Some confuse about TX1 and TX2 FLOPS calculation

Accelerated Computing CUDA CUDA Programming and Performance
1

Hi all,

I am a newbie of CUDA.

I am now evaluating the TX1 and TX2 platform. Then I encountered some problem about the performance of these 2 platforms:

  1. Are there any solid FLOPS values about TX2 ? (FP16 / FP32 / FP64) I only know TX2 has TFLOPS capability.

  2. What are the exact number of FP16 / FP32 / FP64 cores in TX1 and TX2 ? I only know both of them has 256 CUDA cores.

  3. AFAIK, the FLOPS value are calculated as follows:

  4. "Number of SM" * "Number of CUDA cores per SM" * "Peak operating freq. of GPU" * 2 (FFMA)

    5. In TX1, it only contains FP32 cores and FP64 cores (am I right ?), and their FLOPS are:

  • FP32: 1 * 256 * 1000MHz * 2 = 512GFLOPS
  • FP16: 1 * 512 (FP16 is emulated by FP32 cores in TX1) * 1000MHz * 2 = 1024GFLOPS

    • Am I right ?

    Sorry for so many questions.

    Please help. Thanks.

    2

    Some information is covered in this thread:

    [url]https://devtalk.nvidia.com/default/topic/1024825/cuda-programming-and-performance/jetson-tx2-performance/[/url]

    Having said that, you’re probably better off asking TX1 or TX2 questions on the TX1 or TX2 forum:

    [url]https://devtalk.nvidia.com/default/board/139/jetson-embedded-systems/[/url]

    3

    Note that making design decisions on FLOPS alone is rarely a good idea. The application may turn out to be (partially) memory bound, especially on a platform that uses fairly low-performance memory like NVIDIA’s integrated platforms. Also, you are unlikely to get really close to the theoretical FLOPS rate in an actual application. For compiled code, 75% may be as good as it gets.

    In general, FLOPS ratings are OK as a disqualifying criterion, but likely insufficient as a qualifying criterion.

    4

    hello,I am now evaluating the tx1 fp16 calculated performance.but I can’t get the theoretical 1TFLOPS .
    i only get 0.86TFLOPS.
    My experimental steps are as follows.
    1, i load the jstson_clocks.sh before run the test code.
    2,the test code is bellow :using Matrix Multiplication to Test Computing Performance
    GitHub - hma02/cublasHgemm-P100: Code for testing the native float16 matrix multiplication performance on Tesla P100 and V100 GPU based on cublasHgemm
    3, I used fp16’addition and multiplication to write some simple test programs.No theoretical results were obtained.

    What is the cause of this result?Is there any way to get the theoretical TFLOPS? thanks.

    5

    There is no way to get the theoretical TFLOPS on any NVIDIA GPU. Thats why the word “theoretical” is used prominently. Usually getting 80-90% is the best you can do.