Ask HN: How come my Ryzen 3750H is faster than my RTX 2060 in TensorFlow?

by s-p-non 3/18/2020, 1:59:50 AM with 3 comments
  • by Ragib_Zamanon 3/18/2020, 11:28:01 AM

    The network that you train in that tutorial is quite small. Your networks have to get quite large before the overhead of transferring the network onto the GPU is negligible to the cost of training it. You'll see the benefit of the GPU with larger models.

  • by navjack27on 3/18/2020, 3:00:48 AM

    I think my calculations are correct here

      Model       Zen+  2060
  Cores       4     1920
  Threads     8     1920
  Cycles      2.3   1.365
  FP64 GFLOPS 2944  163
  FP32 GFLOPS 5888  5242
  FP16 GFLOPS 11776 10483
    So it would kind of make sense yeah. 2060 isn't that strong.

    But note: I'm not totally sure on the Zen+ theoretical speeds

  • by deathtrader666on 3/18/2020, 5:23:12 AM

    Didn't know that TensorFlow works on AMD GPUs..