Faster network setup: End-to-end configuration of advanced network features automated, fully optimized for AI workloads.<\/li>\n<\/ul>\n\n\n\nSpectrum-4 Ethernet Switch <\/strong><\/strong><\/p>\n\n\n\nThe Spectrum-4 switch is built on a 51.2Tbps ASIC, supporting up to 128 400G Ethernet ports in a single 2U switch. Spectrum-4 is the first Ethernet switch designed for AI workloads. For AI, RoCE has been extended:<\/p>\n\n\n\n
\nRoCE adaptive routing<\/li>\n\n\n\n RoCE performance isolation<\/li>\n\n\n\n Effective bandwidth enhancement on large-scale standard Ethernet<\/li>\n\n\n\n Low latency, low jitter, and short tail latency<\/li>\n<\/ul>\n\n\n\nNVIDIA Spectrum-4 400 Gigabit<\/strong> Ethernet Switch<\/strong><\/strong><\/p>\n\n\n\nBlueField-3 DPU<\/strong><\/strong><\/p>\n\n\n\nThe NVIDIA BlueField-3 DPU is the third-generation data center infrastructure chip that enables organizations to build software-defined, hardware-accelerated IT infrastructures from cloud to core data center to edge. With 400Gb\/s Ethernet network connectivity, the BlueField-3 DPU can offload, accelerate, and isolate software-defined networking, storage, security, and management functions, thereby significantly improving the performance, efficiency, and security of data centers. BlueField-3 provides multi-tenant, secure performance capabilities for north-south and east-west traffic in cloud AI data centers powered by Spectrum-X.<\/p>\n\n\n\nNVIDIA BlueField-3 400Gb\/s<\/strong> Ethernet DPU<\/strong><\/strong><\/p>\n\n\n\nBlueField-3 is built for AI acceleration, integrating an all-to-all engine for AI, NVIDIA GPUDirect, and NVIDIA Magnum IO GPUDirect Storage acceleration technologies.<\/p>\n\n\n\n
In addition, it also has a special network interface mode (NIC) mode that leverages local memory to accelerate large AI clouds. These clouds contain a large number of queue pairs that can be accessed at local addresses instead of using system memory. Finally, it includes NVIDIA Direct Data Placement (DDP) technology to enhance RoCE adaptive routing.<\/p>\n\n\n\n
<\/span>NVIDIA End-To-End Physical Layer (PHY) <\/strong><\/strong><\/span><\/h2>\n\n\n\nSpectrum-X is the only Ethernet network platform built on the same 100G SerDes channel, from switch to DPU to GPU, using NVIDIA\u2019s SerDes technology.<\/p>\n\n\n\n
NVIDIA\u2019s SerDes ensures excellent signal integrity and the lowest bit error rate (BER), greatly reducing the power consumption of the AI cloud. This powerful SerDes technology, combined with NVIDIA\u2019s Hopper GPUs, Spectrum-4, BlueField-3, and Quantum InfiniBand product portfolio, achieves the perfect balance of power efficiency and performance.<\/p>\n\n\n\nTypical Spectrum-X network topology <\/strong><\/strong><\/p>\n\n\n\nSerDes technology plays an important role in modern data transmission, as it can convert parallel data to serial data, and vice versa.<\/p>\n\n\n\n
Using SerDes technology uniformly across all network devices and components in the network or system brings many advantages:<\/p>\n\n\n\n
Cost and power efficiency: The SerDes used by NVIDIA Spectrum-X is optimized for high power efficiency, and does not require gearboxes in the network, which are used to bridge different data rates. Using gearboxes not only increases the complexity of the data path but also adds extra cost and power consumption. Eliminating the need for these gearboxes reduces the initial investment and the operational costs associated with power and cooling.<\/p>\n\n\n\n
System design efficiency: Using the best SerDes technology uniformly in the data center infrastructure provides better signal integrity, reduces the need for system components, and simplifies system design. At the same time, using the same SerDes technology also makes operation easier and improves availability.<\/p>\n\n\n\n
NVIDIA Acceleration Software <\/strong><\/strong><\/p>\n\n\n\nNetQ<\/strong><\/p>\n\n\n\nNVIDIA NetQ is a highly scalable network operations toolset for real-time AI network visibility, troubleshooting, and verification. NetQ leverages NVIDIA switch telemetry data and NVIDIA DOCA telemetry to provide insights into switch and DPU health, integrating the network into the organization\u2019s MLOps system.<\/p>\n\n\n\n
In addition, NetQ traffic telemetry can map the flow paths and behaviors across switch ports and RoCE queues, to analyze the flow situation of specific applications.<\/p>\n\n\n\n
NetQ samples analyze and report the latency (max, min, and average) and buffer occupancy details on each flow path. NetQ GUI reports all possible paths, the details of each path, and the flow behavior. Combining telemetry telemetry with traffic telemetry helps network operators proactively identify the root causes of server and application problems.<\/p>\n\n\n\n
Spectrum SDK<\/p>\n\n\n\n
NVIDIA Ethernet Switch Software Development Kit (SDK) provides the flexibility to implement switching and routing functionality, with complex programmability that does not affect packet rate, bandwidth, or latency performance. With the SDK, server, and network OEMs and network operating system (NOS), vendors can leverage the advanced network features of the Ethernet switch series integrated circuits (ICs) to build flexible, innovative, and cost-optimized switching solutions.<\/p>\n\n\n\n
NVIDIA DOCA<\/p>\n\n\n\n
NVIDIA DOCA is the key to unleashing the potential of the NVIDIA BlueField DPU, offloading, accelerating, and isolating data center workloads. With DOCA, developers can address the growing performance and security demands of modern data centers by creating software-defined, cloud-native, DPU-accelerated services with zero-trust protection.<\/p>\n\n\n\n