Towards Buffer Management with Tiered Main Memory

X Hao, X Zhou, X Yu, M Stonebraker - … of the ACM on Management of …, 2024 - dl.acm.org
The scaling of per-GB DRAM cost has slowed down in recent years. Recent research has
suggested that adding remote memory to a system can further reduce the overall memory …

FragTracer: Real-Time Fragmentation Monitoring Tool for F2FS File System

M Cho, D Kang - Sensors, 2023 - mdpi.com
Emerging hardware devices (eg, NVMe SSD, RISC-V, etc.) open new opportunities for
improving the overall performance of computer systems. In addition, the applications try to …

BypassD: Enabling fast userspace access to shared SSDs

S Yadalam, C Alverti, V Karakostas, J Gandhi… - Proceedings of the 29th …, 2024 - dl.acm.org
Modern storage devices, such as Optane NVMe SSDs, offer ultra-low latency of a few
microseconds and high bandwidth of multiple gigabytes per second. At these speeds, the …

Characterizing the Dilemma of Performance and Index Size in Billion-Scale Vector Search and Breaking It with Second-Tier Memory

R Cheng, Y Peng, X Wei, H Xie, R Chen… - arXiv preprint arXiv …, 2024 - arxiv.org
Vector searches on large-scale datasets are critical to modern online services like web
search and RAG, which necessity storing the datasets and their index on the secondary …

So Far and yet so Near-Accelerating Distributed Joins with CXL

A Baumstark, M Paradies, KU Sattler, S Kläbe… - Proceedings of the 20th …, 2024 - dl.acm.org
Distributed partitioned joins are one of the most expensive operators in distributed DBMSs
where a major part of the execution is attributed to network transfer costs. Although high …

GPU Graph Processing on CXL-Based Microsecond-Latency External Memory

S Sano, Y Bando, K Hiwada, H Kajihara… - Proceedings of the SC' …, 2023 - dl.acm.org
In GPU graph analytics, the use of external memory such as the host DRAM and solid-state
drives is a cost-effective approach to processing large graphs beyond the capacity of the …

Toward CXL-Native Memory Tiering via Device-Side Profiling

Z Zhou, Y Chen, T Zhang, Y Wang, R Shu, S Xu… - arXiv preprint arXiv …, 2024 - arxiv.org
The Compute Express Link (CXL) interconnect has provided the ability to integrate diverse
memory types into servers via byte-addressable SerDes links. Harnessing the full potential …

TieredHM: Hotspot-Optimized Hash Indexing for Memory Semantic SSD Based Hybrid Memory

W Huang, J Zhou, M Wang, Y Zhou… - … on Computer-Aided …, 2024 - ieeexplore.ieee.org
Memory-semantic solid-state drives (MS-SSDs) provide a promising opportunity to enable
the hybrid memory architecture (HMA). The memory-semantic interface enables the CPUs to …

Position: CXL Shared Memory Programming: Barely Distributed and Almost Persistent

Y Xu, S Mahar, Z Liu, M Shen, S Swanson - arXiv preprint arXiv …, 2024 - arxiv.org
While Compute Express Link (CXL) enables support for cache-coherent shared memory
among multiple nodes, it also introduces new types of failures--processes can fail before …

Tiered hashing: Revamping hash indexing under a unified memory-storage hierarchy

J Zhou, J Wu, W Huang, Y Zhou, F Wu, L Shi… - Proceedings of the …, 2022 - dl.acm.org
NAND flash-based Solid State Drives (SSDs) provide a promising opportunity to enable the
unified memory-storage hierarchy (UMH). The UMH renders a single memory address …