aarch64-simd.md (clrsb<mode>2, [...]): New patterns.

        * config/aarch64/aarch64-simd.md (clrsb<mode>2, popcount<mode>2): New
        patterns.
        * config/aarch64/aarch64-simd-builtins.def (clrsb, popcount): New
        builtins.
        * config/aarch64/arm_neon.h (vcls_s8, vcls_s16, vcls_s32, vclsq_s8,
        vclsq_s16, vclsq_s32, vcnt_p8, vcnt_s8, vcnt_u8, vcntq_p8, vcntq_s8,
        vcntq_u8): Rewrite using builtin functions.

Co-Authored-By: Shanyao Chen <chenshanyao@huawei.com>

From-SVN: r218464

gcc/ChangeLog

+2014-12-07  Felix Yang  <felix.yang@huawei.com>
+	    Shanyao Chen  <chenshanyao@huawei.com>
+
+	* config/aarch64/aarch64-simd.md (clrsb<mode>2, popcount<mode>2): New
+	patterns.
+	* config/aarch64/aarch64-simd-builtins.def (clrsb, popcount): New
+	builtins.
+	* config/aarch64/arm_neon.h (vcls_s8, vcls_s16, vcls_s32, vclsq_s8,
+	vclsq_s16, vclsq_s32, vcnt_p8, vcnt_s8, vcnt_u8, vcntq_p8, vcntq_s8,
+	vcntq_u8): Rewrite using builtin functions.
+
 2014-12-07  Jan Hubicka  <hubicka@ucw.cz>
 
 	* symtab.c (symtab_node::equal_address_to): New function.

gcc/config/aarch64/aarch64-simd-builtins.def

@@ -44,8 +44,10 @@
   BUILTIN_VDQF (UNOP, sqrt, 2)
   BUILTIN_VD_BHSI (BINOP, addp, 0)
   VAR1 (UNOP, addp, 0, di)
+  BUILTIN_VDQ_BHSI (UNOP, clrsb, 2)
   BUILTIN_VDQ_BHSI (UNOP, clz, 2)
   BUILTIN_VS (UNOP, ctz, 2)
+  BUILTIN_VB (UNOP, popcount, 2)
 
   /* be_checked_get_lane does its own lane swapping, so not a lane index.  */
   BUILTIN_VALL (GETREG, be_checked_get_lane, 0)

gcc/config/aarch64/aarch64-simd.md

@@ -1903,6 +1903,14 @@
   DONE;
 })
 
+(define_insn "clrsb<mode>2"
+  [(set (match_operand:VDQ_BHSI 0 "register_operand" "=w")
+        (clrsb:VDQ_BHSI (match_operand:VDQ_BHSI 1 "register_operand" "w")))]
+  "TARGET_SIMD"
+  "cls\\t%0.<Vtype>, %1.<Vtype>"
+  [(set_attr "type" "neon_cls<q>")]
+)
+
 (define_insn "clz<mode>2"
  [(set (match_operand:VDQ_BHSI 0 "register_operand" "=w")
        (clz:VDQ_BHSI (match_operand:VDQ_BHSI 1 "register_operand" "w")))]
@@ -1911,6 +1919,14 @@
   [(set_attr "type" "neon_cls<q>")]
 )
 
+(define_insn "popcount<mode>2"
+  [(set (match_operand:VB 0 "register_operand" "=w")
+        (popcount:VB (match_operand:VB 1 "register_operand" "w")))]
+  "TARGET_SIMD"
+  "cnt\\t%0.<Vbtype>, %1.<Vbtype>"
+  [(set_attr "type" "neon_cnt<q>")]
+)
+
 ;; 'across lanes' max and min ops.
 
 ;; Template for outputting a scalar, so we can create __builtins which can be

gcc/config/aarch64/arm_neon.h

@@ -5317,138 +5317,6 @@ vaddlvq_u32 (uint32x4_t a)
   return result;
 }
 
-__extension__ static __inline int8x8_t __attribute__ ((__always_inline__))
-vcls_s8 (int8x8_t a)
-{
-  int8x8_t result;
-  __asm__ ("cls %0.8b,%1.8b"
-           : "=w"(result)
-           : "w"(a)
-           : /* No clobbers */);
-  return result;
-}
-
-__extension__ static __inline int16x4_t __attribute__ ((__always_inline__))
-vcls_s16 (int16x4_t a)
-{
-  int16x4_t result;
-  __asm__ ("cls %0.4h,%1.4h"
-           : "=w"(result)
-           : "w"(a)
-           : /* No clobbers */);
-  return result;
-}
-
-__extension__ static __inline int32x2_t __attribute__ ((__always_inline__))
-vcls_s32 (int32x2_t a)
-{
-  int32x2_t result;
-  __asm__ ("cls %0.2s,%1.2s"
-           : "=w"(result)
-           : "w"(a)
-           : /* No clobbers */);
-  return result;
-}
-
-__extension__ static __inline int8x16_t __attribute__ ((__always_inline__))
-vclsq_s8 (int8x16_t a)
-{
-  int8x16_t result;
-  __asm__ ("cls %0.16b,%1.16b"
-           : "=w"(result)
-           : "w"(a)
-           : /* No clobbers */);
-  return result;
-}
-
-__extension__ static __inline int16x8_t __attribute__ ((__always_inline__))
-vclsq_s16 (int16x8_t a)
-{
-  int16x8_t result;
-  __asm__ ("cls %0.8h,%1.8h"
-           : "=w"(result)
-           : "w"(a)
-           : /* No clobbers */);
-  return result;
-}
-
-__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
-vclsq_s32 (int32x4_t a)
-{
-  int32x4_t result;
-  __asm__ ("cls %0.4s,%1.4s"
-           : "=w"(result)
-           : "w"(a)
-           : /* No clobbers */);
-  return result;
-}
-
-__extension__ static __inline poly8x8_t __attribute__ ((__always_inline__))
-vcnt_p8 (poly8x8_t a)
-{
-  poly8x8_t result;
-  __asm__ ("cnt %0.8b,%1.8b"
-           : "=w"(result)
-           : "w"(a)
-           : /* No clobbers */);
-  return result;
-}
-
-__extension__ static __inline int8x8_t __attribute__ ((__always_inline__))
-vcnt_s8 (int8x8_t a)
-{
-  int8x8_t result;
-  __asm__ ("cnt %0.8b,%1.8b"
-           : "=w"(result)
-           : "w"(a)
-           : /* No clobbers */);
-  return result;
-}
-
-__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__))
-vcnt_u8 (uint8x8_t a)
-{
-  uint8x8_t result;
-  __asm__ ("cnt %0.8b,%1.8b"
-           : "=w"(result)
-           : "w"(a)
-           : /* No clobbers */);
-  return result;
-}
-
-__extension__ static __inline poly8x16_t __attribute__ ((__always_inline__))
-vcntq_p8 (poly8x16_t a)
-{
-  poly8x16_t result;
-  __asm__ ("cnt %0.16b,%1.16b"
-           : "=w"(result)
-           : "w"(a)
-           : /* No clobbers */);
-  return result;
-}
-
-__extension__ static __inline int8x16_t __attribute__ ((__always_inline__))
-vcntq_s8 (int8x16_t a)
-{
-  int8x16_t result;
-  __asm__ ("cnt %0.16b,%1.16b"
-           : "=w"(result)
-           : "w"(a)
-           : /* No clobbers */);
-  return result;
-}
-
-__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__))
-vcntq_u8 (uint8x16_t a)
-{
-  uint8x16_t result;
-  __asm__ ("cnt %0.16b,%1.16b"
-           : "=w"(result)
-           : "w"(a)
-           : /* No clobbers */);
-  return result;
-}
-
 #define vcopyq_lane_f32(a, b, c, d)                                     \
   __extension__                                                         \
     ({                                                                  \
@@ -14082,6 +13950,44 @@ vcltzd_f64 (float64_t __a)
   return __a < 0.0 ? -1ll : 0ll;
 }
 
+/* vcls.  */
+
+__extension__ static __inline int8x8_t __attribute__ ((__always_inline__))
+vcls_s8 (int8x8_t __a)
+{
+  return __builtin_aarch64_clrsbv8qi (__a);
+}
+
+__extension__ static __inline int16x4_t __attribute__ ((__always_inline__))
+vcls_s16 (int16x4_t __a)
+{
+  return __builtin_aarch64_clrsbv4hi (__a);
+}
+
+__extension__ static __inline int32x2_t __attribute__ ((__always_inline__))
+vcls_s32 (int32x2_t __a)
+{
+  return __builtin_aarch64_clrsbv2si (__a);
+}
+
+__extension__ static __inline int8x16_t __attribute__ ((__always_inline__))
+vclsq_s8 (int8x16_t __a)
+{
+  return __builtin_aarch64_clrsbv16qi (__a);
+}
+
+__extension__ static __inline int16x8_t __attribute__ ((__always_inline__))
+vclsq_s16 (int16x8_t __a)
+{
+  return __builtin_aarch64_clrsbv8hi (__a);
+}
+
+__extension__ static __inline int32x4_t __attribute__ ((__always_inline__))
+vclsq_s32 (int32x4_t __a)
+{
+  return __builtin_aarch64_clrsbv4si (__a);
+}
+
 /* vclz.  */
 
 __extension__ static __inline int8x8_t __attribute__ ((__always_inline__))
@@ -14156,6 +14062,44 @@ vclzq_u32 (uint32x4_t __a)
   return (uint32x4_t)__builtin_aarch64_clzv4si ((int32x4_t)__a);
 }
 
+/* vcnt.  */
+
+__extension__ static __inline poly8x8_t __attribute__ ((__always_inline__))
+vcnt_p8 (poly8x8_t __a)
+{
+  return (poly8x8_t) __builtin_aarch64_popcountv8qi ((int8x8_t) __a);
+}
+
+__extension__ static __inline int8x8_t __attribute__ ((__always_inline__))
+vcnt_s8 (int8x8_t __a)
+{
+  return __builtin_aarch64_popcountv8qi (__a);
+}
+
+__extension__ static __inline uint8x8_t __attribute__ ((__always_inline__))
+vcnt_u8 (uint8x8_t __a)
+{
+  return (uint8x8_t) __builtin_aarch64_popcountv8qi ((int8x8_t) __a);
+}
+
+__extension__ static __inline poly8x16_t __attribute__ ((__always_inline__))
+vcntq_p8 (poly8x16_t __a)
+{
+  return (poly8x16_t) __builtin_aarch64_popcountv16qi ((int8x16_t) __a);
+}
+
+__extension__ static __inline int8x16_t __attribute__ ((__always_inline__))
+vcntq_s8 (int8x16_t __a)
+{
+  return __builtin_aarch64_popcountv16qi (__a);
+}
+
+__extension__ static __inline uint8x16_t __attribute__ ((__always_inline__))
+vcntq_u8 (uint8x16_t __a)
+{
+  return (uint8x16_t) __builtin_aarch64_popcountv16qi ((int8x16_t) __a);
+}
+
 /* vcvt (double -> float).  */
 
 __extension__ static __inline float32x2_t __attribute__ ((__always_inline__))