Abstract: Provided is a parallel processor for supporting a floating-point operation. The parallel processor has a flexible structure for easy development of a parallel algorithm involving multimedia computing, requires low hardware cost, and consumes low power. To support floating-point operations, the parallel processor uses floating-point accumulators and a flag for floating-point multiplication. Using the parallel processor, it is possible to process a geometric transformation operation in a 3-dimensional (3D) graphics process at low cost. Also, the cost of a bus width for instructions can be minimized by a partitioned Single-Instruction Multiple-Data (SIMD) method and a method of conditionally executing instructions.

Abstract: Provided is a multi-threshold complementary metal oxide semiconductor (MTCMOS) latch circuit including: a data inverting circuit for inverting and outputting input data under the control of a sleep control signal; a transmission gate for transferring the data signal output from the data inverting circuit under the control of a clock control signal; a signal control circuit for outputting the data signal output from the transmission gate under the control of a reset control signal and the sleep control signal; and a feedback circuit for feeding back the signal output from the signal control circuit and preserving the data in a sleep mode. The MTCMOS latch circuit can minimize power consumption caused by a leakage current due to elements scaled down to nano scale and also contribute to high-speed operation of a logic circuit by using an element having a low threshold voltage.

Abstract: Provided are an arithmetic method and device of a reconfigurable processor. The arithmetic device includes: an Arithmetic Logic Unit (ALU) for performing an addition and subtraction operation and a logic operation of a binary signal; a multiplier for performing a multiplication operation of the binary signal; a shifter for changing an arrangement of the binary signal; a first operand selector and a second operand selector each for selecting one of values output from the ALU, the multiplier, and the shifter; and an adder for adding the values selected by the first operand selector and the second operand selector.

Abstract: Provided is a highly energy-efficient processor architecture. The architecture employs 2-stage dynamic voltage scaling (DVS) and a sleep mode for high energy efficiency, dynamically controls the power supply voltage and activation of an embedded processor with instructions, and thus can prevent performance deterioration while reducing power consumption.

Abstract: Provided is a multi-threshold complementary metal oxide semiconductor (MTCMOS) latch circuit including: a data inverting circuit for inverting and outputting input data under the control of a sleep control signal; a transmission gate for transferring the data signal output from the data inverting circuit under the control of a clock control signal; a signal control circuit for outputting the data signal output from the transmission gate under the control of a reset control signal and the sleep control signal; and a feedback circuit for feeding back the signal output from the signal control circuit and preserving the data in a sleep mode. The MTCMOS latch circuit can minimize power consumption caused by a leakage current due to elements scaled down to nano scale and also contribute to high-speed operation of a logic circuit by using an element having a low threshold voltage.

Abstract: An apparatus for implementing the integrated function of virtual container-11(VC-11) and tributary unit group-2(TUG-2) is configured to transmit and receive a DS-1 network signal and a TUG-2 system signal through a synchronization process in a synchronous multiplexing structure. Data between a network and a system is converted by using only one Tx buffer and one receiving buffer in a transmitter and a receiver respectively. An input of a Tx FIFO buffer is a DS-1 signal of 1.544 Mbps, and an output thereof is a TU-11 frame of 1.728 Mbps including spaces for a path overhead and a pointer. An input of a RX FIFO buffer is the TU-11 signal of 1.728 Mbps in which the path overhead and the pointer are eliminated, and an output thereof is the DS-1 signal of 1.544 Mbps.