Managing the FPGA memory wall: Custom computing or vector processing?

Managing the memory wall is critical for massively parallel FPGA applications where data-sets are large and external memory must be used. We demonstrate that a soft vector processor can efficiently stream data from external memory whilst running computation in parallel. A non-trivial neural computation case study illustrates that multi-core vector processing coupled with careful layout of data structures performs similarly to an elaborate full-custom memory controller and execution pipeline. The vector processing version was far simpler to code so we encourage others to consider vector machines before contemplating a full-custom architecture on FPGA.