[1097] Compile fails using CUDA 6.5RC

[Bryan Novack]

I'm attempting to compile cudpp 2.1 with cuda 6.5RC. It fails every time
with the following error:
nvcc fatal : unsupported gpu architecture 'compute_10'

I did some digging into the CMakeLists files and found in
src/cudpp/CMakeLists.txt (line 91) where it sets GENCODE to compute_10
without first checking the CUDPP_GENCODE_SM10 option.

I was able to get around the problem by commenting this line out, but I
don't know if I am potentially introducing an instability to cudpp.

Thoughts?
Bryan

[Mark Harris]

Starting with CUDA 6.5 support is being dropped for sm_10 (the G80
architecture). So we should also drop support from CUDPP (people who need
it can use old versions of CUDA and CUDPP). We should remove sm_10 in the
master branch.

I created issue #141 to get this fixed.
https://github.com/cudpp/cudpp/issues/141

Mark

Post by Bryan Novack
I'm attempting to compile cudpp 2.1 with cuda 6.5RC. It fails every time
nvcc fatal : unsupported gpu architecture 'compute_10'
I did some digging into the CMakeLists files and found in
src/cudpp/CMakeLists.txt (line 91) where it sets GENCODE to compute_10
without first checking the CUDPP_GENCODE_SM10 option.
I was able to get around the problem by commenting this line out, but I
don't know if I am potentially introducing an instability to cudpp.
Thoughts?
Bryan
--
You received this message because you are subscribed to the Google Groups "CUDPP" group.
To unsubscribe from this group and stop receiving emails from it, send an
Visit this group at http://groups.google.com/group/cudpp.
For more options, visit https://groups.google.com/d/optout.