A CMOS floating-point vector-arithmetic unit

Timmermann, D.D.TimmermannRix, B.B.RixHahn, H.H.HahnHosticka, B.J.B.J.Hosticka2022-03-032022-03-031994https://publica.fraunhofer.de/handle/publica/18431310.1109/4.284719This work describes a floating-point arithmetic unit based on the CORDIC algorithm. The unit computes a full set of high level arithmetic and elementary functions: multiplication, division, (co)sine, hyperbolic (co)sine, square root, natural logarithm, inverse (hyperbolic) tangent, vector norm, and phase. The chip has been integrated in 1.6 fm double-metal, n-well CMOS technology and achieves a normalized peak performance of 220 MFLOPS.enalgorithmAlgorithmusarithmeticArithmetikCORDICfloating pointGleitkomma621A CMOS floating-point vector-arithmetic unitjournal article