NVIDIA MCX516A-CCAT ConnectX-5 EN 2x 100GbE Adapter – Dual-Port QSFP28, RDMA RoHS

The NVIDIA ConnectX-5 EN Ethernet adapter card family provides high performance and flexible solutions with up to two ports of 100GbE connectivity, 750ns latency, up to 200 million messages per second (Mpps), and a record-setting 197Mpps when running an open source Data Path Development Kit (DPDK) over PCIe Gen 4.0. For storage workloads, ConnectX-5 delivers innovative accelerations such as Signature Handover (T10-DIF) in hardware, an embedded PCIe switch, and NVMe over Fabric target offloads.

The MCX516A-CCAT is the dual-port 100GbE QSFP28 member of the ConnectX-5 EN family, with a PCIe Gen 3.0 x16 host interface. It supports Ethernet speeds of 100, 50, 40, 25, 10, and 1 GbE, and is RoHS compliant and ODCC compatible. ConnectX-5 adapter cards are available for PCIe Gen 3.0 and Gen 4.0 servers and support 1, 10, 25, 40, 50, and 100 GbE speeds in stand-up PCIe, OCP 2.0, and OCP 3.0 form factors.

ConnectX-5 also brings advanced Open vSwitch offloads to telecommunications and cloud data centers, driving extremely high packet rates and throughput with reduced CPU resource consumption. This improves data center infrastructure efficiency and supports modern SDN, NFV, and cloud-native deployments.

• Two 100GbE QSFP28 ports (supports 100, 50, 40, 25, 10, and 1 GbE)
• PCIe Gen 3.0 x16 host interface
• Up to 100Gb/s connectivity per port
• Industry-leading throughput, low latency, low CPU utilization, and high message rate
• Tag matching and rendezvous offloads
• Adaptive routing on reliable transport
• Burst buffer offloads for background checkpointing
• NVMe over Fabric offloads
• Backend switch elimination by host chaining
• Embedded PCIe switch
• Enhanced vSwitch/vRouter offloads
• Flexible pipeline
• RoCE for overlay networks
• PCIe Gen 4.0 support across the ConnectX-5 EN family
• RoHS compliant and ODCC compatible
• Various form factors available

ConnectX-5 adapter cards enable data center administrators to benefit from better server utilization and reduced costs, power usage, and cable complexity, allowing more virtual appliances, virtual machines (VMs), and tenants to co-exist on the same hardware. Supported vSwitch/vRouter offload functions include overlay networks (VXLAN, NVGRE, MPLS, GENEVE, and NSH) header encapsulation and decapsulation, stateless offloads of inner packets and packet header rewrite for NAT functionality, and flexible programmable parser and match-action tables for hardware offloads of future protocols.

SR-IOV technology provides dedicated adapter resources, guaranteed isolation, and protection for virtual machines within the server. Network Function Virtualization (NFV) enables a VM to be used as a virtual appliance. Full data-path operation offloads, hairpin hardware capability, and service chaining enable data to be handled by the virtual appliance with minimum CPU utilization.

Mellanox ASAP² (Accelerated Switching and Packet Processing) technology enables offloading the vSwitch/vRouter by handling the data plane in the NIC hardware without modifying the control plane. This results in significantly higher vSwitch/vRouter performance without the associated CPU load. Intelligent ConnectX-5 flexible pipeline capabilities, including flexible parser and flexible match-action tables, are programmable, enabling hardware offloads for future protocols.

NVMe storage devices are gaining popularity by offering very fast storage access. The evolving NVMe over Fabric (NVMe-oF) protocol leverages RDMA connectivity for remote access. ConnectX-5 offers further enhancements by providing NVMe-oF target offloads, enabling very efficient NVMe storage access with no CPU intervention, improving performance and reducing latency.

The embedded PCIe switch enables customers to build standalone storage or machine learning appliances. Standard block and file access protocols leverage RoCE for high-performance storage access. A consolidated compute and storage network achieves significant cost-performance advantages over multi-fabric networks. ConnectX-5 enables an innovative storage rack design, Host Chaining, which enables different servers to interconnect without involving the Top of the Rack (ToR) switch. This lowers data center TCO by reducing CAPEX (cables, NICs, and switch port expenses) and OPEX (switch port management and overall power usage).

Telecommunications service providers are moving toward disaggregation, server virtualization, and orchestration to modernize their networks. They are also moving toward Network Function Virtualization (NFV), which enables rapid deployment of new network services. ConnectX-5 adapter cards drive extremely high packet rates, increased throughput, and higher network efficiency through Open vSwitch Offloads (OvS), OvS over DPDK or ASAP², Network Overlay Virtualization, SR-IOV, and RDMA. This allows for secure data delivery through higher-performance offloads, reducing CPU utilization and boosting data center infrastructure efficiency.

• Cloud and Web 2.0 data centers using SDN and virtual switching
• Storage environments deploying NVMe over Fabric and RoCE-based storage access
• Telecommunications and NFV platforms requiring high packet rates and low CPU utilization
• Virtualized servers using SR-IOV for VM isolation and guaranteed QoS
• Machine learning and storage appliances using the embedded PCIe switch
• Storage rack designs using Host Chaining to eliminate backend switches
• Servers requiring remote boot over Ethernet or iSCSI with UEFI/PXE support

The MCX516A-CCAT uses standard QSFP28 connectivity for 100, 50, 40, 25, 10, and 1 GbE links. It is a PCIe Gen 3.0 x16 card and is compatible with PCIe Gen 3.0, 1.1, and 2.0 interfaces, with auto-negotiation to x16, x8, x4, x2, or x1 lanes. It also supports interoperability with Ethernet switches up to 100GbE, passive copper cables with ESD protection, and powered connectors for optical and active cable support.

Operating system support includes RHEL/CentOS, Windows, FreeBSD, VMware, OpenFabrics Enterprise Distribution (OFED), and OpenFabrics Windows Distribution (WinOF-2). UEFI support is enabled for x86 and Arm servers. Because system-level compatibility can depend on server platform, firmware, and OS/driver versions, please confirm the exact host configuration before ordering.