Showing posts with label chip. Show all posts
Showing posts with label chip. Show all posts

2013-03-22

IBM's liquid-based transistors point to human brain-like chips

IBM's Newest Invention Mimics the Human Brain on an Atomic Level - Adam Clark Estes - The Atlantic Wire

IBM scientists described a new kind of circuit in a paper published in Science on Thursday. There is no chip involve, per se. It's being described accurately as a "post-silicon transistor" and potentially paves the way for the most powerful and efficient computers the world has ever seen. This is possible largely because it mimics the behavior of another hyper-efficient computational marvel: the human brain.

IBM creates liquid-based transistors that can process data like the human brain | VentureBeat

The new technology is based on materials called “correlated electron oxides,” which can be combined with an ionic liquid, or a mixture where half of the molecules carry a positive charge and half are negative. When you apply a tiny ionic voltage to the liquid, the charged particles move to opposite sides of the surface of the oxide material. The charge leaves the oxide and goes into the liquid, changing its conductive state from an insulator to a metal, or from something that does not conduct electricity to something that does.

And it maintains its electrical state until another charge is applied. That part of the research is new and is particularly encouraging. IBM believes it can create non-volatile memory, or chips that save data whether electricity is on or off. It can also make logic chips that would use less power than today’s silicon-based semiconductor chips, which are the brains of everything electronic.

IBM News room - 2013-03-01 Made in IBM Labs: Scientists Discover New Atomic Technique to Charge Memory Chips - United States

The I.B.M. researchers hope that their approach could be used to build more brain-like computers.

The advantage of the new method is that it is both nonvolatile — it requires only a small amount of electricity to change the materials from one state to another, and they then remain in that state — and is potentially reversible, meaning that it could be used to build a device like a transistor.

The researchers noted that while the switching speed of the new materials might never match the raw speed of today’s transistors, their biological-like qualities might make them appropriate for building a new generation of sensors or memories.

2009-12-08

Intel's Single-chip Cloud Computer

http://techresearch.intel.com/UserFiles/en-us/Image/TS-Pics/scc-h-rack2.jpg
clipped from www.examiner.com

Intel working on a 48-core computer

Intel recently announced a single-chip computer that will hold 48 cores. The chip is called a single-chip cloud computer (SCC) because it resembles cloud datacenters.
Intel. Leap ahead.(TM)
Tera-scale Computing Research Program
Tera-scale computing: Unlocking the Future

The Intel® Tera-scale Computing Research Program is a worldwide effort to advance computing technology for the next decade. future applications more compelling and immersive.

"Tera" means 1 trillion, or 1,000,000,000,000. Our vision is to create platforms capable performing of trillions of calculations per second (teraflops) on trillions of bytes of data (terabytes).


blog it

Single-chip Cloud Computer
Inside the Single-chip Cloud Computer
The name “Single-chip Cloud Computer” reflects the fact that the architecture resembles a scalable cluster of computers such as you would find in a cloud, integrated into silicon.
The research chip features:
  • 24 “tiles” with two IA cores per tile
  • A 24-router mesh network with 256 GB/s bisection bandwidth
  • 4 integrated DDR3 memory controllers
  • Hardware support for message-passing
In a sense, the SCC is a microcosm of cloud datacenter. Each core can run a separate OS and software stack and act like an individual compute node that communicates with other compute nodes over a packet-based network.
clipped from www.youtube.com

blog it

Sources:
  1. scc-h-rack2.jpg (JPEG Image, 3000x2000 pixels)
  2. Intel working on a 48-core computer
  3. Tera-scale Computing Research Program
  4. Single-chip Cloud Computer
  5. YouTube - Intel Labs announces Single-chip Cloud Computing experimental chip
Related:
  1. Intel Unveils 48-Core Single-Chip Cloud Computer - HotHardware
  2. Intel 48-Core "Single-Chip Cloud Computer" Improves Power Efficiency - PC World Business Center
  3. Intel's New Concept CPU: 48 Cores On A Single Chip - PC World
  4. Intel hopes 48-core chip will solve new challenges | Deep Tech - CNET News
  5. Photos: Intel's Single-chip Cloud Computer - Page 5 - ZDNet.co.uk

2009-10-06

Personalized Genetic Analysis with IBM DNA Transistor

clipped from www.youtube.com

IBM DNA Transistor

A team of IBM Researchers is exploring new and innovative ways to quickly read human DNA at a low cost -- an advancement that can lead to important breakthroughs in health condition diagnosis and treatment.
clipped from www-03.ibm.com

IBM Research Aims to Build Nanoscale DNA Sequencer to Help Drive Down Cost of Personalized Genetic Analysis


IBM scientists advance genome sequencing project

This advanced research effort to demonstrate a silicon-based “DNA Transistor” could help pave the way to read human DNA easily and quickly, generating advancements in health condition diagnosis and treatment. The challenge in the effort is to slow and control the motion of the DNA through the hole so the reader can accurately decode what is in the DNA.
clipped from www-03.ibm.com
Schematics of the DNA transistor operation for the control of the translocation of a DNA through a nanopore
http://i.zdnet.com/blogs/ibmdna1.jpg
clipped from www-03.ibm.com
A cross section of IBM's DNA Transistor
http://i.zdnet.com/blogs/ibmdna2.jpg
clipped from www.youtube.com

blog it

Sources:
  1. YouTube - IBM DNA Transistor
  2. IBM Press room - 2009-10-06 IBM Research Aims to Build Nanoscale DNA Sequencer to Help Drive Down Cost of Personalized Genetic Analysis - United States
  3. YouTube - IBM DNA Transistor
Related:
  1. Can IBM's DNA transistor someday take genetic sequencing mainstream? | Between the Lines | ZDNet.com
  2. BBC NEWS | Science & Environment | DNA sequencing in a holey new way
  3. IBM Builds 'Bar Code Reader' for DNA - Inventions | Patents | New Inventions | Innovation - FOXNews.com
  4. DNA Analyzer on a Chip Promises Personalized Genetic Analysis | Gadget Lab | Wired.com
  5. IBM Research

2009-04-12

Brain on a Chip -- The FACETS Project

Clipped from: Technology Review: Building a Brain on a Silicon Chip

Technology Review - Published By MIT

Building a Brain on a Silicon Chip

A chip developed by European scientists simulates the learning capabilities of the human brain.





A smart chip:
Scientists in Europe are using conventional chip production techniques to create circuits that mimic the structure and function of the human brain. This early prototype has just 384 neurons and 100,000 synapses, but the latest version contains 200,000 neurons and 50 million synapses.

Clipped from: FACETS The FACETS Project
FACETS Logo Header


The FACETS Project

The goal of the FACETS (Fast Analog Computing with Emergent Transient States) project is to create a theoretical and experimental foundation for the realisation of novel computing paradigms which exploit the concepts experimentally observed in biological nervous systems.

Clipped from: FACETS Motivation

Motivation

To understand the basic concepts behind these properties is essential for two reasons: The life-science point of view and the information-technology point of view.

  • The first point of view has potential medical applications to cure brain and mind related diseases or even the longer-term goals to work towards neural prosthetic devices and artificial sensory organs.
  • The second point of view could lead to new computing devices radically different from contemporary IT technology. Such devices could provide support for complex decision making processes like the one we are currently used to obtain only from human beings.
Clipped from: FACETS Modelling the Brain

Modelling the Brain



In order to solve the model equations, all digital simulations rely on the repeated execution of simple operations on data stored in some kind of memory. This is fundamentally opposite to the realisation in the human nervous system, where 100 billions of neurons and about 1016 synapses operate in parallel in continuous time. There is an enormous gap between nature and simulation, which reaches a complexity in the order of 103 neurons in real-time with a simple integrate-and-fire model and conductance based synapses on the fastest available microprocessors.

Clipped from: FACETS Neural Hardware

Neural Hardware

[...] the only possibility to get a significant gain in simulation speed within the current decade is parallelization of dedicated analog circuits, which implement directly the processes in nerve cells. Dedicated hardware like analog ASICs can be optimized for parallelization. In FACETS' very large scale neural network systems, the cell based calculations will be done using analog models and the communication across medium or long distances using digital (spike-time) coding. With this approach, the final system size is only limited by the available resources and not by physical (signal degradation) or timing limitations.

Clipped from: robots.net - New Neural Hardware from the FACETS Project

New Neural Hardware from the FACETS Project





A new generation of neural network hardware is being developed by the Fast Analog Computing with Emergent Transient States (FACETS) Project. The FACETS hardware will have 200,000 neurons with 50 million synapses built on a single silicon wafer. Current prototypes are running 100,000 times faster than their biological couterparts, allowing a full day of neural activity to be simulated in less than a second. Physicist Karlheinz Meier, who coordinates the project, said,
We may then be able to make computing devices which are radically different and have amazing performance which, at some point, may approach the performance of the human brain – or even go beyond it!”



2008-07-30

Microscope On A Chip

Researchers at Caltech recently developed a revolutionary new type of microscope without lenses. The device is compact enough to be put in a cell phone and can use just sunlight for illumination. This makes it very appealing for Third-World applications,
ScienceDaily: Your source for the latest research news  and science breakthroughs -- updated daily

Bioengineers Develop 'Microscope On A Chip'

ScienceDaily (July 29, 2008) — Researchers at the California Institute of Technology have turned science fiction into reality with their development of a super-compact high-resolution microscope, small enough to fit on a finger tip. This "microscopic microscope" operates without lenses but has the magnifying power of a top-quality optical microscope, can be used in the field to analyze blood samples for malaria or check water supplies for giardia and other pathogens, and can be mass-produced for around $10.

clipped from www.caltech.edu
California Institute of Technology (Click for text-version)
Caltech
Biophotonics Labotatory at Caltech

Nanophotonics and Optofluidics

Changhuei Yang
Optofluidic Microscopy
Fig. 1: compact OFM prototype, compared with a US quarter.
Fig. 2: (a) OFM's layout. Red arrows: illumination; green arrow: flow direction
(b) SeveralOFM images of wild-type C. elegans; white bar =25 µm (for all images)
(c) Aspect ratio map, blue data points: wild -type L1 larvae; red: dpy24 L1 larvae.
clipped from mr.caltech.edu
[image: OFM1.jpg]

An on-chip implementation of the optofluidic microscope.


blog it

Related:
California Institute of Technology
The Changhuei Yang Research Group [Research]
Changhuei Yang
Caltech Press Release, 7/28/2008, Dr. Changhuei Yang
Optofluidic Technology Yields Microscope Without Lenses - The Size Of A
Physorg: Bioengineers develop 'microscope on a chip'
Science Daily: Bioengineers Develop 'Microscope On A Chip'
Technology Review: Tiny $10 Microscope