Loop pipelining for high-throughput stream computation using self-timed rings

We present a technique for increasing the throughput of stream process-ing architectures by removing the bottlenecks caused by loop struc-tures. We implement loops as self-timed pipelined rings that can op-erate on multiple data sets concurrently. Our contribution includes a transformation algorithm which takes as input a high-level program and gives as output the structure of an optimized pipeline ring. Our technique handles nested loops and is further enhanced by loop un-rolling. Simulations run on benchmark examples show a 1.3 to 4.9x speedup without unrolling and a 2.6 to 9.7x speedup with twofold loop unrolling. 1