HLS-Compatible, Embedded-Processor Stream Links

Abstract

Fine-grained dataflow streaming between parallel compute operators provides both a simple form of concurrency and high performance operation. These streams are regularly used to support concurrency within HLS computations on the FPGA. We provide a compatible stream API and implementation that allows FPGA operators to interoperate with operators implemented on the embedded, hardcore processors on SoC FPGAs. With our stream interface, individual operators can be written in C and compiled to either the embedded core or the FPGA from a single source file, and neither FPGA-mapped nor processor-mapped operators need to know whether the other side of the stream is implemented on an embedded core or on the FPGA. This capability also eases processor integration for debugging and development. Our streams support over 100MB/s per core between the ARM A53 cores on the Zynq UltraScale+ and the FPGA fabric even when all four A53 cores concurrently share a single AXI channel.