In this paper, a new method of state code assignment for reduction of switching activities of state transition in asynchronous circuits is proposed. The algorithm is based on a on-hot code and modifies it to reduce switching activities. To estimate switching activities as a cost functions we introduce state transition probability (STP). AS a results, the proposed algorithm has an advantage of 60% over with the conventional code assignment in terms of switching and code length of state assignment.

This paper describes the design and FPGA implementation of a system control unit within a multiprocessor chip which can be used as a node processor ina massively parallel processing (MPP) caches, memory management units, a bus unit and a system control unit. Major functions of the system control unit are locking/unlocking of the shared variables of protected access, synchronization of instruction execution among four integer untis, control of interrupts, generation control of processor's status, etc. The system control unit was modeled in very high level using verilog HDL. Then, it was simulated and verified in an environment where trap handler and external interrupt controller were added. Functional blocks of the system control unit were changed into RTL(register transfer level) model and synthesized using xilinx FPGA cell library in synopsys tool. The synthesized system control unit was implemented by Xilinx FPGA chip (XC4025EPG299) after timing verification.

In this paper, a multiplying digital-to-analog converter (MDAC) circuit for low-power high-resolution CMOS algorithmic A/D converters (ADC's) is proposed. The proposed MDAC is designed to operte properly at a supply at a supply voltge between 3 V and 5 V and employs an analog0domain power reduction technique based on a bias switching circuit so that the total power consumption can be optimized. As metal-to-metal capacitors are implemented as frequency compensation capacitors, opamps' performance can be varied by imperfect process control. The MDAC minimizes the effects by the circuit performance variations with on-chip tuning circuits. The proposed low-power MDAC is implementd as a sub-block of a 10-bit 200kHz algorithmic ADC using a 0.6 um single-poly double-metal n-well CMOS technology. With the power-reduction technique enabled, the power consumption of the experimental ADC is reduced from 11mW to 7mW at a 3.3V supply voltage and the power reduction ratio of 36% is achieved.

In this paper, system application techniques of a low-voltage low-power CMOS comparator are proposed. The proposed techniques employ poly-layer lines instead of conventional dummy cells to improve the accuracy of comparators which are located in both ends of a comparator array. This technique is easily applicable for hihg-density systems such as memory. The proposed circuits are implemented using a 0.6 um signle-poly double-metal n-well CMOS technology and the dissipated power is 0.38 mW. at a 20MHz clock speed based on a 3V supply. The comparator offsets are measured separately and compared for system applications. Using the proposed techniues, the measured comparator offsets are reduced by 40% of a conventional case.

A new temperature and supply-insensitive CMOS current reference circuit was designed and tested. Te temperature insensuitivity was achieved by eliminating the mobility dependence term through the multiplication of two current components, one which is proportional to mobility and the other which is inversely proportional to mobility, by using a newly designed CMOS square root circuit. The CMOS sqare root circuit was derived from its bipolar counterpart by operating the MOS transistors in the subthreshold region. The supply insensitivity was achieved by using an internal voltage generator. Te test chip was designed ans sent out for fabrication by using a 2.mu.m double-poly double-metal n-well CMOS technology. When an external voltage source was used for the square root circuit, the maximum variation and the average temperature sensitivity were measured to be 3% and 21.4ppm/.deg.C, respectively, for the temperature range of -15~130.deg.C. The maximum current variation with supply voltage was measured to be 3% within the commerical supply voltage range of 4.5~5.5V at 30.deg. C.

In this paper, the optimal synthesis algorithm of multiple-valued logic circuits using universal logic modules (ULM) U$_{f}$ based on 3-variable ternary reed-muller expansions is presented. We check the degree of each varable for the coefficients of reed-muller expansions and determine the order of optimal control input variables that minimize the number of ULM U$_{f}$ modules. The order of optimal control input variables is utilized the realization of multiple-valued logic circuits to be constructed by ULM U$_{f}$ modules based on reed-muller expansions using the circuit cost matrix. This algorithm is performed only unit time in order to search for the optimal control input variables. Also, this algorithm is able to be programmed by computer and the run time on programming is O(p$^{n}$ ).

A new method to neglect the third term of the computational energy expression in the single-layer neural network with feedback is introduced. The system often converges to local minima instead of to global minima, because the computational energy is not matched exactly with the cost function being optimized. One of the factors causing these tow functions different is the third term of computational enegy expression. Regarding this third term energy very small, it is always ignored in designing the system. However, a sthe system growing, this third term energy is also growing and this grown term makes the computational energy function much different from the cost function. In results of differency between two functions, system converges to local minima more than before. In this paper, a new method to neglect te third term energy is introduced, so that the system with tis new method has been imroved.

This paper proposes a new method for improving the performances of the neural network for optimization using a hyubrid of gradient descent method and dynamic tunneling system. The update rule of gradient descent method, which has the fast convergence characteristic, is applied for high-speed optimization. The update rule of dynamic tunneling system, which is the deterministic method with a tunneling phenomenon, is applied for global optimization. Having converged to the for escaping the local minima by applying the dynamic tunneling system. The proposed method has been applied to the travelling salesman problems and the optimal task partition problems to evaluate to that of hopfield model using the update rule of gradient descent method.