HPC cloud for scientific and business applications: taxonomy, vision, and research challenges
High performance computing (HPC) clouds are becoming an alternative to on-premise
clusters for executing scientific applications and business analytics services. Most research …
clusters for executing scientific applications and business analytics services. Most research …
Using {One-Sided}{RDMA} Reads to Build a Fast,{CPU-Efficient}{Key-Value} Store
C Mitchell, Y Geng, J Li - … Annual Technical Conference (USENIX ATC 13 …, 2013 - usenix.org
Recent technological trends indicate that future datacenter networks will incorporate High
Performance Computing network features, such as ultra-low latency and CPU bypassing …
Performance Computing network features, such as ultra-low latency and CPU bypassing …
Softsku: Optimizing server architectures for microservice diversity@ scale
The variety and complexity of microservices in warehouse-scale data centers has grown
precipitously over the last few years to support a growing user base and an evolving product …
precipitously over the last few years to support a growing user base and an evolving product …
{ROLEX}: A Scalable {RDMA-oriented} Learned {Key-Value} Store for Disaggregated Memory Systems
Disaggregated memory systems separate monolithic servers into different components,
including compute and memory nodes, to enjoy the benefits of high resource utilization …
including compute and memory nodes, to enjoy the benefits of high resource utilization …
ScaleStore: A fast and cost-efficient storage engine using DRAM, NVMe, and RDMA
In this paper, we propose ScaleStore, a novel distributed storage engine that exploits DRAM
caching, NVMe storage, and RDMA networking to achieve high performance, cost-efficiency …
caching, NVMe storage, and RDMA networking to achieve high performance, cost-efficiency …
An integrated tutorial on InfiniBand, verbs, and MPI
P MacArthur, Q Liu, RD Russell… - … Surveys & Tutorials, 2017 - ieeexplore.ieee.org
This tutorial presents the details of the interconnection network utilized in many high
performance computing (HPC) systems today.“InfiniBand” is the hardware interconnect …
performance computing (HPC) systems today.“InfiniBand” is the hardware interconnect …
The end of a myth: Distributed transactions can scale
The common wisdom is that distributed transactions do not scale. But what if distributed
transactions could be made scalable using the next generation of networks and a redesign …
transactions could be made scalable using the next generation of networks and a redesign …
Balancing {CPU} and network in the cell distributed {B-Tree} store
C Mitchell, K Montgomery, L Nelson, S Sen… - 2016 USENIX Annual …, 2016 - usenix.org
In traditional client-server designs, all requests are processed at the server storing the state,
thereby maintaining strict locality between computation and state. The adoption of RDMA …
thereby maintaining strict locality between computation and state. The adoption of RDMA …
Designing distributed tree-based index structures for fast rdma-capable networks
Over the past decade, in-memory database systems have become prevalent in academia
and industry. However, large data sets often need to be stored distributed across the …
and industry. However, large data sets often need to be stored distributed across the …
[PDF][PDF] DPI: the data processing interface for modern networks
As data processing evolves towards large scale, distributed platforms, the network will
necessarily play a substantial role in achieving efficiency and performance. Increasingly …
necessarily play a substantial role in achieving efficiency and performance. Increasingly …