NVIDIA MCX512A-ACAT ConnectX-5 EN 2x 25GbE Adapter – Dual SFP28, PCIe Gen3 x8, RoCE, DPDK
Product Details:
| Brand Name: | Mellanox |
| Model Number: | MCX512A-ACAT |
| Document: | connectx-5-en-card.pdf |
Payment & Shipping Terms:
| Minimum Order Quantity: | 1pcs |
|---|---|
| Price: | Negotiate |
| Packaging Details: | outer box |
| Delivery Time: | Based on inventory |
| Payment Terms: | T/T |
| Supply Ability: | Supply by project/batch |
|
Detail Information |
|||
| Application: | Server | Interface Type:: | Network |
|---|---|---|---|
| Ports: | Dual | Max Speed: | 25GbE |
| Connector Type: | SFP28 | Type: | Wired |
| Condition: | New And Original | Model: | MCX512A-ACAT |
| Name: | Mellanox Network Card MCX512A-ACAT ConnectX-5 EN Adapter Card 10/25GbE Dual-Port SFP28 PCIe 3.0 X8 | Keyword: | Mellanox Network Card |
| Highlight: | NVIDIA ConnectX-5 25GbE Adapter,Dual SFP28 PCIe Network Card,RoCE DPDK Nvidia Network Card |
||
Product Description
The NVIDIA MCX512A-ACAT is a ConnectX-5 EN Ethernet adapter card featuring two 25GbE SFP28 ports and a PCIe Gen3 x8 host interface. It delivers intelligent RDMA-enabled networking with advanced application offloads for Web 2.0, cloud, storage, and telecommunications platforms, supporting 25, 10, and 1 GbE Ethernet speeds.
The NVIDIA ConnectX-5 EN Ethernet adapter card family provides high-performance, 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 MCX512A-ACAT is the dual-port 25GbE SFP28 member of the ConnectX-5 EN family, equipped with a PCIe Gen 3.0 x8 host interface. It supports Ethernet speeds of 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 25GbE SFP28 ports (supports 25, 10, and 1 GbE)
- PCIe Gen 3.0 x8 host interface
- Up to 100Gb/s connectivity per port across the ConnectX-5 EN portfolio
- 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 MCX512A-ACAT uses standard SFP28 connectivity for 25, 10, and 1 GbE links. It is a PCIe Gen 3.0 x8 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 across the ConnectX-5 EN family, 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.
| Parameter | Value |
|---|---|
| Max network speed | 2x 25GbE |
| Interface type | SFP28 |
| Supported Ethernet speeds | 25, 10, 1 GbE |
| Form factor | PCIe HHHL (half-height, half-length) stand-up card |
| Additional features | UEFI Enabled (x86/Arm) |
| Parameter | Value |
|---|---|
| PCIe generation | PCIe Gen 3.0 x8 |
| PCIe compatibility | PCIe Gen 3.0, 1.1, and 2.0 compatible |
| Link rate | 2.5, 5.0, 8.0, 16.0 GT/s |
| Lane negotiation | Auto-negotiates to x16, x8, x4, x2, or x1 lanes |
| Interrupt mechanisms | MSI / MSI-X |
| Feature | Status |
|---|---|
| PCIe Atomic | Supported |
| TLP (Transaction Layer Packet) Processing Hints (TPH) | Supported |
| Embedded PCIe Switch | Up to 8 bifurcations |
| Downstream Port Containment (DPC) | Enablement for PCIe hot-plug |
| Access Control Service (ACS) | For peer-to-peer secure communication |
| Advanced Error Reporting (AER) | Supported |
| Process Address Space ID (PASID) | Supported |
| Address Translation Services (ATS) | Supported |
| IBM CAPI v2 (Coherent Accelerator Processor Interface) | Supported |
| Feature | Status |
|---|---|
| Hardware-based reliable transport | Supported |
| Collective operations offloads | Supported |
| Vector collective operations offloads | Supported |
| Mellanox PeerDirect RDMA (GPUDirect communication acceleration) | Supported |
| 64/66 encoding | Supported |
| Extended Reliable Connected transport (XRC) | Supported |
| Dynamically Connected Transport (DCT) | Supported |
| Enhanced Atomic operations | Supported |
| Advanced memory mapping (UMR) | Supported |
| On-demand paging (ODP) | Supported |
| MPI Tag Matching | Supported |
| Rendezvous protocol offload | Supported |
| Out-of-order RDMA supporting Adaptive Routing | Supported |
| Burst buffer offload | Supported |
| In-Network Memory registration-free RDMA memory access | Supported |
| Feature | Status |
|---|---|
| RDMA over Converged Ethernet (RoCE) | Supported |
| TCP/UDP/IP stateless offload | Supported |
| LSO, LRO, checksum offload | Supported |
| RSS (also on encapsulated packet), TSS, HDS, VLAN and MPLS tag insertion/stripping, Receive flow steering | Supported |
| Data Plane Development Kit (DPDK) for kernel bypass applications | Supported |
| Open vSwitch (OVS) offload using ASAP² | Supported |
| Flexible match-action flow tables | Supported |
| Tunneling encapsulation/decapsulation | Supported |
| Intelligent interrupt coalescence | Supported |
| Header rewrite supporting hardware offload of NAT router | Supported |
| Feature | Status |
|---|---|
| NVMe over Fabric offloads for target machine | Supported |
| T10 DIF — Signature handover operation at wire speed, for ingress and egress traffic | Supported |
| Storage protocols: SRP, iSER, NFS RDMA, SMB Direct, NVMe-oF | Supported |
| Feature | Status |
|---|---|
| RoCE over Overlay Networks | Supported |
| Stateless offloads for overlay network tunneling protocols | Supported |
| Hardware offload of encapsulation and decapsulation of VXLAN, NVGRE, and GENEVE overlay networks | Supported |
| Feature | Status |
|---|---|
| Single Root IOV address translation and protection | Supported |
| VMware NetQueue support | Supported |
| SR-IOV Virtual Functions | Up to 512 Virtual Functions |
| SR-IOV Physical Functions | Supported |







