Closed vlapse closed 10 years ago
remove the compute_20,code=sm,compute_20 part
I wonder how it got in there in the first place as ccMiner does not and will not support Compute 2.0 devices at this point.
2014-06-14 20:27 GMT+02:00 helllgast notifications@github.com:
Hi.
I cannot compile newest ccminer with -O2 or -O3 optimizations....
/opt/cuda/bin/nvcc -O2 -I . -Xptxas "-abi=no -v" -gencode=arch=compute_20,code=\"sm_20,compute_20\" -gencode=arch=compute_30,code=\"sm_30,compute_30\" -gencode=arch=compute_35,code=\"sm_35,compute_35\" --maxrregcount=80 --ptxas-options=-v -o cuda_groestlcoin.o -c cuda_groestlcoin.cugroestl_functions_quad.cu(258): error: identifier "shfl" is undefined groestl_functions_quad.cu(263): error: identifier "shfl" is undefined groestl_functions_quad.cu(268): error: identifier "shfl" is undefined bitslice_transformations_quad.cu(8): error: identifier "shfl" is undefined bitslice_transformations_quad.cu(414): error: identifier "__shfl" is undefined
5 errors detected in the compilation of "/tmp/tmpxft_0000495c_00000000-13_cuda_groestlcoin.compute_20.cpp1.ii".
— Reply to this email directly or view it on GitHub https://github.com/cbuchner1/ccminer/issues/15.
if you look at Makefile.am in the current github master branch you won't find any mention of Compute 2.0
https://github.com/cbuchner1/ccminer/blob/master/Makefile.am
did you run ./autogen.sh also?
I didn't run ./autogen.sh, my fault sorry...
Hi.
I cannot compile newest ccminer with -O2 or -O3 optimizations....