Design of High-Performance and Low-Power Microelectronics


Omnibase Logic, Inc. is a Fabless Semiconductor Company with a patented breakthrough for the design of integrated circuits. Omnibase was recognized as a Technology Pioneer by The World Economic Forum in Davos, in 2007 for providing a “world-changing” technology. Omnibase holds patents in the United States and other principal chip making and consuming countries around the world. Our IP will lead to new circuit architectures allowing for chips based on multiple-valued logic that can perform more functions, run faster, and cost less.

Find Out More

Technology

Our technology is based on circuitry for the implementation of multiple-valued logic (MVL). This unique voltage mode logic (VML) circuit architecture is protected by US Patent #6,133,754 (referred to as SUS-LOC).

International patents have been secured in all major chip manufacturing and consuming countries. This circuit structure is general in form and can be used to implement any radix. The technology has been implemented in standard CMOS processes with three different chips manufactured. Our CMOS design requires no unique or exotic manufacturing processes, and uses standard design tools.

Currently, digital circuits run on voltage levels that can produce signals that can be interpreted as one of only two states, a “0” or a “1”. To expand the data throughput, MVL circuits use more logical states such as 0,1,2 (ternary) or 0,1,2,3 (quaternary). Use of MVL means fewer wires are needed to move data. More logic operations can be completed per wire and more data can be transmitted, or stored. MVL architecture will allow for smaller devices with reduced component counts and reduced bus widths. Integrated circuits based on MVL technology use less power due to reduced parasitics, reduced clock rates, and reduced logic swings. MVL chips have increased performance over the binary equivalent because of the fundamental mathematical advantage of operating at higher radices.


US Patent #6,133,754 issued for “Multiple-Valued Logic Circuit Architecture; Supplementary Symmetrical Logic Circuit Structure (SUS-LOC)” with allowance of all claims. PCTs filed and issued in principal semiconductor producing and consuming nations.

Designed and fabricated three experimental chips using SUS-LOC technology.

Developed cell library for SUS-LOC chips and simulated performance of SUS-LOC compared to binary chips under research grant to Enssat in France.

Simulated SUS-LOC chip performance compared to binary chips showing 40% less power consumption for SUS-LOC.

Published papers on the performance of SUS-LOC based chips.

Identified Set Theory and Multi-Value Set Theory as target applications with greater than 10,000X performance improvement over standard binary implementations.

Identified three target markets which would benefit from the use of multiple-valued logic:

Artificial Intelligence

Encryption/Security

Machine Learning

Engaged with X-FAB to define process characteristics and validate that ternary logic could be implemented at a Pure Play Foundry.

Two-level logic, referred to as “binary logic” is the primary logic coding method used in digital integrated circuits (ICs) and involves only two levels: 0 and 1. Multiple-Valued Logic (MVL) codes information in multiple levels and typically refers to systems where more than two discrete levels are used in a single conductor.

Digital systems contain internal signals which take on a finite number of values. If n is a positive integer denoting the number of discrete values which can be assumed by such signals, then the system is said to be n-valued, where n ≥ 2. Multiple-valued logic typically refers to systems where n > 2.

Binary signals: n = 2

Ternary signals: n = 3

Quaternary signals: n = 4

Binary information in 3 values = 8

Ternary information is 3 values = 27

Quaternary information in 3 values = 64

MVL principles and methods are general and can be used independent of the actual underlying implementation of the circuits. Several MVL applications are currently implemented in software that executes on a binary microprocessor or field programmable gate array (FPGA).

The “Supplementary Symmetrical Logic Structure” referred to as (SUS-LOC) can be used to realize any “r-valued” logic function. The structure never allows a DC path between a power supply and ground, resulting in a nominally zero DC power. This low-power characteristic is useful in the realization of very-large-scale-integrated (VLSI) multiple-valued logic (MVL) circuits.

The principal features of SUS-LOC include a design structure that allows zero nominal DC power dissipation by providing no DC path between logic-level-defining power sources and ground. In the design of a logical function of radix ‘r’, the resulting structure uses ‘r-1’ power supplies to define the ‘r-1’ non-zero logic levels.

The output node of the r-valued logic function is connected with pass transistor networks to the ‘r-1’ power sources and ground. For any one combination of inputs, only one path from a power supply or ground to the output node is activated. The procedures for designing the pass-transistor networks include the choice of enhancement- or depletion-mode, NMOS or PMOS transistors, and the specification of the selected transistors’ threshold voltages.


Applications

Multi-Level Semiconductor Technology can be applied to many different fields and applications.

Omnibase Logic is actively investigating multiple application areas and has identified solutions in Machine Learning, Artificial Intelligence, and Encryption / Security. If you have an application :


Artificial intelligence (AI) is "the study and design of intelligent agents" where an intelligent agent is a system that perceives its environment and takes actions that maximize its chances of success.

The field was founded on the claim that a central property of humans, intelligence can be so precisely described that it can be simulated by a machine. Artificial intelligence has been the subject of optimism, but has also suffered setbacks and, today, has become an essential part of the technology industry, providing the heavy lifting for many of the most difficult problems in computer science.

AI research is highly technical and specialized, deeply divided into subfields. One subfield of particular interest to multiple-valued logic is an area termed Fuzzy Logic. Fuzzy logic is concerned with the formal principles of approximate reasoning; everything, including truth, is a matter of degree. Precise reasoning is viewed as the limiting case. Fuzzy logic plays a role in the remarkable human ability to make rational decisions in an environment of uncertainty and imprecision.

Machine learning is concerned with the design and development of algorithms that allow computers to evolve behaviors based on empirical data, such as from sensor data or databases.

A learner can take advantage of examples (data) to capture characteristics of interest of their unknown underlying probability distribution. Data can be seen as examples that illustrate relations between observed variables. A major focus of machine learning research is to automatically learn to recognize complex patterns and make intelligent decisions based on data; the difficulty lies in the fact that the set of all possible behaviors given all possible inputs is too large to be covered by the set of observed examples (training data). Hence the learner must generalize from the given examples, so as to be able to produce a useful output in new cases.

Applications for machine learning include machine perception, computer vision, natural language processing, syntactic pattern recognition, search engines, medical diagnosis, bioinformatics, brain-machine interfaces and cheminformatics, detecting credit card fraud, stock market analysis, classifying DNA sequences, speech and handwriting recognition, object recognition in computer vision, game playing, software engineering, adaptive websites, robot locomotion, and structural health monitoring.

Special computers and hardware accelerators have been proposed to do some kind of processing of Boolean functions: evaluation, Boolean operations such as intersection or complementation, checking for tautology or satisfiability, verification, resolution, etc. Since all NP-complete problems can be reduced to one of the above problems and particularly to the 3-SAT Problem. Multiple-valued logic along with a general problem solving methodology can be used to reduce any problem to some consistent labeling problem and next reducing it to some manipulations of multiple-valued logic functions.

FPGA-based hardware accelerators of certain machine learning algorithms have shown 10,000 x performance improvement over software methods. Omnibase Logic is extending these methods into silicon implementations using SUS-LOC to achieve even further improvements and scalability beyond the limits of current FPGA technology.

In cryptography, encryptionis the process of transforming information using an algorithm to make it unreadable to anyone except those possessing special knowledge, usually referred to as a key.

The result of the process is encrypted information. Encryption has long been used by militaries and governments to facilitate secret communication. Encryption is now commonly used in protecting information within many kinds of civilian systems. Encryption is also used to protect data in transit, for example data being transferred via networks (e.g. the Internet, e-commerce), mobile telephones, wireless microphones, wireless intercom systems, Bluetooth devices and bank automatic teller machines.

Encryption, by itself, can protect the confidentiality of messages, but other techniques are still needed to protect the integrity and authenticity of a message. Standards and cryptographic software and hardware to perform encryption are widely available, but successfully using encryption to ensure security is still a challenging problem. A single slip-up in system design or execution can allow successful attacks. By using different radix keys, encryption can be better encoded in fewer bits and provide another level of obscurity.


About Omnibase

Omnibase Logic = 'logic of many bases'

Omnibase Logic was established in 2005 to pursue technologies that can result in considerable improvement over existing semiconductor solutions that use binary logic. Omnibase Logic developed patented technology that is fundamental to these breakthroughs. At Omnibase Logic, we are developing different applications which apply our Multiple-valued logic technology to create unfair product advantages.


The Omnibase Logic management team consists of a strong group of experienced leaders from a variety of disciplines within the semiconductor industry.

Members of the management team have demonstrated a proven track record of success in semiconductor new product development, marketing, and sales. Key executives come from high profile fab-less semiconductor and integrated device manufacturers. Their depth of overall business experience provides Omnibase Logic with a strong, agile and talented senior management team focused on increasing the design payback in the semiconductor industry.

Omnibase Logic, Inc. is a privately held corporation with financing from angel investors committed to the process of technology commercialization.

We welcome investor inquiries. If you are interested in investment information regarding Omnibase Logic, please e-mail us at investor@omnibaselogic.com.

OMNIBASE LOGIC
4899 Montrose Blvd Suite 805
Houston, Texas 77006

Office: 713-520-9222

Email: bill@wvwalker.com


© Copyright Omnibase Logic. All rights reserved.