Durable transactional memory can scale with timestone

RM Krishnan, J Kim, A Mathew, X Fu… - Proceedings of the …, 2020 - dl.acm.org
Non-volatile main memory (NVMM) technologies promise byte addressability and near-
DRAM access that allows developers to build persistent applications with common load and …

Nap: A {Black-Box} Approach to {NUMA-Aware} Persistent Memory Indexes

Q Wang, Y Lu, J Li, J Shu - 15th USENIX Symposium on Operating …, 2021 - usenix.org
We present Nap, a black-box approach that converts concurrent persistent memory (PM)
indexes into NUMA-aware counterparts. Based on the observation that real-world workloads …

Falcon: Fast OLTP Engine for Persistent Cache and Non-Volatile Memory

Z Ji, K Chen, L Wang, M Zhang, Y Wu - Proceedings of the 29th …, 2023 - dl.acm.org
Non-volatile memory (NVM) has the properties of both byte addressable and persistence,
which provides new opportunities for building on-line transaction processing (OLTP) …

{CrossFS}: A cross-layered {Direct-Access} file system

Y Ren, C Min, S Kannan - 14th USENIX Symposium on Operating …, 2020 - usenix.org
We design CrossFS, a cross-layered direct-access file system disaggregated across user-
level, firmware, and kernel layers for scaling I/O performance and improving concurrency …

Hardware transactional memory meets memory persistency

D Castro, P Romano, J Barreto - Journal of Parallel and Distributed …, 2019 - Elsevier
Abstract Persistent Memory (PM) and Hardware Transactional Memory (HTM) are two recent
architectural developments whose joint usage promises to drastically accelerate the …

{ArchTM}:{Architecture-Aware}, high performance transaction for persistent memory

K Wu, J Ren, I Peng, D Li - 19th USENIX Conference on File and Storage …, 2021 - usenix.org
Failure-atomic transactions are a critical mechanism for accessing and manipulating data on
persistent memory (PM) with crash consistency. We identify that small random writes in …

Practical client-side replication: Weak consistency semantics for insecure settings

A van der Linde, J Leitão, N Preguiça - Proceedings of the VLDB …, 2020 - dl.acm.org
Client-side replication and direct client-to-client synchronization can be used to create highly
available, low-latency interactive applications. Causal consistency, the strongest available …

HydraList: A scalable in-memory index using asynchronous updates and partial replication

A Mathew, C Min - Proceedings of the VLDB Endowment, 2020 - dl.acm.org
Increased capacity of main memory has led to the rise of in-memory databases. With disk
access eliminated, efficiency of index structures has become critical for performance in these …

Mv-rlu: Scaling read-log-update with multi-versioning

J Kim, A Mathew, S Kashyap… - Proceedings of the …, 2019 - dl.acm.org
This paper presents multi-version read-log-update (MV-RLU), an extension of the read-log-
update (RLU) synchronization mechanism. While RLU has many merits including an …

{Z-Journal}: Scalable {Per-Core} journaling

J Kim, C Campes, JY Hwang, J Jeong… - 2021 USENIX Annual …, 2021 - usenix.org
File system journaling critically limits the scalability of a file system because all simultaneous
write operations coming from multiple cores must be serialized to be written to the journal …