Enabling floating point exceptions on MinGW GCC? - gcc

Question

How does one enable floating point exceptions on MinGW GCC, where feenableexcept is missing? Even reasonably complete solutions don't actually catch this, though it would appear that they intend to. I would prefer minimal code that is close to whatever future standards will emerge. Preferably, the code should work with and without SSE. A complete solution that shows how to enable the hardware signal, catch it, and reset it is preferable. Compiling cleanly with high optimization levels and full pedantic errors and warnings is a must. The ability to catch multiple times in a unit-test scenario is important. There are several questions that provide partial answers.

Answer 1

This appears to work on my machine. Compile it in MinGW GCC with -fnon-call-exceptions. It isn't fully minimized yet.
#include <xmmintrin.h>
#include <cerrno>
#include <cfenv>
#include <cfloat> //or #include <float.h> // defines _controlfp_s
#include <cmath>
#include <csignal>
#ifdef _WIN32
void feenableexcept(uint16_t fpflags){
/*edit 2015-12-17, my attempt at ASM code was giving me
*problems in more complicated scenarios, so I
*switched to using _controlfp_s. I finally posted it here
*because of the upvote to the ASM version.*/
/*{// http://stackoverflow.com/questions/247053/
uint16_t mask(FE_ALL_EXCEPT & ~fpflags);
asm("fldcw %0" : : "m" (mask) : "cc");
} //https://gcc.gnu.org/onlinedocs/gcc/Extended-Asm.html */
unsigned int new_word(0);
if (fpflags & FE_INVALID) new_word |= _EM_INVALID;
if (fpflags & FE_DIVBYZERO) new_word |= _EM_ZERODIVIDE;
if (fpflags & FE_OVERFLOW) new_word |= _EM_OVERFLOW;
unsigned int cw(0);
_controlfp_s(&cw,~new_word,_MCW_EM);
}
#endif
void fe_reset_traps(){
std::feclearexcept(FE_ALL_EXCEPT); //clear x87 FE state
#ifdef __SSE__
_MM_SET_EXCEPTION_STATE(0); // clear SSE FE state
#endif
feenableexcept(FE_DIVBYZERO|FE_OVERFLOW|FE_INVALID); // set x87 FE mask
#ifdef __SSE__
//set SSE FE mask (orientation of this command is different than the above)
_MM_SET_EXCEPTION_MASK(_MM_MASK_DENORM |_MM_MASK_UNDERFLOW|_MM_MASK_INEXACT);
#endif
}
void sigfpe_handler(int sig){
std::signal(sig,SIG_DFL); // block signal, if needed
std::cerr<<"A floating point exception was encountered. Exiting.\n";
fe_reset_traps(); // in testing mode the throw may not exit, so reset traps
std::signal(sig,&sigfpe_handler); // reinstall handler
throw std::exception();
}
fe_reset_traps();
std::signal(SIGFPE,&sigfpe_handler); // install handler
std::cerr<<"before\n";
std::cerr<<1.0/0.0<<"\n";
std::cerr<<"should be unreachable\n";
I'm sure it's not perfect. Let's hear what everyone else has to contribute.