New architecture combines breakthrough performance for highly parallel applications with accessibility of Intel® Architecture programming
Intel® Xeon® processors currently power over 75 percent of the world’s supercomputing centers. And, with the upcoming release of the Intel® Xeon® Phi™ coprocessor, based on Intel® Many Integrated Cores technology, Intel ushers in the next generation of scientific discovery. Intel Xeon Phi coprocessors deliver higher-than-ever aggregate performance for highly parallel applications—and eliminate much of the need for dual-programming architecture.
While Intel Xeon processors remain the preferred choice for a broad range of applications, Intel Xeon Phi coprocessors are designed to provide efficient performance for highly parallel applications.
Introducing the first generation of Intel Xeon Phi coprocessor
The first Intel Xeon Phi coprocessor, codenamed “Knights Corner,” is being produced on Intel® 22 nm technology, featuring the world’s first 3-D Tri-Gate transistors. Relative to multi-core Intel Xeon processors, Intel Xeon Phi coprocessors have many smaller cores, many more hardware threads, and wider vector units. The high degree of parallelism compensates for the lower speed of each individual core to deliver higher aggregate performance for highly parallel applications.
Greater programmer productivity, shorter time to market
Intel Xeon Phi coprocessors build on established CPU architecture and programming concepts to provide the benefits of code re-use to developers of highly parallel applications. Common programming models for Intel Xeon processors extend to Intel Xeon Phi coprocessors, so as developers embrace high degrees of parallelism, they don’t need to rethink the entire problem.