HPC > Networking
Tech Focus Networking
The latest networking technologies for HPC in 2023 T
he choice to develop a bespoke system or use an end-to-end solution to support scientific
research projects depends on workloads, scale and budget. There are many ways to solve these challenges, but the answer for each organisation will depend on the scale of the challenge and the demand for latency, which inevitably drives the cost of deployment.
As the demand for better performance leads to more highly parallel solutions
and data-intensive computing systems, networking technology is becoming increasingly important in supporting sustained application performance. Networking companies provide high- speed access to data, which can support high throughput workloads. While the main networking technologies used in HPC are based on either Ethernet or InfinBand, there are also other technologies that use PCI-Express to develop networking fabrics to support other ultra-low latency,
high-bandwidth workloads. This is generally based on the use of high-speed, real-time systems, clustered databases, general networking, web services and industrial embedded applications. With the increasing use of AI used in scientific computing, there is a growth in the number of users that require high-speed networking to support research outcomes. These scientists are turning to networking technology providers to support their use of advanced computing infrastructure.
Networking products on the market now The DustPhotonics CARMEL
Ayar Labs is disrupting the traditional performance, cost and efficiency curves of the semiconductor and computing industries by delivering up to a 1,000x improvement in interconnect bandwidth density at one-tenth of the power. They use standard CMOS processing to develop high-speed, high-density, low-power optical interconnect ‘chiplets’ and lasers to replace traditional electrical I/O. DustPhotonics develops
and provides a technology platform for end-to-end Silicon Photonics solutions, addressing the constantly growing needs of hyper- growth data players. Our technology solutions facilitate high-volume manufacturing which enables true scalability. The company’s technology
platform is uniquely built to support the optical networking markets that require higher bandwidth and higher speeds while lowering cost, as well as power consumption.
Product Family supports 400Gb/s and 800Gb/s applications with 400Gb/s DR4 Transmit Photonics IC with integrated laser (TOSA). CARMEL8 delivers 800Gb/s DR8 Transmit Photonics IC with integrated laser - scalable to 1.6 Tb/s. Eoptolink is dedicated
to researching, developing and manufacturing, and markets a diverse portfolio of high-performance, optical transceiver modules and optical components for various ICT applications, such as data centre, telecom networks (FTTx, LTE and transmission), security monitoring and smart grid. Eoptolink is a manufacturer of high-speed optical transceivers. At the heart of the operation is an R&D team that continuously pushes the boundaries of technological advancement to help shape the industry. Eoptolink delivers 100G, 200G, 400G,
30 Scientific Computing World Summer 2023
800G transceiver portfolio with world-class quality and reliability. Founded as a spin-off from the University of Heidelberg in 2011, EXTOLL is a company that delivers products to the high-performance interconnect IP market. Initially active only in the high-performance computing market (specifically networks for HPC), EXTOLL became a semiconductor IP company with early market success in communication, space, industrial and automotive markets. GigaIO provides a rack-scale
composable infrastructure solution that delivers the flexibility and agility of the cloud. GigaIO is committed to open standards and a contributing member to Linux, to the PCIe standard, and to the CXL consortium. It can orchestrate any
compute, acceleration (CPUs, GPUs, FPGAs, ASICs), storage, memory (3D-XPoint) or
networking resource for any workload using an enterprise- class, easy-to-use and open standards high-performance network. It can deploy, expand, reduce or replace all rack resources dynamically in real-time, and fully automate on-premise bare-metal cloud- class infrastructure, delivering higher throughput. GigaIO’s FabreX
technology creates a flexible, performant architecture for your dynamically changing workloads, combining sub- microsecond latency and high-bandwidth networking between all resources and servers in HPC systems. With the pervasive use of AI
across industries, enterprise data centres carry a large number of vital services. Huawei CloudFabric 2.0 solution provides customers with a next-generation data centre network that delivers super capacity, intelligent experience and autonomous driving, helping enterprises
Page 1 |
Page 2 |
Page 3 |
Page 4 |
Page 5 |
Page 6 |
Page 7 |
Page 8 |
Page 9 |
Page 10 |
Page 11 |
Page 12 |
Page 13 |
Page 14 |
Page 15 |
Page 16 |
Page 17 |
Page 18 |
Page 19 |
Page 20 |
Page 21 |
Page 22 |
Page 23 |
Page 24 |
Page 25 |
Page 26 |
Page 27 |
Page 28 |
Page 29 |
Page 30 |
Page 31 |
Page 32 |
Page 33 |
Page 34 |
Page 35 |
Page 36 |
Page 37 |
Page 38 |
Page 39 |
Page 40 |
Page 41 |
Page 42
