Developer Guide


Force Fewer Read Data Reorder Units to Reduce Area (

When the
Intel® oneAPI
implements a ring topology for the global memory interconnect (either by automatic choice or by forcing the ring through
), it widens the interconnect by default to allow more reads to occur in parallel. This allows for saturation of the global memory throughput using read-only traffic.
To narrow the interconnect in order to save area while reducing read-only throughput, use the
option in your
dpcpp -fintelfpga -Xshardware
command, where
is the number of bank's worth of read bandwidth you desire. For example, if on a two-bank BSP, you require only one bank's worth of read bandwidth, set
dpcpp -fintelfpga -Xshardware -Xsnum-reorder=1 <source_file>.cpp

Product and Performance Information


Performance varies by use, configuration and other factors. Learn more at