rs6000: Optimize code generation of vec_reve [PR100868]

gcc/
	PR target/100868
	* config/rs6000/altivec.md (altivec_vreve<mode>2 for VEC_K): Use
	xxbrq for v16qi, xxbrq + xxbrh for v8hi and xxbrq + xxbrw for v4si
	or v4sf when p9_vector is set.
	(altivec_vreve<mode>2 for VEC_64): Defined. Implemented by xxswapd.

gcc/testsuite/
	PR target/100868
	* gcc.target/powerpc/vec_reve_1.c: New test.
	* gcc.target/powerpc/vec_reve_2.c: Likewise.

diff --git a/gcc/config/rs6000/altivec.md b/gcc/config/rs6000/altivec.md
index a057218aa2885a12d07efe22642b7cb93b766a45..ef4321123339e88646c66b71a12c866885923511 100644 (file)
--- a/gcc/config/rs6000/altivec.md
+++ b/gcc/config/rs6000/altivec.md
@@ -3984,12 +3984,43 @@
   DONE;
 })
 
+;; Vector reverse elements for V16QI V8HI V4SI V4SF
 (define_expand "altivec_vreve<mode>2"
-  [(set (match_operand:VEC_A 0 "register_operand" "=v")
-       (unspec:VEC_A [(match_operand:VEC_A 1 "register_operand" "v")]
+  [(set (match_operand:VEC_K 0 "register_operand" "=v")
+       (unspec:VEC_K [(match_operand:VEC_K 1 "register_operand" "v")]
                      UNSPEC_VREVEV))]
   "TARGET_ALTIVEC"
 {
+  if (TARGET_P9_VECTOR)
+    {
+      if (<MODE>mode == V16QImode)
+       emit_insn (gen_p9_xxbrq_v16qi (operands[0], operands[1]));
+      else if (<MODE>mode == V8HImode)
+       {
+         rtx subreg1 = simplify_gen_subreg (V1TImode, operands[1],
+                                            <MODE>mode, 0);
+         rtx temp = gen_reg_rtx (V1TImode);
+         emit_insn (gen_p9_xxbrq_v1ti (temp, subreg1));
+         rtx subreg2 = simplify_gen_subreg (<MODE>mode, temp,
+                                            V1TImode, 0);
+         emit_insn (gen_p9_xxbrh_v8hi (operands[0], subreg2));
+       }
+      else /* V4SI and V4SF.  */
+       {
+         rtx subreg1 = simplify_gen_subreg (V1TImode, operands[1],
+                                            <MODE>mode, 0);
+         rtx temp = gen_reg_rtx (V1TImode);
+         emit_insn (gen_p9_xxbrq_v1ti (temp, subreg1));
+         rtx subreg2 = simplify_gen_subreg (<MODE>mode, temp,
+                                            V1TImode, 0);
+         if (<MODE>mode == V4SImode)
+           emit_insn (gen_p9_xxbrw_v4si (operands[0], subreg2));
+         else
+           emit_insn (gen_p9_xxbrw_v4sf (operands[0], subreg2));
+       }
+      DONE;
+    }
+
   int i, j, size, num_elements;
   rtvec v = rtvec_alloc (16);
   rtx mask = gen_reg_rtx (V16QImode);
@@ -4008,6 +4039,17 @@
   DONE;
 })
 
+;; Vector reverse elements for V2DI V2DF
+(define_expand "altivec_vreve<mode>2"
+  [(set (match_operand:VEC_64 0 "register_operand" "=v")
+       (unspec:VEC_64 [(match_operand:VEC_64 1 "register_operand" "v")]
+                     UNSPEC_VREVEV))]
+  "TARGET_ALTIVEC"
+{
+  emit_insn (gen_xxswapd_<mode> (operands[0], operands[1]));
+  DONE;
+})
+
 ;; Vector SIMD PEM v2.06c defines LVLX, LVLXL, LVRX, LVRXL,
 ;; STVLX, STVLXL, STVVRX, STVRXL are available only on Cell.
 (define_insn "altivec_lvlx"

diff --git a/gcc/testsuite/gcc.target/powerpc/vec_reve_1.c b/gcc/testsuite/gcc.target/powerpc/vec_reve_1.c
new file mode 100644 (file)
index 0000000..120c318
--- /dev/null
+++ b/gcc/testsuite/gcc.target/powerpc/vec_reve_1.c
@@ -0,0 +1,17 @@
+/* { dg-do compile } */
+/* { dg-require-effective-target powerpc_altivec_ok } */
+/* { dg-options "-O2 -maltivec" } */
+
+#include <altivec.h>
+
+vector double foo1 (vector double a)
+{
+   return vec_reve (a);
+}
+
+vector long long foo2 (vector long long a)
+{
+   return vec_reve (a);
+}
+
+/* { dg-final { scan-assembler-times {\mxxpermdi\M} 2 } } */

diff --git a/gcc/testsuite/gcc.target/powerpc/vec_reve_2.c b/gcc/testsuite/gcc.target/powerpc/vec_reve_2.c
new file mode 100644 (file)
index 0000000..9661939
--- /dev/null
+++ b/gcc/testsuite/gcc.target/powerpc/vec_reve_2.c
@@ -0,0 +1,29 @@
+/* { dg-do compile } */
+/* { dg-require-effective-target powerpc_p9vector_ok } */
+/* { dg-options "-mdejagnu-cpu=power9 -O2" } */
+
+#include <altivec.h>
+
+vector int foo1 (vector int a)
+{
+   return vec_reve (a);
+}
+
+vector float foo2 (vector float a)
+{
+   return vec_reve (a);
+}
+
+vector short foo3 (vector short a)
+{
+   return vec_reve (a);
+}
+
+vector char foo4 (vector char a)
+{
+   return vec_reve (a);
+}
+
+/* { dg-final { scan-assembler-times {\mxxbrq\M} 4 } } */
+/* { dg-final { scan-assembler-times {\mxxbrw\M} 2 } } */
+/* { dg-final { scan-assembler-times {\mxxbrh\M} 1 } } */