The Intel® Tera-scale Computing Research Program is a worldwide effort to advance computing technology for the next decade. By scaling multi-core architectures to 10s to 100s of cores and embracing a shift to parallel programming, we aim to enable applications and capabilities only dreamt of today.
"Tera" means 1 trillion, or 1,000,000,000,000. Our vision is to create plaforms capable performing of trillions of calculations per second (teraflops) on trillions of bytes of data (terabytes).
- Scalable multi-core architectures which integrate streamlined processor cores and accelerators using a fast, energy-efficient, modular core-to-core infrastructure.
Examples: 80-core prototype, Tera-scale Emulator, Dynamic Thermal Management, Task Queues.
- Memory sharing and stacking to provide a high bandwidth, flexible, cache & memory hierarchy which supports many simultaneous threads fairly and efficiently.
Examples: 3D Stacking, Cache Quality of Service.
- High Bandwidth I/O and Communications which balance the compute demands with I/O and network demands within the platform power and cost budgets.
Examples: High-speed Copper I/O, Silicon Photonics, I/O Accelerators.
Software Research Vision
- Model-based applications which use tera-scale capabilties to give technology the ability to comprehend data, make decisions, and synthesize virtual possibilities. More>
Examples: Ray Tracing, Physical Modeling, Media Mining and Enhancment
- Parallel programming tools that empower the ordinary programmer to develop applications that use parallelism with scalability & performance, safety & reliability.
Examples: Transactional Memory, Accelerator Exoskeleton, Ct Data-Parallel Programming
- Thread-aware execution environments that provide real-time performance & power management across cores and scale with increasing thread and core counts.
Examples: Many-core Run Time, Tera-scale Virtual Machine
Check out these research project homepages:
