1 Reply Latest reply on Jun 13, 2013 10:40 AM by bragadeesh

    clAmdFft: why 3K case is much slower than 4K?




      I'm experiencing with clAmdFft and see that FFT of 3072x3072 image is way slower than 4096x4096 (ran with 'clAmdFft.Client.exe -g -o -x 4096 -y 4096 -p 20'):

      • 230ms for 3072x3072 image
      • 33ms for 4096x4096


      What causes almost 8 times better performance for 1.7 more data? It should be related to 2^n, I guess. But which way?