https://gcc.gnu.org/bugzilla/show_bug.cgi?id=100119
Bug ID: 100119
Summary: [x86] Conversion unsigned int -> double produces -0
(-m32 -msse2 -mfpmath=sse)
Product: gcc
Version: 10.3.0
Status: UNCONFIRMED
Severity: normal
Priority: P3
Component: target
Assignee: unassigned at gcc dot gnu.org
Reporter: chfast at gmail dot com
Target Milestone: ---
When building for 32-bit x86 but with SSE2 floating-point enabled:
-m32 -msse2 -mfpmath=sse
the conversion from unsigned int 0 to double produces the result of -0.0 when
floating-point rounding mode is set to FE_DOWNWARD.
I used -frounding-math and #pragma STDC FENV_ACCESS ON.
This bug is not present on x87 nor x86_64 builds.
The bug seems to be present at least since GCC 5.
#include <fenv.h>
#pragma STDC FENV_ACCESS ON
__attribute__((noinline)) double u32_to_f64(unsigned x) {
return static_cast<double>(x);
}
int main() {
fesetround(FE_DOWNWARD);
double d = u32_to_f64(0);
return __builtin_signbit(d) != 0; // signbit should be 0
}
The assembly:
u32_to_f64(unsigned int):
sub esp, 12
pxor xmm0, xmm0
mov eax, DWORD PTR [esp+16]
add eax, -2147483648
cvtsi2sd xmm0, eax
addsd xmm0, QWORD PTR .LC0
movsd QWORD PTR [esp], xmm0
fld QWORD PTR [esp]
add esp, 12
ret
main:
lea ecx, [esp+4]
and esp, -16
push DWORD PTR [ecx-4]
push ebp
mov ebp, esp
push ecx
sub esp, 32
push 1024
call fesetround
mov DWORD PTR [esp], 0
call u32_to_f64(unsigned int)
mov ecx, DWORD PTR [ebp-4]
add esp, 16
fstp QWORD PTR [ebp-16]
movsd xmm0, QWORD PTR [ebp-16]
leave
lea esp, [ecx-4]
movmskpd eax, xmm0
and eax, 1
ret
.LC0:
.long 0
.long 1105199104
https://godbolt.org/z/rrMWY9jsG
