Category Archives: Network Card

Accelerating Data Centers: FS Unveils Next-Gen 400G Solutions

Posted on by

As large-scale data centers transition to faster and more scalable infrastructures and with the rapid adoption of hyperscale cloud infrastructures and services, existing 100G networks fall short in meeting current demands. As the next-generation mainstream port technology, 400G significantly increases network bandwidth, enhances link utilization, and assists operators, OTT providers, and other clients in effectively managing unprecedented data traffic growth.

To meet the demand for higher data rates, FS has been actively developing a series of 400G products, including 400G switches, optical modules, cables, and network adapters.

FS 400G Switches

The emergence of 400G data center switches has facilitated the transition from 100G to 400G in data centers, providing flexibility for building large-scale leaf and spine designs while reducing the total number of network devices. This reduction can save costs and decrease power consumption. Whether it’s the powerful N9510-64D or the versatile N9550 series, FS 400G data center switches can deliver the performance and flexibility required for today’s data-intensive applications.

Of particular note is that, as open network switches, the N8550 and N9550 series switches can enhance flexibility by freely choosing preferred operating systems. They are designed to meet customer requirements by providing comprehensive support for L3 features, SONiC and Broadcom chips, and data center functionalities. Additionally, FS offers PicOS-based open network switch operating system solutions, which provide a more flexible, programmable, and scalable network operating system (NOS) at a lower total cost of ownership (TCO).

FS 400G Transceivers

FS offers two different types of packaging for its 400G transceivers: QSFP-DD and OSFP, developed to support 400G with performance as their hallmark. Additionally, FS provides CFP2 DCO transceivers for coherent transmission at various rates (100G/200G/400G) in DWDM applications. Moreover, FS has developed InfiniBand cables and transceivers to enhance the performance of HPC networks, meeting the requirements for high bandwidth, low latency, and highly reliable connections.

FS conducts rigorous testing on its 400G optical modules using advanced analytical equipment, including TX/RX testing, temperature measurement, rate testing, and spectrometer evaluation tests, to ensure the performance and compatibility of the optical modules.

FS 400G Cables

When planning 400G Ethernet cabling or connection schemes, it’s essential to choose devices with low insertion loss and good return loss to meet the performance requirements of high-density data center links. FS offers various wiring options, including DAC/AOC cables and breakout cables. FS DAC/AOC breakout cables provide three connection types to meet high-density requirements for standard and combination connector configurations: 4x100G, 2x200G, and 8x50G. Their low insertion loss and ultra-low crosstalk effectively enhance transmission performance, while their high bend flexibility offers cost-effective solutions for short links.

FS 400G Network Adapters

FS 400G network adapters utilize the industry-leading ConnectX-7 series cards. The ConnectX-7 VPI card offers a 400Gb/s port for InfiniBand, ultra-low latency, and delivers between 330 to 3.7 billion messages per second, enabling top performance and flexibility to meet the growing demands of data center applications. In addition to all existing innovative features from previous versions, the ConnectX-7 card also provides numerous enhanced functionalities to further boost performance and scalability.

FS 400G Networking Soluitons

To maximize the utilization of the 400G product series, FS offers comprehensive 400G network solutions, such as solutions tailored for upgrading from 100G to high-density 400G data centers. These solutions provide diverse and adaptable networking options customized for cloud data centers and AI applications. They are designed to tackle the continuous increase in data center traffic and the growing need for high-bandwidth solutions in extensive 400G data center networks.

For more information about FS 400G products, please read FS 400G Product Family Introduction.

How FS Can Help

Register for an FS account now, choose from our range of 400G products and solutions tailored to your needs, and effortlessly upgrade your network.

Mastering the Basics of GPU Computing

Posted on by

It’s known that training large models is done on clusters of machines with preferably many GPUs per server. This article will introduce the professional terminology and common network architecture of GPU computing.

Exploring Key Components in GPU Computing

PCIe Switch Chip

In the domain of high-performance GPU computing, vital elements such as CPUs, memory modules, NVMe storage, GPUs, and network cards establish fluid connections via the PCIe (Peripheral Component Interconnect Express) bus or specialized PCIe switch chips.

NVLink

NVLink is a wire-based serial multi-lane near-range communications link developed by Nvidia. Unlike PCI Express, a device can consist of muıltiple NVLinks, and devices use mesh networking to communicate instead of a central hub. The protocol was first announced in March 2014 and uses proprietary high-speed signaling interconnect (NVHS).

The technology supports full mesh interconnection between GPUs on the same node. And the development from NVLink 1.0, NVLink 2.0, NVLink 3.0 to NVLink 4.0 has significantly enhanced the two-way bandwidth and improved the performance of GPU computing applications.

NVSwitch

NVSwitch is a switching chip developed by NVIDIA, designed specifically for high-performance computing and artificial intelligence applications. Its primary function is to provide high-speed, low-latency communication between multiple GPUs within the same host.

NVLink Switch

Unlike the NVSwitch, which is integrated into GPU modules within a single host, the NVLink Switch serves as a standalone switch specifically engineered for linking GPUs in a distributed computing environment.

HBM

Several GPU manufacturers have taken innovative ways to address the speed bottleneck by stacking multiple DDR chips to form so-called high-bandwidth memory (HBM) and integrating them with the GPU. This design removes the need for each GPU to traverse the PCIe switch chip when engaging its dedicated memory. As a result, this strategy significantly increases data transfer speeds, potentially achieving significant orders of magnitude improvements.

Bandwidth Unit

In large-scale GPU computing training, performance is directly tied to data transfer speeds, involving pathways such as PCIe, memory, NVLink, HBM, and network bandwidth. Different bandwidth units are used to measure these data rates.

Storage Network Card

The storage network card in GPU architecture connects to the CPU via PCIe, enabling communication with distributed storage systems. It plays a crucial role in efficient data reading and writing for deep learning model training. Additionally, the storage network card handles node management tasks, including SSH (Secure Shell) remote login, system performance monitoring, and collecting related data. These tasks help monitor and maintain the running status of the GPU cluster.

For the above in-depth exploration of various professional terms, you can refer to this article Unveiling the Foundations of GPU Computing-1 from FS community.

High-Performance GPU Fabric

NVSwitch Fabric

In a full mesh network topology, each node is connected directly to all the other nodes. Usually, 8 GPUs are connected in a full-mesh configuration through six NVSwitch chips, also referred to as NVSwitch fabric.

This fabric optimizes data transfer with a bidirectional bandwidth, providing efficient communication between GPUs and supporting parallel computing tasks. The bandwidth per line depends on the NVLink technology utilized, such as NVLink3, enhancing the overall performance in large-scale GPU clusters.

IDC GPU Fabric

The fabric mainly includes computing network and storage network. The computing network is mainly used to connect GPU nodes and support the collaboration of parallel computing tasks. This involves transferring data between multiple GPUs, sharing calculation results, and coordinating the execution of massively parallel computing tasks. The storage network mainly connects GPU nodes and storage systems to support large-scale data read and write operations. This includes loading data from the storage system into GPU memory and writing calculation results back to the storage system.

Want to know more about CPU fabric? Please check this article Unveiling the Foundations of GPU Computing-2 from FS community.

What is Fiber Optic Network Interface Card

Posted on by

Fiber network interface card, scientific name is Fiber Channel HBA. Fiber optic network card use 32/64-bit PCI bus network interface card, the estabishment of the PC or the connection between the server and the switch, to solve the bottleneck problem of the Intranet server NIC mode fiber optic transmission media interface, 32/64bit/66MHz’s Compact PCI bus interface truly support the efficient transmission; integrated communication controller chip to ease the pressure of the CPU data processing; In addition also provided VLAN tagging, data flow priority, power management and other intelligent processing power; driver The library supports multiple operating system platforms. Transfer Protocol of fiber channel protocol, typically via a fiber optic cable connected to the fiber channel switch. Interface types of optical and electrical interfaces. The optical ports are generally via a fiber optic cable for data transmission, interface module is commonly SFP (transmission rate of 2Gb/s) and GBIC (GB/s), the corresponding interface for SC and LC. The electrical port interface type is gererally the DB9 pin or HSSDC.

Fiber Ethernet card shares of the main application of fiber optic Ethernet communication technology, fiber optic network card can provide users with Fast Ethernet computers on the network to provide reliable fiber connection, especially for the access point distance exceeds five lines access distance (100m) place, can completely replace the current commonly used the external photoelectric converter Ethernet RJ45 interface card network structure, to provide users with reliable fiber-to-the-home and fiber to the desktop solution. The user can use the occasion to select the optical interface parameters (including connectors, single / multi-mode fiber, working distance, etc.).

Identification of true and false of the network card

a. Use spray tin plate

High quality network card board commonly used spray tin plate, the fiber optic network adapter plate is white, while the poor network card is yellow.

b. Use the high quality main control chip

The main control chip is the most important parts of the network card, it often determines the merits of the performance of the card, so high quality network card used in the main control chip should be mature products on the market. Market a lot of low quality network card in order to reduce costs and using an older version of the main control chip, which undoubtedly played a discount to the performance of the network card.

c. Most of them adopt SMT type components

High quality network card in addition to the electrolytic capacitors and high voltage ceramic capacitors, and other resistance containers of more reliable and stable than the plug-SMT chip components. The poor quality of most of the network card using the plug-in, which makes heat dissipation and stability of the network card is not good enough.

d. Titanium Goldfinger plating

The high quality network card Goldfinger selection of the titanium gold production, increased its anti-jamming capability and reduced interference from other devices, while Goldfinger node at the arc-shaped design. Most of the poor quality of network card using titanium gold, node turning a right angle, the impact of signal transmission performance.

The factors to be considered in the purchase card

In correct selection of assembly, connection and set up card is often a prerequisite and necessary condition correctly connected network. In general, the purchase card to consider the following factors:

Network Type

Now more popular Ethernet, token ring, FDDI network, etc., should be selected according to the type of network to select the corresponding card.

Transmission Speed

Combined with the physical transmission medium can provide a maximum transmission rate should be based on the bandwidth requirements of server of workstation to select the transmission rate of the network card. Ethernet, for example, the speed options there are variety of 10Mbps, 10/100Mbps, 10bps, but not the rate the higher the more appropriate. For example, a computer connected to the twisted pair have only 100M transmission speed configuration 1000M card is a waste, because at best can only achieve a transmission rate of 100M.

Bus Type

Servers and workstations typically use the PCI, PCI-X or PCI-E bus intelligent card, the PC is basically no longer supported by the ISA connector, so when their PC purchase card, do not buy outdated ISA network card, but should be optional PCI, PCI-X and PCI-E card.

The server NIC support the interface

NIC ultimately with the network connection, so it must have an interface cable through its connection with other computer network equipment. Different network interfaces suitable for different network types, common interface Ethernet RJ-45 interface and LC, SC, FC fiber optic interface.

Price and Brand

Different rates, different brands of NIC large difference in price.

Source: www.fs.com