Nvidia ConnectX-6 User Manual page 12

Feature
Memory Components
Overlay Networks
RDMA and RDMA over Converged
Ethernet (RoCE)
NVIDIA PeerDirect®
CPU Offload
Quality of Service (QoS)
Hardware-based I/O Virtualization
Storage Acceleration
• Proprietary Ethernet protocols (20/40GBASE-R2, 50GBASE-R4)
• IEEE 802.3ad, 802.1AX Link Aggregation
• IEEE 802.1Q, 802.1P VLAN tags and priority
• IEEE 802.1Qau (QCN)
• Congestion Notification
• IEEE 802.1Qaz (ETS)
• IEEE 802.1Qbb (PFC)
• IEEE 802.1Qbg
• IEEE 1588v2
• Jumbo frame support (9.6KB)
• EEPROM - The EEPROM capacity is 32Kbit.
• SPI Quad - includes 256Mbit SPI Quad Flash device (MX25L25645GXDI-08G device by Macronix)
In order to better scale their networks, data center operators often create overlay networks that carry traffic from individual virtual machines over
logical tunnels in encapsulated formats such as NVGRE and VXLAN. While this solves network scalability issues, it hides the TCP packet from the
hardware offloading engines, placing higher loads on the host CPU. ConnectX®-6 Lx effectively addresses this by providing advanced NVGRE and VXLAN
hardware offloading engines that encapsulate and de-capsulate the overlay protocol.
ConnectX®-6 Lx, utilizing RDMA (Remote Data Memory Access) and RoCE (RDMA over Converged Ethernet) technology, delivers low-latency and high-
performance over Band and Ethernet networks. Leveraging data center bridging (DCB) capabilities, as well as ConnectX®-6 Lx, advanced congestion
control hardware mechanisms, RoCE provides efficient low-latency RDMA services over Layer 2 and Layer 3 networks.
PeerDirect® communication provides high-efficiency RDMA access by eliminating unnecessary internal data copies between components on the PCIe
bus (for example, from GPU to CPU), and therefore significantly reduces application run time. ConnectX®-6 Lx advanced acceleration technology
enables higher cluster efficiency and scalability to tens of thousands of nodes.
Adapter functionality enables reduced CPU overhead leaving more CPU resources available for computation tasks.
Open vSwitch (OVS) offload using ASAP
• Flexible match-action flow tables
• Tunneling encapsulation/decapsulation
Support for port-based Quality of Service enabling various application requirements for latency and SLA.
ConnectX®-6 Lx provides dedicated adapter resources and guaranteed isolation and protection for virtual machines within the server.
A consolidated compute and storage network achieves significant cost-performance advantages over multi-fabric networks. Standard block and file
access protocols can leverage RDMA for high-performance storage access.
• NVMe over Fabric offloads for the target machine
Description
2
FRU I C address is (0x50) and is accessible through the PCIe SMBus (Note:
2(TM)
Address 0x58 is reserved.)
12