2.44 GFLOPS 300MHz floating–point vector processing unit for high performance 3D graphics computing

A Vector Unit (VU) for the high performance 3D graphics computing has been developed. Four fMAC (floating-point Multiply-Accumulate) units which execute multiply-add operation with one throughput, one fDIV (floating-point Divide) unit which executes division and square root operations with 6 cycles at 300 MHz and 128 bits × 32 words fReg (floating-point register file) are implemented. This architecture delivers a peak performance of 2.44 GFLOPS at 300MHz.

[1]  C. Heikes,et al.  A dual floating point coprocessor with an FMAC architecture , 1996, 1996 IEEE International Solid-State Circuits Conference. Digest of TEchnical Papers, ISSCC.