A 260mV 468GOPS/W 256b 4-way to 32-way vector shifter with permute-assisted skip in 22nm tri-gate CMOS

A 4-way to 32-way reconfigurable 256b vector shifter with measured 2.3GHz operation consuming 41mW is fabricated in 0.9V, 22nm tri-gate CMOS. Byte-wise any-to-any permute-assisted skip for coarse-grained byte shifts, rotate-back shifter, reconfigurable mask bit generation/decoder and ultra-low voltage circuits enable 38% area reduction and 240mV-1.1V wide dynamic voltage range with a measured 8.2x higher energy efficiency at 260mV compared to nominal 0.9V operation.