i386: Add non-optimize prefetchi intrins

Under -O0, with the "newly" introduced intrins, the variable will be
transformed as mem instead of the origin symbol_ref. The compiler will
then treat the operand as invalid and turn the operation into nop, which
is not expected. Use macro for non-optimize to keep the variable as
symbol_ref just as how prefetch intrin does.

gcc/ChangeLog:

	* config/i386/prfchiintrin.h
	(_m_prefetchit0): Add macro for non-optimized option.
	(_m_prefetchit1): Ditto.

gcc/testsuite/ChangeLog:

	* gcc.target/i386/prefetchi-1b.c: New test.

gcc/config/i386/prfchiintrin.h

@@ -37,6 +37,7 @@
 #define __DISABLE_PREFETCHI__
 #endif /* __PREFETCHI__ */
 
+#ifdef __OPTIMIZE__
 extern __inline void
 __attribute__((__gnu_inline__, __always_inline__, __artificial__))
 _m_prefetchit0 (void* __P)
@@ -50,6 +51,14 @@ _m_prefetchit1 (void* __P)
 {
   __builtin_ia32_prefetchi (__P, 2);
 }
+#else
+#define _m_prefetchit0(P)	\
+  __builtin_ia32_prefetchi(P, 3);
+
+#define _m_prefetchit1(P)	\
+  __builtin_ia32_prefetchi(P, 2);
+
+#endif
 
 #ifdef __DISABLE_PREFETCHI__
 #undef __DISABLE_PREFETCHI__

gcc/testsuite/gcc.target/i386/prefetchi-1b.c

+/* { dg-do compile { target { ! ia32 } } } */
+/* { dg-options "-mprefetchi -O0" } */
+/* { dg-final { scan-assembler-times "\[ \\t\]+prefetchit0\[ \\t\]+bar\\(%rip\\)" 1 } } */
+/* { dg-final { scan-assembler-times "\[ \\t\]+prefetchit1\[ \\t\]+bar\\(%rip\\)" 1 } } */
+
+#include <x86intrin.h>
+
+int
+bar (int a)
+{
+  return a + 1;
+}
+
+int
+foo1 (int b)
+{
+  _m_prefetchit0 (bar);
+  return bar (b) + 1;
+}
+
+int
+foo2 (int b)
+{
+  _m_prefetchit1 (bar);
+  return bar (b) + 1;
+}