Connect-IB adapter cards provide the highest performing and most scalable interconnect solution for server and storage systems. High- performance computing, Web 2.0, cloud, big data, financial services, performance improvements resulting in reduced completion time and lower cost per operation.
World class performance
Connect-IB delivers leading performance with maximum bandwidth, low latency, and computing storage applications. Maximum bandwidth is delivered across PCI Express 3.0 x16 and two 100 Gb/s of throughput together with consistent low latency across all CPU cores. Connect-IB also enables PCI Express 2.0 x16 systems to take full advantage of FDR, delivering at least twice the bandwidth of existing PCIe 2.0 solutions. Connect-IB supports data operations including noncontiguous memory transfers which eliminate unnecessary data copy operations and CPU overhead. Additional application acceleration is achieved with a 4x improvement in message rate compared with previous
The next level of scalability and performance requires the data and application accelerations. MellanoX Messaging (MXM) and Fabric Collective Accelerator (FCA) utilizing CORE-Direct technology accelerates MPI and PGAS communication performance, taking full advantage of Connect-IB enhanced capabilities. Furthermore, Connect-IB introduces an innovative transport service Dynamic Transport, to ensure unlimited scalability for clustering of servers and storage systems.
High performance storageProduct Highlights
Storage nodes will see improved performance with the higher bandwidth FDR delivers, and standard block and file access protocols can leverage InfiniBand RDMA for even better performance. Connect-IB also supports hardware checking of T10 Data Integrity Field/Protection Information (DIF/PI) and other signature types, reducing the CPU overhead and accelerating the data to the application. Signature translation and handover are also done by the adapter, further reducing the load on the CPU. Consolidating compute and achieves superior performance while reducing data center costs and complexities.
- World-class cluster, network, and storage performance
- Guaranteed bandwidth and low-latency services
- I/O consolidation
- Virtualization acceleration
- Scales to tens-of-thousands of nodes
- 1 us MPI ping latency
- GPU communication acceleration
- End-to-end internal data protection
- End-to-end QoS and congestion control
- Hardware-based I/O virtualization