[AArch64] Add alternative 'extr' pattern, calculate rtx cost properly

	* config/aarch64/aarch64.md (*extr<mode>5_insn_alt): New pattern.
	(*extrsi5_insn_uxtw_alt): Likewise.
	* config/aarch64/aarch64.c (aarch64_extr_rtx_p): New function.
	(aarch64_rtx_costs, IOR case): Use above to properly cost extr
	operations.

From-SVN: r222639

diff --git a/gcc/ChangeLog b/gcc/ChangeLog
index 3710788..d24460f 100644 (file)
--- a/gcc/ChangeLog
+++ b/gcc/ChangeLog
@@ -1,5 +1,13 @@
 2015-04-30  Kyrylo Tkachov  <kyrylo.tkachov@arm.com>
 
+       * config/aarch64/aarch64.md (*extr<mode>5_insn_alt): New pattern.
+       (*extrsi5_insn_uxtw_alt): Likewise.
+       * config/aarch64/aarch64.c (aarch64_extr_rtx_p): New function.
+       (aarch64_rtx_costs, IOR case): Use above to properly cost extr
+       operations.
+
+2015-04-30  Kyrylo Tkachov  <kyrylo.tkachov@arm.com>
+
        * config/aarch64/aarch64.c (aarch64_rtx_costs): Handle pattern for
        fabd in ABS case.
 

diff --git a/gcc/config/aarch64/aarch64.c b/gcc/config/aarch64/aarch64.c
index f1aec67..d7ef473 100644 (file)
--- a/gcc/config/aarch64/aarch64.c
+++ b/gcc/config/aarch64/aarch64.c
@@ -5445,6 +5445,51 @@ aarch64_frint_unspec_p (unsigned int u)
     }
 }
 
+/* Return true iff X is an rtx that will match an extr instruction
+   i.e. as described in the *extr<mode>5_insn family of patterns.
+   OP0 and OP1 will be set to the operands of the shifts involved
+   on success and will be NULL_RTX otherwise.  */
+
+static bool
+aarch64_extr_rtx_p (rtx x, rtx *res_op0, rtx *res_op1)
+{
+  rtx op0, op1;
+  machine_mode mode = GET_MODE (x);
+
+  *res_op0 = NULL_RTX;
+  *res_op1 = NULL_RTX;
+
+  if (GET_CODE (x) != IOR)
+    return false;
+
+  op0 = XEXP (x, 0);
+  op1 = XEXP (x, 1);
+
+  if ((GET_CODE (op0) == ASHIFT && GET_CODE (op1) == LSHIFTRT)
+      || (GET_CODE (op1) == ASHIFT && GET_CODE (op0) == LSHIFTRT))
+    {
+     /* Canonicalise locally to ashift in op0, lshiftrt in op1.  */
+      if (GET_CODE (op1) == ASHIFT)
+        std::swap (op0, op1);
+
+      if (!CONST_INT_P (XEXP (op0, 1)) || !CONST_INT_P (XEXP (op1, 1)))
+        return false;
+
+      unsigned HOST_WIDE_INT shft_amnt_0 = UINTVAL (XEXP (op0, 1));
+      unsigned HOST_WIDE_INT shft_amnt_1 = UINTVAL (XEXP (op1, 1));
+
+      if (shft_amnt_0 < GET_MODE_BITSIZE (mode)
+          && shft_amnt_0 + shft_amnt_1 == GET_MODE_BITSIZE (mode))
+        {
+          *res_op0 = XEXP (op0, 0);
+          *res_op1 = XEXP (op1, 0);
+          return true;
+        }
+    }
+
+  return false;
+}
+
 /* Calculate the cost of calculating (if_then_else (OP0) (OP1) (OP2)),
    storing it in *COST.  Result is true if the total cost of the operation
    has now been calculated.  */
@@ -5977,6 +6022,16 @@ cost_plus:
 
           return true;
         }
+
+      if (aarch64_extr_rtx_p (x, &op0, &op1))
+        {
+          *cost += rtx_cost (op0, IOR, 0, speed)
+                   + rtx_cost (op1, IOR, 1, speed);
+          if (speed)
+            *cost += extra_cost->alu.shift;
+
+          return true;
+        }
     /* Fall through.  */
     case XOR:
     case AND:

diff --git a/gcc/config/aarch64/aarch64.md b/gcc/config/aarch64/aarch64.md
index 194bfd3..11c4709 100644 (file)
--- a/gcc/config/aarch64/aarch64.md
+++ b/gcc/config/aarch64/aarch64.md
@@ -3597,6 +3597,21 @@
   [(set_attr "type" "shift_imm")]
 )
 
+;; There are no canonicalisation rules for ashift and lshiftrt inside an ior
+;; so we have to match both orderings.
+(define_insn "*extr<mode>5_insn_alt"
+  [(set (match_operand:GPI 0 "register_operand" "=r")
+       (ior:GPI  (lshiftrt:GPI (match_operand:GPI 2 "register_operand" "r")
+                               (match_operand 4 "const_int_operand" "n"))
+                 (ashift:GPI (match_operand:GPI 1 "register_operand" "r")
+                             (match_operand 3 "const_int_operand" "n"))))]
+  "UINTVAL (operands[3]) < GET_MODE_BITSIZE (<MODE>mode)
+   && (UINTVAL (operands[3]) + UINTVAL (operands[4])
+       == GET_MODE_BITSIZE (<MODE>mode))"
+  "extr\\t%<w>0, %<w>1, %<w>2, %4"
+  [(set_attr "type" "shift_imm")]
+)
+
 ;; zero_extend version of the above
 (define_insn "*extrsi5_insn_uxtw"
   [(set (match_operand:DI 0 "register_operand" "=r")
@@ -3611,6 +3626,19 @@
   [(set_attr "type" "shift_imm")]
 )
 
+(define_insn "*extrsi5_insn_uxtw_alt"
+  [(set (match_operand:DI 0 "register_operand" "=r")
+       (zero_extend:DI
+        (ior:SI (lshiftrt:SI (match_operand:SI 2 "register_operand" "r")
+                              (match_operand 4 "const_int_operand" "n"))
+                (ashift:SI (match_operand:SI 1 "register_operand" "r")
+                           (match_operand 3 "const_int_operand" "n")))))]
+  "UINTVAL (operands[3]) < 32 &&
+   (UINTVAL (operands[3]) + UINTVAL (operands[4]) == 32)"
+  "extr\\t%w0, %w1, %w2, %4"
+  [(set_attr "type" "shift_imm")]
+)
+
 (define_insn "*ror<mode>3_insn"
   [(set (match_operand:GPI 0 "register_operand" "=r")
        (rotate:GPI (match_operand:GPI 1 "register_operand" "r")