Cisco

Cisco CAI-P-N3220 | 2x200GbE QSFP56 | DPU with on-board Arm compute | PCIe Gen5 x16 | RoCEv2, SR-IOV | Inline crypto & NVMe-oF offload

SKU:CAI-P-N3220

Regular price POA
POA
POA
Sale Sold out
Taxes included. Shipping calculated at checkout.

Description

Programmable data processing unit with dual 200GbE ports and integrated Arm-based acceleration. Offloads networking, security, and storage functions from host CPUs to deliver deterministic, low-latency performance for cloud-native, virtualized, and bare-metal environments.

Features

- Dual 200GbE with RDMA for low-latency fabrics
- On-board Arm compute to offload data-plane services
- Inline crypto and microsegmentation for secure multi-tenant clouds
- NVMe-oF acceleration for disaggregated storage
- Comprehensive telemetry and PTP for precise operations

Warranty

All products sold by XS Network Tech include a 12-month warranty on both new and used items. Our in-house technical team thoroughly tests used hardware prior to sale to ensure enterprise-grade reliability.

All technical data should be verified on the manufacturer data sheets.

View full details
  • You may also like
  • Best sellers
  • Related Products

specs-tabs

Collapsible content

FAQs

Technical Specifications

FAQs

Q: How is a DPU different from a standard NIC?
A: A DPU integrates on-board compute to offload networking, security, and storage services from the host, enabling isolation and deterministic performance beyond traditional NIC capabilities.

Q: What optics should I use for 200GbE?
A: Use QSFP56 200G optical modules or QSFP56 DAC/AOC cables appropriate to your reach and fiber type.

Q: Can it run in a PCIe Gen4 slot?
A: Yes, it is backward compatible with PCIe Gen4; throughput to the host will be limited to Gen4 bandwidth.

Q: Does it support SR-IOV and RoCEv2?
A: Yes, SR-IOV virtualization and RoCEv2 RDMA are supported.

Q: Is encryption offload available?
A: Inline IPsec/TLS offload is supported where enabled by firmware and software.

Technical Specifications

- Port configuration: 2x 200GbE
- Cage/form: QSFP56
- Transceiver/cable support: 200G QSFP56 optical modules, AOCs, and DACs (model-dependent)
- DPU compute: On-board multi-core Arm complex for offloaded data paths (DOCA-enabled)
- Host interface: PCIe Gen5 x16 (backward compatible with Gen4)
- Networking: RoCEv2 RDMA, advanced congestion control
- Virtualization: SR-IOV with scalable virtual functions
- Security: Inline IPsec/TLS offload and crypto acceleration (platform/firmware dependent)
- Storage: NVMe-oF (RoCE/TCP) acceleration and GPUDirect Storage enablement
- Observability: Hardware telemetry and flow counters
- Timing: IEEE 1588 PTP
- Jumbo frames: up to 9K (driver/OS dependent)
- Software ecosystem: NVIDIA DOCA SDK, Linux drivers

Recently Viewed

  • Request for a Quote

    Looking for competitive pricing? Submit a request, and our team will provide a tailored quote that fits your needs.

  • Contact Us Directly

    Have a question or need immediate assistance? Call us for expert advice and real-time support.

    Call us Now  
  • Contact Us Directly

    Have a question or need immediate assistance? Call us for expert advice and real-time support.

    Contact us