Subscribe to the gold package and get unlimited access to Shamra Academy
Register a new userOn the Design and Analysis of Quaternary Serial and Parallel Adders
220
0
0.0
(
0
)
Added by
Anindya Das Shohag
Publication date
2010
fields
Informatics Engineering
and research's language is
English
Ask ChatGPT about the research
No Arabic abstract
Optimization techniques for decreasing the time and area of adder circuits have been extensively studied for years mostly in binary logic system. In this paper, we provide the necessary equations required to design a full adder in quaternary logic system. We develop the equations for single-stage parallel adder which works as a carry look-ahead adder. We also provide the design of a logarithmic stage parallel adder which can compute the carries within log2(n) time delay for n qudits. At last, we compare the designs and finally propose a hybrid adder which combines the advantages of serial and parallel adder.
rate research
Read More
We present the evaluation of two different design configurations of a two-stage PrNi$_5$ continuous nuclear demagnetization refrigerator. Serial and parallel configurations of the two stages are considered, with emphasis on the attainable cooling power at sub-mK temperatures and the impact of the design choices on the operation of the refrigerator. Numerical simulations of heat transfer in the setup are used to evaluate the performance of the refrigerator as well as the technological requirements for the essential thermal links. In accord with similar findings for adiabatic demagnetization refrigerators [Shirron, emph{Cryogenics} textbf{62}, 2014], our simulations show that the performance of both configurations improves as the thermal links improve, and that the parallel configuration yields a higher cooling power than the series design for a given thermal link resistance and sample temperature.
The paper derives the inverse and the forward kinematic equations of a serial - parallel 5-axis machine tool: the VERNE machine. This machine is composed of a three-degree-of-freedom (DOF) parallel module and a two-DOF serial tilting table. The parallel module consists of a moving platform that is connected to a fixed base by three non-identical legs. These legs are connected in a way that the combined effects of the three legs lead to an over-constrained mechanism with complex motion. This motion is defined as a simultaneous combination of rotation and translation. In this paper we propose symbolical methods that able to calculate all kinematic solutions and identify the acceptable one by adding analytical constraint on the disposition of legs of the parallel module.
In this work, a novel quaternary algebra has been proposed that can be used to implement an arbitrary quaternary logic function in more than one systematic ways. The proposed logic has evolved from and is closely related to the Boolean algebra for binary domain; yet it does not lack the benefits of a higher-radix system. It offers seamless integration of the binary logic functions and expressions through a set of transforms and allows any binary logic simplification technique to be applied in quaternary domain. Since physical realization of the operators defined in this logic has recently been reported, it has become very important to have a well-defined algebra that will facilitate the algebraic manipulation of the novel quaternary logic and aid in designing various complex logic circuits. Therefore, based on our earlier works, here we describe the complete algebraic representation of this logic for the first time. The efficacy of the logic has been shown by designing and comparing several common logic circuits with existing designs in both binary and quaternary domain.
Neural networks are an increasingly attractive algorithm for natural language processing and pattern recognition. Deep networks with >50M parameters are made possible by modern GPU clusters operating at <50 pJ per op and more recently, production accelerators capable of <5pJ per operation at the board level. However, with the slowing of CMOS scaling, new paradigms will be required to achieve the next several orders of magnitude in performance per watt gains. Using an analog resistive memory (ReRAM) crossbar to perform key matrix operations in an accelerator is an attractive option. This work presents a detailed design using a state of the art 14/16 nm PDK for of an analog crossbar circuit block designed to process three key kernels required in training and inference of neural networks. A detailed circuit and device-level analysis of energy, latency, area, and accuracy are given and compared to relevant designs using standard digital ReRAM and SRAM operations. It is shown that the analog accelerator has a 270x energy and 540x latency advantage over a similar block utilizing only digital ReRAM and takes only 11 fJ per multiply and accumulate (MAC). Compared to an SRAM based accelerator, the energy is 430X better and latency is 34X better. Although training accuracy is degraded in the analog accelerator, several options to improve this are presented. The possible gains over a similar digital-only version of this accelerator block suggest that continued optimization of analog resistive memories is valuable. This detailed circuit and device analysis of a training accelerator may serve as a foundation for further architecture-level studies.
In spite of maturity to the modern electronic design automation (EDA) tools, optimized designs at architectural stage may become sub-optimal after going through physical design flow. Adder design has been such a long studied fundamental problem in VLSI industry yet designers cannot achieve optimal solutions by running EDA tools on the set of available prefix adder architectures. In this paper, we enhance a state-of-the-art prefix adder synthesis algorithm to obtain a much wider solution space in architectural domain. On top of that, a machine learning-based design space exploration methodology is applied to predict the Pareto frontier of the adders in physical domain, which is infeasible by exhaustively running EDA tools for innumerable architectural solutions. Considering the high cost of obtaining the true values for learning, an active learning algorithm is utilized to select the representative data during learning process, which uses less labeled data while achieving better quality of Pareto frontier. Experimental results demonstrate that our framework can achieve Pareto frontier of high quality over a wide design space, bridging the gap between architectural and physical designs.
Log in to be able to interact and post comments
comments
Fetching comments
Sign in to be able to follow your search criteria
