Which when i compile gets transformed to: ’ -o ’ filename ‘.o ’ PIC_Option ’ -I’ matlabroot '/extern/include ’ ] NvccCommandLine = [ 'nvcc -compile ’ cuFileName ’ ’ Host_Compiler_Location ’ ’ PIC_Option = ’ -compiler-options -fPIC -arch=sm_35 -rdc=true’ %invoking the CUDA compiler, nvcc, and then linking with the MEXĬUDA_LIB_Location = ‘/usr/local/cuda-5.0/lib64’ %NVMEX(FILENAME) will create a MEX-File (also with the name FILENAME) by %NVMEX Compiles and links a CUDA file for MATLAB usage Compiling and running of the mex-code was fine with the following command before adding theįunctionality of DYNAMIC PARALLELISM of recursively calling a kernel till some condition. G++ -shared -o test.so test1.o test2.o link.o -L/usr/local/cuda/lib64 -lcudartīut now i am trying to parallelize some code using MATLAB using the MEX interface. Nvcc -arch=sm_20 -Xcompiler ‘-fPIC’ -dlink test1.o test2.o -o link.o Nvcc -arch=sm_20 -Xcompiler ‘-fPIC’ -dc test1.cu test2.cu But got it resolved by the following way. I have some issues with compiling cuda file written in MEX-interface for MATLAB.ĭynamic Parallelism was giving some problem previously in C while running at stampede.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |