x86: Use "%v" to emit VEX encoded instructions for AVX targets

Legacy encodings of SSE instructions incur AVX-SSE domain transition
penalties on some Intel microarchitectures (e.g. Haswell, Broadwell).
Using the VEX forms avoids these penatlies and keeps all instructions
in the VEX decode domain.  Use "%v" sequence to emit the "v" prefix
for opcodes when compiling with -mavx.

No functional changes intended.

Signed-off-by: Uros Bizjak <ubizjak@gmail.com>
Reviewed-by: Florian Weimer <fweimer@redhat.com>
Reviewed-by: H.J. Lu <hjl.tools@gmail.com>

sysdeps/i386/fpu/fclrexcpt.c

@@ -44,13 +44,13 @@ __feclearexcept (int excepts)
       unsigned int xnew_exc;
 
       /* Get the current MXCSR.  */
-      __asm__ ("stmxcsr %0" : "=m" (xnew_exc));
+      __asm__ ("%vstmxcsr %0" : "=m" (xnew_exc));
 
       /* Clear the relevant bits.  */
       xnew_exc &= ~excepts;
 
       /* Put the new data in effect.  */
-      __asm__ ("ldmxcsr %0" : : "m" (xnew_exc));
+      __asm__ ("%vldmxcsr %0" : : "m" (xnew_exc));
     }
 
   /* Success.  */

sysdeps/i386/fpu/fedisblxcpt.c

@@ -41,11 +41,11 @@ fedisableexcept (int excepts)
       unsigned int xnew_exc;
 
       /* Get the current control word.  */
-      __asm__ ("stmxcsr %0" : "=m" (xnew_exc));
+      __asm__ ("%vstmxcsr %0" : "=m" (xnew_exc));
 
       xnew_exc |= excepts << 7;
 
-      __asm__ ("ldmxcsr %0" : : "m" (xnew_exc));
+      __asm__ ("%vldmxcsr %0" : : "m" (xnew_exc));
     }
 
   return old_exc;

sysdeps/i386/fpu/feenablxcpt.c

@@ -41,11 +41,11 @@ feenableexcept (int excepts)
       unsigned int xnew_exc;
 
       /* Get the current control word.  */
-      __asm__ ("stmxcsr %0" : "=m" (xnew_exc));
+      __asm__ ("%vstmxcsr %0" : "=m" (xnew_exc));
 
       xnew_exc &= ~(excepts << 7);
 
-      __asm__ ("ldmxcsr %0" : : "m" (xnew_exc));
+      __asm__ ("%vldmxcsr %0" : : "m" (xnew_exc));
     }
 
   return old_exc;

sysdeps/i386/fpu/fegetenv.c

@@ -30,7 +30,7 @@ __fegetenv (fenv_t *envp)
   __asm__ ("fldenv %0" : : "m" (*envp));
 
   if (CPU_FEATURE_USABLE (SSE))
-    __asm__ ("stmxcsr %0" : "=m" (envp->__eip));
+    __asm__ ("%vstmxcsr %0" : "=m" (envp->__eip));
 
   /* Success.  */
   return 0;

sysdeps/i386/fpu/fegetmode.c

@@ -26,6 +26,6 @@ fegetmode (femode_t *modep)
 {
   _FPU_GETCW (modep->__control_word);
   if (CPU_FEATURE_USABLE (SSE))
-    __asm__ ("stmxcsr %0" : "=m" (modep->__mxcsr));
+    __asm__ ("%vstmxcsr %0" : "=m" (modep->__mxcsr));
   return 0;
 }

sysdeps/i386/fpu/feholdexcpt.c

@@ -33,12 +33,12 @@ __feholdexcept (fenv_t *envp)
       unsigned int xwork;
 
       /* Get the current control word.  */
-      __asm__ ("stmxcsr %0" : "=m" (envp->__eip));
+      __asm__ ("%vstmxcsr %0" : "=m" (envp->__eip));
 
       /* Set all exceptions to non-stop and clear them.  */
       xwork = (envp->__eip | 0x1f80) & ~0x3f;
 
-      __asm__ ("ldmxcsr %0" : : "m" (xwork));
+      __asm__ ("%vldmxcsr %0" : : "m" (xwork));
     }
 
   return 0;

sysdeps/i386/fpu/fesetenv.c

@@ -80,7 +80,7 @@ __fesetenv (const fenv_t *envp)
   if (CPU_FEATURE_USABLE (SSE))
     {
       unsigned int mxcsr;
-      __asm__ ("stmxcsr %0" : "=m" (mxcsr));
+      __asm__ ("%vstmxcsr %0" : "=m" (mxcsr));
 
       if (envp == FE_DFL_ENV)
 	{
@@ -111,7 +111,7 @@ __fesetenv (const fenv_t *envp)
       else
 	mxcsr = envp->__eip;
 
-      __asm__ ("ldmxcsr %0" : : "m" (mxcsr));
+      __asm__ ("%vldmxcsr %0" : : "m" (mxcsr));
     }
 
   /* Success.  */

sysdeps/i386/fpu/fesetexcept.c

@@ -33,13 +33,13 @@ fesetexcept (int excepts)
     {
       /* Get the control word of the SSE unit.  */
       unsigned int mxcsr;
-      __asm__ ("stmxcsr %0" : "=m" (mxcsr));
+      __asm__ ("%vstmxcsr %0" : "=m" (mxcsr));
 
       /* Set relevant flags.  */
       mxcsr |= excepts;
 
       /* Put the new data in effect.  */
-      __asm__ ("ldmxcsr %0" : : "m" (mxcsr));
+      __asm__ ("%vldmxcsr %0" : : "m" (mxcsr));
     }
   else
     {

sysdeps/i386/fpu/fesetmode.c

@@ -37,7 +37,7 @@ fesetmode (const femode_t *modep)
   if (CPU_FEATURE_USABLE (SSE))
     {
       unsigned int mxcsr;
-      __asm__ ("stmxcsr %0" : "=m" (mxcsr));
+      __asm__ ("%vstmxcsr %0" : "=m" (mxcsr));
       /* Preserve SSE exception flags but restore other state in
 	 MXCSR.  */
       mxcsr &= FE_ALL_EXCEPT_X86;
@@ -47,7 +47,7 @@ fesetmode (const femode_t *modep)
 	mxcsr |= FE_ALL_EXCEPT_X86 << 7;
       else
 	mxcsr |= modep->__mxcsr & ~FE_ALL_EXCEPT_X86;
-      __asm__ ("ldmxcsr %0" : : "m" (mxcsr));
+      __asm__ ("%vldmxcsr %0" : : "m" (mxcsr));
     }
   return 0;
 }

sysdeps/i386/fpu/fesetround.c

@@ -39,10 +39,10 @@ __fesetround (int round)
     {
       unsigned int xcw;
 
-      __asm__ ("stmxcsr %0" : "=m" (xcw));
+      __asm__ ("%vstmxcsr %0" : "=m" (xcw));
       xcw &= ~0x6000;
       xcw |= round << 3;
-      __asm__ ("ldmxcsr %0" : : "m" (xcw));
+      __asm__ ("%vldmxcsr %0" : : "m" (xcw));
     }
 
   return 0;

sysdeps/i386/fpu/feupdateenv.c

@@ -31,7 +31,7 @@ __feupdateenv (const fenv_t *envp)
 
   /* If the CPU supports SSE we test the MXCSR as well.  */
   if (CPU_FEATURE_USABLE (SSE))
-    __asm__ ("stmxcsr %0" : "=m" (xtemp));
+    __asm__ ("%vstmxcsr %0" : "=m" (xtemp));
 
   temp = (temp | xtemp) & FE_ALL_EXCEPT;
 

sysdeps/i386/fpu/fgetexcptflg.c

@@ -37,7 +37,7 @@ __fegetexceptflag (fexcept_t *flagp, int excepts)
       unsigned int sse_exc;
 
       /* Get the current MXCSR.  */
-      __asm__ ("stmxcsr %0" : "=m" (sse_exc));
+      __asm__ ("%vstmxcsr %0" : "=m" (sse_exc));
 
       *flagp |= sse_exc & excepts & FE_ALL_EXCEPT;
     }

sysdeps/i386/fpu/fsetexcptflg.c

@@ -50,13 +50,13 @@ __fesetexceptflag (const fexcept_t *flagp, int excepts)
       __asm__ ("fldenv %0" : : "m" (temp));
 
       /* And now similarly for SSE.  */
-      __asm__ ("stmxcsr %0" : "=m" (mxcsr));
+      __asm__ ("%vstmxcsr %0" : "=m" (mxcsr));
 
       /* Clear or set relevant flags.  */
       mxcsr ^= (mxcsr ^ *flagp) & excepts;
 
       /* Put the new data in effect.  */
-      __asm__ ("ldmxcsr %0" : : "m" (mxcsr));
+      __asm__ ("%vldmxcsr %0" : : "m" (mxcsr));
     }
   else
     {

sysdeps/i386/fpu/ftestexcept.c

@@ -31,7 +31,7 @@ __fetestexcept (int excepts)
 
   /* If the CPU supports SSE we test the MXCSR as well.  */
   if (CPU_FEATURE_USABLE (SSE))
-    __asm__ ("stmxcsr %0" : "=m" (xtemp));
+    __asm__ ("%vstmxcsr %0" : "=m" (xtemp));
 
   return (temp | xtemp) & excepts & FE_ALL_EXCEPT;
 }

sysdeps/i386/setfpucw.c

@@ -43,11 +43,11 @@ __setfpucw (fpu_control_t set)
       unsigned int xnew_exc;
 
       /* Get the current MXCSR.  */
-      __asm__ ("stmxcsr %0" : "=m" (xnew_exc));
+      __asm__ ("%vstmxcsr %0" : "=m" (xnew_exc));
 
       xnew_exc &= ~((0xc00 << 3) | (FE_ALL_EXCEPT << 7));
       xnew_exc |= ((set & 0xc00) << 3) | ((set & FE_ALL_EXCEPT) << 7);
 
-      __asm__ ("ldmxcsr %0" : : "m" (xnew_exc));
+      __asm__ ("%vldmxcsr %0" : : "m" (xnew_exc));
     }
 }

sysdeps/x86/fpu/fenv_private.h

@@ -18,22 +18,14 @@
    need not care for both the 387 and the sse unit, only the one we're
    actually using.  */
 
-#if defined __AVX__ || defined SSE2AVX
-# define STMXCSR "vstmxcsr"
-# define LDMXCSR "vldmxcsr"
-#else
-# define STMXCSR "stmxcsr"
-# define LDMXCSR "ldmxcsr"
-#endif
-
 static __always_inline void
 libc_feholdexcept_sse (fenv_t *e)
 {
   unsigned int mxcsr;
-  asm (STMXCSR " %0" : "=m" (mxcsr));
+  asm ("%vstmxcsr %0" : "=m" (mxcsr));
   e->__mxcsr = mxcsr;
   mxcsr = (mxcsr | 0x1f80) & ~0x3f;
-  asm volatile (LDMXCSR " %0" : : "m" (mxcsr));
+  asm volatile ("%vldmxcsr %0" : : "m" (mxcsr));
 }
 
 static __always_inline void
@@ -51,9 +43,9 @@ static __always_inline void
 libc_fesetround_sse (int r)
 {
   unsigned int mxcsr;
-  asm (STMXCSR " %0" : "=m" (mxcsr));
+  asm ("%vstmxcsr %0" : "=m" (mxcsr));
   mxcsr = (mxcsr & ~0x6000) | (r << 3);
-  asm volatile (LDMXCSR " %0" : : "m" (mxcsr));
+  asm volatile ("%vldmxcsr %0" : : "m" (mxcsr));
 }
 
 static __always_inline void
@@ -69,10 +61,10 @@ static __always_inline void
 libc_feholdexcept_setround_sse (fenv_t *e, int r)
 {
   unsigned int mxcsr;
-  asm (STMXCSR " %0" : "=m" (mxcsr));
+  asm ("%vstmxcsr %0" : "=m" (mxcsr));
   e->__mxcsr = mxcsr;
   mxcsr = ((mxcsr | 0x1f80) & ~0x603f) | (r << 3);
-  asm volatile (LDMXCSR " %0" : : "m" (mxcsr));
+  asm volatile ("%vldmxcsr %0" : : "m" (mxcsr));
 }
 
 /* Set both rounding mode and precision.  A convenience function for use
@@ -104,7 +96,7 @@ static __always_inline int
 libc_fetestexcept_sse (int e)
 {
   unsigned int mxcsr;
-  asm volatile (STMXCSR " %0" : "=m" (mxcsr));
+  asm volatile ("%vstmxcsr %0" : "=m" (mxcsr));
   return mxcsr & e & FE_ALL_EXCEPT;
 }
 
@@ -119,7 +111,7 @@ libc_fetestexcept_387 (int ex)
 static __always_inline void
 libc_fesetenv_sse (fenv_t *e)
 {
-  asm volatile (LDMXCSR " %0" : : "m" (e->__mxcsr));
+  asm volatile ("%vldmxcsr %0" : : "m" (e->__mxcsr));
 }
 
 static __always_inline void
@@ -137,13 +129,13 @@ static __always_inline int
 libc_feupdateenv_test_sse (fenv_t *e, int ex)
 {
   unsigned int mxcsr, old_mxcsr, cur_ex;
-  asm volatile (STMXCSR " %0" : "=m" (mxcsr));
+  asm volatile ("%vstmxcsr %0" : "=m" (mxcsr));
   cur_ex = mxcsr & FE_ALL_EXCEPT;
 
   /* Merge current exceptions with the old environment.  */
   old_mxcsr = e->__mxcsr;
   mxcsr = old_mxcsr | cur_ex;
-  asm volatile (LDMXCSR " %0" : : "m" (mxcsr));
+  asm volatile ("%vldmxcsr %0" : : "m" (mxcsr));
 
   /* Raise SIGFPE for any new exceptions since the hold.  Expect that
      the normal environment has all exceptions masked.  */
@@ -189,10 +181,10 @@ static __always_inline void
 libc_feholdsetround_sse (fenv_t *e, int r)
 {
   unsigned int mxcsr;
-  asm (STMXCSR " %0" : "=m" (mxcsr));
+  asm ("%vstmxcsr %0" : "=m" (mxcsr));
   e->__mxcsr = mxcsr;
   mxcsr = (mxcsr & ~0x6000) | (r << 3);
-  asm volatile (LDMXCSR " %0" : : "m" (mxcsr));
+  asm volatile ("%vldmxcsr %0" : : "m" (mxcsr));
 }
 
 static __always_inline void
@@ -223,9 +215,9 @@ static __always_inline void
 libc_feresetround_sse (fenv_t *e)
 {
   unsigned int mxcsr;
-  asm (STMXCSR " %0" : "=m" (mxcsr));
+  asm ("%vstmxcsr %0" : "=m" (mxcsr));
   mxcsr = (mxcsr & ~0x6000) | (e->__mxcsr & 0x6000);
-  asm volatile (LDMXCSR " %0" : : "m" (mxcsr));
+  asm volatile ("%vldmxcsr %0" : : "m" (mxcsr));
 }
 
 static __always_inline void
@@ -315,13 +307,13 @@ static __always_inline void
 libc_feholdexcept_setround_sse_ctx (struct rm_ctx *ctx, int r)
 {
   unsigned int mxcsr, new_mxcsr;
-  asm (STMXCSR " %0" : "=m" (mxcsr));
+  asm ("%vstmxcsr %0" : "=m" (mxcsr));
   new_mxcsr = ((mxcsr | 0x1f80) & ~0x603f) | (r << 3);
 
   ctx->env.__mxcsr = mxcsr;
   if (__glibc_unlikely (mxcsr != new_mxcsr))
     {
-      asm volatile (LDMXCSR " %0" : : "m" (new_mxcsr));
+      asm volatile ("%vldmxcsr %0" : : "m" (new_mxcsr));
       ctx->updated_status = true;
     }
   else
@@ -412,13 +404,13 @@ libc_feholdsetround_sse_ctx (struct rm_ctx *ctx, int r)
 {
   unsigned int mxcsr, new_mxcsr;
 
-  asm (STMXCSR " %0" : "=m" (mxcsr));
+  asm ("%vstmxcsr %0" : "=m" (mxcsr));
   new_mxcsr = (mxcsr & ~0x6000) | (r << 3);
 
   ctx->env.__mxcsr = mxcsr;
   if (__glibc_unlikely (new_mxcsr != mxcsr))
     {
-      asm volatile (LDMXCSR " %0" : : "m" (new_mxcsr));
+      asm volatile ("%vldmxcsr %0" : : "m" (new_mxcsr));
       ctx->updated_status = true;
     }
   else

sysdeps/x86/fpu/sfp-machine.h

@@ -39,15 +39,9 @@ typedef unsigned int UTItype __attribute__ ((mode (TI)));
 
 # define FP_RND_MASK		0x6000
 
-# ifdef __AVX__
-#  define AVX_INSN_PREFIX	"v"
-# else
-#  define AVX_INSN_PREFIX	""
-# endif
-
 # define FP_INIT_ROUNDMODE					\
   do {								\
-    __asm__ __volatile__ (AVX_INSN_PREFIX "stmxcsr\t%0" : "=m" (_fcw)); \
+    __asm__ __volatile__ ("%vstmxcsr\t%0" : "=m" (_fcw));	\
   } while (0)
 #else
 # define _FP_W_TYPE_SIZE	32

sysdeps/x86/fpu/test-fenv-sse-2.c

@@ -29,14 +29,14 @@ static uint32_t
 get_sse_mxcsr (void)
 {
   uint32_t temp;
-  __asm__ __volatile__ ("stmxcsr %0" : "=m" (temp));
+  __asm__ __volatile__ ("%vstmxcsr %0" : "=m" (temp));
   return temp;
 }
 
 static void
 set_sse_mxcsr (uint32_t val)
 {
-  __asm__ __volatile__ ("ldmxcsr %0" : : "m" (val));
+  __asm__ __volatile__ ("%vldmxcsr %0" : : "m" (val));
 }
 
 static void

sysdeps/x86_64/fpu/fclrexcpt.c

@@ -38,13 +38,13 @@ __feclearexcept (int excepts)
   __asm__ ("fldenv %0" : : "m" (temp));
 
   /* And the same procedure for SSE.  */
-  __asm__ ("stmxcsr %0" : "=m" (mxcsr));
+  __asm__ ("%vstmxcsr %0" : "=m" (mxcsr));
 
   /* Clear the relevant bits.  */
   mxcsr &= ~excepts;
 
   /* And put them into effect.  */
-  __asm__ ("ldmxcsr %0" : : "m" (mxcsr));
+  __asm__ ("%vldmxcsr %0" : : "m" (mxcsr));
 
   /* Success.  */
   return 0;

sysdeps/x86_64/fpu/fedisblxcpt.c

@@ -35,11 +35,11 @@ fedisableexcept (int excepts)
   __asm__ ("fldcw %0" : : "m" (new_exc));
 
   /* And now the same for the SSE MXCSR register.  */
-  __asm__ ("stmxcsr %0" : "=m" (new));
+  __asm__ ("%vstmxcsr %0" : "=m" (new));
 
   /* The SSE exception masks are shifted by 7 bits.  */
   new |= excepts << 7;
-  __asm__ ("ldmxcsr %0" : : "m" (new));
+  __asm__ ("%vldmxcsr %0" : : "m" (new));
 
   return old_exc;
 }

sysdeps/x86_64/fpu/feenablxcpt.c

@@ -35,11 +35,11 @@ feenableexcept (int excepts)
   __asm__ ("fldcw %0" : : "m" (new_exc));
 
   /* And now the same for the SSE MXCSR register.  */
-  __asm__ ("stmxcsr %0" : "=m" (new));
+  __asm__ ("%vstmxcsr %0" : "=m" (new));
 
   /* The SSE exception masks are shifted by 7 bits.  */
   new &= ~(excepts << 7);
-  __asm__ ("ldmxcsr %0" : : "m" (new));
+  __asm__ ("%vldmxcsr %0" : : "m" (new));
 
   return old_exc;
 }

sysdeps/x86_64/fpu/fegetenv.c

@@ -25,7 +25,7 @@ __fegetenv (fenv_t *envp)
 	   /* fnstenv changes the exception mask, so load back the
 	      stored environment.  */
 	   "fldenv %0\n"
-	   "stmxcsr %1" : "=m" (*envp), "=m" (envp->__mxcsr));
+	   "%vstmxcsr %1" : "=m" (*envp), "=m" (envp->__mxcsr));
 
   /* Success.  */
   return 0;

sysdeps/x86_64/fpu/fegetmode.c

@@ -23,6 +23,6 @@ int
 fegetmode (femode_t *modep)
 {
   _FPU_GETCW (modep->__control_word);
-  __asm__ ("stmxcsr %0" : "=m" (modep->__mxcsr));
+  __asm__ ("%vstmxcsr %0" : "=m" (modep->__mxcsr));
   return 0;
 }

sysdeps/x86_64/fpu/feholdexcpt.c

@@ -26,13 +26,13 @@ __feholdexcept (fenv_t *envp)
   /* Store the environment.  Recall that fnstenv has a side effect of
      masking all exceptions.  Then clear all exceptions.  */
   __asm__ ("fnstenv %0\n\t"
-	   "stmxcsr %1\n\t"
+	   "%vstmxcsr %1\n\t"
 	   "fnclex"
 	   : "=m" (*envp), "=m" (envp->__mxcsr));
 
   /* Set the SSE MXCSR register.  */
   mxcsr = (envp->__mxcsr | 0x1f80) & ~0x3f;
-  __asm__ ("ldmxcsr %0" : : "m" (mxcsr));
+  __asm__ ("%vldmxcsr %0" : : "m" (mxcsr));
 
   return 0;
 }

sysdeps/x86_64/fpu/fesetenv.c

@@ -36,7 +36,7 @@ __fesetenv (const fenv_t *envp)
      Therefore, we get the current environment and replace the values
      we want to use from the environment specified by the parameter.  */
   __asm__ ("fnstenv %0\n"
-	   "stmxcsr %1" : "=m" (temp), "=m" (temp.__mxcsr));
+	   "%vstmxcsr %1" : "=m" (temp), "=m" (temp.__mxcsr));
 
   if (envp == FE_DFL_ENV)
     {
@@ -104,7 +104,7 @@ __fesetenv (const fenv_t *envp)
     }
 
   __asm__ ("fldenv %0\n"
-	   "ldmxcsr %1" : : "m" (temp), "m" (temp.__mxcsr));
+	   "%vldmxcsr %1" : : "m" (temp), "m" (temp.__mxcsr));
 
   /* Success.  */
   return 0;

sysdeps/x86_64/fpu/fesetexcept.c

@@ -23,9 +23,9 @@ fesetexcept (int excepts)
 {
   unsigned int mxcsr;
 
-  __asm__ ("stmxcsr %0" : "=m" (mxcsr));
+  __asm__ ("%vstmxcsr %0" : "=m" (mxcsr));
   mxcsr |= excepts & FE_ALL_EXCEPT;
-  __asm__ ("ldmxcsr %0" : : "m" (mxcsr));
+  __asm__ ("%vldmxcsr %0" : : "m" (mxcsr));
 
   return 0;
 }

sysdeps/x86_64/fpu/fesetmode.c

@@ -28,7 +28,7 @@ fesetmode (const femode_t *modep)
 {
   fpu_control_t cw;
   unsigned int mxcsr;
-  __asm__ ("stmxcsr %0" : "=m" (mxcsr));
+  __asm__ ("%vstmxcsr %0" : "=m" (mxcsr));
   /* Preserve SSE exception flags but restore other state in
      MXCSR.  */
   mxcsr &= FE_ALL_EXCEPT_X86;
@@ -45,6 +45,6 @@ fesetmode (const femode_t *modep)
       mxcsr |= modep->__mxcsr & ~FE_ALL_EXCEPT_X86;
     }
   _FPU_SETCW (cw);
-  __asm__ ("ldmxcsr %0" : : "m" (mxcsr));
+  __asm__ ("%vldmxcsr %0" : : "m" (mxcsr));
   return 0;
 }

sysdeps/x86_64/fpu/fesetround.c

@@ -36,10 +36,10 @@ __fesetround (int round)
 
   /* And now the MSCSR register for SSE, the precision is at different bit
      positions in the different units, we need to shift it 3 bits.  */
-  asm ("stmxcsr %0" : "=m" (mxcsr));
+  asm ("%vstmxcsr %0" : "=m" (mxcsr));
   mxcsr &= ~ 0x6000;
   mxcsr |= round << 3;
-  asm ("ldmxcsr %0" : : "m" (mxcsr));
+  asm ("%vldmxcsr %0" : : "m" (mxcsr));
 
   return 0;
 }

sysdeps/x86_64/fpu/feupdateenv.c

@@ -25,7 +25,7 @@ __feupdateenv (const fenv_t *envp)
   unsigned int xtemp;
 
   /* Save current exceptions.  */
-  __asm__ ("fnstsw %0\n\tstmxcsr %1" : "=m" (temp), "=m" (xtemp));
+  __asm__ ("fnstsw %0\n\t%vstmxcsr %1" : "=m" (temp), "=m" (xtemp));
   temp = (temp | xtemp) & FE_ALL_EXCEPT;
 
   /* Install new environment.  */

sysdeps/x86_64/fpu/fgetexcptflg.c

@@ -26,7 +26,7 @@ fegetexceptflag (fexcept_t *flagp, int excepts)
 
   /* Get the current exceptions for the x87 FPU and SSE unit.  */
   __asm__ ("fnstsw %0\n"
-	   "stmxcsr %1" : "=m" (temp), "=m" (mxscr));
+	   "%vstmxcsr %1" : "=m" (temp), "=m" (mxscr));
 
   *flagp = (temp | mxscr) & FE_ALL_EXCEPT & excepts;
 

sysdeps/x86_64/fpu/fraiseexcpt.c

@@ -33,7 +33,7 @@ __feraiseexcept (int excepts)
       /* One example of an invalid operation is 0.0 / 0.0.  */
       float f = 0.0;
 
-      __asm__ __volatile__ ("divss %0, %0 " : "+x" (f));
+      __asm__ __volatile__ ("%vdivss %0, %0 " : "+x" (f));
       (void) &f;
     }
 
@@ -43,7 +43,7 @@ __feraiseexcept (int excepts)
       float f = 1.0;
       float g = 0.0;
 
-      __asm__ __volatile__ ("divss %1, %0" : "+x" (f) : "x" (g));
+      __asm__ __volatile__ ("%vdivss %1, %0" : "+x" (f) : "x" (g));
       (void) &f;
     }
 

sysdeps/x86_64/fpu/fsetexcptflg.c

@@ -44,13 +44,13 @@ fesetexceptflag (const fexcept_t *flagp, int excepts)
   __asm__ ("fldenv %0" : : "m" (temp));
 
   /* And now similarly for SSE.  */
-  __asm__ ("stmxcsr %0" : "=m" (mxcsr));
+  __asm__ ("%vstmxcsr %0" : "=m" (mxcsr));
 
   /* Clear or set relevant flags.  */
   mxcsr ^= (mxcsr ^ *flagp) & excepts;
 
   /* Put the new data in effect.  */
-  __asm__ ("ldmxcsr %0" : : "m" (mxcsr));
+  __asm__ ("%vldmxcsr %0" : : "m" (mxcsr));
 
   /* Success.  */
   return 0;

sysdeps/x86_64/fpu/ftestexcept.c

@@ -26,7 +26,7 @@ __fetestexcept (int excepts)
 
   /* Get current exceptions.  */
   __asm__ ("fnstsw %0\n"
-	   "stmxcsr %1" : "=m" (temp), "=m" (mxscr));
+	   "%vstmxcsr %1" : "=m" (temp), "=m" (mxscr));
 
   return (temp | mxscr) & excepts & FE_ALL_EXCEPT;
 }