Low Latency, Parallel Computing Scheme
Parallel Computing Harnessing Unary Encoding
A new frontier in computing, opened in the last decade, uses unary encoding: the data is not packed, but complex computations such as Gamma correction and edge detection in an image can be performed using very simple logic. This new computing method provides a deterministic parallel bit shufﬂing network that uses a simple, deterministic thermometer encoding of data to achieve near optimal subsampling. The approach results in zero random ﬂuctuation and high accuracy, yet keeps the output bit stream length constant, hence overcoming the impractical large code size in a zerofluctuation stochastic code. It uses core “stochastic” logic circuits that do not employ constant coefﬁcients, making them signiﬁcantly smaller than traditional stochastic logic that potentially spend a signiﬁcant amount of resources to generate such constant coefﬁcients. The lowlatency, parallel computation scheme in the context of unary stochastic and unary deterministic computing that enables computing a parallel unary stream (i.e., all bits are generated in a single digital clock cycle, using parallel copies of a stochastic logic, generating the output stream in one clock cycle). It uses a hardwired, deterministic shuffling network that decorrelates inputs and allows for low errors in general (even zero errors in some cases). Rather than relying on randomness as an essential requirement for stochastic logic input, deterministic shuffling and subsampling techniques are described for generating inputs to the core stochastic logic.
Smaller Area than Stochastic Methods
Conventional binary has been the dominant encoding of data in digital systems due to its compact representation. However, it requires the data to be “unpacked” before computation (e.g., multiplication has to be broken into partial product and accumulation operations). Stochastic computing suffers from random fluctuations and unpredictability of the output. Previous solutions to this problem involve significantly increasing the code size, which is not practical. Stochastic computing and deterministic computing on unary streams use simple “stochastic” logic to perform complex computation. However, one of the major limitations with this method is its long latency and circuit depth. This technology offers a parallel implementation that uses both a thermometer code and a hardwired deterministic shuffling method, which significantly decreases latency with a moderate increase in area. When compared to previous stochastic computing methods, results on feedforward and feedback circuits show, on average, an (area × delay) value 7x smaller than of conventional binary and 8x smaller than previous stochastic work at a10bit binary resolution.
Comparison vs. Conventional Binary  

No. of Bits  10  11  12  13 
AreaDelay Product  8x smaller  4x smaller  2x smaller  1x 
BENEFITS AND FEATURES:
 Simple, deterministic thermometer encoding of data
 Achieves very good to optimal subsampling
 Zero random ﬂuctuation and high accuracy
 Keeps output bit stream length constant
 Core “stochastic” logic circuits
 Lowlatency, parallel computation scheme
 Enables computing a parallel unary stream
 Hardwired, deterministic shuffling method decorrelates inputs and allows for low errors
 Superior to binary computing for medium resolutions (812 bits)
APPLICATIONS:
 FPGA architectures: FPGAs provide two useful features this method uses: abundant buffered routing resources and flipflops, and the ability to handle large fanouts
 ASIC
 Fullcustom digital chips operating in domains (e.g., image processing and signal processing)
 Lowpower signal/image processing, e.g., in Internet of Things
 Machine learning/deep learning systems
 Approximate computing applications and applications that tolerate some degree of uncertainty (e.g., video processing, image tagging)
Phase of Development  Conceptual
ResearchersInterested in Licensing? 

The University relies on industry partners to scale up technologies to large enough production capacity for commercial purposes. The license is available for this technology and would be for the sale, manufacture or use of products claimed by the issued patents. Please contact Doug Franz to share your business needs and technical interest in this technology and if you are interested in licensing the technology for further research and development. 

swap_vertical_circlelibrary_booksReferences (0)

swap_vertical_circlecloud_downloadSupporting documents (0)Additional files may be available once you've completed the transaction for this product. If you've already done so, please log into your account and visit My account / Downloads section to view them.