InfiniBand -- ConnectX-3 delivers low-latency, high-bandwidth, and computing efficiency for performance-driven server and storage clustering applications. Efficient computing is achieved by offloading from the CPU protocol processing and data movement overhead such as RDMA and send/receive semantics, allowing more processor power for the application. CORE-Direct™ brings the next level of performance improvement by offloading application overhead such as data broadcasting and gathering as well as global synchronization communication routines.
RDMA over Converged Ethernet -- ConnectX-3 utilizing IBTA RoCE technology delivers similar low latency and high performance over Ethernet networks. Leveraging Data Center Bridging capabilities, RoCE provides efficient low-latency RDMA services over Layer 2 Ethernet.
Storage Accelerated -- A consolidated compute and storage network achieves significant cost- performance advantages over multifabric networks. Standard block and file access protocols can leverage InfiniBand RDMA for high-performance storage access. T11-compliant encapsulation (FCoIB or FCoE) with full hardware offloads simplifies the storage network while keeping existing Fibre Channel targets.
- Virtual protocol interconnect (VPI)
- CPU offload of transport operations
- Fibre Channel encapsulation (FCoIB or FCoE)
- I/O consolidation for networking, storage, and management applications
- Scalable to tens of thousands of nodes