Hello!
Attached patch emits necessary emms instructions to fix mixed
V2SFmode/SFmode runtime test on 32bit x86 targets. The patch also
reorders functions a bit to group together MMX argument handlings, so
it becomes less fragile w.r.t. MMX/x87 interactions.
2013-12-15 Uros Bizjak <[email protected]>
* gcc.dg/vect/vect-nop-move.c (foo32x2_be): Call
__builtin_ia32_emms for 32bit x86 targets.
(foo32x2_le): Ditto.
(main): Reorder function calls.
Tested on x86_64-pc-linux-gnu {,-m32} and committed to mainline.
Uros.
Index: gcc.dg/vect/vect-nop-move.c
===================================================================
--- gcc.dg/vect/vect-nop-move.c (revision 205996)
+++ gcc.dg/vect/vect-nop-move.c (working copy)
@@ -30,12 +30,21 @@ bar (float a)
NOINLINE float
foo32x2_be (float32x2_t x)
{
+#ifdef __i386__
+ /* ix86 passes float32x2 vector arguments in mmx registers. We need to
+ emit emms to empty MMS state and reenable x87 stack before float value
+ can be loaded to and passed in x87 floating-point return register. */
+ __builtin_ia32_emms ();
+#endif
return bar (x[1]);
}
NOINLINE float
foo32x2_le (float32x2_t x)
{
+#ifdef __i386__
+ __builtin_ia32_emms ();
+#endif
return bar (x[0]);
}
@@ -45,16 +54,16 @@ main()
float32x4_t a = { 0.0f, 1.0f, 2.0f, 3.0f };
float32x2_t b = { 0.0f, 1.0f };
- if (foo32x4_be (a) != 3.0f)
+ if (foo32x2_be (b) != 1.0f)
abort ();
- if (foo32x4_le (a) != 0.0f)
+ if (foo32x2_le (b) != 0.0f)
abort ();
- if (foo32x2_be (b) != 1.0f)
+ if (foo32x4_be (a) != 3.0f)
abort ();
- if (foo32x2_le (b) != 0.0f)
+ if (foo32x4_le (a) != 0.0f)
abort ();
return 0;