Subscribe to RSS Add to Technorati Faves Digg This Page Send to Stumble Upon Bookmark on Delicious

Tera-scale Demos at IDF

posted by Sean Koehl on September 20, 2007

Following up on Brian’s post yesterday, here’s some pics and info on the Tera-scale demos we have here at IDF.

80-Core Teraflops Research Processor

ts-demo-1.jpg

Here’s Paolo and Nitin, part of the team showcasing the 80-Core Teraflops Research Processor. This represents an important milestone towards enabling future processors with 10s to 100s of cores. It is the first programmable chip to deliver more than one Teraflops of performance, and consumes very little power. This prototype focuses on exploring scalable, energy–efficient designs for future multi–core chips as well as core–to–core interconnect and clocking.

Multi-Core Hardware Emulator

ts-demo-2.jpg

Franz, Elmar and Thorsten are from our Germany labs. Their emulator system enables fast, accurate emulation of future multi-core architectures. Based on FPGA technology, future designs can be prototyped with short turnaround times. It has a rich set of debug features supports analyzing platform performance vs. other designs. They showed an xperimental eight-core Intel Architecture CPU running a real OS on the emulation system.

Safer Software Execution through Log-Based Architectures

ts-demo-3.jpg

Lifeguards, software tools that proactively monitor programs for potential problems, can improve the reliability of end user systems by catching software errors at runtime. Collaboratively, Intel and Carnegie Mellon University are exploring Log-Based Architectures, new hardware enhancements designed to improve lifeguard performance on multi-core processors. Michael and Shimin demonstrated an example enhanced lifeguard detecting a computer virus attack.

Taking Applications Tera-Scale with Ct

ts-demo-4.jpg

Ct, an advanced data parallel programming environment, extends C for throughput computing to maximize programmability and performance of several applications on present and future multi-core platforms. Jane and Mohan compared conventional parallel programming and Ct, specifically for image processing and game physics applications.

Ray Traced Gaming

ts-demo-5.jpg

The ultimate goal for computer-generated graphics is to create photorealistic imagery generated on the fly. Ray tracing models the behavior of light to create shadows and reflections much better and more easily than the techniques used to render interactive 3-D graphics today. Daniel showed that the time is nearing when tera-scale computing will finally make real-time ray tracing possible.

Comments (0)
del.icio.us StumbleUpon Digg It
tagged: , , , , , ,

Post Your Comment




Comment Policy: We welcome your comments, however all comments are moderated. Offensive, off-topic or fraudulent comments will be deleted and not displayed. By submitting a comment to an Intel Blog, you agree to our legal information and privacy policy terms, including having your name displayed with your comment and that you are 13 years old or older. Your name and personal information will not be used for any other purpose, and your e-mail address will not be published.

Disclaimer: Opinions expressed here and in any corresponding comments are the personal opinions of the original authors, and do not necessarily reflect the views of Intel. All Intel names and trademarks are the property of Intel Corporation or its subsidiaries in the United States and other countries. Other names and brands may be claimed as the property of others.