National Chung Cheng University

Rong-Guey Chang

Shuenn-Yuh Lee

Jia-Hua Hong

Chih-Yuan Chen

Chia-Hsien Su

Tzong-Yen Lin

Yuan-Shin Hwang

Shao-Yang Wang

A segmental allocation method of expanding RISC processor register includes the steps of a) setting an instruction format of the RISC processor, the destination register field being set having 6 bits to correspond to 64 registers and at least one source register field having at least 4 bits to correspond to at least 16 registers; b) providing two solutions to the problem resulting from that the instruction format in the step a) goes beyond range under some circumstances; and c) setting a register segment allocation algorithm having the steps of c1) providing and grouping a plurality of pseudo registers; c2) prioritizing the pseudo registers in each of the groups; c3) combining the groups pursuant to the priorities thereof; and c4) locating the physical register of lowest computational cost.

Prioritized assignment of sub-range registers of circularly addressable extended register file to loop variables in RISC processor

The present invention discloses a power-aware compiling method, wherein the power model of an application program are established via building and analyzing the control flow chart and the data flow chart of the application program; each functional unit of the application program is assigned a power mode; a judgment is undertaken to determine whether the idle functional units are independent; if none dependency exists between those idle function units, the program codes of the same idle function units are merged into a new basic block, and the idle functional units are turned off for saving power; each new basic block is assigned an appropriate power mode; the basic blocks with the same power modes are merged to reduce the transitions between different power modes; thus, the power consumed by changing voltage or frequency can be decreased.

Power-aware compiling method

The present invention discloses a sigma-delta modulator architecture capable of automatically improving dynamic range and a method for the same. Based on the concept that different dynamic ranges of a sigma-delta modulator can be obtained via adjusting the signal power gain thereof, the present invention provides a novel algorithm to implement an automation program. The present invention finds out several sets of dynamic-range curves to improve the overall dynamic range. Via a high-level sigma-delta modulator architecture, the present invention can calculate the required feedforward coefficients. Further, the present invention install in the sigma-delta modulator architecture with four additional components, including a peak detection unit, a comparator unit, a digital coefficient control unit and a switch unit, to dynamically detect the output of the sigma-delta modulator and dynamically modify the feedforward coefficient of the sigma-delta modulator. Thus is extended the dynamic range of the sigma-delta modulator.

Sigma-delta modulator architecture capable of automatically improving dynamic range method for the same

The present invention provides a method and system for processing an instruction set, which can be applied to compress the operation part of a sequence of instructions in the instruction set and to perform the corresponding decompression. Upon the compression, the sequence of instructions is divided into a operation part and a register part, then recursively compress consecutive instructions with two operation codes that emerge repeatedly in the sequence of instructions until no further compression can be performed. The compression leads to form a binary tree which constitutes of nodes corresponding to the original operation codes or the ones derived from them in the recursive compression process. Furthermore, a pre-fetch mechanism is used in the present invention to promote the performance upon decompression. According to standard tests performed with SPEC 2000, DSPstone, Mediabench, and MPEG4 benchmarks on the basis of the ARM instruction set, a code size reduction of 33% on average with a decompression overhead of only 3% can be reached.

Growing community of inventors

Minsyong, Taiwan

Rong-Guey Chang