MAGMA Forum

I think you need to add LAPACK. The ATLAS library provides the BLAS routines, not the higher-level LAPACK routines. For what it's worth, here is how I link a generic program with ATLAS (but not using magma). Your libraries may differ. # -lifcore resolves undefined reference to `for_write_seq_fmt' # ...

MAGMA does not replace the existing BLAS and LAPACK libraries on the CPU. It supplements them with functions to run on the GPU. In fact, MAGMA routines use both the existing BLAS on the CPU (e.g., ATLAS, MKL) and BLAS on the GPU (e.g., CUBLAS, MAGMABLAS). Certainly you could write a wrapper to call ...

What version of CUDA are you using? Version 4.0 and 4.1 both define cublasStatus_t in the cublas.h. If you can't upgrade, a work around is to define it as John suggests.
-mark

You can safely use the cublas functions. The magmablas functions are in some cases faster but otherwise provide the same functionality. The magmablas_dtrsm should be defined in magmablas/dtrsm_tesla.cu.
-mark

No, that's the correct function to use. I didn't realize that function had only the complex version.
-mark

All four precisions (single, double, single complex, double complex) are available in clMAGMA for QR and Cholesky. However, LU factorization is currently only in single precision. We intend to add support for other precisions but don't have a definite time table yet.
-mark

Magma does not have tridiagonal (or banded) solvers for the GPU. My guess is the tridiagonal solver in LAPACK (dgtsv or dptsv) on the CPU is faster than transferring a tridiagonal matrix to the GPU, solving, and transferring the results back. This is because a tridiagonal solve has O(n) operations o...

Can you check that the CUDADIR is correct? I.e., if you list that directory you should see something like: > ls /usr/local/cuda/lib64/ libcublas.so@ libcufft.so@ libcusparse.so@ libcublas.so.4@ libcufft.so.4@ libcusparse.so.4@ libcublas.so.4.0.17* libcufft.so.4.0.17* libcusparse.so.4.0.17* libcudart...

Can you give some details about what you tried, what it did, what you expected, what is your environment (version of Linux, compiler, etc.)?

On Linux, as a first step you need to edit the make.inc file. Several example make.inc files are given.

-mark

Yes, that header is in the CUDA install, for instance, /usr/local/cuda/include/cuda_runtime_api.h Based on your compile line, I would expect that in /usr/share/Modules/modulefiles/cuda/include/cuda_runtime_api.h If you can't read that directory, you need to consult with your system administrator. Ch...