Tensorrt: Support on 1080 and Titan X

[anmol039w]

Hi does this sample works on GTX 1080 ti and Titian X?

[rmccorm4]

Hi @anmol039w,

You can see the support matrix for hardware here: https://docs.nvidia.com/deeplearning/sdk/tensorrt-support-matrix/index.html#hardware-precision-matrix

And according to here: http://www.nvidia.com/object/geforce_family.html, both GTX 1080 ti and Titan X have Compute Capability 6.1

Please refer to the support matrix row above corresponding to CC6.1 for what is supported and not supported.

[rmccorm4]

Closing - Reopen if you are still having a problem.

[anmol039w]

Thanks for the support ryan

On Wed, 30 Oct, 2019, 7:54 am Ryan McCormick, [e-mail]
wrote:

Closing - Reopen if you are still having a problem.

—
You are receiving this because you were mentioned.
Reply to this email directly, view it on GitHub
https://github.com/NVIDIA/TensorRT/issues/158?email_source=notifications&email_token=AIXDC6L22NJCRWDSALS7HDLQRDV4ZA5CNFSM4JALJPRKYY3PNVWWK3TUL52HS4DFVREXG43VMVBW63LNMVXHJKTDN5WW2ZLOORPWSZGOECSWOIQ#issuecomment-547710754,
or unsubscribe
https://github.com/notifications/unsubscribe-auth/AIXDC6L5K6URMVHTW2DKVXDQRDV4ZANCNFSM4JALJPRA
.

[Edwardmark]

@rmccorm4 how to get compute capability using cpp code?

[rmccorm4]

@Edwardmark I'm not sure off the top of my head. What's your goal for knowing CC?

TensorRT has some built-in methods to see if the hardware supports things like FP16/INT8, if that's what you're looking for:
https://docs.nvidia.com/deeplearning/sdk/tensorrt-api/c_api/classnvinfer1_1_1_i_builder.html#a1d18b948852cb088d22a87cff70a2b2f