The NVIDIA® ConnectX®-8 SuperNIC™ is optimized to supercharge hyperscale AI computing workloads. With support for both InfiniBand and Ethernet networking at up to 800 gigabits per second (Gb/s), ConnectX-8 SuperNIC delivers high-speed, efficient network connectivity, significantly enhancing system performance for AI factories and cloud data center environments.
| Model NO. | C8240(900-9X81Q-00CN-ST0) |
| Ports | Dual-Port |
| Technology | Infiniband |
| Interface Type | Qsfp112 |
| Specification | 16.7cm x 6.9cm |
| Origin | India / Israel / China |
| Transmission Rate | 400gbe |
| Function | Laop, Stackable, Vlan Support |
| Host Interface | Gen6 X16 |
| Transport Package | Packing |
| Trademark | Mellanox |

C8240(900-9X81Q-00CN-ST0)
C8240(900-9X81Q-00CN-ST0)
The NVIDIA® ConnectX®-8 SuperNIC™ is optimized to supercharge hyperscale AI computing workloads. With support for both InfiniBand and Ethernet networking at up to 800 gigabits per second (Gb/s), ConnectX-8 SuperNIC delivers high-speed, efficient network connectivity, significantly enhancing system performance for AI factories and cloud data center environments.
Powerful Networking for Generative AI
Central to NVIDIA’s AI networking portfolio, ConnectX-8 SuperNICs fuel the next wave of innovation in forming accelerated, massive-scale AI compute fabrics. They seamlessly integrate with next-gen NVIDIA networking platforms, providing end-
to-end 800Gb/s connectivity. These platforms offer the robustness, feature sets, and scalability required for trillion-parameter GPU computing and generative AI applications.
C8240(900-9X81Q-00CN-ST0)
With enhanced power efficiency, ConnectX-8 SuperNICs support the creation of sustainable AI data centers operating hundreds of thousands of GPUs, ensuring a future-ready infrastructure for AI advancements.
ConnectX-8 SuperNICs enable advanced routing and telemetry-based congestion control capabilities, achieving the highest network performance and peak AI workload efficiency. Additionally, ConnectX-8 InfiniBand SuperNICs extend the
capabilities of NVIDIA® Scalable Hierarchical Aggregation and Reduction Protocol to boost In-network computing in high-performance computing environments, further enhancing overall efficiency and performance.
Specification
| Model | NVIDIA SKU | Port Type | Supported Speed | Form Factor | PCIe Express | Socket Direct Extension Option | Crypto | Secure Boot | Bracket Type |
| C8240 | 900-9X81Q-00CN-ST0 | Dual-port QSFP112 | InfiniBand: NDR IB (Default) Ethernet: 400GbE | Half-Height, Half-Length (HHHL) | PCIe 6 x16 | YES | YES | YES | Tall Bracket |
| C8180 | 900-9X81E-00EX-ST0 | Single-cage OSFP | InfiniBand: 800Gbs XDR IB (Default) Ethernet: 2x400GbE | Half-Height, Half-Length (HHHL) | PCIe 6 x16 | YES | YES | YES | Tall Bracket |
| 900-9X81E-00EX-DT0 | Single-cage OSFP | InfiniBand: 800Gbs XDR IB (Default) Ethernet: 2x400GbE | Half-Height, Half-Length (HHHL) | PCIe 6 x16 | YES | YES | YES | Tall Bracket | |
| C8180LPartner Cooled | 900-9X81E-00EX-SL0 | Single-cage OSFP | InfiniBand: 800Gbs XDR IB (Default) Ethernet: 2x400GbE | Half-Height, Half-Length (HHHL) | PCIe 6 x16 | YES | YES | YES | Tall Bracket |
| Physical | SuperNIC Dimensions: PCIe Half Height, Half Length 2.69 in. x 6.58 in. (68.50mm x 168.40mm) | ||
| Interfaces | SeeSupported Interfaces | ||
| PCI Express Interface | Gen6 SERDES @ 64GT/s, x16 lanes (Gen 5 compatible) | ||
| Optional: Additional PCIe x16 Gen5 @ SERDES 32GT/s through the PCIe auxiliary card and MCIO harness | |||
| Networking Port: Single cage OSFP InfiniBand and Ethernet | |||
| Data Rate | InfiniBand (Default) | XDR/NDR/HDR/HDR100/EDR/SDR | |
| Ethernet | 400/200/100 Gb/s Ethernet | ||
| Protocol Support | InfiniBand: IBTA v1.7aAuto-Negotiation: XDR (4 lanes x 200Gb/s per ) port, NDR (4 lanes x 100Gb/s per lane) port, NDR200 (2 lanes x 100Gb/s per lane) port, HDR (50Gb/s per lane) port, HDR100 (2 lane x 50Gb/s per lane) port, EDR (25Gb/s per lane) port, FDR (14.0625Gb/s per lane), 1X/2X/4X SDR (2.5Gb/s per lane). | ||
| Ethernet: 400GAUI-4 C2M, 400GBASE-CR4, 200GAUI-2 C2M, 200GAUI-4 C2M, 200GBASE-CR4, 100GAUI-2 C2M, 100GAUI-1 C2M, 100GBASE-CR4, 100GBASE-CR2, 100GBASE-CR1, 50GAUI-2 C2M, 50GAUI-1 C2M, 50GBASE-CR, 50GBASE-R2 , 40GBASE-CR4, 40GBASE-R2, 25GBASE-R, 10GBASE-R, 10GBASE-CX4, 1000BASE-CX, CAUI-4 C2M, 25GAUI C2M, XLAUI C2M , XLPPI, SFI | |||
| Capabilities | 900-9X81Q-00CN-ST0 | Secure Boot Enabled, Crypto Enabled with x16 PCIe extension option | |
| 900-9X81E-00EX-DT0 | Secure Boot Enabled, Crypto Enabled with x16 PCIe Down-Stream Port Extension Option | ||
| Electrical and Thermal Specifications | Voltage: 12V, 3.3V, 3.3VAUX | ||
| The complete electrical and thermal specifications are provided in “NVIDIA ConnectX-8 SuperNIC Product Specifications” document. You can access the document either by logging into NVOnline or by contacting your NVIDIA representative. | |||
| Environmental | Temperature | Operational | 0°C to 55°C |
| Non-operational | -40°C to 70°Cb | ||
| Humidity | Operational | 10% to 85% relative humidity | |
| Non-operational | 10% to 90% relative humidity | ||
| Altitude (Operational) | 3050m | ||
| Regulatory | Safety: CB / cTUVus / CE | ||
| EMC: CE / FCC / VCCI / ICES / RCM / KC | |||
| RoHS: RoHS Compliant | |||
| Notes:a. The ConnectX-8 SuperNICs supplement the IBTA auto-negotiation specification to get better bit error rates and longer cable reaches. This supplemental feature only initiates when connected to another NVIDIA InfiniBand product.b. The non-operational storage temperature specifications apply to the product without its package. | |||
Sageconnect is a reliable provider of IT network system integration and solutions for global enterprise customers.
Copyright © 2024 starsurge mellanox network. Powered by starsurgemellanox network.