Product: Intel® Composer XE 2013 update 1
Compiler Version: Intel® C/C++ Compiler version 13.0.1.117, build date 20121010
Problem: If a C or C++ main program explicitly offloads an OpenMP construct containing an OpenMP parallel reduction to a coprocessor, it may give an incorrect result, e.g.
[cpp] double sum=0.;
#pragma offload target(mic) inout(sum)
#pragma omp parallel for reduction(+:sum)
for(i=1;i<=n;i++) sum += (double)i;
[/cpp]
The problem does not affect native applications for Intel® Xeon Phi™ coprocessors, Fortran applications, or applications built with the original release of Intel Composer XE 2013 (Intel C/C++ compiler 13.0.0.079). Entire functions that are offloaded, that internally contain OpenMP reductions, are not affected; neither are offloads of OpenMP constructs from functions other than the main program.
Workaround: The problem may be worked around by wrapping the offloaded OpenMP construct within a function, e.g.
[cpp] __attribute((target(mic))) double reduce(int n) {
int i;
double sum=0.;
#pragma omp parallel for reduction(+:sum)
for(i=1;i<=n;i++) sum += (double)i;
return sum;
}
…
double mysum;
#pragma offload target(mic:0) inout(mysum) in(n)
{
mysum = reduce(n);
}
[/cpp]
This issue will be addressed in a forthcoming compiler update.
Additional information may be requested via your Intel Premier Support account.
