diff mbox series

[V4,rs6000] Support vrotr<mode>3 for int vector types

Message ID 97bfbaab-a9b9-e1e9-2a08-7822a577d0ea@linux.ibm.com
State New
Headers show
Series [V4,rs6000] Support vrotr<mode>3 for int vector types | expand

Commit Message

Kewen.Lin July 26, 2019, 3:33 a.m. UTC 
Hi Segher,

You can just ignore the previous version and review the current
with one comment change and "=" line move.

Sorry for the inconvenience.


Thanks,
Kewen
diff mbox series

Patch

diff --git a/gcc/config/rs6000/altivec.md b/gcc/config/rs6000/altivec.md
index b6a22d9010c..217c7afdf17 100644
--- a/gcc/config/rs6000/altivec.md
+++ b/gcc/config/rs6000/altivec.md
@@ -1666,6 +1666,56 @@ 
   "vrl<VI_char> %0,%1,%2"
   [(set_attr "type" "vecsimple")])
 
+;; Here these trunc_vrl<VI2> are for vrotr<mode>3 expansion.
+;; since SHIFT_COUNT_TRUNCATED is set as zero, to append one explicit
+;; AND to indicate truncation but emit vrl<VI_char> insn.
+(define_insn "trunc_vrlv2di"
+  [(set (match_operand:V2DI 0 "register_operand" "=v")
+	(rotate:V2DI (match_operand:V2DI 1 "register_operand" "v")
+	  (and:V2DI (match_operand:V2DI 2 "register_operand" "v")
+	    (const_vector:V2DI [(const_int 63) (const_int 63)]))))]
+  "VECTOR_UNIT_P8_VECTOR_P (V2DImode)"
+  "vrld %0,%1,%2"
+  [(set_attr "type" "vecsimple")])
+
+(define_insn "trunc_vrlv4si"
+  [(set (match_operand:V4SI 0 "register_operand" "=v")
+	(rotate:V4SI (match_operand:V4SI 1 "register_operand" "v")
+	  (and:V4SI (match_operand:V4SI 2 "register_operand" "v")
+	    (const_vector:V4SI [(const_int 31) (const_int 31)
+			      (const_int 31) (const_int 31)]))))]
+  "VECTOR_UNIT_ALTIVEC_P (V4SImode)"
+  "vrlw %0,%1,%2"
+  [(set_attr "type" "vecsimple")])
+
+(define_insn "trunc_vrlv8hi"
+  [(set (match_operand:V8HI 0 "register_operand" "=v")
+	(rotate:V8HI (match_operand:V8HI 1 "register_operand" "v")
+	  (and:V8HI (match_operand:V8HI 2 "register_operand" "v")
+	    (const_vector:V8HI [(const_int 15) (const_int 15)
+			      (const_int 15) (const_int 15)
+			      (const_int 15) (const_int 15)
+			      (const_int 15) (const_int 15)]))))]
+  "VECTOR_UNIT_ALTIVEC_P (V8HImode)"
+  "vrlh %0,%1,%2"
+  [(set_attr "type" "vecsimple")])
+
+(define_insn "trunc_vrlv16qi"
+  [(set (match_operand:V16QI 0 "register_operand" "=v")
+	(rotate:V16QI (match_operand:V16QI 1 "register_operand" "v")
+	  (and:V16QI (match_operand:V16QI 2 "register_operand" "v")
+	    (const_vector:V16QI [(const_int 7) (const_int 7)
+			    (const_int 7) (const_int 7)
+			    (const_int 7) (const_int 7)
+			    (const_int 7) (const_int 7)
+			    (const_int 7) (const_int 7)
+			    (const_int 7) (const_int 7)
+			    (const_int 7) (const_int 7)
+			    (const_int 7) (const_int 7)]))))]
+  "VECTOR_UNIT_ALTIVEC_P (V16QImode)"
+  "vrlb %0,%1,%2"
+  [(set_attr "type" "vecsimple")])
+
 (define_insn "altivec_vrl<VI_char>mi"
   [(set (match_operand:VIlong 0 "register_operand" "=v")
         (unspec:VIlong [(match_operand:VIlong 1 "register_operand" "0")
diff --git a/gcc/config/rs6000/predicates.md b/gcc/config/rs6000/predicates.md
index 8ca98299950..c4c74630d26 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_const_vector"
+  (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..a7e6c6c256f 100644
--- a/gcc/config/rs6000/vector.md
+++ b/gcc/config/rs6000/vector.md
@@ -1260,6 +1260,35 @@ 
   "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_const_vector")))]
+  "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);
+      emit_insn (gen_vrotl<mode>3 (operands[0], operands[1], rot_count));
+    }
+  else
+    {
+      emit_insn (gen_neg<mode>2 (rot_count, operands[2]));
+      emit_insn (gen_trunc_vrl<mode> (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..7461f3b6317
--- /dev/null
+++ b/gcc/testsuite/gcc.target/powerpc/vec_rotate-1.c
@@ -0,0 +1,46 @@ 
+/* { 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.  */
+
+#define N 256
+unsigned long long sud[N], rud[N];
+unsigned int suw[N], ruw[N];
+unsigned short suh[N], ruh[N];
+unsigned char sub[N], rub[N];
+
+void
+testULL ()
+{
+  for (int i = 0; i < 256; ++i)
+    rud[i] = (sud[i] >> 8) | (sud[i] << (sizeof (sud[0]) * 8 - 8));
+}
+
+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 {\mvrld\M} { target powerpc_p8vector_ok } } } */
+/* { 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..bdfa1e25d07
--- /dev/null
+++ b/gcc/testsuite/gcc.target/powerpc/vec_rotate-2.c
@@ -0,0 +1,47 @@ 
+/* { 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.  */
+
+#define N 256
+unsigned long long sud[N], rud[N];
+unsigned int suw[N], ruw[N];
+unsigned short suh[N], ruh[N];
+unsigned char sub[N], rub[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));
+}
+
+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 {\mvrld\M} { target powerpc_p8vector_ok } } } */
+/* { dg-final { scan-assembler {\mvrlw\M} } } */
+/* { dg-final { scan-assembler {\mvrlh\M} } } */
+/* { dg-final { scan-assembler {\mvrlb\M} } } */