NVIDIA Mellanox MCX516A-CCAT ConnectX®-5 EN Network Interface Card ,100GbE, Dual-port QSFP28, PCIe Gen 3.0 x16, Tall bracket

Нажмите, чтобы открыть расширенный вид

NVIDIA Mellanox MCX516A-CCAT ConnectX®-5 EN Network Interface Card ,100GbE, Dual-port QSFP28, PCIe Gen 3.0 x16, Tall bracket

Name: NVIDIA Mellanox MCX516A-CCAT ConnectX®-5 EN Network Interface Card ,100GbE, Dual-port QSFP28, PCIe Gen 3.0 x16, Tall bracket
Brand: Naddod
SKU: 101935
Price: 875.00 USD
Availability: InStock
Rating: 5.0 (18 reviews)

#101935

Модель: MCX516A-CCAT

Продал: 2579

В наличии: 95

Brand:

NVIDIA/Mellanox (Ethernet)

Обзор предметов

Up to 100Gb/s connectivity per port
Industry-leading throughput, low latency, low CPU utilization, and high message rate
Smart interconnect for x86, Power, Arm, and GPU-based compute and storage platforms
Advanced storage capabilities, including NVMe-oF offloads
Efficient I/O consolidation, lowering data center costs and complexity

NVIDIA Mellanox MCX516A-CCAT ConnectX®-5 EN Network Interface Card ,100GbE, Dual-port QSFP28, PCIe Gen 3.0 x16, Tall bracket

Бесплатная доставка по всему миру для заказов свыше $ 99

Технические характеристики

Applications

Особенности продукта

Вопросы и Ответы

Отзывы клиентов

Ресурсы

Технические характеристики

Applications

Особенности продукта

Вопросы и Ответы

Отзывы клиентов

Ресурсы

Description

NVIDIA Mellanox MCX516A-CCAT ConnectX®-5 EN Network Interface Card ,100GbE, Dual-port QSFP28, PCIe Gen 3.0 x16, Tall bracket

ConnectX-5 Ethernet adapter cards provide high performance and flexible solutions with up to two ports of 100GbE connectivity and 750ns latency. For storage workloads, ConnectX-5 delivers a range of innovative accelerations, such as Signature Handover (T10-DIF) in hardware, an embedded PCIe Switch, and NVMe over Fabric target offloads. ConnectX-5 adapter cards also bring advanced Open vSwitch offloads to telecommunications and cloud data centers to drive extremely high packet rates and throughput with reduced CPU resource consumption, thus boosting data center infrastructure efficiency.

Технические характеристики

Part Number

MCX516A-CCAT

Data Transmission Rate

Ethernet: 10/25/40/50/100 Gb/s

Network Connector Type

Dual-port QSFP28

Application

Ethernet

Host Interface

PCIe x16 Gen 3.0 @ SERDES 8GT/s

Technology

RoCE

Adapter Card Size

2.71in. x 5.6in. (68.90mm x 142.24 mm)

RoHS

RoHS Compliant

Temperature

Operational: 0°C to 55°C
Storage: -40°C to 70°C

Supported operating systems

Linux, Windows, VMware

Applications

Особенности продукта

GPU Direct RDMA

GPU Direct allows for direct data transfers from one GPU memory to another GPU memory, enabling direct remote access between GPU memories. This greatly enhances the efficiency of GPU cluster operations, offering significant improvements in both bandwidth and latency.

Advanced Network Offloads

Accelerate data plane, networking, storage, and security, enabling in-network computing and in-network memory capabilities. Offloading CPU-intensive I/O operations enhances host efficiency.

Accelerating Network Performance

By employing accelerated switching and packet processing technologies, network performance can be enhanced while reducing CPU overhead in the transmission of Internet Protocol (IP) packets, thereby freeing up more processor cycles to run applications.