Closed egoist-sx closed 8 years ago
Hi, thanks for testing it. My guess is that it has to deal with the compute capability. It is specified in the CMakeLists.txt file, as an NVCC flag: -gencode arch=compute_30,code=sm_30; Can you try to set it to 35 or higher?
Thanks for your reply. I have tested with 32(which I used for other project) and 35. But all result in same error as before.
I'm trying to replicate it but I don't have a maxwell architecture yet. I removed platform specific flags from the CMakeLists.txt file, can you try to build it again? Please remove the build folder first.
After removing specific flags, dataset_main works, but all_test failed at seed_matrix_test with following error message "Value of: cu_converge.at
Thank you for your solution :D
I have successfully built the program, but when I run "dataset_main" it terminate with following error: terminate called after thjrowing an instance of 'rmd::CudaException' what(): CudaException: Unable to bind texture: cudaError code: invalid texture reference (18)
In addition, "all_test" only pass for first test, it failed on the others for for similar reason as above. My system is Ubuntu 14.04 with Cuda 7.0 (GTX980)
Thanks for any advice!