Unable to run P2P sample on a three gpu system

Accelerated Computing CUDA CUDA Programming and Performance
1

Hi,
I have 3 GPUs installed in an X99 system. When I run simpleP2P sample from cuda toolkit, it shows P2P not possible. My concern is, can I make it do P2P or I can’t?

Sample Output:

[./simpleP2P] - Starting...
Checking for multiple GPUs...
CUDA-capable device count: 3
> GPU0 = "TITAN X (Pascal)" IS  capable of Peer-to-Peer (P2P)
> GPU1 = "GeForce GTX TITAN X" IS  capable of Peer-to-Peer (P2P)
> GPU2 = "GeForce GTX 1060 6GB" IS  capable of Peer-to-Peer (P2P)

Checking GPU(s) for support of peer to peer memory access...
> Peer access from TITAN X (Pascal) (GPU0) -> GeForce GTX TITAN X (GPU1) : No
> Peer access from TITAN X (Pascal) (GPU0) -> GeForce GTX 1060 6GB (GPU2) : No
> Peer access from GeForce GTX TITAN X (GPU1) -> TITAN X (Pascal) (GPU0) : No
> Peer access from GeForce GTX TITAN X (GPU1) -> GeForce GTX 1060 6GB (GPU2) : No
> Peer access from GeForce GTX 1060 6GB (GPU2) -> TITAN X (Pascal) (GPU0) : No
> Peer access from GeForce GTX 1060 6GB (GPU2) -> GeForce GTX TITAN X (GPU1) : No
Two or more GPUs with SM 2.0 or higher capability are required for ./simpleP2P.
Peer to Peer access is not available amongst GPUs in the system, waiving test.

cat /proc/cpuinfo

processor	: 15
vendor_id	: GenuineIntel
cpu family	: 6
model		: 63
model name	: Intel(R) Core(TM) i7-5960X CPU @ 3.00GHz
stepping	: 2
microcode	: 0x2d
cpu MHz		: 1200.000
cache size	: 20480 KB
physical id	: 0
siblings	: 16
core id		: 7
cpu cores	: 8
apicid		: 15
initial apicid	: 15
fpu		: yes
fpu_exception	: yes
cpuid level	: 15
wp		: yes
flags		: fpu vme de pse tsc msr pae mce cx8 apic sep mtrr pge mca cmov pat pse36 clflush dts acpi mmx fxsr sse sse2 ss ht tm pbe syscall nx pdpe1gb rdtscp lm constant_tsc arch_perfmon pebs bts rep_good nopl xtopology nonstop_tsc aperfmperf eagerfpu pni pclmulqdq dtes64 monitor ds_cpl vmx est tm2 ssse3 fma cx16 xtpr pdcm pcid dca sse4_1 sse4_2 x2apic movbe popcnt tsc_deadline_timer aes xsave avx f16c rdrand lahf_lm abm ida arat epb xsaveopt pln pts dtherm tpr_shadow vnmi flexpriority ept vpid fsgsbase tsc_adjust bmi1 avx2 smep bmi2 erms invpcid
bogomips	: 5996.51
clflush size	: 64
cache_alignment	: 64
address sizes	: 46 bits physical, 48 bits virtual
power management:
2

probably not.

P2P capability depends on having GPUs on the same PCIE root complex. It also generally requires the GPUs to be of the same type or architecture.

If you want to run P2P work, its recommended to use identical GPUs and make sure all the GPUs are on the same PCIE switch tree or root complex.