Nimble page management for tiered memory systems

Z Yan, D Lustig, D Nellans… - Proceedings of the Twenty …, 2019 - dl.acm.org
Software-controlled heterogeneous memory systems have the potential to increase the
performance and cost efficiency of computing systems. However they can only deliver on …

Efficient hardware-assisted logging with asynchronous and direct-update for persistent memory

J Jeong, CH Park, J Huh… - 2018 51st Annual IEEE …, 2018 - ieeexplore.ieee.org
Supporting atomic durability in emerging persistent memory requires data consistency
across potential system failures. For atomic durability support in the non-volatile memory, the …

Hinuma: Numa-aware data placement and migration in hybrid memory systems

Z Duan, H Liu, X Liao, H Jin, W Jiang… - 2019 IEEE 37th …, 2019 - ieeexplore.ieee.org
Non-uniform memory access (NUMA) architectures feature asymmetrical memory access
latencies on different CPU nodes. Hybrid memory systems composed of non-volatile …

Design and implementation of bandwidth-aware memory placement and migration policies for heterogeneous memory systems

S Yu, S Park, W Baek - Proceedings of the International Conference on …, 2017 - dl.acm.org
Heterogeneous memory systems that comprise memory nodes based on widely-different
device technologies (eg, DRAM and nonvolatile memory (NVM)) are emerging in various …

HotR: Alleviating read/write interference with hot read data replication for flash storage

S Wu, W Zhang, B Mao, H Jiang - 2019 Design, Automation & …, 2019 - ieeexplore.ieee.org
The read/write interference problem of flash storage remains a critical concern under
workloads with a mixture of read and write requests. To significantly improve the read …

Ohm-gpu: Integrating new optical network and heterogeneous memory into gpu multi-processors

J Zhang, M Jung - MICRO-54: 54th Annual IEEE/ACM International …, 2021 - dl.acm.org
Traditional graphics processing units (GPUs) suffer from the low memory capacity and
demand for high memory bandwidth. To address these challenges, we propose Ohm-GPU …

Distributed Page Table: Harnessing Physical Memory as an Unbounded Hashed Page Table

O Kwon, Y Lee, J Park, S Jang, B Tak… - 2024 57th IEEE/ACM …, 2024 - ieeexplore.ieee.org
Virtual memory systems rely on the page table, a crucial component that maps virtual
addresses to physical addresses (ie, address translation). While the Radix Page Table …

Straggler-aware parallel graph processing in hybrid memory systems

W Liu, H Liu, X Liao, H Jin… - 2021 IEEE/ACM 21st …, 2021 - ieeexplore.ieee.org
Hybrid memory systems composed of DRAM and Non-Volatile Memory (NVM) can offer very
large memory capacity for data-intensive applications such as graph processing. The …

Hotness-and lifetime-aware data placement and migration for high-performance deep learning on heterogeneous memory systems

M Han, J Hyun, S Park, W Baek - IEEE Transactions on …, 2019 - ieeexplore.ieee.org
Heterogeneous memory systems that comprise memory nodes with disparate architectural
characteristics (eg, DRAM and high-bandwidth memory (HBM)) have surfaced as a …

MORSE: Memory Overwrite Time Guided Soft Writes to Improve ReRAM Energy and Endurance

D Singh, D Yeung - Proceedings of the 2024 International Conference …, 2024 - dl.acm.org
ReRAM is an attractive main memory technology due to its high density and low idle power.
However, ReRAM exhibits costly writes, especially in terms of energy and endurance. Prior …