[PATCH 2/2] ARC: Use intrinsics for __builtin_sub_overflow*()

[Shahab Vahedi <Shahab.Vahedi@synopsys.com>]

This patch covers signed and unsigned subtractions.  The generated code
would be something along these lines:

signed:
  sub.f   r0, r1, r2
  b.v     @label

unsigned:
  sub.f   r0, r1, r2
  b.c     @label

gcc/ChangeLog:

	* config/arc/arc.md (subsi3_v): New insn.
	(subvsi4): New expand.
	(subsi3_c): New insn.
	(usubvsi4): New expand.

gcc/testsuite/ChangeLog:

	* gcc.target/arc/overflow-2.c: New.

Signed-off-by: Shahab Vahedi <shahab@synopsys.com>
---
 gcc/config/arc/arc.md                     | 48 +++++++++++
 gcc/testsuite/gcc.target/arc/overflow-2.c | 97 +++++++++++++++++++++++
 2 files changed, 145 insertions(+)
 create mode 100644 gcc/testsuite/gcc.target/arc/overflow-2.c

diff --git a/gcc/config/arc/arc.md b/gcc/config/arc/arc.md
index 9d011f6b4a9..34e9e1a7f1d 100644
--- a/gcc/config/arc/arc.md
+++ b/gcc/config/arc/arc.md
@@ -2973,6 +2973,54 @@ archs4x, archs4xd"
   (set_attr "cpu_facility" "*,cd,*,*,*,*,*,*,*,*")
   ])
 
+(define_insn "subsi3_v"
+  [(set (match_operand:SI	    0 "register_operand"  "=r,r,r,  r")
+	(minus:SI (match_operand:SI 1 "register_operand"   "r,r,0,  r")
+		  (match_operand:SI 2 "nonmemory_operand"  "r,L,I,C32")))
+   (set (reg:CC_V CC_REG)
+	(compare:CC_V (sign_extend:DI (minus:SI (match_dup 1)
+						(match_dup 2)))
+		      (minus:DI (sign_extend:DI (match_dup 1))
+				(sign_extend:DI (match_dup 2)))))]
+   ""
+   "sub.f\\t%0,%1,%2"
+   [(set_attr "cond"	"set")
+    (set_attr "type"	"compare")
+    (set_attr "length"	"4,4,4,8")])
+
+(define_expand "subvsi4"
+ [(match_operand:SI 0 "register_operand")
+  (match_operand:SI 1 "register_operand")
+  (match_operand:SI 2 "nonmemory_operand")
+  (label_ref (match_operand 3 "" ""))]
+  ""
+  "emit_insn (gen_subsi3_v (operands[0], operands[1], operands[2]));
+   arc_gen_unlikely_cbranch (NE, CC_Vmode, operands[3]);
+   DONE;")
+
+(define_insn "subsi3_c"
+  [(set (match_operand:SI	    0 "register_operand"  "=r,r,r,  r")
+	(minus:SI (match_operand:SI 1 "register_operand"   "r,r,0,  r")
+		  (match_operand:SI 2 "nonmemory_operand"  "r,L,I,C32")))
+   (set (reg:CC_C CC_REG)
+	(compare:CC_C (match_dup 1)
+		      (match_dup 2)))]
+   ""
+   "sub.f\\t%0,%1,%2"
+   [(set_attr "cond"	"set")
+    (set_attr "type"	"compare")
+    (set_attr "length"	"4,4,4,8")])
+
+(define_expand "usubvsi4"
+  [(match_operand:SI 0 "register_operand")
+   (match_operand:SI 1 "register_operand")
+   (match_operand:SI 2 "nonmemory_operand")
+   (label_ref (match_operand 3 "" ""))]
+   ""
+   "emit_insn (gen_subsi3_c (operands[0], operands[1], operands[2]));
+    arc_gen_unlikely_cbranch (LTU, CC_Cmode, operands[3]);
+    DONE;")
+
 (define_expand "subdi3"
   [(set (match_operand:DI 0 "register_operand" "")
 	(minus:DI (match_operand:DI 1 "register_operand" "")
diff --git a/gcc/testsuite/gcc.target/arc/overflow-2.c b/gcc/testsuite/gcc.target/arc/overflow-2.c
new file mode 100644
index 00000000000..b4de8c03b22
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arc/overflow-2.c
@@ -0,0 +1,97 @@
+/* { dg-do compile } */
+/* { dg-options "-O1" } */
+
+#include <stdbool.h>
+#include <stdint.h>
+
+/*
+ * sub.f  r0,r0,r1
+ * st_s   r0,[r2]
+ * mov_s  r0,1
+ * j_s.d  [blink]
+ * mov.nv r0,0
+ */
+bool sub_overflow (int32_t a, int32_t b, int32_t *res)
+{
+  return __builtin_sub_overflow (a, b, res);
+}
+
+/*
+ * sub.f  r0,r0,-1234
+ * st_s   r0,[r1]
+ * mov_s  r0,1
+ * j_s.d  [blink]
+ * mov.nv r0,0
+ */
+bool subi_overflow (int32_t a, int32_t *res)
+{
+  return __builtin_sub_overflow (a, -1234, res);
+}
+
+/*
+ * sub.f  r3,r0,r1
+ * st_s   r3,[r2]
+ * j_s.d  [blink]
+ * setlo  r0,r0,r1
+ */
+bool usub_overflow (uint32_t a, uint32_t b, uint32_t *res)
+{
+  return __builtin_sub_overflow (a, b, res);
+}
+
+/*
+ * sub.f  r2,r0,4321
+ * seths  r0,4320,r0
+ * j_s.d  [blink]
+ * st_s   r2,[r1]
+ */
+bool usubi_overflow (uint32_t a, uint32_t *res)
+{
+  return __builtin_sub_overflow (a, 4321, res);
+}
+
+/*
+ * sub.f  r0,r0,r1
+ * mov_s  r0,1
+ * j_s.d  [blink]
+ * mov.nv r0,0
+ */
+bool sub_overflow_p (int32_t a, int32_t b, int32_t res)
+{
+  return __builtin_sub_overflow_p (a, b, res);
+}
+
+/*
+ * sub.f  r0,r0,-1000
+ * mov_s  r0,1
+ * j_s.d  [blink]
+ * mov.nv r0,0
+ */
+bool subi_overflow_p (int32_t a, int32_t res)
+{
+  return __builtin_sub_overflow_p (a, -1000, res);
+}
+
+/*
+ * j_s.d  [blink]
+ * setlo  r0,r0,r1
+ */
+bool usub_overflow_p (uint32_t a, uint32_t b, uint32_t res)
+{
+  return __builtin_sub_overflow_p (a, b, res);
+}
+
+/*
+ * seths  r0,1999,r0
+ * j_s.d  [blink]
+ */
+bool usubi_overflow_p (uint32_t a, uint32_t res)
+{
+  return __builtin_sub_overflow_p (a, 2000, res);
+}
+
+/* { dg-final { scan-assembler-times "sub.f\\s\+"   6 } } */
+/* { dg-final { scan-assembler-times "mov\.nv\\s\+" 4 } } */
+/* { dg-final { scan-assembler-times "setlo\\s\+"   2 } } */
+/* { dg-final { scan-assembler-times "seths\\s\+"   2 } } */
+/* { dg-final { scan-assembler-not   "cmp" } } */
-- 
2.42.0