NVIDIA Mellanox MCX623106AN-CDAT ConnectX®-6 Dx EN Adapter Card, 100GbE, Dual-Port QSFP56 PCIe 4.0 x16, No Crypto Tall Bracket

#101938
#101938
Modèle: MCX623106AN-CDAT
  Vendu:  2324
En stock 45
Brand:
NVIDIA/Mellanox (Ethernet)
NVIDIA/Mellanox (Ethernet)

Articles en vedette

  • Up to 100 Gb/s bandwidth
  • Flexible programmable pipeline for new network flows
  • ASAP2 - Accelerated Switching and Packet Processing for virtual switches/routers
  • IPsec and TLS in-line crypto acceleration
  • Hardware Root-of-Trust and secure firmware update
  • Connection Tracking offload
  • Advanced RoCE capabilities
  • Platform agnostic: x86, Power, Arm
NVIDIA Mellanox MCX623106AN-CDAT ConnectX®-6 Dx EN Adapter Card, 100GbE, Dual-Port QSFP56 PCIe 4.0 x16, No Crypto Tall Bracket
NVIDIA Mellanox MCX623106AN-CDAT ConnectX®-6 Dx EN Adapter Card, 100GbE, Dual-Port QSFP56 PCIe 4.0 x16, No Crypto Tall Bracket
Caractéristiques
Applications
Points forts du produit
questions et réponses
Avis des clients
Ressources
Caractéristiques
Applications
Points forts du produit
questions et réponses
Avis des clients
Ressources
Description

NVIDIA Mellanox MCX623106AN-CDAT ConnectX®-6 Dx EN Adapter Card, 100GbE, Dual-Port QSFP56 PCIe 4.0 x16, No Crypto Tall Bracket

ConnectX-6 Dx SmartNIC is the industry's most secure and advanced cloud network interface card to accelerate mission-critical data-center applications, such as security, virtualization, SDN/NFV, big data, machine learning, and storage. The SmartNIC delivers the highest return on investment (ROI) of any smart network interface card.

Caractéristiques
Part Number
MCX623106AN-CDAT
Data Transmission Rate
Ethernet: 1/10/25/40/50/100 Gb/s
Network Connector Type
Dual-port QSFP56
Application
Ethernet
Host Interface
PCIe x16 Gen 3.0/4.0 @ SERDES 16GT/s
Technology
RoCE
Adapter Card Size
5.59in. x 2.71in (142.00mm x 68.90mm)
RoHS
RoHS Compliant
Temperature
Operational: 0°C to 55°C
Storage: -40°C to 70°C
Supported operating systems
Linux, Windows, VMware
Applications
Points forts du produit
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.

questions et réponses
Poser une question
no data
Avis des clients
Certification de qualité
ISO140012015
ISO 90012015
ISO450012018
FDA
FCC
CE
RoHS
TUV-Mark
UL
WEEE
ISO140012015
ISO 90012015
ISO450012018
FDA
FCC
CE
RoHS
TUV-Mark
UL
WEEE
Ce que nous fournissons