Intel’s Tera-scale Computing Project: The first five years, the next five years

The Intel tera-scale computing research project is an effort to advance computing technology for the next decade. By scaling todaypsilas multi-core architectures to 10s and 100s of cores and embracing a shift to parallel programming, the goal is to enable applications and capabilities only dreamed of today. In his keynote Justin Rattner will talk about the hardware and software research vision for the program. He will address hardware challenges with scaling multi-core architectures to integrate programmable cores and fixed-function accelerators, flexible cache and memory hierarchy, and high bandwidth on-die networks to ensure high throughput. On the software front, he will talk about thread-aware execution environments to provide high scalability and energy-efficiency across the cores and parallel programming tools for mere mortal programmers. The talk will also highlight future applications like integrated real-time physics and visualization and non-textual media mining which along with many others benefit from high degrees of concurrency.