Single-chip Cloud Computer – Energy Efficiency with Real-Time Advanced Power Management
Archived series ("Inactive feed" status)
When? This feed was archived on May 11, 2019 01:47 (). Last successful fetch was on January 27, 2019 02:22 ()
Why? Inactive feed status. Our servers were unable to retrieve a valid podcast feed for a sustained period.
What now? You might be able to find a more up-to-date version using the search function. This series will no longer be checked for updates. If you believe this to be in error, please check if the publisher's feed link below is valid and contact support to request the feed be restored or if you have any other concerns about this.
Manage episode 155003004 series 1142818
In this demo with Rob F. Van der Wijngaart, Senior Software Engineer, Intel:
The experimental chip was designed to operate from as high as 125W to as low as 25W by providing a variety of advanced capabilities to manage power consumption. Power use is largely determined by the cores’ clock speeds and operating voltages. The chip has a unique ability to mix and match voltages and clock speeds for the different cores, or even to turn off entire regions of the chip when not needed. These capabilities can be controlled by software, allowing the application or operating system to intelligently manage power consumption, adapting in real time to use only the energy that is really needed. The demonstration displays how power levels for different sections of the chip change in response to the needs of a series of tasks whose power requirements vary over time. The tasks of the application are modeled after parallel computations.
This podcast is from the live webcast at the Clift Hotel in San Francisco on December 2, 2009. This demo followed Intel CTO, Justin Rattner’s opening remarks on the Single-Chip Cloud Computer, the latest Intel Labs milestone in the Intel Tera-scale Computing Research Program.
71 episodes
