magma_dgels_gpu error when trying to compile

Open discussion for MAGMA library (Matrix Algebra on GPU and Multicore Architectures)
Post Reply
Posts: 1
Joined: Thu Mar 05, 2020 11:01 am

magma_dgels_gpu error when trying to compile

Post by outterspace » Thu Mar 05, 2020 11:07 am

Hey, hope someone experienced can help regarding this error.

I try to solve a least squares problem using "magma_dgels_gpu()" of the MAGMA Library. I have the "Tesla C2050 GPU.

Whenever I try to compile a code I get this error: function “magma_dgels_gpu” --> error “magma_trans_t”.

Please help.

Posts: 918
Joined: Fri Jan 06, 2012 2:13 pm

Re: magma_dgels_gpu error when trying to compile

Post by mgates3 » Thu Mar 05, 2020 11:04 pm

Can you give more specifics such as:
version of MAGMA (e.g., MAGMA 2.5.2)
C/C++ compiler & version (e.g., g++ 9.2.0)
CUDA version (e.g., CUDA 10.0)
Is this an error compiling MAGMA, or an error compiling your application using MAGMA?
If it's your application, please include a minimum code example that exhibits the error.
Please include the compiler command that fails and its output, e.g.:

Code: Select all

magma> make src/zgetrf.o
g++ -m64 -O3 -fPIC -fopenmp -DNDEBUG -DADD_ -Wall -Wshadow -DMAGMA_NOAFFINITY -pedantic -Wno-long-long -std=c++11 -DHAVE_CUBLAS -DMIN_CUDA_ARCH=600 -I/usr/local/cuda-10.1.update2/include -I./include -I./control -c -o src/zgetrf.o src/zgetrf.cpp
src/zgetrf.cpp:327:1: error: 'xx' does not name a type
  327 | xx
      | ^~
make: *** [src/zgetrf.o] Error 1

Post Reply