The xerbla error handling function can be replaced by your own xerbla function as described here: https://software.intel.com/en-us/node/522122.
However, the LAPACK_ functions, like LAPACKE_sgels(), use LAPACKE_xerbla() to print error messages instead of xerbla(). This is different than documented at https://software.intel.com/en-us/node/522122. Unfortunately, LAPACKE_xerbla() does not seem to be documented, as far as I can see. I would like to replace LAPACKE_xerbla() with my own function, but to do so I need the function declaration. I only found a function description at netlib.org: http://www.netlib.org/lapack/lapacke_utils.h, which declares LAPACKE_xerbla() as "void LAPACKE_xerbla( const char *name, lapack_int info );"
Is this the correct definition for the LAPACKE_xerbla function in MKL? And is this documented somewhere?