We introduce a three-dimensional (3-D) processorin-memory integrated circuit design that provides progressively increasing processing power as the number of stacked dies increases, while incurring no extra design effort or mask sets. Innovative techniques for processor/memory redundancy and fast global bus evaluation are described. The architecture can be augmented with a nearest-neighbor physical 3-D communications network that can substantially reduce interconnect lengths and relieve routing congestion. The test chip, with 128 Kb of memory and 512 processing elements (PEs) on two fully depleted silicon-on-insulator (SOI) dies, can achieve a peak of 170 billion-bit-operations per second at 400 MHz.Index Terms-Memory architecture, multiprocessor interconnection, parallel processing, silicon-on-insulator (SOI) technology.

No abstract