A SINGLE/DOUBLE PRECISION FLOATING-POINT MULTIPLIER DESIGN FOR MULTIMEDIA APPLICATIONS

Modern graphic processors, multimedia processors, and general-purpose processors with multimedia extensions provide SIMD floating-point instructions. SIMD floating-point multiplication is commonly used in 2D and 3D applications, which mostly use single precision floating-point operands. Consequently, efficient single precision multiplier units are crucial for high performance systems. This paper introduces a novel floating point multiplier that can perform either a double precision or two parallel single-precision floating-point multiplications. The proposed design uses approximately 10% more hardware and has 33% more delay compared to a conventional double precision floating- point multiplier.