Related papers: CoRD: Converged RDMA Dataplane for High-Performanc…
Contemporary distributed computing workloads, including scientific computation, data mining, and machine learning, increasingly demand OS networking with minimal latency as well as high throughput, security, and reliability. However,…
Overheads in Operating System kernel network stacks and sockets have been hindering OSes from managing networking operations efficiently for years. Moreover, when building Remote Procedure Calls over TCP, certain TCP features do not match…
AI transport libraries move bytes efficiently, but they commonly assume that buffers are already correctly allocated, placed, shared, registered, and safe under completion and teardown pressure. This paper presents dmaplane, a Linux kernel…
The network interface adapter (NIC) is a critical component of a cloud server occupying a unique position. Not only is network performance vital to efficient operation of the machine, but unlike compute accelerators like GPUs, the network…
Although significant recent progress has been made in improving the multi-core scalability of high throughput transactional database systems, modern systems still fail to achieve scalable throughput for workloads involving frequent access…
Increasing data center network speed coupled with application requirements for high throughput and low latencies have raised the efficiency bar for network stacks. To reduce substantial kernel overhead in network processing, recent…
In order to fully utilize "big data", it is often required to use "big models". Such models tend to grow with the complexity and size of the training data, and do not make strong parametric assumptions upfront on the nature of the…
In this paper, we conduct systematic measurement studies to show that the high memory bandwidth consumption of modern distributed applications can lead to a significant drop of network throughput and a large increase of tail latency in…
Next generation high-performance RDMA-capable networks will require a fundamental rethinking of the design and architecture of modern distributed DBMSs. These systems are commonly designed and optimized under the assumption that the network…
Conventional wisdom holds that an efficient interface between an OS running on a CPU and a high-bandwidth I/O device should use Direct Memory Access (DMA) to offload data transfer, descriptor rings for buffering and queuing, and interrupts…
For deep learning inference on edge devices, hardware configurations achieving the same throughput can differ by 2$\times$ in power consumption, yet operators often struggle to find the efficient ones without exhaustive profiling. Existing…
Kernel-based online learning has often shown state-of-the-art performance for many online learning tasks. It, however, suffers from a major shortcoming, that is, the unbounded number of support vectors, making it non-scalable and unsuitable…
We propose network coding as an energy efficient data transmission technique in core networks with non-bypass and bypass routing approaches. The improvement in energy efficiency is achieved through reduction in the traffic flows passing…
Intersession network coding (NC) can provide significant performance benefits via mixing packets at wireless routers; these benefits are especially pronounced when NC is applied in conjunction with intelligent link scheduling. NC however…
Protected user-level libraries have been proposed as a way to allow mutually distrusting applications to safely share kernel-bypass services. In this paper, we identify and solve several previously unaddressed obstacles to realizing this…
The main goal of routing protocol is to efficiency delivers data from source to destination. All routing protocols are the same in this goal, but the way they adopt to achieve it is different, so routing strategy has an egregious role on…
Histograms are widely used in medical imaging, network intrusion detection, packet analysis and other stream-based high throughput applications. However, while porting such software stacks to the GPU, the computation of the histogram is a…
Major data centre providers are introducing RDMA-based networks for their tenants, as well as for operating the underlying infrastructure. In comparison to traditional socket-based network stacks, RDMA-based networks offer higher…
RDMA is vital for efficient distributed training across datacenters, but millisecond-scale latencies complicate the design of its reliability layer. We show that depending on long-haul link characteristics, such as drop rate, distance and…
Parallel processing, the core of High Performance Computing (HPC), was and still the most effective way in improving the speed of computer systems. For the past few years, the substantial developments in the computing power of processors…