DeepAI AI Chat
Log In Sign Up

Introduction of the Residue Number Arithmetic Logic Unit With Brief Computational Complexity Analysis

by   Eric B. Olsen, et al.

Digital System Research has pioneered the mathematics and design for a new class of computing machine using residue numbers. Unlike prior art, the new breakthrough provides methods and apparatus for general purpose computation using several new residue based fractional representations. The result is that fractional arithmetic may be performed without carry. Additionally, fractional operations such as addition, subtraction and multiplication of a fraction by an integer occur in a single clock period, regardless of word size. Fractional multiplication is of the order O(p), where p equals the number of residues. More significantly, complex operations, such as sum of products, may be performed in an extended format, where fractional products are performed and summed using single clock instructions, regardless of word width, and where a normalization operation with an execution time of the order O(p) is performed as a final step.


page 1

page 2

page 3

page 4


Proposal for a High Precision Tensor Processing Unit

This whitepaper proposes the design and adoption of a new generation of ...

Reachability relations of timed pushdown automata

Timed pushdown automata (TPDA) are an expressive formalism combining rec...

The Integer Approximation of Undirected Graphical Models

Machine learning on resource-constrained ubiquitous devices suffers from...

Integer undirected graphical models for resource-constrained systems

Machine learning on resource-constrained ubiquitous devices suffers from...

Which arithmetic operations can be performed in constant time in the RAM model with addition?

In the literature of algorithms, the specific computation model is often...

Efficient Floating Point Arithmetic for Quantum Computers

One of the major promises of quantum computing is the realization of SIM...

Egyptian multiplication and some of its ramifications

Fast exponentiation with an integer exponent relies on squaring of the b...