rs6000: Fix up *intrin.h for C89 [PR104239]

When writing testcases for the previously posted patch, I have noticed
that 3 of the headers aren't valid C89 (I didn't have any dg-options
so -ansi -pedantic-errors was implied and these errors were reported).

The following patch fixes those, ok for trunk?

Note, as can be seen even in this patch, seems older rs6000/*intrin.h
headers uglify not just argument names (__A instead of A etc.), but also
automatic variable names and other local identifiers, while e.g. emmintrin.h
or bmi2intrin.h clearly uglify only the argument names and not local
variables.  I think that should be fixed but don't have time for that myself
(libstdc++ or e.g. the x86 headers uglify everything; this is so that one
can
 #define result a + b
 #include <x86intrin.h>
etc.).

2022-01-26  Jakub Jelinek  <jakub@redhat.com>

	PR target/104239
	* config/rs6000/emmintrin.h (_mm_sad_epu8): Use __asm__ instead of
	asm.
	* config/rs6000/smmintrin.h (_mm_minpos_epu16): Declare iterator
	before for loop instead of for init clause.
	* config/rs6000/bmi2intrin.h (_pext_u64): Likewise.

	* gcc.target/powerpc/pr104239-3.c: New test.

4 files changed, 13 insertions, 3 deletions

diff --git a/gcc/config/rs6000/bmi2intrin.h b/gcc/config/rs6000/bmi2intrin.h
index 931a61d..f2d7eb5 100644
--- a/gcc/config/rs6000/bmi2intrin.h
+++ b/gcc/config/rs6000/bmi2intrin.h
@@ -118,7 +118,8 @@ _pext_u64 (unsigned long long __X, unsigned long long __M)
       /* Also if the pext mask is constant, then the popcount is
        constant, we can evaluate the following loop at compile
        time and use a constant bit permute vector.  */
-      for (long i = 0; i < __builtin_popcountl (__M); i++)
+      long i;
+      for (i = 0; i < __builtin_popcountl (__M); i++)
 	{
 	  c = __builtin_clzl (m);
 	  p = (p << 8) | c;
diff --git a/gcc/config/rs6000/emmintrin.h b/gcc/config/rs6000/emmintrin.h
index 6065dc7..71abcca 100644
--- a/gcc/config/rs6000/emmintrin.h
+++ b/gcc/config/rs6000/emmintrin.h
@@ -2215,7 +2215,7 @@ _mm_sad_epu8 (__m128i __A, __m128i __B)
   vsum = (__vector signed int) vec_sum4s (vabsdiff, zero);
 #ifdef __LITTLE_ENDIAN__
   /* Sum across four integers with two integer results.  */
-  asm ("vsum2sws %0,%1,%2" : "=v" (result) : "v" (vsum), "v" (zero));
+  __asm__ ("vsum2sws %0,%1,%2" : "=v" (result) : "v" (vsum), "v" (zero));
   /* Note: vec_sum2s could be used here, but on little-endian, vector
      shifts are added that are not needed for this use-case.
      A vector shift to correctly position the 32-bit integer results
diff --git a/gcc/config/rs6000/smmintrin.h b/gcc/config/rs6000/smmintrin.h
index 4f90c2e..cca2f7d 100644
--- a/gcc/config/rs6000/smmintrin.h
+++ b/gcc/config/rs6000/smmintrin.h
@@ -687,7 +687,8 @@ _mm_minpos_epu16 (__m128i __A)
   union __u __u = { .__m = __A }, __r = { .__m = {0} };
   unsigned short __ridx = 0;
   unsigned short __rmin = __u.__uh[__ridx];
-  for (unsigned long __i = 1; __i < 8; __i++)
+  unsigned long __i;
+  for (__i = 1; __i < 8; __i++)
     {
       if (__u.__uh[__i] < __rmin)
 	{
diff --git a/gcc/testsuite/gcc.target/powerpc/pr104239-3.c b/gcc/testsuite/gcc.target/powerpc/pr104239-3.c
new file mode 100644
index 0000000..6d64e5d
--- /dev/null
+++ b/gcc/testsuite/gcc.target/powerpc/pr104239-3.c
@@ -0,0 +1,8 @@
+/* PR target/104239 */
+/* { dg-do compile } */
+/* { dg-options "-O2 -mdejagnu-cpu=power8 -DNO_WARN_X86_INTRINSICS -std=c89" } */
+/* { dg-require-effective-target powerpc_p8vector_ok } */
+
+#include <x86intrin.h>
+
+int i;