At the International Supercomputing Conference 2012, Intel announced that Xeon Phi is the new brand name for all future Intel Many Integrated Core Architecture (Intel MIC Architecture) products.
The first offering from the Intel Xeon Phi family of processors have been christened Knights Corner. The Xeon Phi coprocessor uses the same 22nm 3D Tri-Gate transistor technology found on Ivy Bridge processors and comes in the form of a PCIe expansion card. Each coprocessor contains fifty cores and features a minimum of 8GB of GDDR5 memory. The card operates independently of the host operating system, courtesy of its own Linux operating system that manages each x86 core. The coprocessor is compatible with x86 programming models and will be used in high performance computing (HPC) environments.
Intel is positioning the Xeon Phi series as an alternative to NVIDIA's Tesla GPU as developers familiar with x86 programming models will not have to pick up new skillsets for NVIDIA's CUDA framework. The Xeon Phi series is part of Intel's High Performance Computing (HPC) program and it can be considered the successor to Intel's defunct Larrabee project that attempted to compete with GPUs in the realm of highly-parallelized streaming processing.
With the launch of Knights Corner, Intel hopes to challenge NVIDIA's CUDA ecosystem of GP-GPU computing with its Tesla GPUs. Since the strengths of the Xeon Phi series of coprocessors are touted to be in double-precision floating point performance, Intel should focused on championing the Knight Corner as a worthy challenger to NVIDIA's Tesla K10.
Intel has not announced any pricing details with regards to Knights Corner, but it is speculated that Xeon Phi solutions will be commercially available by the end of this year.