil, Latchesar Ionkov, Jason Lee, Frank
Mueller, Michael Lang, Referred ACM SRC Poster at Supercomputing (SC'19)
Nov 2019.
-
"Symbiotic HW Cache and SW DTLB Prefetching for DRAM/NVM Hybrid Memory"
by Onkar Patil, Frank Mueller, Latchesar Ionkov, Jason Lee and Michael Lang,
in IEEE Symposium on Modelling, Analysis, and Simulation of Computer
and Telecommunication Systems (MASCOTS), Nov 2020.
-
PEARS: A Performance-Aware Static and Dynamic Framework for Heterogeneous Memory
by Onkar Patil, Latchesar Ionkov, Jason Lee, Frank Mueller, Michael Lang,
in International Symposium on Memory Systems (MEMSYS), Oct 2021, pages.
-
NVM-based energy and cost efficient HPC clusters
by Onkar Patil, Latchesar Ionkov, Jason Lee, Frank Mueller, Michael Lang,
in International Symposium on Memory Systems (MEMSYS), Oct 2021, pages.
Theses: