[arm] Early split addvdi4

This patch adds early splitting for addvdi4; it's very similar to the
uaddvdi4 splitter, but the details are just different enough in
places, especially for the patterns that match the splitting, where we
have to compare against the non-widened version to detect if overflow
occurred.

I've also added a testcase to the testsuite for a couple of constants
that caught me out during the development of this patch.  They're
probably arm-specific values, but the test is generic enough that I've
included it for all targets.

[gcc]
	* config/arm/arm.c (arm_select_cc_mode): Allow either the first
	or second operand of the PLUS inside a DImode equality test to be
	sign-extend when selecting CC_Vmode.
	* config/arm/arm.md (addvdi4): Early-split the operation into SImode
	instructions.
	(addsi3_cin_vout_reg, addsi3_cin_vout_imm, addsi3_cin_vout_0): New
	expand patterns.
	(addsi3_cin_vout_reg_insn, addsi3_cin_vout_imm_insn): New patterns.
	(addsi3_cin_vout_0): Likewise.
	(adddi3_compareV): Delete.

[gcc/testsuite]
	* gcc.dg/builtin-arith-overflow-3.c: New test.

From-SVN: r277186

5 files changed, 220 insertions, 22 deletions

diff --git a/gcc/ChangeLog b/gcc/ChangeLog
index 4a5a139..8275411 100644
--- a/gcc/ChangeLog
+++ b/gcc/ChangeLog
@@ -1,5 +1,18 @@
 2019-10-18  Richard Earnshaw  <rearnsha@arm.com>
 
+	* config/arm/arm.c (arm_select_cc_mode): Allow either the first
+	or second operand of the PLUS inside a DImode equality test to be
+	sign-extend when selecting CC_Vmode.
+	* config/arm/arm.md (addvdi4): Early-split the operation into SImode
+	instructions.
+	(addsi3_cin_vout_reg, addsi3_cin_vout_imm, addsi3_cin_vout_0): New
+	expand patterns.
+	(addsi3_cin_vout_reg_insn, addsi3_cin_vout_imm_insn): New patterns.
+	(addsi3_cin_vout_0): Likewise.
+	(adddi3_compareV): Delete.
+
+2019-10-18  Richard Earnshaw  <rearnsha@arm.com>
+
 	* config/arm/arm.md (addsi3_compareV_reg_nosum): New insn.
 	(addsi3_compareV_imm_nosum): New insn.  Also add peephole2 patterns
 	to transform this back into the summation version when that leads
diff --git a/gcc/config/arm/arm.c b/gcc/config/arm/arm.c
index ba23970..fe240b2 100644
--- a/gcc/config/arm/arm.c
+++ b/gcc/config/arm/arm.c
@@ -15414,7 +15414,8 @@ arm_select_cc_mode (enum rtx_code op, rtx x, rtx y)
   if (GET_MODE (x) == DImode
       && (op == EQ || op == NE)
       && GET_CODE (x) == PLUS
-      && GET_CODE (XEXP (x, 0)) == SIGN_EXTEND
+      && (GET_CODE (XEXP (x, 0)) == SIGN_EXTEND
+	  || GET_CODE (XEXP (x, 1)) == SIGN_EXTEND)
       && GET_CODE (y) == SIGN_EXTEND
       && GET_CODE (XEXP (y, 0)) == PLUS)
     return CC_Vmode;
diff --git a/gcc/config/arm/arm.md b/gcc/config/arm/arm.md
index be002f7..e9e0ca9 100644
--- a/gcc/config/arm/arm.md
+++ b/gcc/config/arm/arm.md
@@ -505,18 +505,173 @@
 })
 
 (define_expand "addvdi4"
-  [(match_operand:DI 0 "register_operand")
-   (match_operand:DI 1 "register_operand")
-   (match_operand:DI 2 "register_operand")
+  [(match_operand:DI 0 "s_register_operand")
+   (match_operand:DI 1 "s_register_operand")
+   (match_operand:DI 2 "reg_or_int_operand")
    (match_operand 3 "")]
   "TARGET_32BIT"
 {
-  emit_insn (gen_adddi3_compareV (operands[0], operands[1], operands[2]));
-  arm_gen_unlikely_cbranch (NE, CC_Vmode, operands[3]);
+  rtx lo_result, hi_result;
+  rtx lo_op1, hi_op1, lo_op2, hi_op2;
+  arm_decompose_di_binop (operands[1], operands[2], &lo_op1, &hi_op1,
+			  &lo_op2, &hi_op2);
+  lo_result = gen_lowpart (SImode, operands[0]);
+  hi_result = gen_highpart (SImode, operands[0]);
+
+  if (lo_op2 == const0_rtx)
+    {
+      emit_move_insn (lo_result, lo_op1);
+      if (!arm_add_operand (hi_op2, SImode))
+	hi_op2 = force_reg (SImode, hi_op2);
+
+      emit_insn (gen_addvsi4 (hi_result, hi_op1, hi_op2, operands[3]));
+    }
+  else
+    {
+      if (!arm_add_operand (lo_op2, SImode))
+	lo_op2 = force_reg (SImode, lo_op2);
+      if (!arm_not_operand (hi_op2, SImode))
+	hi_op2 = force_reg (SImode, hi_op2);
+
+      emit_insn (gen_addsi3_compare_op1 (lo_result, lo_op1, lo_op2));
+
+      if (hi_op2 == const0_rtx)
+        emit_insn (gen_addsi3_cin_vout_0 (hi_result, hi_op1));
+      else if (CONST_INT_P (hi_op2))
+        emit_insn (gen_addsi3_cin_vout_imm (hi_result, hi_op1, hi_op2));
+      else
+        emit_insn (gen_addsi3_cin_vout_reg (hi_result, hi_op1, hi_op2));
+
+      arm_gen_unlikely_cbranch (NE, CC_Vmode, operands[3]);
+    }
 
   DONE;
 })
 
+(define_expand "addsi3_cin_vout_reg"
+  [(parallel
+    [(set (match_dup 3)
+	  (compare:CC_V
+	   (plus:DI
+	    (plus:DI (match_dup 4)
+		     (sign_extend:DI (match_operand:SI 1 "s_register_operand")))
+	    (sign_extend:DI (match_operand:SI 2 "s_register_operand")))
+	   (sign_extend:DI (plus:SI (plus:SI (match_dup 5) (match_dup 1))
+				    (match_dup 2)))))
+     (set (match_operand:SI 0 "s_register_operand")
+	  (plus:SI (plus:SI (match_dup 5) (match_dup 1))
+		   (match_dup 2)))])]
+  "TARGET_32BIT"
+  {
+    operands[3] = gen_rtx_REG (CC_Vmode, CC_REGNUM);
+    rtx ccin = gen_rtx_REG (CC_Cmode, CC_REGNUM);
+    operands[4] = gen_rtx_LTU (DImode, ccin, const0_rtx);
+    operands[5] = gen_rtx_LTU (SImode, ccin, const0_rtx);
+  }
+)
+
+(define_insn "*addsi3_cin_vout_reg_insn"
+  [(set (reg:CC_V CC_REGNUM)
+	(compare:CC_V
+	 (plus:DI
+	  (plus:DI
+	   (match_operand:DI 3 "arm_carry_operation" "")
+	   (sign_extend:DI (match_operand:SI 1 "s_register_operand" "%0,r")))
+	  (sign_extend:DI (match_operand:SI 2 "s_register_operand" "l,r")))
+	 (sign_extend:DI
+	  (plus:SI (plus:SI (match_operand:SI 4 "arm_carry_operation" "")
+			    (match_dup 1))
+		   (match_dup 2)))))
+   (set (match_operand:SI 0 "s_register_operand" "=l,r")
+	(plus:SI (plus:SI (match_dup 4) (match_dup 1))
+		 (match_dup 2)))]
+  "TARGET_32BIT"
+  "@
+   adcs%?\\t%0, %0, %2
+   adcs%?\\t%0, %1, %2"
+  [(set_attr "type" "alus_sreg")
+   (set_attr "arch" "t2,*")
+   (set_attr "length" "2,4")]
+)
+
+(define_expand "addsi3_cin_vout_imm"
+  [(parallel
+    [(set (match_dup 3)
+	  (compare:CC_V
+	   (plus:DI
+	    (plus:DI (match_dup 4)
+		     (sign_extend:DI (match_operand:SI 1 "s_register_operand")))
+	    (match_dup 2))
+	   (sign_extend:DI (plus:SI (plus:SI (match_dup 5) (match_dup 1))
+				    (match_dup 2)))))
+     (set (match_operand:SI 0 "s_register_operand")
+	  (plus:SI (plus:SI (match_dup 5) (match_dup 1))
+		   (match_operand 2 "arm_adcimm_operand")))])]
+  "TARGET_32BIT"
+  {
+    operands[3] = gen_rtx_REG (CC_Vmode, CC_REGNUM);
+    rtx ccin = gen_rtx_REG (CC_Cmode, CC_REGNUM);
+    operands[4] = gen_rtx_LTU (DImode, ccin, const0_rtx);
+    operands[5] = gen_rtx_LTU (SImode, ccin, const0_rtx);
+  }
+)
+
+(define_insn "*addsi3_cin_vout_imm_insn"
+  [(set (reg:CC_V CC_REGNUM)
+	(compare:CC_V
+	 (plus:DI
+	  (plus:DI
+	   (match_operand:DI 3 "arm_carry_operation" "")
+	   (sign_extend:DI (match_operand:SI 1 "s_register_operand" "r,r")))
+	  (match_operand 2 "arm_adcimm_operand" "I,K"))
+	 (sign_extend:DI
+	  (plus:SI (plus:SI (match_operand:SI 4 "arm_carry_operation" "")
+			    (match_dup 1))
+		   (match_dup 2)))))
+   (set (match_operand:SI 0 "s_register_operand" "=r,r")
+	(plus:SI (plus:SI (match_dup 4) (match_dup 1))
+		 (match_dup 2)))]
+  "TARGET_32BIT"
+  "@
+   adcs%?\\t%0, %1, %2
+   sbcs%?\\t%0, %1, #%B2"
+  [(set_attr "type" "alus_imm")]
+)
+
+(define_expand "addsi3_cin_vout_0"
+  [(parallel
+    [(set (match_dup 2)
+	  (compare:CC_V
+	   (plus:DI (match_dup 3)
+		    (sign_extend:DI (match_operand:SI 1 "s_register_operand")))
+	   (sign_extend:DI (plus:SI (match_dup 4) (match_dup 1)))))
+     (set (match_operand:SI 0 "s_register_operand")
+	  (plus:SI (match_dup 4) (match_dup 1)))])]
+  "TARGET_32BIT"
+  {
+    operands[2] = gen_rtx_REG (CC_Vmode, CC_REGNUM);
+    rtx ccin = gen_rtx_REG (CC_Cmode, CC_REGNUM);
+    operands[3] = gen_rtx_LTU (DImode, ccin, const0_rtx);
+    operands[4] = gen_rtx_LTU (SImode, ccin, const0_rtx);
+  }
+)
+
+(define_insn "*addsi3_cin_vout_0_insn"
+  [(set (reg:CC_V CC_REGNUM)
+	(compare:CC_V
+	 (plus:DI
+	  (match_operand:DI 2 "arm_carry_operation" "")
+	  (sign_extend:DI (match_operand:SI 1 "s_register_operand" "r")))
+	 (sign_extend:DI (plus:SI
+			  (match_operand:SI 3 "arm_carry_operation" "")
+			  (match_dup 1)))))
+   (set (match_operand:SI 0 "s_register_operand" "=r")
+	(plus:SI (match_dup 3) (match_dup 1)))]
+  "TARGET_32BIT"
+  "adcs%?\\t%0, %1, #0"
+  [(set_attr "type" "alus_imm")]
+)
+
 (define_expand "uaddvsi4"
   [(match_operand:SI 0 "s_register_operand")
    (match_operand:SI 1 "s_register_operand")
@@ -770,22 +925,6 @@
  ]
 )
 
-(define_insn "adddi3_compareV"
-  [(set (reg:CC_V CC_REGNUM)
-	(ne:CC_V
-	  (plus:TI
-	    (sign_extend:TI (match_operand:DI 1 "s_register_operand" "r"))
-	    (sign_extend:TI (match_operand:DI 2 "s_register_operand" "r")))
-	  (sign_extend:TI (plus:DI (match_dup 1) (match_dup 2)))))
-   (set (match_operand:DI 0 "s_register_operand" "=&r")
-	(plus:DI (match_dup 1) (match_dup 2)))]
-  "TARGET_32BIT"
-  "adds\\t%Q0, %Q1, %Q2;adcs\\t%R0, %R1, %R2"
- [(set_attr "conds" "set")
-   (set_attr "length" "8")
-   (set_attr "type" "multiple")]
-)
-
 (define_insn "addsi3_compareV_reg"
   [(set (reg:CC_V CC_REGNUM)
 	(compare:CC_V
diff --git a/gcc/testsuite/ChangeLog b/gcc/testsuite/ChangeLog
index d5d934d..4267ac4 100644
--- a/gcc/testsuite/ChangeLog
+++ b/gcc/testsuite/ChangeLog
@@ -1,5 +1,9 @@
 2019-10-18  Richard Earnshaw  <rearnsha@arm.com>
 
+	* gcc.dg/builtin-arith-overflow-3.c: New test.
+
+2019-10-18  Richard Earnshaw  <rearnsha@arm.com>
+
 	* gcc.target/arm/negdi-3.c: Remove XFAIL markers.
 
 2019-10-18  Richard Earnshaw  <rearnsha@arm.com>
diff --git a/gcc/testsuite/gcc.dg/builtin-arith-overflow-3.c b/gcc/testsuite/gcc.dg/builtin-arith-overflow-3.c
new file mode 100644
index 0000000..6feae1e
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/builtin-arith-overflow-3.c
@@ -0,0 +1,41 @@
+/* { dg-do run } */
+/* { dg-options "-O2" } */
+
+static int cnt = 0;
+
+#define LL_MIN ((long long)(-__LONG_LONG_MAX__ - 1))
+
+#define SC1 (LL_MIN + 5)
+#define UC1 ((1ULL << (__LONG_LONG_WIDTH__ - 1)) | 5ULL)
+#define UC2 (~UC1)
+
+long long __attribute__ ((noinline, noclone))
+f1 (long long a)
+{
+  long long x;
+  if (__builtin_add_overflow (a, SC1, &x)) cnt++;
+  return x;
+}
+
+unsigned long long __attribute__ ((noinline, noclone))
+f2 (unsigned long long a)
+{
+  unsigned long long x;
+  if (__builtin_add_overflow (a, UC1, &x))
+    cnt++;
+  return x;
+}
+
+int main ()
+{
+  if (f1 (-5) != LL_MIN) __builtin_abort ();
+  if (cnt != 0) __builtin_abort ();
+  f1 (-6);
+  if (cnt != 1) __builtin_abort ();
+  cnt = 0;
+  if (f2 (UC2) != ~0ULL) __builtin_abort ();
+  if (cnt != 0) __builtin_abort ();
+  if (f2 (UC2 + 1) != 0) __builtin_abort ();
+  if (cnt != 1) __builtin_abort ();
+  return 0;
+}