Illegal instruction in std::remainder (libsystem_m.dylib) when floating point exceptions enabled on M1 mac

Call to std::remainder(double(411.0), int(365)); results in a crash due to a nan in libsystem_m.dylib. MCVE program is provided + lldb backtrace and system report.

$ clang++ -g -arch arm64 -std=c++20 main.cpp -o test
$ ./test
ori_fpcr=0, new_fpcr=1792
std::fmod(simTimeInDays, numDays) = 46
Illegal instruction: 4

main.cpp

#include <cassert>
#include <cfenv>
#include <cmath>
#include <iostream>

#if !defined(__arm64__) || !defined(__APPLE__)
#  error "Meant to be run on arm64 apple"
#endif

inline int feenableexcept(unsigned int excepts) {
  static fenv_t fenv;
  if (std::fegetenv(&fenv) != 0) {
    return -1;
  }
  const unsigned long long old_fpcr = fenv.__fpcr;
  const unsigned int old_excepts = (old_fpcr >> 8u) & unsigned(FE_ALL_EXCEPT);

  // Check the bits passed are valid, and bit shift them
  const unsigned int new_excepts = excepts & unsigned(FE_ALL_EXCEPT);
  const unsigned long long new_fpcr = new_excepts << 8u;

  // Set the new bits
  fenv.__fpcr = fenv.__fpcr | new_fpcr;

  return (std::fesetenv(&fenv) != 0) ? -1 : static_cast<int>(old_excepts);
}

int main([[maybe_unused]] int argc, [[maybe_unused]] const char** argv) {

  constexpr unsigned int flags = FE_DIVBYZERO | FE_INVALID | FE_OVERFLOW;
  static_assert(flags == 7);
  constexpr uint32_t fpcr_flags_shifted = flags << 8;
  constexpr uint32_t fpcr_flags = (__fpcr_trap_divbyzero | __fpcr_trap_invalid | __fpcr_trap_overflow);
  static_assert(fpcr_flags_shifted == fpcr_flags);
  static_assert(fpcr_flags_shifted == 1792);

  uint32_t ori_fpcr = __builtin_arm_rsr("fpcr");
  feenableexcept(flags);
  uint32_t new_fpcr = __builtin_arm_rsr("fpcr");

  // std::cout << "(FE_DIVBYZERO | FE_INVALID | FE_OVERFLOW) = " << flags << '\n';
  // std::cout << "((FE_DIVBYZERO | FE_INVALID | FE_OVERFLOW) << 8) = " << fpcr_flags_shifted << '\n';
  // std::cout << "(__fpcr_trap_divbyzero | __fpcr_trap_invalid | __fpcr_trap_overflow) = " << fpcr_flags << '\n';
  std::cout << "ori_fpcr=" << ori_fpcr << ", new_fpcr=" << new_fpcr << '\n';

  const double simTimeInDays = 411.0;
  const int numDays = 365;

  // This is fine
  std::cout << "std::fmod(simTimeInDays, numDays) = " << std::fmod(simTimeInDays, numDays) << '\n';

  // This isn't
  std::cout << "std::fmod(simTimeInDays, numDays) = " << std::remainder(simTimeInDays, numDays) << '\n';

  return 0;
}

backtrace: see attachment

$ system_profiler SPSoftwareDataType SPHardwareDataType
Software:

    System Software Overview:

      System Version: macOS 13.2 (22D49)
      Kernel Version: Darwin 22.3.0
      Boot Volume: Macintosh HD
      Boot Mode: Normal
      Secure Virtual Memory: Enabled
      System Integrity Protection: Enabled
      Time since boot: 7 hours, 58 minutes

Hardware:

    Hardware Overview:

      Model Name: MacBook Pro
      Model Identifier: MacBookPro18,2
      Model Number: Z14V000NBFN/A
      Chip: Apple M1 Max
      Total Number of Cores: 10 (8 performance and 2 efficiency)
      Memory: 64 GB
      System Firmware Version: 8419.80.7
      OS Loader Version: 8419.80.7
      Activation Lock Status: Enabled

$ otool -L test
test:
	/usr/lib/libc++.1.dylib (compatibility version 1.0.0, current version 1300.36.0)
	/usr/lib/libSystem.B.dylib (compatibility version 1.0.0, current version 1319.0.0

$ clang++ --version
Apple clang version 14.0.0 (clang-1400.0.29.202)
Target: arm64-apple-darwin22.3.0
Thread model: posix
InstalledDir: /Library/Developer/CommandLineTools/usr/bin