46513results about "Cooling/ventilation/heating modifications" patented technology

A novel massively parallel supercomputer of hundreds of teraOPS-scale includes node architectures based upon System-On-a-Chip technology, i.e., each processing node comprises a single Application Specific Integrated Circuit (ASIC). Within each ASIC node is a plurality of processing elements each of which consists of a central processing unit (CPU) and plurality of floating point processors to enable optimal balance of computational performance, packaging density, low cost, and power and cooling requirements. The plurality of processors within a single node may be used individually or simultaneously to work on any combination of computation or communication as required by the particular algorithm being solved or executed at any point in time. The system-on-a-chip ASIC nodes are interconnected by multiple independent networks that optimally maximizes packet communications throughput and minimizes latency. In the preferred embodiment, the multiple networks include three high-speed networks for parallel algorithm message passing including a Torus, Global Tree, and a Global Asynchronous network that provides global barrier and notification functions. These multiple independent networks may be collaboratively or independently utilized according to the needs or phases of an algorithm for optimizing algorithm processing performance. For particular classes of parallel algorithms, or parts of parallel calculations, this architecture exhibits exceptional computational performance, and may be enabled to perform calculations for new classes of parallel algorithms. Additional networks are provided for external connectivity and used for Input / Output, System Management and Configuration, and Debug and Monitoring functions. Special node packaging techniques implementing midplane and other hardware devices facilitates partitioning of the supercomputer in multiple networks for optimizing supercomputing resources.

System-in packages, or multichip modules, are described which can include multi-layer chips and multi-layer dummy substrates over a carrier, multiple through vias blindly or completely through the multi-layer chips and completely through the multi-layer dummy substrates, multiple metal plugs in the through vias, and multiple metal interconnects, connected to the metal plugs, between the multi-layer chips. The multi-layer chips can be connected to each other or to an external circuit or structure, such as mother board, ball grid array (BGA) substrate, printed circuit board, metal substrate, glass substrate, or ceramic substrate, through the metal plugs and the metal interconnects.

Apparatus and methods according to the present invention preferably utilize electroosmotic pumps that are capable of generating high pressure and flow without moving mechanical parts and the associated generation of unacceptable electrical and acoustic noise, as well as the associated reduction in reliability. These electroosmotic pumps are preferably fabricated with materials and structures that improve performance, efficiency, and reduce weight and manufacturing cost relative to presently available micropumps. These electroosmotic pumps also preferably allow for recapture of evolved gases and deposited materials, which may provide for long-term closed-loop operation. Apparatus and methods according to the present invention also allow active regulation of the temperature of the device through electrical control of the flow through the pump and can utilize multiple cooling loops to allow independent regulation of the special and temporal characteristics of the device temperature profiles. Novel microchannel structures are also described.