[PATCH V5, rs6000] Support vrotr<mode>3 for int vector types

[Kewen.Lin]

Hi Segher,

Sorry for the late, I've addressed your comments in the attached patch.
Some points:
  1) Remove explict AND part.
  2) Rename predicate name to vint_reg_or_vint_const.
  3) Split test cases into altivec and power8.

As to the predicate name and usage, I checked the current vector shifts, 
they don't need to check const_vector specially (like right to left 
conversion), excepting for the one "vec_shr_<mode>", but it checks for
scalar const int.

Btw, I've changed the 
  +      rtx imm_vec = 
  +	simplify_const_unary_operation
back to 
  +      rtx imm_vec
  +	= simplify_const_unary_operation
Otherwise check_GNU_style will report "Trailing operator" error.  :(

Bootstrapped and regtested on powerpc64le-unknown-linux-gnu.

Thanks,
Kewen

------------

gcc/ChangeLog

2019-08-02  Kewen Lin  <linkw@gcc.gnu.org>

	* config/rs6000/predicates.md (vint_reg_or_vint_const): New predicate.
	* config/rs6000/vector.md (vrotr<mode>3): New define_expand.

gcc/testsuite/ChangeLog

2019-08-02  Kewen Lin  <linkw@gcc.gnu.org>

	* gcc.target/powerpc/vec_rotate-1.c: New test.
	* gcc.target/powerpc/vec_rotate-2.c: New test.
	* gcc.target/powerpc/vec_rotate-3.c: New test.
	* gcc.target/powerpc/vec_rotate-4.c: New test.

-------------- next part --------------
diff --git a/gcc/config/rs6000/predicates.md b/gcc/config/rs6000/predicates.md
index 8ca98299950..faf057425a8 100644
--- a/gcc/config/rs6000/predicates.md
+++ b/gcc/config/rs6000/predicates.md
@@ -163,6 +163,17 @@
   return VINT_REGNO_P (REGNO (op));
 })
 
+;; Return 1 if op is a vector register that operates on integer vectors
+;; or if op is a const vector with integer vector modes.
+(define_predicate "vint_reg_or_vint_const"
+  (match_code "reg,subreg,const_vector")
+{
+  if (GET_CODE (op) == CONST_VECTOR && GET_MODE_CLASS (mode) == MODE_VECTOR_INT)
+    return 1;
+
+  return vint_operand (op, mode);
+})
+
 ;; Return 1 if op is a vector register to do logical operations on (and, or,
 ;; xor, etc.)
 (define_predicate "vlogical_operand"
diff --git a/gcc/config/rs6000/vector.md b/gcc/config/rs6000/vector.md
index 70bcfe02e22..3111ca9029f 100644
--- a/gcc/config/rs6000/vector.md
+++ b/gcc/config/rs6000/vector.md
@@ -1260,6 +1260,33 @@
   "VECTOR_UNIT_ALTIVEC_OR_VSX_P (<MODE>mode)"
   "")
 
+;; Expanders for rotatert to make use of vrotl
+(define_expand "vrotr<mode>3"
+  [(set (match_operand:VEC_I 0 "vint_operand")
+	(rotatert:VEC_I (match_operand:VEC_I 1 "vint_operand")
+		(match_operand:VEC_I 2 "vint_reg_or_vint_const")))]
+  "VECTOR_UNIT_ALTIVEC_OR_VSX_P (<MODE>mode)"
+{
+  rtx rot_count = gen_reg_rtx (<MODE>mode);
+  if (GET_CODE (operands[2]) == CONST_VECTOR)
+    {
+      machine_mode inner_mode = GET_MODE_INNER (<MODE>mode);
+      unsigned int bits = GET_MODE_PRECISION (inner_mode);
+      rtx mask_vec = gen_const_vec_duplicate (<MODE>mode, GEN_INT (bits - 1));
+      rtx imm_vec
+	= simplify_const_unary_operation (NEG, <MODE>mode, operands[2],
+					  GET_MODE (operands[2]));
+      imm_vec
+	= simplify_const_binary_operation (AND, <MODE>mode, imm_vec, mask_vec);
+      rot_count = force_reg (<MODE>mode, imm_vec);
+    }
+  else
+    emit_insn (gen_neg<mode>2 (rot_count, operands[2]));
+
+  emit_insn (gen_vrotl<mode>3 (operands[0], operands[1], rot_count));
+  DONE;
+})
+
 ;; Expanders for arithmetic shift left on each vector element
 (define_expand "vashl<mode>3"
   [(set (match_operand:VEC_I 0 "vint_operand")
diff --git a/gcc/testsuite/gcc.target/powerpc/vec_rotate-1.c b/gcc/testsuite/gcc.target/powerpc/vec_rotate-1.c
new file mode 100644
index 00000000000..f035a578292
--- /dev/null
+++ b/gcc/testsuite/gcc.target/powerpc/vec_rotate-1.c
@@ -0,0 +1,39 @@
+/* { dg-options "-O3" } */
+/* { dg-require-effective-target powerpc_altivec_ok } */
+
+/* Check vectorizer can exploit vector rotation instructions on Power, mainly
+   for the case rotation count is const number.
+
+   Check for instructions vrlb/vrlh/vrlw only available if altivec supported. */
+
+#define N 256
+unsigned int suw[N], ruw[N];
+unsigned short suh[N], ruh[N];
+unsigned char sub[N], rub[N];
+
+void
+testUW ()
+{
+  for (int i = 0; i < 256; ++i)
+    ruw[i] = (suw[i] >> 8) | (suw[i] << (sizeof (suw[0]) * 8 - 8));
+}
+
+void
+testUH ()
+{
+  for (int i = 0; i < 256; ++i)
+    ruh[i] = (unsigned short) (suh[i] >> 9)
+	     | (unsigned short) (suh[i] << (sizeof (suh[0]) * 8 - 9));
+}
+
+void
+testUB ()
+{
+  for (int i = 0; i < 256; ++i)
+    rub[i] = (unsigned char) (sub[i] >> 5)
+	     | (unsigned char) (sub[i] << (sizeof (sub[0]) * 8 - 5));
+}
+
+/* { dg-final { scan-assembler {\mvrlw\M} } } */
+/* { dg-final { scan-assembler {\mvrlh\M} } } */
+/* { dg-final { scan-assembler {\mvrlb\M} } } */
diff --git a/gcc/testsuite/gcc.target/powerpc/vec_rotate-2.c b/gcc/testsuite/gcc.target/powerpc/vec_rotate-2.c
new file mode 100644
index 00000000000..0a2a965ddcb
--- /dev/null
+++ b/gcc/testsuite/gcc.target/powerpc/vec_rotate-2.c
@@ -0,0 +1,19 @@
+/* { dg-require-effective-target powerpc_p8vector_ok } */
+/* { dg-options "-O3 -mdejagnu-cpu=power8" } */
+
+/* Check vectorizer can exploit vector rotation instructions on Power8, mainly
+   for the case rotation count is const number.
+
+   Check for vrld which is available on Power8 and above.  */
+
+#define N 256
+unsigned long long sud[N], rud[N];
+
+void
+testULL ()
+{
+  for (int i = 0; i < 256; ++i)
+    rud[i] = (sud[i] >> 8) | (sud[i] << (sizeof (sud[0]) * 8 - 8));
+}
+
+/* { dg-final { scan-assembler {\mvrld\M} } } */
diff --git a/gcc/testsuite/gcc.target/powerpc/vec_rotate-3.c b/gcc/testsuite/gcc.target/powerpc/vec_rotate-3.c
new file mode 100644
index 00000000000..5e90ae6fd63
--- /dev/null
+++ b/gcc/testsuite/gcc.target/powerpc/vec_rotate-3.c
@@ -0,0 +1,40 @@
+/* { dg-options "-O3" } */
+/* { dg-require-effective-target powerpc_altivec_ok } */
+
+/* Check vectorizer can exploit vector rotation instructions on Power, mainly
+   for the case rotation count isn't const number.
+
+   Check for instructions vrlb/vrlh/vrlw only available if altivec supported. */
+
+#define N 256
+unsigned int suw[N], ruw[N];
+unsigned short suh[N], ruh[N];
+unsigned char sub[N], rub[N];
+extern unsigned char rot_cnt;
+
+void
+testUW ()
+{
+  for (int i = 0; i < 256; ++i)
+    ruw[i] = (suw[i] >> rot_cnt) | (suw[i] << (sizeof (suw[0]) * 8 - rot_cnt));
+}
+
+void
+testUH ()
+{
+  for (int i = 0; i < 256; ++i)
+    ruh[i] = (unsigned short) (suh[i] >> rot_cnt)
+	     | (unsigned short) (suh[i] << (sizeof (suh[0]) * 8 - rot_cnt));
+}
+
+void
+testUB ()
+{
+  for (int i = 0; i < 256; ++i)
+    rub[i] = (unsigned char) (sub[i] >> rot_cnt)
+	     | (unsigned char) (sub[i] << (sizeof (sub[0]) * 8 - rot_cnt));
+}
+
+/* { dg-final { scan-assembler {\mvrlw\M} } } */
+/* { dg-final { scan-assembler {\mvrlh\M} } } */
+/* { dg-final { scan-assembler {\mvrlb\M} } } */
diff --git a/gcc/testsuite/gcc.target/powerpc/vec_rotate-4.c b/gcc/testsuite/gcc.target/powerpc/vec_rotate-4.c
new file mode 100644
index 00000000000..0d3e8378ed6
--- /dev/null
+++ b/gcc/testsuite/gcc.target/powerpc/vec_rotate-4.c
@@ -0,0 +1,20 @@
+/* { dg-require-effective-target powerpc_p8vector_ok } */
+/* { dg-options "-O3 -mdejagnu-cpu=power8" } */
+
+/* Check vectorizer can exploit vector rotation instructions on Power8, mainly
+   for the case rotation count isn't const number.
+
+   Check for vrld which is available on Power8 and above.  */
+
+#define N 256
+unsigned long long sud[N], rud[N];
+extern unsigned char rot_cnt;
+
+void
+testULL ()
+{
+  for (int i = 0; i < 256; ++i)
+    rud[i] = (sud[i] >> rot_cnt) | (sud[i] << (sizeof (sud[0]) * 8 - rot_cnt));
+}
+
+/* { dg-final { scan-assembler {\mvrld\M} } } */