Low Power Interconnects for SIMD Computers

Driven by continued scaling of Moore’s Law, the number of processing elements on a die are increasing dramatically. Recently there has been a surge of wide single instruction multiple data architectures designed to handle computa-tionally intensive applications like 3D graphics, high defini-tion video, image processing, and wireless communication. A limit of the SIMD width of these types of architectures is the scalability of the interconnect network between the processing elements in terms of both area and power. To mitigate this problem, we propose the use of a new interconnect topology, XRAM, which is a low power high performance matrix style crossbar. It re-uses output buses for control programming, and stores multiple swizzle configurations at the cross points using SRAM cells, signif-icantly reducing routing congestion and control signaling. We show that compared to conventionally implemented crossbars, the area scales with the product of input×output ports while consuming almost 50 % less energy. We present an application case study, color-space conversion, utilizing XRAM and show a 1.4x gain in performance while con-suming 1.5-2.5x less power. I