re PR target/46997 (new ia64 vector instructions are broken on HP-UX (big-endian))

2011-02-04  Richard Henderson  <rth@redhat.com>
	    Steve Ellcey  <sje@cup.hp.com>

	PR target/46997
	* config/ia64/predicates.md (mux1_brcst_element): New.
	* config/ia64/ia64-protos.h (ia64_unpack_assemble): New.
	* config/ia64/ia64.c (ia64_unpack_assemble): New.
	(ia64_unpack_sign): New.
	(ia64_expand_unpack): Rewrite using new routines.
	(ia64_expand_widen_sum): Ditto.
	(ia64_expand_dot_prod_v8qi): Ditto.
	* config/ia64/vect.md (mulv8qi3): Rewrite to use new
	routines, add endian check.
	(pmpy2_even): Rename from pmpy2_r, add endian check.
	(pmpy2_odd): Rename from pmpy2_l, add endian check.
	(vec_widen_smult_lo_v4hi): Rewrite using new routines.
	(vec_widen_smult_hi_v4hi): Ditto.
	(vec_widen_umult_lo_v4hi): Ditto.
	(vec_widen_umult_hi_v4hi): Ditto.
	(mulv2si3): Change endian checks.
	(sdot_prodv4hi): Rewrite with new calls.
	(udot_prodv4hi): New.
	(vec_pack_ssat_v4hi): Add endian check.
	(vec_pack_usat_v4hi): Ditto.
	(vec_pack_ssat_v2si): Ditto.
	(max1_even): Rename from max1_r, add endian check.
	(max1_odd): Rename from max1_l, add endian check.
	(*mux1_rev): Format change.
	(*mux1_mix): Ditto.
	(*mux1_shuf): Ditto.
	(*mux1_alt): Ditto.
	(*mux1_brcst_v8qi): Use new predicate.
	(vec_extract_evenv8qi): Remove endian check.
	(vec_extract_oddv8qi): Ditto.
	(vec_interleave_lowv4hi): Format change.
	(vec_interleave_highv4hi): Ditto.
	(mix2_even): Rename from mix2_r, add endian check.
	(mix2_odd): Rename from mux2_l, add endian check.
	(*mux2): Fix mask setting for TARGET_BIG_ENDIAN.
	(vec_extract_evenodd_helper): Format change.
	(vec_extract_evenv4hi): Remove endian check.
	(vec_extract_oddv4hi): Remove endian check.
	(vec_interleave_lowv2si): Format change.
	(vec_interleave_highv2si): Format change.
	(vec_initv2si): Remove endian check.
	(vecinit_v2si): Add endian check.
	(reduc_splus_v2sf): Add endian check.
	(reduc_smax_v2sf): Ditto.
	(reduc_smin_v2sf): Ditto.
	(vec_initv2sf): Remove endian check.
	(fpack): Add endian check.
	(fswap): Add endian check.
	(vec_interleave_highv2sf): Add endian check.
	(vec_interleave_lowv2sf): Add endian check.
	(fmix_lr): Add endian check.
	(vec_setv2sf): Format change.
	(*vec_extractv2sf_0_be): Use shift to extract operand.
	(*vec_extractv2sf_1_be): New.
	(vec_pack_trunc_v4hi): Add endian check.
	(vec_pack_trunc_v2si): Format change.

Co-Authored-By: Steve Ellcey <sje@cup.hp.com>

From-SVN: r169840

gcc/ChangeLog

+2011-02-04  Richard Henderson  <rth@redhat.com>
+	    Steve Ellcey  <sje@cup.hp.com>
+
+	PR target/46997
+	* config/ia64/predicates.md (mux1_brcst_element): New.
+	* config/ia64/ia64-protos.h (ia64_unpack_assemble): New.
+	* config/ia64/ia64.c (ia64_unpack_assemble): New.
+	(ia64_unpack_sign): New.
+	(ia64_expand_unpack): Rewrite using new routines.
+	(ia64_expand_widen_sum): Ditto.
+	(ia64_expand_dot_prod_v8qi): Ditto.
+	* config/ia64/vect.md (mulv8qi3): Rewrite to use new
+	routines, add endian check.
+	(pmpy2_even): Rename from pmpy2_r, add endian check.
+	(pmpy2_odd): Rename from pmpy2_l, add endian check.
+	(vec_widen_smult_lo_v4hi): Rewrite using new routines.
+	(vec_widen_smult_hi_v4hi): Ditto.
+	(vec_widen_umult_lo_v4hi): Ditto.
+	(vec_widen_umult_hi_v4hi): Ditto.
+	(mulv2si3): Change endian checks.
+	(sdot_prodv4hi): Rewrite with new calls.
+	(udot_prodv4hi): New.
+	(vec_pack_ssat_v4hi): Add endian check.
+	(vec_pack_usat_v4hi): Ditto.
+	(vec_pack_ssat_v2si): Ditto.
+	(max1_even): Rename from max1_r, add endian check.
+	(max1_odd): Rename from max1_l, add endian check.
+	(*mux1_rev): Format change.
+	(*mux1_mix): Ditto.
+	(*mux1_shuf): Ditto.
+	(*mux1_alt): Ditto.
+	(*mux1_brcst_v8qi): Use new predicate.
+	(vec_extract_evenv8qi): Remove endian check.
+	(vec_extract_oddv8qi): Ditto.
+	(vec_interleave_lowv4hi): Format change.
+	(vec_interleave_highv4hi): Ditto.
+	(mix2_even): Rename from mix2_r, add endian check.
+	(mix2_odd): Rename from mux2_l, add endian check.
+	(*mux2): Fix mask setting for TARGET_BIG_ENDIAN.
+	(vec_extract_evenodd_helper): Format change.
+	(vec_extract_evenv4hi): Remove endian check.
+	(vec_extract_oddv4hi): Remove endian check.
+	(vec_interleave_lowv2si): Format change.
+	(vec_interleave_highv2si): Format change.
+	(vec_initv2si): Remove endian check.
+	(vecinit_v2si): Add endian check.
+	(reduc_splus_v2sf): Add endian check.
+	(reduc_smax_v2sf): Ditto.
+	(reduc_smin_v2sf): Ditto.
+	(vec_initv2sf): Remove endian check.
+	(fpack): Add endian check.
+	(fswap): Add endian check.
+	(vec_interleave_highv2sf): Add endian check.
+	(vec_interleave_lowv2sf): Add endian check.
+	(fmix_lr): Add endian check.
+	(vec_setv2sf): Format change.
+	(*vec_extractv2sf_0_be): Use shift to extract operand.
+	(*vec_extractv2sf_1_be): New.
+	(vec_pack_trunc_v4hi): Add endian check.
+	(vec_pack_trunc_v2si): Format change.
+
 2011-02-04  Jakub Jelinek  <jakub@redhat.com>
 
 	PR inline-asm/23200

gcc/config/ia64/ia64-protos.h

@@ -39,9 +39,9 @@ extern bool ia64_expand_movxf_movrf (enum machine_mode, rtx[]);
 extern void ia64_expand_compare (rtx *, rtx *, rtx *);
 extern void ia64_expand_vecint_cmov (rtx[]);
 extern bool ia64_expand_vecint_minmax (enum rtx_code, enum machine_mode, rtx[]);
+extern void ia64_unpack_assemble (rtx, rtx, rtx, bool);
 extern void ia64_expand_unpack (rtx [], bool, bool);
 extern void ia64_expand_widen_sum (rtx[], bool);
-extern void ia64_expand_widen_mul_v4hi (rtx [], bool, bool);
 extern void ia64_expand_dot_prod_v8qi (rtx[], bool);
 extern void ia64_expand_call (rtx, rtx, rtx, int);
 extern void ia64_split_call (rtx, rtx, rtx, rtx, rtx, int, int);

gcc/config/ia64/ia64.c

@@ -1972,12 +1972,13 @@ ia64_expand_vecint_minmax (enum rtx_code code, enum machine_mode mode,
   return true;
 }
 
-/* Emit an integral vector unpack operation.  */
+/* The vectors LO and HI each contain N halves of a double-wide vector.
+   Reassemble either the first N/2 or the second N/2 elements.  */
 
 void
-ia64_expand_unpack (rtx operands[3], bool unsignedp, bool highp)
+ia64_unpack_assemble (rtx out, rtx lo, rtx hi, bool highp)
 {
-  enum machine_mode mode = GET_MODE (operands[1]);
+  enum machine_mode mode = GET_MODE (lo);
   rtx (*gen) (rtx, rtx, rtx);
   rtx x;
 
@@ -1993,110 +1994,66 @@ ia64_expand_unpack (rtx operands[3], bool unsignedp, bool highp)
       gcc_unreachable ();
     }
 
-  /* Fill in x with the sign extension of each element in op1.  */
-  if (unsignedp)
-    x = CONST0_RTX (mode);
-  else
-    {
-      bool neg;
-
-      x = gen_reg_rtx (mode);
-
-      neg = ia64_expand_vecint_compare (LT, mode, x, operands[1],
-					CONST0_RTX (mode));
-      gcc_assert (!neg);
-    }
-
+  x = gen_lowpart (mode, out);
   if (TARGET_BIG_ENDIAN)
-    emit_insn (gen (gen_lowpart (mode, operands[0]), x, operands[1]));
+    x = gen (x, hi, lo);
   else
-    emit_insn (gen (gen_lowpart (mode, operands[0]), operands[1], x));
+    x = gen (x, lo, hi);
+  emit_insn (x);
 }
 
-/* Emit an integral vector widening sum operations.  */
+/* Return a vector of the sign-extension of VEC.  */
 
-void
-ia64_expand_widen_sum (rtx operands[3], bool unsignedp)
+static rtx
+ia64_unpack_sign (rtx vec, bool unsignedp)
 {
-  rtx l, h, x, s;
-  enum machine_mode wmode, mode;
-  rtx (*unpack_l) (rtx, rtx, rtx);
-  rtx (*unpack_h) (rtx, rtx, rtx);
-  rtx (*plus) (rtx, rtx, rtx);
-
-  wmode = GET_MODE (operands[0]);
-  mode = GET_MODE (operands[1]);
+  enum machine_mode mode = GET_MODE (vec);
+  rtx zero = CONST0_RTX (mode);
 
-  switch (mode)
-    {
-    case V8QImode:
-      unpack_l = gen_vec_interleave_lowv8qi;
-      unpack_h = gen_vec_interleave_highv8qi;
-      plus = gen_addv4hi3;
-      break;
-    case V4HImode:
-      unpack_l = gen_vec_interleave_lowv4hi;
-      unpack_h = gen_vec_interleave_highv4hi;
-      plus = gen_addv2si3;
-      break;
-    default:
-      gcc_unreachable ();
-    }
-
-  /* Fill in x with the sign extension of each element in op1.  */
   if (unsignedp)
-    x = CONST0_RTX (mode);
+    return zero;
   else
     {
+      rtx sign = gen_reg_rtx (mode);
       bool neg;
 
-      x = gen_reg_rtx (mode);
-
-      neg = ia64_expand_vecint_compare (LT, mode, x, operands[1],
-					CONST0_RTX (mode));
+      neg = ia64_expand_vecint_compare (LT, mode, sign, vec, zero);
       gcc_assert (!neg);
+
+      return sign;
     }
+}
 
-  l = gen_reg_rtx (wmode);
-  h = gen_reg_rtx (wmode);
-  s = gen_reg_rtx (wmode);
+/* Emit an integral vector unpack operation.  */
 
-  if (TARGET_BIG_ENDIAN)
-    {
-      emit_insn (unpack_l (gen_lowpart (mode, l), x, operands[1]));
-      emit_insn (unpack_h (gen_lowpart (mode, h), x, operands[1]));
-    }
-  else
-    {
-      emit_insn (unpack_l (gen_lowpart (mode, l), operands[1], x));
-      emit_insn (unpack_h (gen_lowpart (mode, h), operands[1], x));
-    }
-  emit_insn (plus (s, l, operands[2]));
-  emit_insn (plus (operands[0], h, s));
+void
+ia64_expand_unpack (rtx operands[3], bool unsignedp, bool highp)
+{
+  rtx sign = ia64_unpack_sign (operands[1], unsignedp);
+  ia64_unpack_assemble (operands[0], operands[1], sign, highp);
 }
 
+/* Emit an integral vector widening sum operations.  */
+
 void
-ia64_expand_widen_mul_v4hi (rtx operands[3], bool unsignedp, bool highp)
+ia64_expand_widen_sum (rtx operands[3], bool unsignedp)
 {
-  rtx l = gen_reg_rtx (V4HImode);
-  rtx h = gen_reg_rtx (V4HImode);
-  rtx (*mulhigh)(rtx, rtx, rtx, rtx);
-  rtx (*interl)(rtx, rtx, rtx);
+  enum machine_mode wmode;
+  rtx l, h, t, sign;
 
-  emit_insn (gen_mulv4hi3 (l, operands[1], operands[2]));
+  sign = ia64_unpack_sign (operands[1], unsignedp);
+
+  wmode = GET_MODE (operands[0]);
+  l = gen_reg_rtx (wmode);
+  h = gen_reg_rtx (wmode);
 
-  /* For signed, pmpy2.r would appear to more closely match this operation.
-     However, the vectorizer is more likely to use the LO and HI patterns
-     in pairs. At which point, with this formulation, the first two insns
-     of each can be CSEd.  */
-  mulhigh = unsignedp ? gen_pmpyshr2_u : gen_pmpyshr2;
-  emit_insn (mulhigh (h, operands[1], operands[2], GEN_INT (16)));
+  ia64_unpack_assemble (l, operands[1], sign, false);
+  ia64_unpack_assemble (h, operands[1], sign, true);
 
-  interl = highp ? gen_vec_interleave_highv4hi : gen_vec_interleave_lowv4hi;
-  if (TARGET_BIG_ENDIAN)
-    emit_insn (interl (gen_lowpart (V4HImode, operands[0]), h, l));
-  else
-    emit_insn (interl (gen_lowpart (V4HImode, operands[0]), l, h));
+  t = expand_binop (wmode, add_optab, l, operands[2], NULL, 0, OPTAB_DIRECT);
+  t = expand_binop (wmode, add_optab, h, t, operands[0], 0, OPTAB_DIRECT);
+  if (t != operands[0])
+    emit_move_insn (operands[0], t);
 }
 
 /* Emit a signed or unsigned V8QI dot product operation.  */
@@ -2104,62 +2061,31 @@ ia64_expand_widen_mul_v4hi (rtx operands[3], bool unsignedp, bool highp)
 void
 ia64_expand_dot_prod_v8qi (rtx operands[4], bool unsignedp)
 {
-  rtx l1, l2, h1, h2, x1, x2, p1, p2, p3, p4, s1, s2, s3;
+  rtx op1, op2, sn1, sn2, l1, l2, h1, h2;
+  rtx p1, p2, p3, p4, s1, s2, s3;
 
-  /* Fill in x1 and x2 with the sign extension of each element.  */
-  if (unsignedp)
-    x1 = x2 = CONST0_RTX (V8QImode);
-  else
-    {
-      bool neg;
-
-      x1 = gen_reg_rtx (V8QImode);
-      x2 = gen_reg_rtx (V8QImode);
-
-      neg = ia64_expand_vecint_compare (LT, V8QImode, x1, operands[1],
-					CONST0_RTX (V8QImode));
-      gcc_assert (!neg);
-      neg = ia64_expand_vecint_compare (LT, V8QImode, x2, operands[2],
-					CONST0_RTX (V8QImode));
-      gcc_assert (!neg);
-    }
+  op1 = operands[1];
+  op2 = operands[2];
+  sn1 = ia64_unpack_sign (op1, unsignedp);
+  sn2 = ia64_unpack_sign (op2, unsignedp);
 
   l1 = gen_reg_rtx (V4HImode);
   l2 = gen_reg_rtx (V4HImode);
   h1 = gen_reg_rtx (V4HImode);
   h2 = gen_reg_rtx (V4HImode);
-
-  if (TARGET_BIG_ENDIAN)
-    {
-      emit_insn (gen_vec_interleave_lowv8qi
-		 (gen_lowpart (V8QImode, l1), x1, operands[1]));
-      emit_insn (gen_vec_interleave_lowv8qi
-		 (gen_lowpart (V8QImode, l2), x2, operands[2]));
-      emit_insn (gen_vec_interleave_highv8qi
-		 (gen_lowpart (V8QImode, h1), x1, operands[1]));
-      emit_insn (gen_vec_interleave_highv8qi
-		 (gen_lowpart (V8QImode, h2), x2, operands[2]));
-    }
-  else
-    {
-      emit_insn (gen_vec_interleave_lowv8qi
-		 (gen_lowpart (V8QImode, l1), operands[1], x1));
-      emit_insn (gen_vec_interleave_lowv8qi
-		 (gen_lowpart (V8QImode, l2), operands[2], x2));
-      emit_insn (gen_vec_interleave_highv8qi
-		 (gen_lowpart (V8QImode, h1), operands[1], x1));
-      emit_insn (gen_vec_interleave_highv8qi
-		 (gen_lowpart (V8QImode, h2), operands[2], x2));
-    }
+  ia64_unpack_assemble (l1, op1, sn1, false);
+  ia64_unpack_assemble (l2, op2, sn2, false);
+  ia64_unpack_assemble (h1, op1, sn1, true);
+  ia64_unpack_assemble (h2, op2, sn2, true);
 
   p1 = gen_reg_rtx (V2SImode);
   p2 = gen_reg_rtx (V2SImode);
   p3 = gen_reg_rtx (V2SImode);
   p4 = gen_reg_rtx (V2SImode);
-  emit_insn (gen_pmpy2_r (p1, l1, l2));
-  emit_insn (gen_pmpy2_l (p2, l1, l2));
-  emit_insn (gen_pmpy2_r (p3, h1, h2));
-  emit_insn (gen_pmpy2_l (p4, h1, h2));
+  emit_insn (gen_pmpy2_even (p1, l1, l2));
+  emit_insn (gen_pmpy2_even (p2, h1, h2));
+  emit_insn (gen_pmpy2_odd (p3, l1, l2));
+  emit_insn (gen_pmpy2_odd (p4, h1, h2));
 
   s1 = gen_reg_rtx (V2SImode);
   s2 = gen_reg_rtx (V2SImode);

gcc/config/ia64/predicates.md

@@ -624,3 +624,7 @@
   return REG_P (op) && REG_POINTER (op);
 })
 
+;; True if this is the right-most vector element; for mux1 @brcst.
+(define_predicate "mux1_brcst_element"
+  (and (match_code "const_int")
+       (match_test "INTVAL (op) == (TARGET_BIG_ENDIAN ? 7 : 0)")))

gcc/config/ia64/vect.md

@@ -172,35 +172,14 @@
 		   (match_operand:V8QI 2 "gr_register_operand" "r")))]
   ""
 {
-  rtx r1, l1, r2, l2, rm, lm;
-
-  r1 = gen_reg_rtx (V4HImode);
-  l1 = gen_reg_rtx (V4HImode);
-  r2 = gen_reg_rtx (V4HImode);
-  l2 = gen_reg_rtx (V4HImode);
-
-  /* Zero-extend the QImode elements into two words of HImode elements
-     by interleaving them with zero bytes.  */
-  emit_insn (gen_mix1_r (gen_lowpart (V8QImode, r1),
-                         operands[1], CONST0_RTX (V8QImode)));
-  emit_insn (gen_mix1_r (gen_lowpart (V8QImode, r2),
-                         operands[2], CONST0_RTX (V8QImode)));
-  emit_insn (gen_mix1_l (gen_lowpart (V8QImode, l1),
-                         operands[1], CONST0_RTX (V8QImode)));
-  emit_insn (gen_mix1_l (gen_lowpart (V8QImode, l2),
-                         operands[2], CONST0_RTX (V8QImode)));
-
-  /* Multiply.  */
-  rm = gen_reg_rtx (V4HImode);
-  lm = gen_reg_rtx (V4HImode);
-  emit_insn (gen_mulv4hi3 (rm, r1, r2));
-  emit_insn (gen_mulv4hi3 (lm, l1, l2));
-
-  /* Zap the high order bytes of the HImode elements by overwriting those
-     in one part with the low order bytes of the other.  */
-  emit_insn (gen_mix1_r (operands[0],
-                         gen_lowpart (V8QImode, rm),
-                         gen_lowpart (V8QImode, lm)));
+  rtx l = gen_reg_rtx (V4HImode);
+  rtx h = gen_reg_rtx (V4HImode);
+  emit_insn (gen_vec_widen_umult_lo_v8qi (l, operands[1], operands[2]));
+  emit_insn (gen_vec_widen_umult_hi_v8qi (h, operands[1], operands[2]));
+  if (TARGET_BIG_ENDIAN)
+    emit_insn (gen_vec_pack_trunc_v4hi (operands[0], h, l));
+  else
+    emit_insn (gen_vec_pack_trunc_v4hi (operands[0], l, h));
   DONE;
 })
 
@@ -296,7 +275,7 @@
   "pmpyshr2.u %0 = %1, %2, %3"
   [(set_attr "itanium_class" "mmmul")])
 
-(define_insn "pmpy2_r"
+(define_insn "pmpy2_even"
   [(set (match_operand:V2SI 0 "gr_register_operand" "=r")
 	(mult:V2SI
 	  (vec_select:V2SI
@@ -308,10 +287,16 @@
 	      (match_operand:V4HI 2 "gr_register_operand" "r"))
 	    (parallel [(const_int 0) (const_int 2)]))))]
   ""
-  "pmpy2.r %0 = %1, %2"
+{
+  /* Recall that vector elements are numbered in memory order.  */
+  if (TARGET_BIG_ENDIAN)
+    return "%,pmpy2.l %0 = %1, %2";
+  else
+    return "%,pmpy2.r %0 = %1, %2";
+}
   [(set_attr "itanium_class" "mmshf")])
 
-(define_insn "pmpy2_l"
+(define_insn "pmpy2_odd"
   [(set (match_operand:V2SI 0 "gr_register_operand" "=r")
 	(mult:V2SI
 	  (vec_select:V2SI
@@ -323,7 +308,13 @@
 	      (match_operand:V4HI 2 "gr_register_operand" "r"))
 	    (parallel [(const_int 1) (const_int 3)]))))]
   ""
-  "pmpy2.l %0 = %1, %2"
+{
+  /* Recall that vector elements are numbered in memory order.  */
+  if (TARGET_BIG_ENDIAN)
+    return "%,pmpy2.r %0 = %1, %2";
+  else
+    return "%,pmpy2.l %0 = %1, %2";
+}
   [(set_attr "itanium_class" "mmshf")])
 
 (define_expand "vec_widen_smult_lo_v4hi"
@@ -332,7 +323,11 @@
    (match_operand:V4HI 2 "gr_register_operand" "")]
   ""
 {
-  ia64_expand_widen_mul_v4hi (operands, false, false);
+  rtx l = gen_reg_rtx (V4HImode);
+  rtx h = gen_reg_rtx (V4HImode);
+  emit_insn (gen_mulv4hi3 (l, operands[1], operands[2]));
+  emit_insn (gen_pmpyshr2 (h, operands[1], operands[2], GEN_INT (16)));
+  ia64_unpack_assemble (operands[0], l, h, false);
   DONE;
 })
 
@@ -342,7 +337,11 @@
    (match_operand:V4HI 2 "gr_register_operand" "")]
   ""
 {
-  ia64_expand_widen_mul_v4hi (operands, false, true);
+  rtx l = gen_reg_rtx (V4HImode);
+  rtx h = gen_reg_rtx (V4HImode);
+  emit_insn (gen_mulv4hi3 (l, operands[1], operands[2]));
+  emit_insn (gen_pmpyshr2 (h, operands[1], operands[2], GEN_INT (16)));
+  ia64_unpack_assemble (operands[0], l, h, true);
   DONE;
 })
 
@@ -352,7 +351,11 @@
    (match_operand:V4HI 2 "gr_register_operand" "")]
   ""
 {
-  ia64_expand_widen_mul_v4hi (operands, true, false);
+  rtx l = gen_reg_rtx (V4HImode);
+  rtx h = gen_reg_rtx (V4HImode);
+  emit_insn (gen_mulv4hi3 (l, operands[1], operands[2]));
+  emit_insn (gen_pmpyshr2_u (h, operands[1], operands[2], GEN_INT (16)));
+  ia64_unpack_assemble (operands[0], l, h, false);
   DONE;
 })
 
@@ -362,7 +365,11 @@
    (match_operand:V4HI 2 "gr_register_operand" "")]
   ""
 {
-  ia64_expand_widen_mul_v4hi (operands, true, true);
+  rtx l = gen_reg_rtx (V4HImode);
+  rtx h = gen_reg_rtx (V4HImode);
+  emit_insn (gen_mulv4hi3 (l, operands[1], operands[2]));
+  emit_insn (gen_pmpyshr2_u (h, operands[1], operands[2], GEN_INT (16)));
+  ia64_unpack_assemble (operands[0], l, h, true);
   DONE;
 })
 
@@ -390,12 +397,8 @@
      of the full 32-bit product.  */
 
   /* T0 = CDBA.  */
-  if (TARGET_BIG_ENDIAN)
-    x = gen_rtx_PARALLEL (VOIDmode, gen_rtvec (4, GEN_INT (3), const2_rtx,
-					       const1_rtx, const0_rtx));
-  else
-    x = gen_rtx_PARALLEL (VOIDmode, gen_rtvec (4, const1_rtx, const0_rtx,
-					       GEN_INT (3), const2_rtx));
+  x = gen_rtx_PARALLEL (VOIDmode, gen_rtvec (4, const1_rtx, const0_rtx,
+					     GEN_INT (3), const2_rtx));
   x = gen_rtx_VEC_SELECT (V4HImode, op1h, x);
   emit_insn (gen_rtx_SET (VOIDmode, t0, x));
 
@@ -409,15 +412,28 @@
   emit_insn (gen_mulv4hi3 (t3, t0, op2h));
 
   /* T4 = CY.h, CY.l, AW.h, AW.l = CY, AW.  */
-  emit_insn (gen_mix2_r (gen_lowpart (V4HImode, t4), t1, t2));
+  x = gen_lowpart (V4HImode, t4);
+  if (TARGET_BIG_ENDIAN)
+    x = gen_mix2_odd (x, t2, t1);
+  else
+    x = gen_mix2_even (x, t1, t2);
+  emit_insn (x);
 
   /* T5 = CZ.l, 0, AX.l, 0 = CZ << 16, AX << 16.  */
-  emit_insn (gen_mix2_l (gen_lowpart (V4HImode, t5),
-			 CONST0_RTX (V4HImode), t3));
+  x = gen_lowpart (V4HImode, t5);
+  if (TARGET_BIG_ENDIAN)
+    x = gen_mix2_even (x, t3, CONST0_RTX (V4HImode));
+  else
+    x = gen_mix2_odd (x, CONST0_RTX (V4HImode), t3);
+  emit_insn (x);
 
   /* T6 = DY.l, 0, BW.l, 0 = DY << 16, BW << 16.  */
-  emit_insn (gen_mix2_r (gen_lowpart (V4HImode, t6),
-			 CONST0_RTX (V4HImode), t3));
+  x = gen_lowpart (V4HImode, t6);
+  if (TARGET_BIG_ENDIAN)
+    x = gen_mix2_odd (x, t3, CONST0_RTX (V4HImode));
+  else
+    x = gen_mix2_even (x, CONST0_RTX (V4HImode), t3);
+  emit_insn (x);
 
   emit_insn (gen_addv2si3 (t7, t4, t5));
   emit_insn (gen_addv2si3 (operands[0], t6, t7));
@@ -612,16 +628,36 @@
    (match_operand:V2SI 3 "gr_register_operand" "")]
   ""
 {
-  rtx l, r, t;
+  rtx e, o, t;
+
+  e = gen_reg_rtx (V2SImode);
+  o = gen_reg_rtx (V2SImode);
+  t = gen_reg_rtx (V2SImode);
+
+  emit_insn (gen_pmpy2_even (e, operands[1], operands[2]));
+  emit_insn (gen_pmpy2_odd (o, operands[1], operands[2]));
+  emit_insn (gen_addv2si3 (t, e, operands[3]));
+  emit_insn (gen_addv2si3 (operands[0], t, o));
+  DONE;
+})
+
+(define_expand "udot_prodv4hi"
+  [(match_operand:V2SI 0 "gr_register_operand" "")
+   (match_operand:V4HI 1 "gr_register_operand" "")
+   (match_operand:V4HI 2 "gr_register_operand" "")
+   (match_operand:V2SI 3 "gr_register_operand" "")]
+  ""
+{
+  rtx l, h, t;
 
-  r = gen_reg_rtx (V2SImode);
   l = gen_reg_rtx (V2SImode);
+  h = gen_reg_rtx (V2SImode);
   t = gen_reg_rtx (V2SImode);
 
-  emit_insn (gen_pmpy2_r (r, operands[1], operands[2]));
-  emit_insn (gen_pmpy2_l (l, operands[1], operands[2]));
-  emit_insn (gen_addv2si3 (t, r, operands[3]));
-  emit_insn (gen_addv2si3 (operands[0], t, l));
+  emit_insn (gen_vec_widen_umult_lo_v4hi (l, operands[1], operands[2]));
+  emit_insn (gen_vec_widen_umult_hi_v4hi (h, operands[1], operands[2]));
+  emit_insn (gen_addv2si3 (t, l, operands[3]));
+  emit_insn (gen_addv2si3 (operands[0], t, h));
   DONE;
 })
 
@@ -677,7 +713,13 @@
 	  (ss_truncate:V4QI
 	    (match_operand:V4HI 2 "gr_reg_or_0_operand" "rU"))))]
   ""
-  "pack2.sss %0 = %r1, %r2"
+{
+  /* Recall that vector elements are numbered in memory order.  */
+  if (TARGET_BIG_ENDIAN)
+    return "%,pack2.sss %0 = %r2, %r1";
+  else
+    return "%,pack2.sss %0 = %r1, %r2";
+}
   [(set_attr "itanium_class" "mmshf")])
 
 (define_insn "vec_pack_usat_v4hi"
@@ -688,7 +730,13 @@
 	  (us_truncate:V4QI
 	    (match_operand:V4HI 2 "gr_reg_or_0_operand" "rU"))))]
   ""
-  "pack2.uss %0 = %r1, %r2"
+{
+  /* Recall that vector elements are numbered in memory order.  */
+  if (TARGET_BIG_ENDIAN)
+    return "%,pack2.uss %0 = %r2, %r1";
+  else
+    return "%,pack2.uss %0 = %r1, %r2";
+}
   [(set_attr "itanium_class" "mmshf")])
 
 (define_insn "vec_pack_ssat_v2si"
@@ -699,7 +747,13 @@
 	  (ss_truncate:V2HI
 	    (match_operand:V2SI 2 "gr_reg_or_0_operand" "rU"))))]
   ""
-  "pack4.sss %0 = %r1, %r2"
+{
+  /* Recall that vector elements are numbered in memory order.  */
+  if (TARGET_BIG_ENDIAN)
+    return "%,pack4.sss %0 = %r2, %r1";
+  else
+    return "%,pack4.sss %0 = %r1, %r2";
+}
   [(set_attr "itanium_class" "mmshf")])
 
 (define_insn "vec_interleave_lowv8qi"
@@ -742,54 +796,54 @@
 }
   [(set_attr "itanium_class" "mmshf")])
 
-(define_insn "mix1_r"
+(define_insn "mix1_even"
   [(set (match_operand:V8QI 0 "gr_register_operand" "=r")
 	(vec_select:V8QI
 	  (vec_concat:V16QI
 	    (match_operand:V8QI 1 "gr_reg_or_0_operand" "rU")
 	    (match_operand:V8QI 2 "gr_reg_or_0_operand" "rU"))
-	  (parallel [(const_int 0)
-		     (const_int 8)
-		     (const_int 2)
-		     (const_int 10)
-		     (const_int 4)
-		     (const_int 12)
-		     (const_int 6)
-		     (const_int 14)])))]
-  ""
-  "mix1.r %0 = %r2, %r1"
+	  (parallel [(const_int 0) (const_int 8)
+		     (const_int 2) (const_int 10)
+		     (const_int 4) (const_int 12)
+		     (const_int 6) (const_int 14)])))]
+  ""
+{
+  /* Recall that vector elements are numbered in memory order.  */
+  if (TARGET_BIG_ENDIAN)
+    return "%,mix1.l %0 = %r1, %r2";
+  else
+    return "%,mix1.r %0 = %r2, %r1";
+}
   [(set_attr "itanium_class" "mmshf")])
 
-(define_insn "mix1_l"
+(define_insn "mix1_odd"
   [(set (match_operand:V8QI 0 "gr_register_operand" "=r")
 	(vec_select:V8QI
 	  (vec_concat:V16QI
 	    (match_operand:V8QI 1 "gr_reg_or_0_operand" "rU")
 	    (match_operand:V8QI 2 "gr_reg_or_0_operand" "rU"))
-	  (parallel [(const_int 1)
-		     (const_int 9)
-		     (const_int 3)
-		     (const_int 11)
-		     (const_int 5)
-		     (const_int 13)
-		     (const_int 7)
-		     (const_int 15)])))]
-  ""
-  "mix1.l %0 = %r2, %r1"
+	  (parallel [(const_int 1) (const_int 9)
+		     (const_int 3) (const_int 11)
+		     (const_int 5) (const_int 13)
+		     (const_int 7) (const_int 15)])))]
+  ""
+{
+  /* Recall that vector elements are numbered in memory order.  */
+  if (TARGET_BIG_ENDIAN)
+    return "%,mix1.r %0 = %r1, %r2";
+  else
+    return "%,mix1.l %0 = %r2, %r1";
+}
   [(set_attr "itanium_class" "mmshf")])
 
 (define_insn "*mux1_rev"
   [(set (match_operand:V8QI 0 "gr_register_operand" "=r")
 	(vec_select:V8QI
 	  (match_operand:V8QI 1 "gr_register_operand" "r")
-	  (parallel [(const_int 7)
-		     (const_int 6)
-		     (const_int 5)
-		     (const_int 4)
-		     (const_int 3)
-		     (const_int 2)
-		     (const_int 1)
-		     (const_int 0)])))]
+	  (parallel [(const_int 7) (const_int 6)
+		     (const_int 5) (const_int 4)
+		     (const_int 3) (const_int 2)
+		     (const_int 1) (const_int 0)])))]
   ""
   "mux1 %0 = %1, @rev"
   [(set_attr "itanium_class" "mmshf")])
@@ -798,14 +852,10 @@
   [(set (match_operand:V8QI 0 "gr_register_operand" "=r")
 	(vec_select:V8QI
 	  (match_operand:V8QI 1 "gr_register_operand" "r")
-	  (parallel [(const_int 0)
-		     (const_int 4)
-		     (const_int 2)
-		     (const_int 6)
-		     (const_int 1)
-		     (const_int 5)
-		     (const_int 3)
-		     (const_int 7)])))]
+	  (parallel [(const_int 0) (const_int 4)
+		     (const_int 2) (const_int 6)
+		     (const_int 1) (const_int 5)
+		     (const_int 3) (const_int 7)])))]
   ""
   "mux1 %0 = %1, @mix"
   [(set_attr "itanium_class" "mmshf")])
@@ -814,14 +864,10 @@
   [(set (match_operand:V8QI 0 "gr_register_operand" "=r")
 	(vec_select:V8QI
 	  (match_operand:V8QI 1 "gr_register_operand" "r")
-	  (parallel [(const_int 0)
-		     (const_int 4)
-		     (const_int 1)
-		     (const_int 5)
-		     (const_int 2)
-		     (const_int 6)
-		     (const_int 3)
-		     (const_int 7)])))]
+	  (parallel [(const_int 0) (const_int 4)
+		     (const_int 1) (const_int 5)
+		     (const_int 2) (const_int 6)
+		     (const_int 3) (const_int 7)])))]
   ""
   "mux1 %0 = %1, @shuf"
   [(set_attr "itanium_class" "mmshf")])
@@ -830,14 +876,10 @@
   [(set (match_operand:V8QI 0 "gr_register_operand" "=r")
 	(vec_select:V8QI
 	  (match_operand:V8QI 1 "gr_register_operand" "r")
-	  (parallel [(const_int 0)
-		     (const_int 2)
-		     (const_int 4)
-		     (const_int 6)
-		     (const_int 1)
-		     (const_int 3)
-		     (const_int 5)
-		     (const_int 7)])))]
+	  (parallel [(const_int 0) (const_int 2)
+		     (const_int 4) (const_int 6)
+		     (const_int 1) (const_int 3)
+		     (const_int 5) (const_int 7)])))]
   ""
   "mux1 %0 = %1, @alt"
   [(set_attr "itanium_class" "mmshf")])
@@ -846,14 +888,14 @@
   [(set (match_operand:V8QI 0 "gr_register_operand" "=r")
 	(vec_select:V8QI
 	  (match_operand:V8QI 1 "gr_register_operand" "r")
-	  (parallel [(const_int 0)
-		     (const_int 0)
-		     (const_int 0)
-		     (const_int 0)
-		     (const_int 0)
-		     (const_int 0)
-		     (const_int 0)
-		     (const_int 0)])))]
+	  (parallel [(match_operand 2 "mux1_brcst_element" "")
+		     (match_dup 2)
+		     (match_dup 2)
+		     (match_dup 2)
+		     (match_dup 2)
+		     (match_dup 2)
+		     (match_dup 2)
+		     (match_dup 2)])))]
   ""
   "mux1 %0 = %1, @brcst"
   [(set_attr "itanium_class" "mmshf")])
@@ -873,10 +915,7 @@
   ""
 {
   rtx temp = gen_reg_rtx (V8QImode);
-  if (TARGET_BIG_ENDIAN)
-    emit_insn (gen_mix1_l (temp, operands[2], operands[1]));
-  else
-    emit_insn (gen_mix1_r (temp, operands[1], operands[2]));
+  emit_insn (gen_mix1_even (temp, operands[1], operands[2]));
   emit_insn (gen_mux1_alt (operands[0], temp));
   DONE;
 })
@@ -888,10 +927,7 @@
   ""
 {
   rtx temp = gen_reg_rtx (V8QImode);
-  if (TARGET_BIG_ENDIAN)
-    emit_insn (gen_mix1_r (temp, operands[2], operands[1]));
-  else
-    emit_insn (gen_mix1_l (temp, operands[1], operands[2]));
+  emit_insn (gen_mix1_odd (temp, operands[1], operands[2]));
   emit_insn (gen_mux1_alt (operands[0], temp));
   DONE;
 })
@@ -902,10 +938,8 @@
 	  (vec_concat:V8HI
 	    (match_operand:V4HI 1 "gr_reg_or_0_operand" "rU")
 	    (match_operand:V4HI 2 "gr_reg_or_0_operand" "rU"))
-	  (parallel [(const_int 0)
-		     (const_int 4)
-		     (const_int 1)
-		     (const_int 5)])))]
+	  (parallel [(const_int 0) (const_int 4)
+		     (const_int 1) (const_int 5)])))]
   ""
 {
   /* Recall that vector elements are numbered in memory order.  */
@@ -922,10 +956,8 @@
 	  (vec_concat:V8HI
 	    (match_operand:V4HI 1 "gr_reg_or_0_operand" "rU")
 	    (match_operand:V4HI 2 "gr_reg_or_0_operand" "rU"))
-	  (parallel [(const_int 2)
-		     (const_int 6)
-		     (const_int 3)
-		     (const_int 7)])))]
+	  (parallel [(const_int 2) (const_int 6)
+		     (const_int 3) (const_int 7)])))]
   ""
 {
   /* Recall that vector elements are numbered in memory order.  */
@@ -936,32 +968,40 @@
 }
   [(set_attr "itanium_class" "mmshf")])
 
-(define_insn "mix2_r"
+(define_insn "mix2_even"
   [(set (match_operand:V4HI 0 "gr_register_operand" "=r")
 	(vec_select:V4HI
 	  (vec_concat:V8HI
 	    (match_operand:V4HI 1 "gr_reg_or_0_operand" "rU")
 	    (match_operand:V4HI 2 "gr_reg_or_0_operand" "rU"))
-	  (parallel [(const_int 0)
-		     (const_int 4)
-		     (const_int 2)
-		     (const_int 6)])))]
+	  (parallel [(const_int 0) (const_int 4)
+		     (const_int 2) (const_int 6)])))]
   ""
-  "mix2.r %0 = %r2, %r1"
+{
+  /* Recall that vector elements are numbered in memory order.  */
+  if (TARGET_BIG_ENDIAN)
+    return "%,mix2.l %0 = %r1, %r2";
+  else
+    return "%,mix2.r %0 = %r2, %r1";
+}
   [(set_attr "itanium_class" "mmshf")])
 
-(define_insn "mix2_l"
+(define_insn "mix2_odd"
   [(set (match_operand:V4HI 0 "gr_register_operand" "=r")
 	(vec_select:V4HI
 	  (vec_concat:V8HI
 	    (match_operand:V4HI 1 "gr_reg_or_0_operand" "rU")
 	    (match_operand:V4HI 2 "gr_reg_or_0_operand" "rU"))
-	  (parallel [(const_int 1)
-		     (const_int 5)
-		     (const_int 3)
-		     (const_int 7)])))]
+	  (parallel [(const_int 1) (const_int 5)
+		     (const_int 3) (const_int 7)])))]
   ""
-  "mix2.l %0 = %r2, %r1"
+{
+  /* Recall that vector elements are numbered in memory order.  */
+  if (TARGET_BIG_ENDIAN)
+    return "%,mix2.r %0 = %r1, %r2";
+  else
+    return "%,mix2.l %0 = %r2, %r1";
+}
   [(set_attr "itanium_class" "mmshf")])
 
 (define_insn "*mux2"
@@ -974,17 +1014,17 @@
 		     (match_operand 5 "const_int_2bit_operand" "")])))]
   ""
 {
-  int mask;
+  int mask = 0;
   if (TARGET_BIG_ENDIAN)
     {
-      mask  = INTVAL (operands[2]) << 4;
-      mask |= INTVAL (operands[3]) << 6;
-      mask |= INTVAL (operands[4]);
-      mask |= INTVAL (operands[5]) << 2;
+      mask |= (3 - INTVAL (operands[2])) << 6;
+      mask |= (3 - INTVAL (operands[3])) << 4;
+      mask |= (3 - INTVAL (operands[4])) << 2;
+      mask |= 3 - INTVAL (operands[5]);
     }
   else
     {
-      mask  = INTVAL (operands[2]);
+      mask |= INTVAL (operands[2]);
       mask |= INTVAL (operands[3]) << 2;
       mask |= INTVAL (operands[4]) << 4;
       mask |= INTVAL (operands[5]) << 6;
@@ -998,10 +1038,8 @@
   [(set (match_operand:V4HI 0 "gr_register_operand" "")
 	(vec_select:V4HI
 	  (match_operand:V4HI 1 "gr_register_operand" "")
-	  (parallel [(const_int 0)
-		     (const_int 2)
-		     (const_int 1)
-		     (const_int 3)])))]
+	  (parallel [(const_int 0) (const_int 2)
+		     (const_int 1) (const_int 3)])))]
   "")
 
 (define_expand "vec_extract_evenv4hi"
@@ -1011,10 +1049,7 @@
   ""
 {
   rtx temp = gen_reg_rtx (V4HImode);
-  if (TARGET_BIG_ENDIAN)
-    emit_insn (gen_mix2_l (temp, operands[1], operands[2]));
-  else
-    emit_insn (gen_mix2_r (temp, operands[1], operands[2]));
+  emit_insn (gen_mix2_even (temp, operands[1], operands[2]));
   emit_insn (gen_vec_extract_evenodd_helper (operands[0], temp));
   DONE;
 })
@@ -1026,10 +1061,7 @@
   ""
 {
   rtx temp = gen_reg_rtx (V4HImode);
-  if (TARGET_BIG_ENDIAN)
-    emit_insn (gen_mix2_r (temp, operands[1], operands[2]));
-  else
-    emit_insn (gen_mix2_l (temp, operands[1], operands[2]));
+  emit_insn (gen_mix2_odd (temp, operands[1], operands[2]));
   emit_insn (gen_vec_extract_evenodd_helper (operands[0], temp));
   DONE;
 })
@@ -1042,15 +1074,13 @@
   "mux2 %0 = %1, 0"
   [(set_attr "itanium_class" "mmshf")])
 
-;; Note that mix4.r performs the exact same operation.
 (define_insn "vec_interleave_lowv2si"
   [(set (match_operand:V2SI 0 "gr_register_operand" "=r")
 	(vec_select:V2SI
 	  (vec_concat:V4SI
 	    (match_operand:V2SI 1 "gr_reg_or_0_operand" "rU")
 	    (match_operand:V2SI 2 "gr_reg_or_0_operand" "rU"))
-	  (parallel [(const_int 0)
-		     (const_int 2)])))]
+	  (parallel [(const_int 0) (const_int 2)])))]
   ""
 {
   /* Recall that vector elements are numbered in memory order.  */
@@ -1061,15 +1091,13 @@
 }
   [(set_attr "itanium_class" "mmshf")])
 
-;; Note that mix4.l performs the exact same operation.
 (define_insn "vec_interleave_highv2si"
   [(set (match_operand:V2SI 0 "gr_register_operand" "=r")
 	(vec_select:V2SI
 	  (vec_concat:V4SI
 	    (match_operand:V2SI 1 "gr_reg_or_0_operand" "rU")
 	    (match_operand:V2SI 2 "gr_reg_or_0_operand" "rU"))
-	  (parallel [(const_int 1)
-		     (const_int 3)])))]
+	  (parallel [(const_int 1) (const_int 3)])))]
   ""
 {
   /* Recall that vector elements are numbered in memory order.  */
@@ -1088,7 +1116,7 @@
 {
   if (TARGET_BIG_ENDIAN)
     emit_insn (gen_vec_interleave_highv2si (operands[0], operands[1],
-					   operands[2]));
+					    operands[2]));
   else
     emit_insn (gen_vec_interleave_lowv2si (operands[0], operands[1],
 					   operands[2]));
@@ -1103,7 +1131,7 @@
 {
   if (TARGET_BIG_ENDIAN)
     emit_insn (gen_vec_interleave_lowv2si (operands[0], operands[1],
-					    operands[2]));
+					   operands[2]));
   else
     emit_insn (gen_vec_interleave_highv2si (operands[0], operands[1],
 					    operands[2]));
@@ -1131,10 +1159,7 @@
   if (!gr_reg_or_0_operand (op2, SImode))
     op2 = force_reg (SImode, op2);
 
-  if (TARGET_BIG_ENDIAN)
-    x = gen_rtx_VEC_CONCAT (V2SImode, op2, op1);
-  else
-    x = gen_rtx_VEC_CONCAT (V2SImode, op1, op2);
+  x = gen_rtx_VEC_CONCAT (V2SImode, op1, op2);
   emit_insn (gen_rtx_SET (VOIDmode, operands[0], x));
   DONE;
 })
@@ -1145,7 +1170,13 @@
 	  (match_operand:SI 1 "gr_reg_or_0_operand" "rO")
 	  (match_operand:SI 2 "gr_reg_or_0_operand" "rO")))]
   ""
-  "unpack4.l %0 = %r2, %r1"
+{
+  /* Recall that vector elements are numbered in memory order.  */
+  if (TARGET_BIG_ENDIAN)
+    return "%,unpack4.l %0 = %r1, %r2";
+  else
+    return "%,unpack4.l %0 = %r2, %r1";
+}
   [(set_attr "itanium_class" "mmshf")])
 
 ;; Missing operations
@@ -1315,7 +1346,10 @@
   ""
 {
   rtx tmp = gen_reg_rtx (V2SFmode);
-  emit_insn (gen_fswap (tmp, operands[1], CONST0_RTX (V2SFmode)));
+  if (TARGET_BIG_ENDIAN)
+    emit_insn (gen_fswap (tmp, CONST0_RTX (V2SFmode), operands[1]));
+  else
+    emit_insn (gen_fswap (tmp, operands[1], CONST0_RTX (V2SFmode)));
   emit_insn (gen_addv2sf3 (operands[0], operands[1], tmp));
   DONE;
 })
@@ -1326,7 +1360,10 @@
   ""
 {
   rtx tmp = gen_reg_rtx (V2SFmode);
-  emit_insn (gen_fswap (tmp, operands[1], CONST0_RTX (V2SFmode)));
+  if (TARGET_BIG_ENDIAN)
+    emit_insn (gen_fswap (tmp, CONST0_RTX (V2SFmode), operands[1]));
+  else
+    emit_insn (gen_fswap (tmp, operands[1], CONST0_RTX (V2SFmode)));
   emit_insn (gen_smaxv2sf3 (operands[0], operands[1], tmp));
   DONE;
 })
@@ -1337,7 +1374,10 @@
   ""
 {
   rtx tmp = gen_reg_rtx (V2SFmode);
-  emit_insn (gen_fswap (tmp, operands[1], CONST0_RTX (V2SFmode)));
+  if (TARGET_BIG_ENDIAN)
+    emit_insn (gen_fswap (tmp, CONST0_RTX (V2SFmode), operands[1]));
+  else
+    emit_insn (gen_fswap (tmp, operands[1], CONST0_RTX (V2SFmode)));
   emit_insn (gen_sminv2sf3 (operands[0], operands[1], tmp));
   DONE;
 })
@@ -1403,10 +1443,7 @@
   if (!fr_reg_or_fp01_operand (op2, SFmode))
     op2 = force_reg (SFmode, op2);
 
-  if (TARGET_BIG_ENDIAN)
-    emit_insn (gen_fpack (operands[0], op2, op1));
-  else
-    emit_insn (gen_fpack (operands[0], op1, op2));
+  emit_insn (gen_fpack (operands[0], op1, op2));
   DONE;
 })
 
@@ -1416,7 +1453,13 @@
 	  (match_operand:SF 1 "fr_reg_or_fp01_operand" "fG")
 	  (match_operand:SF 2 "fr_reg_or_fp01_operand" "fG")))]
   ""
-  "fpack %0 = %F2, %F1"
+{
+  /* Recall that vector elements are numbered in memory order.  */
+  if (TARGET_BIG_ENDIAN)
+    return "%,fpack %0 = %F1, %F2";
+  else
+    return "%,fpack %0 = %F2, %F1";
+}
   [(set_attr "itanium_class" "fmisc")])
 
 (define_insn "fswap"
@@ -1427,7 +1470,13 @@
 	    (match_operand:V2SF 2 "fr_reg_or_0_operand" "fU"))
 	  (parallel [(const_int 1) (const_int 2)])))]
   ""
-  "fswap %0 = %F1, %F2"
+{
+  /* Recall that vector elements are numbered in memory order.  */
+  if (TARGET_BIG_ENDIAN)
+    return "%,fswap %0 = %F2, %F1";
+  else
+    return "%,fswap %0 = %F1, %F2";
+}
   [(set_attr "itanium_class" "fmisc")])
 
 (define_insn "vec_interleave_highv2sf"
@@ -1438,7 +1487,13 @@
 	    (match_operand:V2SF 2 "fr_reg_or_0_operand" "fU"))
 	  (parallel [(const_int 1) (const_int 3)])))]
   ""
-  "fmix.l %0 = %F2, %F1"
+{
+  /* Recall that vector elements are numbered in memory order.  */
+  if (TARGET_BIG_ENDIAN)
+    return "%,fmix.r %0 = %F1, %F2";
+  else
+    return "%,fmix.l %0 = %F2, %F1";
+}
   [(set_attr "itanium_class" "fmisc")])
 
 (define_insn "vec_interleave_lowv2sf"
@@ -1449,7 +1504,13 @@
 	    (match_operand:V2SF 2 "fr_reg_or_0_operand" "fU"))
 	  (parallel [(const_int 0) (const_int 2)])))]
   ""
-  "fmix.r %0 = %F2, %F1"
+{
+  /* Recall that vector elements are numbered in memory order.  */
+  if (TARGET_BIG_ENDIAN)
+    return "%,fmix.l %0 = %F1, %F2";
+  else
+    return "%,fmix.r %0 = %F2, %F1";
+}
   [(set_attr "itanium_class" "fmisc")])
 
 (define_insn "fmix_lr"
@@ -1460,7 +1521,13 @@
 	    (match_operand:V2SF 2 "fr_reg_or_0_operand" "fU"))
 	  (parallel [(const_int 0) (const_int 3)])))]
   ""
-  "fmix.lr %0 = %F2, %F1"
+{
+  /* Recall that vector elements are numbered in memory order.  */
+  if (TARGET_BIG_ENDIAN)
+    return "%,fmix.lr %0 = %F1, %F2";
+  else
+    return "%,fmix.lr %0 = %F2, %F1";
+}
   [(set_attr "itanium_class" "fmisc")])
 
 (define_expand "vec_extract_evenv2sf"
@@ -1485,23 +1552,24 @@
   DONE;
 })
 
-
 (define_expand "vec_setv2sf"
   [(match_operand:V2SF 0 "fr_register_operand" "")
    (match_operand:SF 1 "fr_register_operand" "")
    (match_operand 2 "const_int_operand" "")]
   ""
 {
+  rtx op0 = operands[0];
   rtx tmp = gen_reg_rtx (V2SFmode);
+
   emit_insn (gen_fpack (tmp, operands[1], CONST0_RTX (SFmode)));
 
   switch (INTVAL (operands[2]))
     {
     case 0:
-      emit_insn (gen_fmix_lr (operands[0], tmp, operands[0]));
+      emit_insn (gen_fmix_lr (op0, tmp, op0));
       break;
     case 1:
-      emit_insn (gen_vec_interleave_lowv2sf (operands[0], operands[0], tmp));
+      emit_insn (gen_vec_interleave_lowv2sf (op0, op0, tmp));
       break;
     default:
       gcc_unreachable ();
@@ -1528,8 +1596,8 @@
 })
 
 (define_insn_and_split "*vec_extractv2sf_0_be"
-  [(set (match_operand:SF 0 "register_operand" "=r,f")
-	(unspec:SF [(match_operand:V2SF 1 "register_operand" "rf,r")
+  [(set (match_operand:SF 0 "register_operand" "=rf,r")
+	(unspec:SF [(match_operand:V2SF 1 "nonimmediate_operand" "m,r")
 		    (const_int 0)]
 		   UNSPEC_VECT_EXTR))]
   "TARGET_BIG_ENDIAN"
@@ -1537,31 +1605,44 @@
   "reload_completed"
   [(set (match_dup 0) (match_dup 1))]
 {
-  if (REG_P (operands[1]) && FR_REGNO_P (REGNO (operands[1])))
-    operands[0] = gen_rtx_REG (V2SFmode, REGNO (operands[0]));
+  if (MEM_P (operands[1]))
+    operands[1] = adjust_address (operands[1], SFmode, 0);
   else
-    operands[1] = gen_rtx_REG (SFmode, REGNO (operands[1]));
+    {
+      emit_insn (gen_lshrdi3 (operands[0], operands[1], GEN_INT (32)));
+      DONE;
+    }
 })
 
-(define_insn_and_split "*vec_extractv2sf_1"
+(define_insn_and_split "*vec_extractv2sf_1_le"
   [(set (match_operand:SF 0 "register_operand" "=r")
 	(unspec:SF [(match_operand:V2SF 1 "register_operand" "r")
 		    (const_int 1)]
 		   UNSPEC_VECT_EXTR))]
-  ""
+  "!TARGET_BIG_ENDIAN"
   "#"
-  "reload_completed"
+  "&& reload_completed"
   [(const_int 0)]
 {
   operands[0] = gen_rtx_REG (DImode, REGNO (operands[0]));
   operands[1] = gen_rtx_REG (DImode, REGNO (operands[1]));
-  if (TARGET_BIG_ENDIAN)
-    emit_move_insn (operands[0], operands[1]);
-  else
-    emit_insn (gen_lshrdi3 (operands[0], operands[1], GEN_INT (32)));
+  emit_insn (gen_lshrdi3 (operands[0], operands[1], GEN_INT (32)));
   DONE;
 })
 
+(define_insn_and_split "*vec_extractv2sf_1_be"
+  [(set (match_operand:SF 0 "register_operand" "=rf")
+	(unspec:SF [(match_operand:V2SF 1 "register_operand" "r")
+		    (const_int 1)]
+		   UNSPEC_VECT_EXTR))]
+  "TARGET_BIG_ENDIAN"
+  "#"
+  "&& reload_completed"
+  [(set (match_dup 0) (match_dup 1))]
+{
+  operands[1] = gen_rtx_REG (SFmode, REGNO (operands[1]));
+})
+
 (define_expand "vec_extractv2sf"
   [(set (match_operand:SF 0 "register_operand" "")
 	(unspec:SF [(match_operand:V2SF 1 "register_operand" "")
@@ -1610,11 +1691,14 @@
   [(match_operand:V8QI 0 "gr_register_operand" "")
    (match_operand:V4HI 1 "gr_register_operand" "")
    (match_operand:V4HI 2 "gr_register_operand" "")]
-  "!TARGET_BIG_ENDIAN"
+  ""
 {
-  rtx op1 = gen_lowpart(V8QImode, operands[1]);
-  rtx op2 = gen_lowpart(V8QImode, operands[2]);
-  emit_insn (gen_vec_extract_evenv8qi (operands[0], op1, op2));
+  rtx op1 = gen_lowpart (V8QImode, operands[1]);
+  rtx op2 = gen_lowpart (V8QImode, operands[2]);
+  if (TARGET_BIG_ENDIAN)
+    emit_insn (gen_vec_extract_oddv8qi (operands[0], op1, op2));
+  else
+    emit_insn (gen_vec_extract_evenv8qi (operands[0], op1, op2));
   DONE;
 })
 
@@ -1624,8 +1708,8 @@
    (match_operand:V2SI 2 "gr_register_operand" "")]
   ""
 {
-  rtx op1 = gen_lowpart(V4HImode, operands[1]);
-  rtx op2 = gen_lowpart(V4HImode, operands[2]);
+  rtx op1 = gen_lowpart (V4HImode, operands[1]);
+  rtx op2 = gen_lowpart (V4HImode, operands[2]);
   if (TARGET_BIG_ENDIAN)
     emit_insn (gen_vec_extract_oddv4hi (operands[0], op1, op2));
   else