@@ -48,9 +48,11 @@ struct fenv
};
#ifdef __SSE_MATH__
-# define __math_force_eval(x) asm volatile ("" : : "x" (x));
+# define __math_force_eval_div(x, y) \
+ do { asm ("" : "+x" (x)); asm volatile ("" : : "x" (x / y)); } while (0)
#else
-# define __math_force_eval(x) asm volatile ("" : : "f" (x));
+# define __math_force_eval_div(x, y) \
+ do { asm ("" : "+t" (x)); asm volatile ("" : : "f" (x / y)); } while (0)
#endif
/* Raise the supported floating-point exceptions from EXCEPTS. Other
@@ -59,14 +61,15 @@ struct fenv
void
__atomic_feraiseexcept (int excepts)
{
+ struct fenv temp;
+
if (excepts & FE_INVALID)
{
float f = 0.0f;
- __math_force_eval (f / f);
+ __math_force_eval_div (f, f);
}
if (excepts & FE_DENORM)
{
- struct fenv temp;
asm volatile ("fnstenv\t%0" : "=m" (temp));
temp.__status_word |= FE_DENORM;
asm volatile ("fldenv\t%0" : : "m" (temp));
@@ -75,11 +78,10 @@ __atomic_feraiseexcept (int excepts)
if (excepts & FE_DIVBYZERO)
{
float f = 1.0f, g = 0.0f;
- __math_force_eval (f / g);
+ __math_force_eval_div (f, g);
}
if (excepts & FE_OVERFLOW)
{
- struct fenv temp;
asm volatile ("fnstenv\t%0" : "=m" (temp));
temp.__status_word |= FE_OVERFLOW;
asm volatile ("fldenv\t%0" : : "m" (temp));
@@ -87,7 +89,6 @@ __atomic_feraiseexcept (int excepts)
}
if (excepts & FE_UNDERFLOW)
{
- struct fenv temp;
asm volatile ("fnstenv\t%0" : "=m" (temp));
temp.__status_word |= FE_UNDERFLOW;
asm volatile ("fldenv\t%0" : : "m" (temp));
@@ -96,11 +97,6 @@ __atomic_feraiseexcept (int excepts)
if (excepts & FE_INEXACT)
{
float f = 1.0f, g = 3.0f;
-#ifdef __SSE_MATH__
- asm volatile ("%vdivss\t{%1, %d0|%d0, %1}" : "+x" (f) : "xm" (g));
-#else
- asm volatile ("fdivs\t%1" : "+t" (f) : "m" (g));
- /* No need for fwait, exception is triggered by emitted fstp. */
-#endif
+ __math_force_eval_div (f, g);
}
}
@@ -42,22 +42,25 @@ struct fenv
};
#ifdef __SSE_MATH__
-# define __math_force_eval(x) asm volatile ("" : : "x" (x));
+# define __math_force_eval_div(x, y) \
+ do { asm ("" : "+x" (x)); asm volatile ("" : : "x" (x / y)); } while (0)
#else
-# define __math_force_eval(x) asm volatile ("" : : "f" (x));
+# define __math_force_eval_div(x, y) \
+ do { asm ("" : "+t" (x)); asm volatile ("" : : "f" (x / y)); } while (0)
#endif
void
__sfp_handle_exceptions (int _fex)
{
+ struct fenv temp;
+
if (_fex & FP_EX_INVALID)
{
float f = 0.0f;
- __math_force_eval (f / f);
+ __math_force_eval_div (f, f);
}
if (_fex & FP_EX_DENORM)
{
- struct fenv temp;
asm volatile ("fnstenv\t%0" : "=m" (temp));
temp.__status_word |= FP_EX_DENORM;
asm volatile ("fldenv\t%0" : : "m" (temp));
@@ -66,11 +69,10 @@ __sfp_handle_exceptions (int _fex)
if (_fex & FP_EX_DIVZERO)
{
float f = 1.0f, g = 0.0f;
- __math_force_eval (f / g);
+ __math_force_eval_div (f, g);
}
if (_fex & FP_EX_OVERFLOW)
{
- struct fenv temp;
asm volatile ("fnstenv\t%0" : "=m" (temp));
temp.__status_word |= FP_EX_OVERFLOW;
asm volatile ("fldenv\t%0" : : "m" (temp));
@@ -78,7 +80,6 @@ __sfp_handle_exceptions (int _fex)
}
if (_fex & FP_EX_UNDERFLOW)
{
- struct fenv temp;
asm volatile ("fnstenv\t%0" : "=m" (temp));
temp.__status_word |= FP_EX_UNDERFLOW;
asm volatile ("fldenv\t%0" : : "m" (temp));
@@ -87,12 +88,7 @@ __sfp_handle_exceptions (int _fex)
if (_fex & FP_EX_INEXACT)
{
float f = 1.0f, g = 3.0f;
-#ifdef __SSE_MATH__
- asm volatile ("%vdivss\t{%1, %d0|%d0, %1}" : "+x" (f) : "xm" (g));
-#else
- asm volatile ("fdivs\t%1" : "+t" (f) : "m" (g));
- /* No need for fwait, exception is triggered by emitted fstp. */
-#endif
+ __math_force_eval_div (f, g);
}
}
#endif
@@ -69,7 +69,7 @@ has_sse (void)
/* This structure corresponds to the layout of the block
written by FSTENV. */
-typedef struct
+struct fenv
{
unsigned short int __control_word;
unsigned short int __unused1;
@@ -79,22 +79,28 @@ typedef struct
unsigned short int __unused3;
unsigned int __eip;
unsigned short int __cs_selector;
- unsigned short int __opcode;
+ unsigned int __opcode:11;
+ unsigned int __unused4:5;
unsigned int __data_offset;
unsigned short int __data_selector;
unsigned short int __unused5;
unsigned int __mxcsr;
-}
-my_fenv_t;
+};
/* Check we can actually store the FPU state in the allocated size. */
-_Static_assert (sizeof(my_fenv_t) <= (size_t) GFC_FPE_STATE_BUFFER_SIZE,
+_Static_assert (sizeof(struct fenv) <= (size_t) GFC_FPE_STATE_BUFFER_SIZE,
"GFC_FPE_STATE_BUFFER_SIZE is too small");
#ifdef __SSE_MATH__
-# define __math_force_eval(x) __asm__ __volatile__ ("" : : "x" (x));
+# define __math_force_eval_div(x, y) \
+ do { \
+ __asm__ ("" : "+x" (x)); __asm__ __volatile__ ("" : : "x" (x / y)); \
+ } while (0)
#else
-# define __math_force_eval(x) __asm__ __volatile__ ("" : : "f" (x));
+# define __math_force_eval_div(x, y) \
+ do { \
+ __asm__ ("" : "+t" (x)); __asm__ __volatile__ ("" : : "f" (x / y)); \
+ } while (0)
#endif
/* Raise the supported floating-point exceptions from EXCEPTS. Other
@@ -104,14 +110,15 @@ _Static_assert (sizeof(my_fenv_t) <= (size_t) GFC_FPE_STATE_BUFFER_SIZE,
static void
local_feraiseexcept (int excepts)
{
+ struct fenv temp;
+
if (excepts & _FPU_MASK_IM)
{
float f = 0.0f;
- __math_force_eval (f / f);
+ __math_force_eval_div (f, f);
}
if (excepts & _FPU_MASK_DM)
{
- my_fenv_t temp;
__asm__ __volatile__ ("fnstenv\t%0" : "=m" (temp));
temp.__status_word |= _FPU_MASK_DM;
__asm__ __volatile__ ("fldenv\t%0" : : "m" (temp));
@@ -120,11 +127,10 @@ local_feraiseexcept (int excepts)
if (excepts & _FPU_MASK_ZM)
{
float f = 1.0f, g = 0.0f;
- __math_force_eval (f / g);
+ __math_force_eval_div (f, g);
}
if (excepts & _FPU_MASK_OM)
{
- my_fenv_t temp;
__asm__ __volatile__ ("fnstenv\t%0" : "=m" (temp));
temp.__status_word |= _FPU_MASK_OM;
__asm__ __volatile__ ("fldenv\t%0" : : "m" (temp));
@@ -132,7 +138,6 @@ local_feraiseexcept (int excepts)
}
if (excepts & _FPU_MASK_UM)
{
- my_fenv_t temp;
__asm__ __volatile__ ("fnstenv\t%0" : "=m" (temp));
temp.__status_word |= _FPU_MASK_UM;
__asm__ __volatile__ ("fldenv\t%0" : : "m" (temp));
@@ -141,12 +146,7 @@ local_feraiseexcept (int excepts)
if (excepts & _FPU_MASK_PM)
{
float f = 1.0f, g = 3.0f;
-#ifdef __SSE_MATH__
- __asm__ __volatile__ ("%vdivss\t{%1, %d0|%d0, %1}" : "+x" (f) : "xm" (g));
-#else
- __asm__ __volatile__ ("fdivs\t%1" : "+t" (f) : "m" (g));
- /* No need for fwait, exception is triggered by emitted fstp. */
-#endif
+ __math_force_eval_div (f, g);
}
}
@@ -272,7 +272,7 @@ get_fpu_except_flags (void)
void
set_fpu_except_flags (int set, int clear)
{
- my_fenv_t temp;
+ struct fenv temp;
int exc_set = 0, exc_clr = 0;
/* Translate from GFC_PE_* values to _FPU_MASK_* values. */
@@ -426,7 +426,7 @@ support_fpu_rounding_mode (int mode __attribute__((unused)))
void
get_fpu_state (void *state)
{
- my_fenv_t *envp = state;
+ struct fenv *envp = state;
__asm__ __volatile__ ("fnstenv\t%0" : "=m" (*envp));
@@ -441,7 +441,7 @@ get_fpu_state (void *state)
void
set_fpu_state (void *state)
{
- my_fenv_t *envp = state;
+ struct fenv *envp = state;
/* glibc sources (sysdeps/x86_64/fpu/fesetenv.c) do something more
complex than this, but I think it suffices in our case. */
Introduce math_force_eval_div to use generic division to generate INEXACT as well as INVALID and DIVZERO exceptions. libgcc/ChangeLog: 2020-05-06 Uroš Bizjak <ubizjak@gmail.com> * config/i386/sfp-exceptions.c (__math_force_eval): Remove. (__math_force_eval_div): New define. (__sfp_handle_exceptions): Use __math_force_eval_div to use generic division to generate INVALID, DIVZERO and INEXACT exceptions. libatomic/ChangeLog: 2020-05-06 Uroš Bizjak <ubizjak@gmail.com> * config/x86/fenv.c (__math_force_eval): Remove. (__math_force_eval_div): New define. (__atomic_deraiseexcept): Use __math_force_eval_div to use generic division to generate INVALID, DIVZERO and INEXACT exceptions. libgfortran/ChangeLog: 2020-05-06 Uroš Bizjak <ubizjak@gmail.com> * config/fpu-387.h (__math_force_eval): Remove. (__math_force_eval_div): New define. (local_feraiseexcept): Use __math_force_eval_div to use generic division to generate INVALID, DIVZERO and INEXACT exceptions. (struct fenv): Define named struct instead of typedef. Bootstrapped and regression tested on x86_64-linux-gnu {,-m32}. Committed to mainline. Uros.