skip to main content
OSTI.GOV title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Data Structures for Parallel High Speed Streaming.


Abstract not provided.

Publication Date:
Research Org.:
Sandia National Lab. (SNL-NM), Albuquerque, NM (United States)
Sponsoring Org.:
USDOE National Nuclear Security Administration (NNSA)
OSTI Identifier:
Report Number(s):
DOE Contract Number:
Resource Type:
Resource Relation:
Conference: Proposed for presentation at the Intern Symposium held July 26, 2016 in Albuquerque, New Mexico, United States.
Country of Publication:
United States

Citation Formats

Porter, Alexandra Marie. Data Structures for Parallel High Speed Streaming.. United States: N. p., 2016. Web.
Porter, Alexandra Marie. Data Structures for Parallel High Speed Streaming.. United States.
Porter, Alexandra Marie. 2016. "Data Structures for Parallel High Speed Streaming.". United States. doi:.
title = {Data Structures for Parallel High Speed Streaming.},
author = {Porter, Alexandra Marie},
abstractNote = {Abstract not provided.},
doi = {},
journal = {},
number = ,
volume = ,
place = {United States},
year = 2016,
month = 7

Other availability
Please see Document Availability for additional information on obtaining the full-text document. Library patrons may search WorldCat to identify libraries that hold this conference proceeding.

Save / Share:
  • This paper describes the methods, algorithms, and implementation of high-throughput video processing.
  • For longer-distant, high speed data links, optical fibre becomes most cost-effective than copper or other hard wire cable systems. Fermilab supplied to Finisar Corp. of Menlo Park, CA., a set of specifications for card functions, sizes and interconnector pin assignments. Finisar designed and assembled a set of fiber optical P.C. cards using 100 megabyte/sec commercial optoelectronics and a serialization and deserialization HOT-ROD chipset designed by GAZELLE Microcircuits, Inc. (A Tri Quint Semiconductors company). The cooperative effort between Fermilab and Finisar has allowed Fermilab to created a reliable 50 Megabytes/sec (40 bit parallel RS485 DART data bus) cable to cable extendermore » using a virtually invisible Fiber Channel point-to-point(FC-0) fiber optical single-simplex system. The system is easily capable of sustaining a 50 megabytes/sec of data, control and status line throughput at distances of 1625 feet (500 meters) using standard multi-mode fiber.« less
  • Low-power photoreceivers based on InGaAs/InP heterojunction bipolar transistors (HBTs) and p-i-n diodes for highly-parallel optical data links have been designed, fabricated and characterized. The receivers and designed to operate from 980 nm to over 1.3 {mu}m and interface directly with 3.3 V CMOS. SPICE was utilized to investigate circuit topographies that minimize power dissipation while maintaining large signal operation required to interface directly with CMOS. Low-power dissipation of {approximately}10 mW/channel has been achieved at bit rates up to 800 Mbits/sec. Performance characteristics of discrete HBTs and of low-power photoreceivers fabricated with p-i-n/HBT circuits are reported.
  • The present conference discusses aerobrake-maneuver vehicle aerothermodynamics, aerothermal issues in the structural design of high speed vehicles, laser surface-alloying of superlight metals with ceramic surfaces, high-temperature Al alloys for supersonic and hypersonic vehicles, advanced metallics for high temperature airframes, novel materials for engine applications, and the development status of computational methods for high temperature structural design. Also discussed are a transient thermal-structural analysis using adaptive unstructured remeshing and mesh movement, the FEM thermoviscoplastic analysis of aerospace structures, hot-structures testing techniques, a thermal-structural analysis of a carbon-carbon/refractory metal heat pipe-cooled leading edge, dynamic effects in thermoviscoplastic structures, microlevel thermal effects inmore » metal-matrix composites (MMCs), thermomechanical effects in the plasma spray manufacture of MMC monotapes, and intelligent HIP processing. Most of the presentations at this conference were abstracted previously (see A91-16027 to A91-16047).« less
  • A very fast processor, called NETZ, of unconventional architecture, was developed for real-time execution of highly complex computational algorithm. The unconventional architecture design includes advanced techniques such as the incorporation of two processors working in parallel, parallel processing and pipelining including a high-speed hardware multiplier, the use of a special loop counter, and the use of a variable-length computation cycle. A horizontal microprogrammed control unit allows fast parallel execution. 7 references.