Dds: Dpu-optimized disaggregated storage

Q Zhang, P Bernstein, B Chandramouli, J Hu… - arxiv preprint arxiv …, 2024 - arxiv.org
This extended report presents DDS, a novel disaggregated storage architecture enabled by
emerging networking hardware, namely DPUs (Data Processing Units). DPUs can optimize …

SepHash: A Write-Optimized Hash Index On Disaggregated Memory via Separate Segment Structure

X Min, K Lu, P Liu, J Wan, C **e, D Wang… - Proceedings of the …, 2024 - dl.acm.org
Disaggregated memory separates compute and memory resources into independent pools
connected by fast RDMA (Remote Direct Memory Access) networks, which can improve …

Scythe: A Low-latency RDMA-enabled Distributed Transaction System for Disaggregated Memory

K Lu, S Zhao, H Shan, Q Wei, G Li, J Wan… - ACM Transactions on …, 2024 - dl.acm.org
Disaggregated memory separates compute and memory resources into independent pools
connected by RDMA (Remote Direct Memory Access) networks, which can improve memory …

EDM: An Ultra-Low Latency Ethernet Fabric for Memory Disaggregation

W Su, V Shrivastav - arxiv preprint arxiv:2411.08300, 2024 - arxiv.org
Achieving low remote memory access latency remains the biggest challenge in realizing
memory disaggregation over Ethernet inside the datacenter. We present EDM that tries to …

RPCAcc: A High-Performance and Reconfigurable PCIe-attached RPC Accelerator

J Zhang, H Huang, X Xu, X Li, M Liu, Z Wang - arxiv preprint arxiv …, 2024 - arxiv.org
The emerging microservice/serverless-based cloud programming paradigm and the rising
networking speeds leave the RPC stack as the predominant data center tax. Domain …

A Programming Model for Disaggregated Memory over CXL

G Assa, M Friedman, O Lahav - arxiv preprint arxiv:2407.16300, 2024 - arxiv.org
CXL (Compute Express Link) is an emerging open industry-standard interconnect between
processing and memory devices that is expected to revolutionize the way systems are …

DPDPU: Data Processing with DPUs

J Hu, PA Bernstein, J Li, Q Zhang - arxiv preprint arxiv:2407.13658, 2024 - arxiv.org
Improving the performance and reducing the cost of cloud data systems is increasingly
challenging. Data processing units (DPUs) are a promising solution, but utilizing them for …

Disaggregated Memory with SmartNIC Offloading: a Case Study on Graph Processing

J Wahlgren, G Schieffer, M Gokhale… - 2024 IEEE 36th …, 2024 - ieeexplore.ieee.org
Disaggregated memory breaks the boundary of monolithic servers to enable memory
provisioning on demand. Using network-attached memory to provide memory expansion for …

DFabric: Scaling Out Data Parallel Applications with CXL-Ethernet Hybrid Interconnects

X Zhang, K Liu, Y Chang, K Zhang, M Chen - arxiv preprint arxiv …, 2024 - arxiv.org
Emerging interconnects, such as CXL and NVLink, have been integrated into the intra-host
topology to scale more accelerators and facilitate efficient communication between them …

Toward Zero-waste Terabit Networked Systems

L Yu - 2024 - search.proquest.com
To support modern applications, computer networks perform a plethora of auxiliary functions
beyond basic application data forwarding. Obvious examples include serialization and …