altivec.md (mulv4sf3): Rewrite to add -0.0 vector.

2002-12-23  Aldy Hernandez  <aldyh@redhat.com>

	PR/8763
	* config/rs6000/altivec.md (mulv4sf3): Rewrite to add -0.0 vector.
	(altivec_vspltisw_v4sf): Name pattern.
	(altivec_vslw_v4sf): New pattern.

From-SVN: r60453

diff --git a/gcc/ChangeLog b/gcc/ChangeLog
index 37b47fd54a176ff5bb2b41df00411d7fdb8d05ed..6fd530633cd40cdafaa1e5a4ede20105ee9e8e53 100644 (file)
--- a/gcc/ChangeLog
+++ b/gcc/ChangeLog
@@ -1,3 +1,10 @@
+2002-12-23  Aldy Hernandez  <aldyh@redhat.com>
+
+        PR/8763
+        * config/rs6000/altivec.md (mulv4sf3): Rewrite to add -0.0 vector.
+        (altivec_vspltisw_v4sf): Name pattern.
+        (altivec_vslw_v4sf): New pattern.
+
 2002-12-23  Joseph S. Myers  <jsm@polyomino.org.uk>
 
        * doc/include/gcc-common.texi: Define DEVELOPMENT.

diff --git a/gcc/config/rs6000/altivec.md b/gcc/config/rs6000/altivec.md
index 063fe522135fd913edec92f3d8d9e75722cf614a..c3f67d2210eef1fab71188e14b8941d5fe188f7c 100644 (file)
--- a/gcc/config/rs6000/altivec.md
+++ b/gcc/config/rs6000/altivec.md
@@ -490,18 +490,27 @@
   "vmaddfp %0,%1,%2,%3"
   [(set_attr "type" "vecfloat")])
 
-;; The unspec here is a vec splat of 0. We do multiply as a fused
-;; multiply-add with an add of a 0 vector. 
+;; We do multiply as a fused multiply-add with an add of a -0.0 vector.
 
 (define_expand "mulv4sf3"
-  [(set (match_dup 3) (unspec:V4SF [(const_int 0)] 142))
-   (set (match_operand:V4SF 0 "register_operand" "=v")
-        (plus:V4SF (mult:V4SF (match_operand:V4SF 1 "register_operand" "v")
-                             (match_operand:V4SF 2 "register_operand" "v"))
-                  (match_dup 3)))]
+  [(use (match_operand:V4SF 0 "register_operand" ""))
+   (use (match_operand:V4SF 1 "register_operand" ""))
+   (use (match_operand:V4SF 2 "register_operand" ""))]
   "TARGET_ALTIVEC && TARGET_FUSED_MADD"
   "
-{ operands[3] = gen_reg_rtx (V4SFmode); }")
+{
+  rtx neg0;
+
+  /* Generate [-0.0, -0.0, -0.0, -0.0].  */
+  neg0 = gen_reg_rtx (V4SFmode);
+  emit_insn (gen_altivec_vspltisw_v4sf (neg0, GEN_INT (-1)));
+  emit_insn (gen_altivec_vslw_v4sf (neg0, neg0, neg0));
+
+  /* Use the multiply-add.  */
+  emit_insn (gen_altivec_vmaddfp (operands[0], operands[1], operands[2],
+                                 neg0));
+  DONE;
+}")
 
 ;; Fused multiply subtract 
 (define_insn "altivec_vnmsubfp"
@@ -1043,6 +1052,14 @@
   "vslw %0,%1,%2"
   [(set_attr "type" "vecsimple")])
 
+(define_insn "altivec_vslw_v4sf"
+  [(set (match_operand:V4SF 0 "register_operand" "=v")
+        (unspec:V4SF [(match_operand:V4SF 1 "register_operand" "v")
+                      (match_operand:V4SF 2 "register_operand" "v")] 109))]
+  "TARGET_ALTIVEC"
+  "vslw %0,%1,%2"
+  [(set_attr "type" "vecsimple")])
+
 (define_insn "altivec_vsl"
   [(set (match_operand:V4SI 0 "register_operand" "=v")
         (unspec:V4SI [(match_operand:V4SI 1 "register_operand" "v")
@@ -1315,7 +1332,7 @@
   "vspltisw %0, %1"
   [(set_attr "type" "vecperm")])
 
-(define_insn ""
+(define_insn "altivec_vspltisw_v4sf"
   [(set (match_operand:V4SF 0 "register_operand" "=v")
         (unspec:V4SF [(match_operand:QI 1 "immediate_operand" "i")] 142))]
   "TARGET_ALTIVEC"