NVIDIA graphic card and CUDA architecture pairs

-

Matching SM architectures (CUDA arch and CUDA gencode) for various NVIDIA cards

I’ve seen some confusion regarding NVIDIA’s nvcc sm flags and what they’re used for:
When compiling with NVCC, the arch flag (‘-arch‘) specifies the name of the NVIDIA GPU architecture that the CUDA files will be compiled for.
Gencodes (‘-gencode‘) allows for more PTX generations, and can be repeated many times for different architectures.

When should different ‘gencodes’ or ‘cuda arch’ be used?

When you compile CUDA code, you should always compile only one ‘-arch‘ flag that matches your most used GPU cards. This will enable faster runtime, because code generation will occur during compilation.
If you only mention ‘-gencode‘, but omit the ‘-arch‘ flag, the GPU code generation will occur on the JIT compiler by the CUDA driver.
When you want to speed up CUDA compilation, you want to reduce the amount of irrelevant ‘-gencode‘ flags. However, sometimes you may wish to have better CUDA backwards compatibility by adding more comprehensive ‘-gencode‘ flags.
Find out which GPU you have, and which CUDA version you have first.

How to check which CUDA version is installed on Linux

There are several ways and steps you could check which CUDA version is installed on your Linux box

Identify the CUDA location and version with NVCC

Run which nvcc to find if nvcc is installed properly.
You should see something like /usr/bin/nvcc. If that appears, your NVCC is installed in the standard directory.
    

  1. ~ $ which nvcc
    2. 

  2. /usr/bin/nvcc
    3.
If you have installed the CUDA toolkit but which nvcc returns no results, you might need to add the directory to your path.
You can check nvcc --version to get the CUDA compiler version, which matches the toolkit version:
    

  1. ~ $ nvcc --version
    2. 

  2. nvcc: NVIDIA (R) Cuda compiler driver
    3. 

  3. Copyright (c) 2005-2016 NVIDIA Corporation
    4. 

  4. Built on Tue_Jan_10_13:22:03_CST_2017
    5. 

  5. Cuda compilation tools, release 8.0, V8.0.61
    6.
This means that we have CUDA version 8.0.61 installed.

Identify CUDA version from CUDA code

Use the cudaDriverGetVersion() API call. You can find an example of using cudaDriverGetVersion() here.

Identifying which CUDA driver version is installed and active in the kernel

    

  1. ~ $ cat /proc/driver/nvidia/version
    2. 

  2. NVRM version: NVIDIA UNIX x86_64 Kernel Module  367.48  Sat Sep  3 18:21:08 PDT 2016
    3. 

  3. GCC version:  gcc version 4.8.5 20150623 (Red Hat 4.8.5-11) (GCC)
    4.

Identifying which GPU card is installed and what version

Using nvidia-smi is the best way I’ve found to get a holistic view of everything – both GPU card model and driver version.
The driver version is 367.48 as seen below, and the cards are two Tesla K40m.
    

  1. ~ $ nvidia-smi
    2. 

  2. Tue Jun  6 12:43:17 2017
    3. 

  3. +-----------------------------------------------------------------------------+
    4. 

  4. | NVIDIA-SMI 367.48                 Driver Version: 367.48                    |
    5. 

  5. |-------------------------------+----------------------+----------------------+
    6. 

  6. | GPU  Name        Persistence-M| Bus-Id        Disp.A | Volatile Uncorr. ECC |
    7. 

  7. | Fan  Temp  Perf  Pwr:Usage/Cap|         Memory-Usage | GPU-Util  Compute M. |
    8. 

  8. |===============================+======================+======================|
    9. 

  9. |   0  Tesla K40m          On   | 0000:04:00.0     Off |                   0* |
    10. 

  10. | N/A   48C    P0    67W / 235W |  12MiB / 11439MiB    |      0%      Default |
    11. 

  11. +-------------------------------+----------------------+----------------------+
    12. 

  12. |   1  Tesla K40m          On   | 0000:42:00.0     Off |                   0* |
    13. 

  13. | N/A   54C    P0    68W / 235W |  0MiB / 11439MiB     |      0%      Default |
    14. 

  14. +-------------------------------+----------------------+----------------------+
    15. 

  15.  
    16. 

  16. +-----------------------------------------------------------------------------+
    17. 

  17. | Processes:                                                       GPU Memory |
    18. 

  18. |  GPU       PID  Type  Process name                               Usage      |
    19. 

  19. |=============================================================================
    20.

Troubleshooting

After installing a new version of CUDA, there are some situations that require rebooting the machine to have the driver versions load properly. It is my recommendation to reboot after performing the kernel-headers upgrade/install process, and after installing CUDA – to verify that everything is loaded correctly.


Supported SM and Gencode variations

Below are the supported sm variations and sample cards from that generation

Supported on CUDA 7 and later

  • Fermi (CUDA 3.2 until CUDA 8) (deprecated from CUDA 9):
    • SM20 or SM_20, compute_30 – Older cards such as GeForce 400, 500, 600, GT-630
  • Kepler (CUDA 5 and later):
    • SM30 or SM_30, compute_30 – Kepler architecture (generic – Tesla K40/K80, GeForce 700, GT-730)
      Adds support for unified memory programming
    • SM35 or SM_35, compute_35 – More specific Tesla K40Adds support for dynamic parallelism. Shows no real benefit over SM30 in my experience.
    • SM37 or SM_37, compute_37 – More specific Tesla K80Adds a few more registers. Shows no real benefit over SM30 in my experience
  • Maxwell (CUDA 6 and later):
    • SM50 or SM_50, compute_50 – Tesla/Quadro M series
    • SM52 or SM_52, compute_52 – Quadro M6000 , GeForce 900, GTX-970, GTX-980, GTX Titan X
    • SM53 or SM_53, compute_53 – Tegra (Jetson) TX1 / Tegra X1
  • Pascal (CUDA 8 and later)
    • SM60 or SM_60, compute_60 – GP100/Tesla P100 – DGX-1 (Generic Pascal)
    • SM61 or SM_61, compute_61 – GTX 1080, GTX 1070, GTX 1060, GTX 1050, GTX 1030, Titan Xp, Tesla P40, Tesla P4, Discrete GPU on the NVIDIA Drive PX2
    • SM62 or SM_62, compute_62 – Integrated GPU on the NVIDIA Drive PX2, Tegra (Jetson) TX2
  • Volta (CUDA 9 and later)
    • SM70 or SM_70, compute_70 – Tesla V100, GTX 1180 (GV104)
    • SM71 or SM_71, compute_71 – probably not implemented
    • SM72 or SM_72, compute_72 – currently unknown
  • Turing (CUDA 10 and later)
    • SM75 or SM_75, compute_75 – RTX 2080, Titan RTX, Quadro R8000

Sample Flags

According to NVIDIA:
The arch= clause of the -gencode= command-line option to nvcc specifies the front-end compilation target and must always be a PTX version. The code= clause specifies the back-end compilation target and can either be cubin or PTX or both. Only the back-end target version(s) specified by the code= clause will be retained in the resulting binary; at least one must be PTX to provide Volta compatibility.
Sample flags for generation on CUDA 7 for maximum compatibility:
    

  1. -arch=sm_30 \
    2. 

  2.  -gencode=arch=compute_20,code=sm_20 \
    3. 

  3.  -gencode=arch=compute_30,code=sm_30 \
    4. 

  4.  -gencode=arch=compute_50,code=sm_50 \
    5. 

  5.  -gencode=arch=compute_52,code=sm_52 \
    6. 

  6.  -gencode=arch=compute_52,code=compute_52
    7.
Sample flags for generation on CUDA 8 for maximum compatibility:
    

  1. -arch=sm_30 \
    2. 

  2.  -gencode=arch=compute_20,code=sm_20 \
    3. 

  3.  -gencode=arch=compute_30,code=sm_30 \
    4. 

  4.  -gencode=arch=compute_50,code=sm_50 \
    5. 

  5.  -gencode=arch=compute_52,code=sm_52 \
    6. 

  6.  -gencode=arch=compute_60,code=sm_60 \
    7. 

  7.  -gencode=arch=compute_61,code=sm_61 \
    8. 

  8.  -gencode=arch=compute_61,code=compute_61
    9.
Sample flags for generation on CUDA 9 for maximum compatibility with Volta cards.
Note the removed SM_20:
    

  1. -arch=sm_50 \
    2. 

  2.  -gencode=arch=compute_50,code=sm_50 \
    3. 

  3.  -gencode=arch=compute_52,code=sm_52 \
    4. 

  4.  -gencode=arch=compute_60,code=sm_60 \
    5. 

  5.  -gencode=arch=compute_61,code=sm_61 \
    6. 

  6.  -gencode=arch=compute_70,code=sm_70 \
    7. 

  7.  -gencode=arch=compute_70,code=compute_70
    8.
Sample flags for generation on CUDA 10 for maximum compatibility with Turing cards:
    

  1. -arch=sm_50   \
    2. 

  2.  -gencode=arch=compute_50,code=sm_50 \
    3. 

  3.  -gencode=arch=compute_52,code=sm_52 \
    4. 

  4.  -gencode=arch=compute_60,code=sm_60 \
    5. 

  5.  -gencode=arch=compute_61,code=sm_61 \
    6. 

  6.  -gencode=arch=compute_70,code=sm_70 \
    7. 

  7.  -gencode=arch=compute_75,code=sm_75 \<br /> -gencode=arch=compute_75,code=compute_75
    8.

Comments

Post a Comment

Popular posts from this blog

SOX - Sound eXchange - How to use SOX for audio processing tasks in research.

-
This article is part of the on-going Software for Geeks series. SoX stands for So und e X change. SoX is a cross-platform command line audio utility tool that works on Linux, Windows and MacOS. It is very helpful in the following areas while dealing with audio and music files. Audio File Converter Editing audio files Changing audio attributes Adding audio effects Plus lot of advanced sound manipulation features In general, audio data is described by following four characteristics: Rate – The sample rate is in samples per second. For example, 44100/8000 Data size – The precision the data is stored in.  For example, 8/16 bits Data encoding – What encoding the data type uses. For example, u-law,a-law Channels – How many channels are contained in the audio data.  For example, Stereo 2 channels SoX supports over 20 audio file formats. To get the list of all supported formats, execute sox -h from the command line. One of the major benefits of a command-line audio/mu
Read more

Sox of Silence - Original post - http://digitalcardboard.com/blog/2009/08/25/the-sox-of-silence/

-
Image
The SoX of Silence SoX is, by their own definition,  the Swiss Army knife of audio manipulation. And no doubt it’s full of fun with slicing and dicing and playback and recording and filtering and effects capabilities. But SoX is a command line tool, which means obscure syntax and parameters in order to get things done. I’ve been trying off and on for months to try to understand the  silence  filter from within SoX, which allows one to remove silence from the beginning, middle, or end of the audio. Sounds, simple, doesn’t it?  Well, it should be. Below is the  man page for the  silence  filter : silence  [-l] above-periods [duration threshold[d|%] [below-periods duration threshold[d|%]] Removes silence from the beginning, middle, or end of the audio. Silence is anything below a specified threshold. The above-periods value is used to indicate if audio should be trimmed at the beginning of the audio. A value of zero indicates no silence should be trimmed from the beg
Read more

How to get video or audio duration of a file using ffmpeg?

-
Today we will learn How to get the duration of a file using ffmpeg 1. Format Container Duration - [This works for both Video and Audio Files - better to report numbers using this command] ffprobe -v error -show_entries format=duration \ -of default=noprint_wrappers=1:nokey=1 input.mp4     2. Video Stream Duration - [This works only for Videos]   ffprobe -v error -select_streams v:0 -show_entries stream=duration \ -of default=noprint_wrappers=1:nokey=1 input.mp4     Content author - https://superuser.com/questions/650291/how-to-get-video-duration-in-seconds
Read more