Power and Area-Efficient Unified Computation of Vector and Elementary Functions for Handheld 3D Graphics Systems
Issue No.04 - April (2008 vol.57)
DOI Bookmark: http://doi.ieeecomputersociety.org/10.1109/TC.2008.12
A unified computation method of vector and transcendental function is proposed for handheld 3D graphics systems. It unifies vector operations like vector multiply, multiply-and-add, divide, divide-by-square-root and dot product and transcendental functions like trigonometric, inverse trigonometric, hyperbolic, inverse hyperbolic, power (x<sup>y</sup> with two variables) and logarithm to arbitrary base in a single four-way arithmetic platform. A number system called fixed-point hybrid number system (FXP-HNS), which combines the fixed-point number system (FXP) and logarithmic number system (LNS), is proposed for the power- and area-efficient unification. Low power and small area logarithmic and antilogarithmic conversion schemes are also proposed for the data conversion between FXP and LNS in the FXP-HNS and achieve 0.41 percent and 0.08 percent maximum conversion error, respectively. The unified arithmetic unit based on the proposed schemes is presented with fully pipelined architecture and achieves single cycle throughput with maximum four-cycle latency for all the supported operations.
Computer Arithmetic, unified arithmetic unit, vector operations, transcendental functions, logarithmic number system, 3D computer graphics, handheld systems
Hyejung Kim, Byeong-Gyu Nam, "Power and Area-Efficient Unified Computation of Vector and Elementary Functions for Handheld 3D Graphics Systems", IEEE Transactions on Computers, vol.57, no. 4, pp. 490-504, April 2008, doi:10.1109/TC.2008.12