ARC: Improve DImode left shift by a single bit.

This patch improves the code generated for x << 1 (and for x + x) when
X is 64-bit DImode, using the same two instruction code sequence used
for DImode addition.

For the test case:

long long foo(long long x) { return x << 1; }

GCC -O2 currently generates the following code:

foo:    lsr     r2,r0,31
        asl_s   r1,r1,1
        asl_s   r0,r0,1
        j_s.d   [blink]
        or_s    r1,r1,r2

and on CPU without a barrel shifter, i.e. -mcpu=em

foo:	add.f   0,r0,r0
        asl_s   r1,r1
        rlc     r2,0
        asl_s   r0,r0
        j_s.d   [blink]
        or_s    r1,r1,r2

with this patch (both with and without a barrel shifter):

foo:	add.f   r0,r0,r0
        j_s.d   [blink]
        adc     r1,r1,r1

A similar optimization is also applicable to H8300H, that could also use
a two instruction sequence (plus rts) but currently GCC generates 16
instructions (plus an rts) for foo above.

2023-11-03  Roger Sayle  <roger@nextmovesoftware.com>

gcc/ChangeLog
	* config/arc/arc.md (addsi3): Fix GNU-style code formatting.
	(adddi3): Change define_expand to generate a *adddi3.
	(*adddi3): New define_insn_and_split to lower DImode additions
	during the split1 pass (after combine and before reload).
	(ashldi3): New define_expand to (only) generate *ashldi3_cnt1
	for DImode left shifts by a single bit.
	(*ashldi3_cnt1): New define_insn_and_split to lower DImode
	left shifts by one bit to an *adddi3.

gcc/testsuite/ChangeLog
	* gcc.target/arc/adddi3-1.c: New test case.
	* gcc.target/arc/ashldi3-1.c: Likewise.

diff --git a/gcc/config/arc/arc.md b/gcc/config/arc/arc.md
index 96ff62d56d8e8f1cfcc252c0fc79a9af2b0a5596..77029783a2a476b94d3a18d7b2b27ea2f3335f3a 100644 (file)
--- a/gcc/config/arc/arc.md
+++ b/gcc/config/arc/arc.md
@@ -2675,19 +2675,28 @@ archs4x, archs4xd"
        (plus:SI (match_operand:SI 1 "register_operand" "")
                 (match_operand:SI 2 "nonmemory_operand" "")))]
   ""
-  "if (flag_pic && arc_raw_symbolic_reference_mentioned_p (operands[2], false))
-     {
-       operands[2]=force_reg(SImode, operands[2]);
-     }
-  ")
+{
+  if (flag_pic && arc_raw_symbolic_reference_mentioned_p (operands[2], false))
+    operands[2] = force_reg (SImode, operands[2]);
+})
 
 (define_expand "adddi3"
+  [(parallel
+      [(set (match_operand:DI 0 "register_operand" "")
+           (plus:DI (match_operand:DI 1 "register_operand" "")
+                    (match_operand:DI 2 "nonmemory_operand" "")))
+       (clobber (reg:CC CC_REG))])])
+
+(define_insn_and_split "*adddi3"
   [(set (match_operand:DI 0 "register_operand" "")
        (plus:DI (match_operand:DI 1 "register_operand" "")
                 (match_operand:DI 2 "nonmemory_operand" "")))
    (clobber (reg:CC CC_REG))]
-  ""
-  "
+  "arc_pre_reload_split ()"
+  "#"
+  "&& 1"
+  [(const_int 0)]
+{
   rtx l0 = gen_lowpart (SImode, operands[0]);
   rtx h0 = gen_highpart (SImode, operands[0]);
   rtx l1 = gen_lowpart (SImode, operands[1]);
@@ -2719,11 +2728,12 @@ archs4x, archs4xd"
           gen_rtx_LTU (VOIDmode, gen_rtx_REG (CC_Cmode, CC_REG), GEN_INT (0)),
           gen_rtx_SET (h0, plus_constant (SImode, h0, 1))));
       DONE;
-      }
+    }
   emit_insn (gen_add_f (l0, l1, l2));
   emit_insn (gen_adc (h0, h1, h2));
   DONE;
-")
+}
+  [(set_attr "length" "8")])
 
 (define_insn "add_f"
   [(set (reg:CC_C CC_REG)
@@ -3493,6 +3503,33 @@ archs4x, archs4xd"
   [(set_attr "type" "shift")
    (set_attr "length" "16,20")])
 
+;; DImode shifts
+
+(define_expand "ashldi3"
+  [(parallel
+      [(set (match_operand:DI 0 "register_operand")
+           (ashift:DI (match_operand:DI 1 "register_operand")
+                      (match_operand:QI 2 "const_int_operand")))
+       (clobber (reg:CC CC_REG))])]
+  ""
+{
+  if (operands[2] != const1_rtx)
+    FAIL;
+})
+
+(define_insn_and_split "*ashldi3_cnt1"
+  [(set (match_operand:DI 0 "register_operand")
+       (ashift:DI (match_operand:DI 1 "register_operand")
+                  (const_int 1)))
+   (clobber (reg:CC CC_REG))]
+  "arc_pre_reload_split ()"
+  "#"
+  "&& 1"
+  [(parallel [(set (match_dup 0) (plus:DI (match_dup 1) (match_dup 1)))
+             (clobber (reg:CC CC_REG))])]
+  ""
+  [(set_attr "length" "8")])
+
 ;; Rotate instructions.
 
 (define_insn "rotrsi3_insn"

diff --git a/gcc/testsuite/gcc.target/arc/adddi3-1.c b/gcc/testsuite/gcc.target/arc/adddi3-1.c
new file mode 100644 (file)
index 0000000..b3077c3
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arc/adddi3-1.c
@@ -0,0 +1,10 @@
+/* { dg-do compile } */
+/* { dg-options "-O2" } */
+
+long long foo(long long x, long long y)
+{
+  return x + y;
+}
+
+/* { dg-final { scan-assembler "add.f\\s+r0,r0,r2" } } */
+/* { dg-final { scan-assembler "adc\\s+r1,r1,r3" } } */

diff --git a/gcc/testsuite/gcc.target/arc/ashldi3-1.c b/gcc/testsuite/gcc.target/arc/ashldi3-1.c
new file mode 100644 (file)
index 0000000..6fe4ff4
--- /dev/null
+++ b/gcc/testsuite/gcc.target/arc/ashldi3-1.c
@@ -0,0 +1,10 @@
+/* { dg-do compile } */
+/* { dg-options "-O2" } */
+
+long long foo(long long x)
+{
+  return x << 1;
+}
+
+/* { dg-final { scan-assembler "add.f\\s+r0,r0,r0" } } */
+/* { dg-final { scan-assembler "adc\\s+r1,r1,r1" } } */