This 10 gigabit AT2 Ethernet server adapter showcases Intel's second-generation standards-based 10BASE-T adapter in a low-profile PCI Express form factor. It provides bandwidth intensive applications highly affordable 10 gigabit Ethernet (GbE) network performance with cost-effective RJ-45 connections for distances up to 100 meters. High-speed server connectivity - once reserved for costly, proprietary technologies such as high performance computing (HPC) clusters and grid-based computing - can now be achieved with the standardized connectivity of the Intel 10 Gigabit AT2 Server Adapter. Intel's adapter also provides 1000BASE-T support for gigabit connections to legacy switches.
Intel 82598EB 10 Gigabit Ethernet Controller
- Industry-leading, energy-efficient design for next-generation 10 gigabit performance and multi-core processors
Low-profile
-Enables higher bandwidth and throughput from standard and low-profile PCIe slots and servers
Load balancing on multiple CPUs
-Increases performance on multi-processor systems by efficiently balancing network loads across CPU cores when used with Receive-Side Scaling from Microsoft or Scalable I/O on Linux
Intel QuickData Technology
-DMA Engine: Enhances data acceleration across the platform (network, chipset, processor), thereby lowering CPU utilization
-Direct Cache Access (DCA): Allows the processor to pre-fetch the data from memory, thereby avoiding cache misses and improving service level agreements (SLA) of the applications
iSCSI remote boot support
-Provides centralized storage area network (SAN) management at a lower cost than competing iSCSI solutions
MSI-X support
-Minimizes the overhead of interrupts
-Allows load balancing of interrupt handling between different cores/CPUs
Virtual Machine Device queues (VMDq)
-Allows the efficient routing of packets to the correct target machine in a virtualized environment using multiple hardware queues
-Ensures transmit fairness and prevents head-of-line blocking
Low latency
-Ability to toggle between the interrupt aggregation and non-aggregation mode based on the type of data being transferred
Optimized queues: 32 transmit (Tx) and 64 receive(Rx) per port
-Enhances network performance and reduces CPU utilization in the virtualized environment
-Reduces I/O overhead on the hypervisor in a virtualized server by performing data sorting and coalescing in the network silicon
Network packet handling without waiting or buffer overflow
-Efficient packet prioritization
Support for most network operating systems (NOS)
-Enables widespread deployment