def check_force_gemv_init():
if check_force_gemv_init._force_init_beta is None:
from theano.gof.cmodule import GCC_compiler
"""
Test issue 1569.
Namely when evaluating
beta*y + alpha*dot(A, x)
where we set y * beta = zeros of the correct dimensions we
do not actually set y = zeros and instead let the BLAS
perform beta*y with uninitialized memory for
speed. Occasionally the memory contains values that are
equivalent to NaN in which case the product beta*y contains
NaN's for correctly implemented BLAS libraries. In this
situation, since we are introducing the NaN's, we need to test
whether the BLAS performs correctly. If it *does*, i.e. it
actually performs the multiplication beta*y which will result
in NaN's in the result, then we need intialize the memory to
zeros.
"""
test_code = """
#include <math.h>
extern "C" void dgemv_(char*, const int*, const int*, const double *, const double *, const int*, const double *, const int*, const double *, double *, const int *);
int main() {
double A[2][2] = {{1., 1.}, {1., 1.}};
double x[2] = {1., 1.};
double y[2] = {NAN, NAN};
const int s = 2;
const int inc = 1;
const double alpha = 1.0;
const double beta = 0.0;
dgemv_("T", &s, &s, &alpha, A, &s, x, &inc, &beta, &y, &inc);
return (isnan(y[0]) || isnan(y[1]) ? 1 : 0;
}
"""
res = GCC_compiler.try_compile_tmp(test_code, tmp_prefix='check_beta_',
flags=ldflags(libs=True, flags=True,
libs_dir=True),
try_run=True)
if res:
if res[0]:
check_force_gemv_init._force_init_beta = res[1]
else:
check_force_gemv_init._force_init_beta = False
else:
check_force_gemv_init._force_init_beta = False
return check_force_gemv_init._force_init_beta
def c_header_dirs(self):
return ldflags(libs=False, include_dir=True)
def c_lib_dirs(self):
return ldflags(libs=False, libs_dir=True)
def c_compile_args(self):
compile_args = ldflags(libs=False, flags=True)
compile_args += super(BaseCorrMM, self).c_compile_args()
return compile_args
def c_libraries(self):
return ldflags()
def c_compile_args(self):
return ldflags(libs=False, flags=True)
def c_compile_args(self):
flags = ldflags(libs=False, flags=True)
flags.append('-Werror')
return flags
def c_libraries(self):
return blas.ldflags()
def c_libraries(self):
return ldflags()
def c_compile_args(self):
compile_args = ldflags(libs=False, flags=True)
compile_args += super(MKLOp, self).c_compile_args()
return compile_args
def c_header_dirs(self):
return ldflags(libs=False, include_dir=True)
def c_lib_dirs(self):
return ldflags(libs=False, libs_dir=True)
def c_compile_args(self):
return ldflags(libs=False, flags=True)
def c_compile_args(self):
compile_args = ldflags(libs=False, flags=True)
compile_args += super(Concatenate, self).c_compile_args()
return compile_args
def c_compile_args(self):
compile_args = ldflags(libs=False, flags=True)
compile_args += super(BaseCorrMM, self).c_compile_args()
return compile_args