[I386, PATCH] Fix for PR53435

[Alexander Ivchenko]

Hi, could pls have a look to fix for
http://gcc.gnu.org/bugzilla/show_bug.cgi?id=53435

Changelog entry:

2012-05-21  Alexander Ivchenko  <alexander.ivche...@intel.com>

        PR target/53435
        * config/i386/i386.c (ix86_expand_vec_perm): Use correct op.
        (ix86_expand_vec_perm): Use int mode instead of float.
        (expand_vec_perm_pshufb): Remove handling of useseless type
        conversion.

Patch attached. Bootstrap passes.

OK for trunk?

thanks,
Alexander

diff --git gcc/config/i386/i386.c gcc/config/i386/i386.c
index f09b2bb..b4ad6ed 100644
--- gcc/config/i386/i386.c
+++ gcc/config/i386/i386.c
@@ -19956,7 +19956,7 @@ ix86_expand_vec_perm (rtx operands[])
              t1 = gen_reg_rtx (V8SImode);
              t2 = gen_reg_rtx (V8SImode);
              emit_insn (gen_avx2_permvarv8si (t1, op0, mask));
-             emit_insn (gen_avx2_permvarv8si (t2, op0, mask));
+             emit_insn (gen_avx2_permvarv8si (t2, op1, mask));
              goto merge_two;
            }
          return;
@@ -19989,10 +19989,10 @@ ix86_expand_vec_perm (rtx operands[])

         case V4SFmode:
          t1 = gen_reg_rtx (V8SFmode);
-         t2 = gen_reg_rtx (V8SFmode);
-         mask = gen_lowpart (V4SFmode, mask);
+         t2 = gen_reg_rtx (V8SImode);
+         mask = gen_lowpart (V4SImode, mask);
          emit_insn (gen_avx_vec_concatv8sf (t1, op0, op1));
-         emit_insn (gen_avx_vec_concatv8sf (t2, mask, mask));
+         emit_insn (gen_avx_vec_concatv8si (t2, mask, mask));
          emit_insn (gen_avx2_permvarv8sf (t1, t1, t2));
          emit_insn (gen_avx_vextractf128v8sf (target, t1, const0_rtx));
          return;
@@ -36508,12 +36508,6 @@ expand_vec_perm_pshufb (struct expand_vec_perm_d *d)
                                gen_rtvec_v (GET_MODE_NUNITS (vmode), rperm));
   vperm = force_reg (vmode, vperm);

-  if (vmode == V8SImode && d->vmode == V8SFmode)
-    {
-      vmode = V8SFmode;
-      vperm = gen_lowpart (vmode, vperm);
-    }
-
   target = gen_lowpart (vmode, d->target);
   op0 = gen_lowpart (vmode, d->op0);
   if (d->one_operand_p)