For one it was an oversight to leave dup_{hi,lo}() undefined for 512-bit
vector size. And then in FMA testing we can also arrange for the
compiler to (hopefully) recognize broadcasting potential.

Signed-off-by: Jan Beulich <jbeulich@suse.com>

--- a/tools/tests/x86_emulator/simd.c
+++ b/tools/tests/x86_emulator/simd.c
@@ -912,6 +912,13 @@ static inline vec_t movlhps(vec_t x, vec
 })
 #  endif
 # endif
+#elif VEC_SIZE == 64
+# if FLOAT_SIZE == 4
+#  define dup_hi(x) B(movshdup, _mask, x, undef(), ~0)
+#  define dup_lo(x) B(movsldup, _mask, x, undef(), ~0)
+# elif FLOAT_SIZE == 8
+#  define dup_lo(x) B(movddup, _mask, x, undef(), ~0)
+# endif
 #endif
 #if VEC_SIZE == 16 && defined(__SSSE3__) && !defined(__AVX512VL__)
 # if INT_SIZE == 1
--- a/tools/tests/x86_emulator/simd-fma.c
+++ b/tools/tests/x86_emulator/simd-fma.c
@@ -63,6 +63,9 @@ int fma_test(void)
 {
     unsigned int i;
     vec_t x, y, z, src, inv, one;
+#ifdef __AVX512F__
+    typeof(one[0]) one_ = 1;
+#endif
 
     for ( i = 0; i < ELEM_COUNT; ++i )
     {
@@ -71,6 +74,10 @@ int fma_test(void)
         one[i] = 1;
     }
 
+#ifdef __AVX512F__
+# define one one_
+#endif
+
     x = (src + one) * inv;
     y = (src - one) * inv;
     touch(src);
@@ -93,22 +100,28 @@ int fma_test(void)
     x = src + inv;
     y = src - inv;
     touch(inv);
+    touch(one);
     z = src * one + inv;
     if ( !eq(x, z) ) return __LINE__;
 
     touch(inv);
+    touch(one);
     z = -src * one - inv;
     if ( !eq(-x, z) ) return __LINE__;
 
     touch(inv);
+    touch(one);
     z = src * one - inv;
     if ( !eq(y, z) ) return __LINE__;
 
     touch(inv);
+    touch(one);
     z = -src * one + inv;
     if ( !eq(-y, z) ) return __LINE__;
     touch(inv);
 
+#undef one
+
 #if defined(addsub) && defined(fmaddsub)
     x = addsub(src * inv, one);
     y = addsub(src * inv, -one);