C:\ProgramData\NVIDIA Corporation\CUDA Samples\v10.2\bin\win64\Debug>p2pBandwidthLatencyTest
[P2P (Peer-to-Peer) GPU Bandwidth Latency Test]
Device: 0, GeForce RTX 2080 Ti, pciBusID: 5, pciDeviceID: 0, pciDomainID:0
Device: 1, GeForce RTX 2080 Ti, pciBusID: 9, 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
     0 504.81   3.12
     1   3.04 517.49
Unidirectional P2P=Enabled Bandwidth (P2P Writes) Matrix (GB/s)
   D\D     0      1
     0 502.39  46.83
     1  46.90 516.66
Bidirectional P2P=Disabled Bandwidth Matrix (GB/s)
   D\D     0      1
     0 514.37   4.32
     1   4.74 522.24
Bidirectional P2P=Enabled Bandwidth Matrix (GB/s)
   D\D     0      1
     0 512.63  92.45
     1  92.57 518.02
P2P=Disabled Latency Matrix (us)
   GPU     0      1
     0   3.54 120.46
     1 116.23   3.34

   CPU     0      1
     0   2.72  50.57
     1  51.23   2.61
P2P=Enabled Latency (P2P Writes) Matrix (us)
   GPU     0      1
     0   7.25   1.70
     1   1.64   4.49

   CPU     0      1
     0   2.64   1.55
     1   1.56   2.54

NOTE: The CUDA Samples are not meant for performance measurements. Results may vary when GPU Boost is enabled.

C:\ProgramData\NVIDIA Corporation\CUDA Samples\v10.2\bin\win64\Debug>