> >> I did get strange results when my sync pulse was too short, but that is >> likely just the block resetting before the reorder finishes. > > as laura points out, the FFT's minimum sync pulse period is tricky: > see casper memo #24 > http://casper.berkeley.edu/memos/sync_memo_v1.pdf > > btw, many people have reported the green block FFT takes considerably > more resources than the pink block FFT. henry chased this down to the > FFT's re-order block, which has a very different implementation > in the green block. should we change the reorder part > of the green FFT back to the way it was done in the pink block?
If there is no speed penalty for the slimmer version, then yes! Otherwise, Maybe! We are both size and timing bound. John > > dan >
