i386-gen: preserve fp control word in gen_cvt_ftoi

- Use runtime function for conversion
- Also initialize fp with tcc -run on windows

This fixes a bug where
  double x = 1.0;
  double y = 1.0000000000000001;
  double z = x < y ? 0 : sqrt (x*x - y*y);
caused a bad sqrt because rounding precision for the x < y comparison
was different to the one used within the sqrt function.

This also fixes a bug where
  printf("%d, %d", (int)pow(10, 2), (int)pow(10, 2));
would print
  100, 99

Unrelated:
  win32: document relative include & lib lookup
  win32: normalize_slashes: do not mirror silly gcc behavior
  This reverts part of commit 8a81f9e1036637e21a47e14fb56bf64133546890
  winapi: add missing WINAPI decl. for some functions

1 files changed, 17 insertions, 6 deletions

diff --git a/lib/libtcc1.c b/lib/libtcc1.c
index 53dbec4..a94a82d 100644
--- a/lib/libtcc1.c
+++ b/lib/libtcc1.c
@@ -478,13 +478,24 @@ long long __ashldi3(long long a, int b)
 #endif
 }
 
-#if defined(__i386__)
-/* FPU control word for rounding to nearest mode */
-unsigned short __tcc_fpu_control = 0x137f;
-/* FPU control word for round to zero mode for int conversion */
-unsigned short __tcc_int_fpu_control = 0x137f | 0x0c00;
+#ifndef _WIN32
+void __tcc_fpinit(void)
+{
+    unsigned c = 0x137F;
+    __asm__ __volatile__ ("fldcw %0" : "=m" (c));
+}
 #endif
-
+long long __tcc_cvt_ftol(long double x)
+{
+    unsigned c0, c1;
+    long long ret;
+    __asm__ __volatile__ ("fnstcw %0" : "=m" (c0));
+    c1 = c0 | 0x0C00;
+    __asm__ __volatile__ ("fldcw %0" : "=m" (c1));
+    __asm__ __volatile__ ("fistpll %0"  : "=m" (ret));
+    __asm__ __volatile__ ("fldcw %0" : "=m" (c0));
+    return ret;
+}
 #endif /* !__x86_64__ */
 
 /* XXX: fix tcc's code generator to do this instead */