C:\Windows\system32>cd C:\ProgramData\NVIDIA Corporation\CUDA Samples\v10.2\bin\win64\Debug C:\ProgramData\NVIDIA Corporation\CUDA Samples\v10.2\bin\win64\Debug>simpleP2P [simpleP2P] - Starting... Checking for multiple GPUs... CUDA-capable device count: 2 Checking GPU(s) for support of peer to peer memory access... > Peer access from TITAN RTX (GPU0) -> TITAN RTX (GPU1) : Yes > Peer access from TITAN RTX (GPU1) -> TITAN RTX (GPU0) : Yes Enabling peer access between GPU0 and GPU1... Allocating buffers (64MB on GPU0, GPU1 and CPU Host)... Creating event handles... cudaMemcpyPeer / cudaMemcpy between GPU0 and GPU1: 40.52GB/s Preparing host buffer and memcpy to GPU0... Run kernel on GPU1, taking source data from GPU0 and writing to GPU1... Run kernel on GPU0, taking source data from GPU1 and writing to GPU0... Copy data back to host from GPU0 and verify results... Disabling peer access... Shutting down... Test passed C:\ProgramData\NVIDIA Corporation\CUDA Samples\v10.2\bin\win64\Debug>nvcc -V nvcc: NVIDIA (R) Cuda compiler driver Copyright (c) 2005-2019 NVIDIA Corporation Built on Wed_Oct_23_19:32:27_Pacific_Daylight_Time_2019 Cuda compilation tools, release 10.2, V10.2.89 C:\ProgramData\NVIDIA Corporation\CUDA Samples\v10.2\bin\win64\Debug>nvidia-smi nvlink -c GPU 0: TITAN RTX (UUID: GPU-7fb51c1d-c1e7-35cc-aad7-66971f05ddb7) Link 0, P2P is supported: true Link 0, Access to system memory supported: true Link 0, P2P atomics supported: true Link 0, System memory atomics supported: true Link 0, SLI is supported: true Link 0, Link is supported: false Link 1, P2P is supported: true Link 1, Access to system memory supported: true Link 1, P2P atomics supported: true Link 1, System memory atomics supported: true Link 1, SLI is supported: true Link 1, Link is supported: false GPU 1: TITAN RTX (UUID: GPU-5a71d61e-f130-637a-b33d-4df555b0ed88) Link 0, P2P is supported: true Link 0, Access to system memory supported: true Link 0, P2P atomics supported: true Link 0, System memory atomics supported: true Link 0, SLI is supported: true Link 0, Link is supported: false Link 1, P2P is supported: true Link 1, Access to system memory supported: true Link 1, P2P atomics supported: true Link 1, System memory atomics supported: true Link 1, SLI is supported: true Link 1, Link is supported: false C:\ProgramData\NVIDIA Corporation\CUDA Samples\v10.2\bin\win64\Debug>cd C:\ProgramData\NVIDIA Corporation\CUDA Samples\v10.2\bin\win64\Debug C:\ProgramData\NVIDIA Corporation\CUDA Samples\v10.2\bin\win64\Debug>p2pBandwidthLatencyTest [P2P (Peer-to-Peer) GPU Bandwidth Latency Test] Device: 0, TITAN RTX, pciBusID: 1, pciDeviceID: 0, pciDomainID:0 Device: 1, TITAN RTX, pciBusID: 47, 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 0 375.51 9.56 1 10.39 540.52 Unidirectional P2P=Enabled Bandwidth (P2P Writes) Matrix (GB/s) D\D 0 1 0 539.63 46.93 1 46.94 537.36 Bidirectional P2P=Disabled Bandwidth Matrix (GB/s) D\D 0 1 0 544.35 13.28 1 14.13 552.50 Bidirectional P2P=Enabled Bandwidth Matrix (GB/s) D\D 0 1 0 546.26 91.47 1 93.13 551.73 P2P=Disabled Latency Matrix (us) GPU 0 1 0 4.34 124.52 1 140.83 3.95 CPU 0 1 0 2.20 40.13 1 38.64 2.09 P2P=Enabled Latency (P2P Writes) Matrix (us) GPU 0 1 0 4.22 1.71 1 1.91 4.77 CPU 0 1 0 2.12 1.21 1 1.20 2.08 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>