Check NVLink in Windows

Please note that you need to Install Nvidia drivers in Windows or Install CUDA toolkit in Windows before checking NVLink connections. Also, Switch GPU mode to TCC.

Install Visual Studio

Let’s ensure everything is functioning correctly by runnig cuda-samples from the official repository. To accomplish this, we need to install Visual Studio 2022 CE (Community Edition) sequentially and reinstall CUDA Toolkit to activate VS plugins. Visit https://visualstudio.microsoft.com/downloads/ to download the Visual Studio 2022:

Execute the downloaded installer, tick Desktop development with C++, and click the Install button:

Run tests

Re-install CUDA toolkit using our step-by-step guide Install CUDA toolkit in Windows. Reboot server and download ZIP-archive with cuda-samples. Unzip it and open the subdirectory Samples\1_Utilities\bandwidthTest. Double click on bandwidthTest_vs2022 and run using Ctrl + F5 keyboard shortcut:

[CUDA Bandwidth Test] - Starting...
  Running on...
  
   Device 0: NVIDIA RTX A6000
   Quick Mode
  
   Host to Device Bandwidth, 1 Device(s)
   PINNED Memory Transfers
     Transfer Size (Bytes)        Bandwidth(GB/s)
     32000000                     6.0
  
   Device to Host Bandwidth, 1 Device(s)
   PINNED Memory Transfers
     Transfer Size (Bytes)        Bandwidth(GB/s)
     32000000                     6.6
  
   Device to Device Bandwidth, 1 Device(s)
   PINNED Memory Transfers
     Transfer Size (Bytes)        Bandwidth(GB/s)
     32000000                     637.2
  
  Result = PASS
  
  NOTE: The CUDA Samples are not meant for performance measurements. Results may vary when GPU Boost is enabled.

You can run any sample. Try Samples\5_Domain_Specific\p2pBandwidthLatencyTest to see your topology and connectivity matrix:

[P2P (Peer-to-Peer) GPU Bandwidth Latency Test]
  Device: 0, NVIDIA RTX A6000, pciBusID: 3, pciDeviceID: 0, pciDomainID:0
  Device: 1, NVIDIA RTX A6000, pciBusID: 4, pciDeviceID: 0, pciDomainID:0
  Device=0 CAN Access Peer Device=1
  Device=1 CAN Access Peer Device=0
  
  ***NOTE: In case a device doesn't have P2P access to other one, it falls back to normal memcopy procedure.
  So you can see lesser Bandwidth (GB/s) and unstable Latency (us) in those cases.
  
  P2P Connectivity Matrix
       D\D     0     1
       0       1     1
       1       1     1
  Unidirectional P2P=Disabled Bandwidth Matrix (GB/s)
     D\D     0      1
       0 671.38   6.06
       1   6.06 671.47
  Unidirectional P2P=Enabled Bandwidth (P2P Writes) Matrix (GB/s)
     D\D     0      1
       0 631.31  52.73
       1  52.83 673.00
  Bidirectional P2P=Disabled Bandwidth Matrix (GB/s)
     D\D     0      1
       0 645.00   8.19
       1   8.11 677.87
  Bidirectional P2P=Enabled Bandwidth Matrix (GB/s)
     D\D     0      1
       0 655.96 101.78
       1 101.70 677.92
  P2P=Disabled Latency Matrix (us)
     GPU     0      1
       0   2.20  49.07
       1  10.33   2.20
  
     CPU     0      1
       0   3.55   7.01
       1   6.79   3.39
  P2P=Enabled Latency (P2P Writes) Matrix (us)
     GPU     0      1
       0   2.19   1.33
       1   1.26   2.22
  
     CPU     0      1
       0   6.80   4.86
       1   2.09   3.02
  
  NOTE: The CUDA Samples are not meant for performance measurements. Results may vary when GPU Boost is enabled.