[AArch64][2/3] Recognise rev16 operations on SImode and DImode data

       * config/aarch64/aarch64.md (rev16<mode>2): New pattern.
       (rev16<mode>2_alt): Likewise.
       * config/aarch64/aarch64.c (aarch64_rtx_costs): Handle rev16 case.
       * config/arm/aarch-common.c (aarch_rev16_shright_mask_imm_p): New.
       (aarch_rev16_shleft_mask_imm_p): Likewise.
       (aarch_rev16_p_1): Likewise.
       (aarch_rev16_p): Likewise.
       * config/arm/aarch-common-protos.h (aarch_rev16_p): Declare extern.
       (aarch_rev16_shright_mask_imm_p): Likewise.
       (aarch_rev16_shleft_mask_imm_p): Likewise.

       * gcc.target/aarch64/rev16_1.c: New test.

From-SVN: r209704

7 files changed, 194 insertions, 0 deletions

diff --git a/gcc/ChangeLog b/gcc/ChangeLog
index 6d3bab8..1b8dd62 100644
--- a/gcc/ChangeLog
+++ b/gcc/ChangeLog
@@ -1,5 +1,18 @@
 2014-04-23  Kyrylo Tkachov  <kyrylo.tkachov@arm.com>
 
+       * config/aarch64/aarch64.md (rev16<mode>2): New pattern.
+       (rev16<mode>2_alt): Likewise.
+       * config/aarch64/aarch64.c (aarch64_rtx_costs): Handle rev16 case.
+       * config/arm/aarch-common.c (aarch_rev16_shright_mask_imm_p): New.
+       (aarch_rev16_shleft_mask_imm_p): Likewise.
+       (aarch_rev16_p_1): Likewise.
+       (aarch_rev16_p): Likewise.
+       * config/arm/aarch-common-protos.h (aarch_rev16_p): Declare extern.
+       (aarch_rev16_shright_mask_imm_p): Likewise.
+       (aarch_rev16_shleft_mask_imm_p): Likewise.
+
+2014-04-23  Kyrylo Tkachov  <kyrylo.tkachov@arm.com>
+
        * config/arm/aarch-common-protos.h (alu_cost_table): Add rev field.
        * config/arm/aarch-cost-tables.h (generic_extra_costs): Specify
        rev cost.
diff --git a/gcc/config/aarch64/aarch64.c b/gcc/config/aarch64/aarch64.c
index dacd7ee..68c29aa 100644
--- a/gcc/config/aarch64/aarch64.c
+++ b/gcc/config/aarch64/aarch64.c
@@ -4695,6 +4695,16 @@ aarch64_rtx_costs (rtx x, int code, int outer ATTRIBUTE_UNUSED,
       return false;
 
     case IOR:
+      if (aarch_rev16_p (x))
+        {
+          *cost = COSTS_N_INSNS (1);
+
+          if (speed)
+            *cost += extra_cost->alu.rev;
+
+          return true;
+        }
+    /* Fall through.  */
     case XOR:
     case AND:
     cost_logic:
diff --git a/gcc/config/aarch64/aarch64.md b/gcc/config/aarch64/aarch64.md
index ee32b6c..98c46d1 100644
--- a/gcc/config/aarch64/aarch64.md
+++ b/gcc/config/aarch64/aarch64.md
@@ -3253,6 +3253,38 @@
   [(set_attr "type" "rev")]
 )
 
+;; There are no canonicalisation rules for the position of the lshiftrt, ashift
+;; operations within an IOR/AND RTX, therefore we have two patterns matching
+;; each valid permutation.
+
+(define_insn "rev16<mode>2"
+  [(set (match_operand:GPI 0 "register_operand" "=r")
+        (ior:GPI (and:GPI (ashift:GPI (match_operand:GPI 1 "register_operand" "r")
+                                      (const_int 8))
+                          (match_operand:GPI 3 "const_int_operand" "n"))
+                 (and:GPI (lshiftrt:GPI (match_dup 1)
+                                        (const_int 8))
+                          (match_operand:GPI 2 "const_int_operand" "n"))))]
+  "aarch_rev16_shleft_mask_imm_p (operands[3], <MODE>mode)
+   && aarch_rev16_shright_mask_imm_p (operands[2], <MODE>mode)"
+  "rev16\\t%<w>0, %<w>1"
+  [(set_attr "type" "rev")]
+)
+
+(define_insn "rev16<mode>2_alt"
+  [(set (match_operand:GPI 0 "register_operand" "=r")
+        (ior:GPI (and:GPI (lshiftrt:GPI (match_operand:GPI 1 "register_operand" "r")
+                                        (const_int 8))
+                          (match_operand:GPI 2 "const_int_operand" "n"))
+                 (and:GPI (ashift:GPI (match_dup 1)
+                                      (const_int 8))
+                          (match_operand:GPI 3 "const_int_operand" "n"))))]
+  "aarch_rev16_shleft_mask_imm_p (operands[3], <MODE>mode)
+   && aarch_rev16_shright_mask_imm_p (operands[2], <MODE>mode)"
+  "rev16\\t%<w>0, %<w>1"
+  [(set_attr "type" "rev")]
+)
+
 ;; zero_extend version of above
 (define_insn "*bswapsi2_uxtw"
   [(set (match_operand:DI 0 "register_operand" "=r")
diff --git a/gcc/config/arm/aarch-common-protos.h b/gcc/config/arm/aarch-common-protos.h
index 5693c31..1b60d78 100644
--- a/gcc/config/arm/aarch-common-protos.h
+++ b/gcc/config/arm/aarch-common-protos.h
@@ -24,6 +24,9 @@
 #define GCC_AARCH_COMMON_PROTOS_H
 
 extern int aarch_crypto_can_dual_issue (rtx, rtx);
+extern bool aarch_rev16_p (rtx);
+extern bool aarch_rev16_shleft_mask_imm_p (rtx, enum machine_mode);
+extern bool aarch_rev16_shright_mask_imm_p (rtx, enum machine_mode);
 extern int arm_early_load_addr_dep (rtx, rtx);
 extern int arm_early_store_addr_dep (rtx, rtx);
 extern int arm_mac_accumulator_is_mul_result (rtx, rtx);
diff --git a/gcc/config/arm/aarch-common.c b/gcc/config/arm/aarch-common.c
index af8fc99..884d4b3 100644
--- a/gcc/config/arm/aarch-common.c
+++ b/gcc/config/arm/aarch-common.c
@@ -191,6 +191,79 @@ arm_get_set_operands (rtx producer, rtx consumer,
   return 0;
 }
 
+bool
+aarch_rev16_shright_mask_imm_p (rtx val, enum machine_mode mode)
+{
+  return CONST_INT_P (val)
+         && INTVAL (val) == trunc_int_for_mode (0xff00ff00ff00ff, mode);
+}
+
+bool
+aarch_rev16_shleft_mask_imm_p (rtx val, enum machine_mode mode)
+{
+  return CONST_INT_P (val)
+         && INTVAL (val) == trunc_int_for_mode (0xff00ff00ff00ff00, mode);
+}
+
+
+static bool
+aarch_rev16_p_1 (rtx lhs, rtx rhs, enum machine_mode mode)
+{
+  if (GET_CODE (lhs) == AND
+         && GET_CODE (XEXP (lhs, 0)) == ASHIFT
+            && CONST_INT_P (XEXP (XEXP (lhs, 0), 1))
+            && INTVAL (XEXP (XEXP (lhs, 0), 1)) == 8
+            && REG_P (XEXP (XEXP (lhs, 0), 0))
+         && CONST_INT_P (XEXP (lhs, 1))
+      && GET_CODE (rhs) == AND
+         && GET_CODE (XEXP (rhs, 0)) == LSHIFTRT
+            && REG_P (XEXP (XEXP (rhs, 0), 0))
+            && CONST_INT_P (XEXP (XEXP (rhs, 0), 1))
+            && INTVAL (XEXP (XEXP (rhs, 0), 1)) == 8
+         && CONST_INT_P (XEXP (rhs, 1))
+      && REGNO (XEXP (XEXP (rhs, 0), 0)) == REGNO (XEXP (XEXP (lhs, 0), 0)))
+
+    {
+      rtx lhs_mask = XEXP (lhs, 1);
+      rtx rhs_mask = XEXP (rhs, 1);
+
+      return aarch_rev16_shright_mask_imm_p (rhs_mask, mode)
+             && aarch_rev16_shleft_mask_imm_p (lhs_mask, mode);
+    }
+
+  return false;
+}
+
+/* Recognise a sequence of bitwise operations corresponding to a rev16 operation.
+   These will be of the form:
+     ((x >> 8) & 0x00ff00ff)
+   | ((x << 8) & 0xff00ff00)
+   for SImode and with similar but wider bitmasks for DImode.
+   The two sub-expressions of the IOR can appear on either side so check both
+   permutations with the help of aarch_rev16_p_1 above.  */
+
+bool
+aarch_rev16_p (rtx x)
+{
+  rtx left_sub_rtx, right_sub_rtx;
+  bool is_rev = false;
+
+  if (GET_CODE (x) != IOR)
+    return false;
+
+  left_sub_rtx = XEXP (x, 0);
+  right_sub_rtx = XEXP (x, 1);
+
+  /* There are no canonicalisation rules for the position of the two shifts
+     involved in a rev, so try both permutations.  */
+  is_rev = aarch_rev16_p_1 (left_sub_rtx, right_sub_rtx, GET_MODE (x));
+
+  if (!is_rev)
+    is_rev = aarch_rev16_p_1 (right_sub_rtx, left_sub_rtx, GET_MODE (x));
+
+  return is_rev;
+}
+
 /* Return nonzero if the CONSUMER instruction (a load) does need
    PRODUCER's value to calculate the address.  */
 int
diff --git a/gcc/testsuite/ChangeLog b/gcc/testsuite/ChangeLog
index e74096c..9f1e7ce 100644
--- a/gcc/testsuite/ChangeLog
+++ b/gcc/testsuite/ChangeLog
@@ -1,3 +1,7 @@
+2014-04-23  Kyrylo Tkachov  <kyrylo.tkachov@arm.com>
+
+       * gcc.target/aarch64/rev16_1.c: New test.
+
 2014-04-23  Richard Biener  <rguenther@suse.de>
 
 	PR tree-optimization/60903
diff --git a/gcc/testsuite/gcc.target/aarch64/rev16_1.c b/gcc/testsuite/gcc.target/aarch64/rev16_1.c
new file mode 100644
index 0000000..126d3c0
--- /dev/null
+++ b/gcc/testsuite/gcc.target/aarch64/rev16_1.c
@@ -0,0 +1,59 @@
+/* { dg-options "-O2" } */
+/* { dg-do run } */
+
+extern void abort (void);
+
+typedef unsigned int __u32;
+
+__u32
+__rev16_32_alt (__u32 x)
+{
+  return (((__u32)(x) & (__u32)0xff00ff00UL) >> 8)
+         | (((__u32)(x) & (__u32)0x00ff00ffUL) << 8);
+}
+
+__u32
+__rev16_32 (__u32 x)
+{
+  return (((__u32)(x) & (__u32)0x00ff00ffUL) << 8)
+         | (((__u32)(x) & (__u32)0xff00ff00UL) >> 8);
+}
+
+typedef unsigned long long __u64;
+
+__u64
+__rev16_64_alt (__u64 x)
+{
+  return (((__u64)(x) & (__u64)0xff00ff00ff00ff00UL) >> 8)
+         | (((__u64)(x) & (__u64)0x00ff00ff00ff00ffUL) << 8);
+}
+
+__u64
+__rev16_64 (__u64 x)
+{
+  return (((__u64)(x) & (__u64)0x00ff00ff00ff00ffUL) << 8)
+         | (((__u64)(x) & (__u64)0xff00ff00ff00ff00UL) >> 8);
+}
+
+int
+main (void)
+{
+  volatile __u32 in32 = 0x12345678;
+  volatile __u32 expected32 = 0x34127856;
+  volatile __u64 in64 = 0x1234567890abcdefUL;
+  volatile __u64 expected64 = 0x34127856ab90efcdUL;
+
+  if (__rev16_32 (in32) != expected32)
+    abort ();
+
+  if (__rev16_32_alt (in32) != expected32)
+    abort ();
+
+  if (__rev16_64 (in64) != expected64)
+    abort ();
+
+  if (__rev16_64_alt (in64) != expected64)
+    abort ();
+
+  return 0;
+}