MCX654106A-Ecat Connectx-6 Vpi Dual-Port Qsfp56 100gbe Ultra-Low Latency Network Card

Product Details
Customization: Available
Type: Wired
Bandwidth: 200g
Gold Member Since 2024

Suppliers with verified business licenses

Audited Supplier Audited Supplier

Audited by an independent third-party inspection agency

to see all verified strength labels (20)
  • MCX654106A-Ecat Connectx-6 Vpi Dual-Port Qsfp56 100gbe Ultra-Low Latency Network Card
  • MCX654106A-Ecat Connectx-6 Vpi Dual-Port Qsfp56 100gbe Ultra-Low Latency Network Card
  • MCX654106A-Ecat Connectx-6 Vpi Dual-Port Qsfp56 100gbe Ultra-Low Latency Network Card
  • MCX654106A-Ecat Connectx-6 Vpi Dual-Port Qsfp56 100gbe Ultra-Low Latency Network Card
  • MCX654106A-Ecat Connectx-6 Vpi Dual-Port Qsfp56 100gbe Ultra-Low Latency Network Card
Find Similar Products
  • Overview
  • Detailed Photos
  • After Sales Service
Overview

Basic Info.

Model NO.
MCX654106A-ECAT
Interface
PCI Express
Transmission Rate
100/50/40/25/10gbe Ethernet
Application
Server
Connecting Medium
Optical Fibre
Motherboard Integrated
Separate Network Card
Frequency Range
-
Type of Network
10-Gigabit Ethernet
Field
Server
RoHS
Support
Roce
Support
Chip Type
Connectx-6 Vpi
Hardware Interface
Pcie 3.0/4.0 X16
Transport Package
Carton
Specification
Original specification
Trademark
Mellanox
Origin
China

Product Description

Complex workloads demand ultra-fast processing of high-resolution simulations, extreme-size datasets, and highly-parallelized algorithms. As these computing requirements continue to grow, NVIDIA Quantum InfiniBand-the world's only fully offloadable, In-Network Computing acceleration technology-provides the dramatic leap in performance needed to achieve unmatched results in high performance computing (HPC), AI, and hyperscale cloud infrastructures-with less cost and complexity.
NVIDIA® ConnectX®-6 InfiniBand smart adapter cards are a key element in the NVIDIA Quantum InfiniBand platform. ConnectX-6 provides up to two ports of 200Gb/s InfiniBand and Ethernet(1) connectivity with extremely low latency, high message rate, smart offloads, and NVIDIA In-Network Computing acceleration that improve performance and scalability.
 
Basic information  
model MCX654106A-ECAT
brand NVIDIA/Mellanox
Adapter type ConnectX-6 VPI Dual-Protocol Adapter Card
performance parameter  
transmission speed HDR100/EDR InfiniBand (100Gb/s), 100GbE Ethernet (Backward compatible with 25/50GbE)
Protocol support Dual Protocol Switching (InfiniBand/Ethernet)
delay <0.6 microseconds
Message rate 215 million messages/second
Hardware specification  
interface type Dual-Port QSFP56
bus interface PCIe 3.0 x16 (Compatible with PCIe 4.0)
functional performance  
hardware acceleration RDMA/RoCE v2, SR-IOV Virtualization, Hardware Encryption (XTS-AES)
compatibility Supports 50G SerDes (PAM4) and 25G SerDes (NRZ)
security certificate RoHS/CE Certified
Software support  
operating system Linux, Windows, VMware, FreeBSD
Application scenario  
Typical application High-Performance Computing (HPC), AI Training Clusters, Cloud Data Center Networking Acceleration
 
Detailed Photos
MCX654106A-Ecat Connectx-6 Vpi Dual-Port Qsfp56 100gbe Ultra-Low Latency Network Card
MCX654106A-Ecat Connectx-6 Vpi Dual-Port Qsfp56 100gbe Ultra-Low Latency Network Card
MCX654106A-Ecat Connectx-6 Vpi Dual-Port Qsfp56 100gbe Ultra-Low Latency Network Card
MCX654106A-Ecat Connectx-6 Vpi Dual-Port Qsfp56 100gbe Ultra-Low Latency Network Card
MCX654106A-Ecat Connectx-6 Vpi Dual-Port Qsfp56 100gbe Ultra-Low Latency Network Card

Product features:
Up to HDR100 EDR InfiniBand and 100GbE Ethernet connection per port.
Up to 215 million messages per second
A delay of less than 0.6 microseconds
Block-level XTS-AES hardware encryption
Support FIPS
Advanced storage functions, including block-level encryption and checksum offload.
Supports ports based on 50G SerDes (PAM4) and 25G SerDes (NRZ).
First-class packet pacing with sub-nanosecond accuracy
Support PCIe Gen3.0x16.
Meet RoHS standards
ODCC compatibility

Product advantages:
Industry-leading throughput, low CPU utilization and high message rate.
Highest performance and smartest architecture for computing and storage infrastructure.
Cutting-edge performance of virtualized networks, including network function virtualization (NFV)
Host Link Technology for Economical Rack Design
It is suitable for intelligent interconnection of computing and storage platforms based on x86, Power, Arm, GPU and FPGA.
Flexible and programmable pipeline for new network flow
Efficient service chain support
Improve the efficiency of I/O integration and reduce the cost and complexity of data center.

After Sales Service

Q:Are you trading company or manufacturer?

A:We are factory.

Q:How long is your delivery time?
A:Generally it is 2-5 days if the goods are in stock. or it is 10 days if the goods are not in stock, it is according to quantity.

Q:Do you have MOQ?
A:For stock products,we don't have MOQ. For custom product,we ask for low MOQ.

Q:Can you offer a better price?Any discount?
A:Yes,surely. We're source factory and providing reasonable price.

Q:What is your warranty period?
A:Different products have different warranties.This warranty does not cover damage caused by man-made damage,improper care,negligence,normal wear tear,and force majeure such as natural disasters,earthquakes,fires ,etc.
 

Send your message to this supplier

*From:
*To:
*Message:

Enter between 20 to 4,000 characters.

This is not what you are looking for? Post a Sourcing Request Now
Contact Supplier