[SH, committeð] PR 60884 - reduce code size of inlined strlen

[Oleg Endo]

Hi,

The attached patch reduces the code size of inlined builtin strlen
functions on SH a little bit.
Tested on r210083 with
make -k check RUNTESTFLAGS="--target_board=sh-sim
\{-m2/-ml,-m2/-mb,-m2a/-mb,-m4/-ml,-m4/-mb,-m4a/-ml,-m4a/-mb}"

and no new failures, except for gcc.target/sh/pr53976-1.c on SH2 and
SH2A.  Using builtin strlen for checking the sett/clrt optimization pass
was a bit inappropriate in this case.

Committed as r210187.

Cheers,
Oleg

gcc/ChangeLog:
        PR target/60884
        * config/sh/sh-mem.cc (sh_expand_strlen): Use loop when emitting
        unrolled byte insns.  Emit address increments after move insns.

gcc/testsuite/ChangeLog:
        PR target/60884
        * gcc.target/sh/pr53976-1.c (test_02): Remove inappropriate test case.
        (test_03): Rename to test_02.

Index: gcc/testsuite/gcc.target/sh/pr53976-1.c
===================================================================
--- gcc/testsuite/gcc.target/sh/pr53976-1.c	(revision 210185)
+++ gcc/testsuite/gcc.target/sh/pr53976-1.c	(working copy)
@@ -24,15 +24,8 @@
 }
 
 int
-test_02 (const char* a)
+test_02 (int a, int b, int c, int d)
 {
-  /* Must not see a sett after the inlined strlen.  */
-  return __builtin_strlen (a);
-}
-
-int
-test_03 (int a, int b, int c, int d)
-{
   /* One of the blocks should have a sett and the other one should not.  */
   if (d > 4)
     return a + b + 1;
Index: gcc/config/sh/sh-mem.cc
===================================================================
--- gcc/config/sh/sh-mem.cc	(revision 210185)
+++ gcc/config/sh/sh-mem.cc	(working copy)
@@ -568,7 +568,7 @@
 
   addr1 = adjust_automodify_address (addr1, SImode, current_addr, 0);
 
-  /*start long loop.  */
+  /* start long loop.  */
   emit_label (L_loop_long);
 
   /* tmp1 is aligned, OK to load.  */
@@ -589,29 +589,15 @@
   addr1 = adjust_address (addr1, QImode, 0);
 
   /* unroll remaining bytes.  */
-  emit_insn (gen_extendqisi2 (tmp1, addr1));
-  emit_insn (gen_cmpeqsi_t (tmp1, const0_rtx));
-  jump = emit_jump_insn (gen_branch_true (L_return));
-  add_int_reg_note (jump, REG_BR_PROB, prob_likely);
+  for (int i = 0; i < 4; ++i)
+    {
+      emit_insn (gen_extendqisi2 (tmp1, addr1));
+      emit_move_insn (current_addr, plus_constant (Pmode, current_addr, 1));
+      emit_insn (gen_cmpeqsi_t (tmp1, const0_rtx));
+      jump = emit_jump_insn (gen_branch_true (L_return));
+      add_int_reg_note (jump, REG_BR_PROB, prob_likely);
+    }
 
-  emit_move_insn (current_addr, plus_constant (Pmode, current_addr, 1));
-
-  emit_insn (gen_extendqisi2 (tmp1, addr1));
-  emit_insn (gen_cmpeqsi_t (tmp1, const0_rtx));
-  jump = emit_jump_insn (gen_branch_true (L_return));
-  add_int_reg_note (jump, REG_BR_PROB, prob_likely);
-
-  emit_move_insn (current_addr, plus_constant (Pmode, current_addr, 1));
-
-  emit_insn (gen_extendqisi2 (tmp1, addr1));
-  emit_insn (gen_cmpeqsi_t (tmp1, const0_rtx));
-  jump = emit_jump_insn (gen_branch_true (L_return));
-  add_int_reg_note (jump, REG_BR_PROB, prob_likely);
-
-  emit_move_insn (current_addr, plus_constant (Pmode, current_addr, 1));
-
-  emit_insn (gen_extendqisi2 (tmp1, addr1));
-  jump = emit_jump_insn (gen_jump_compact (L_return));
   emit_barrier_after (jump);
 
   /* start byte loop.  */
@@ -626,10 +612,9 @@
 
   /* end loop.  */
 
-  emit_insn (gen_addsi3 (start_addr, start_addr, GEN_INT (1)));
-
   emit_label (L_return);
 
+  emit_insn (gen_addsi3 (start_addr, start_addr, GEN_INT (1)));
   emit_insn (gen_subsi3 (operands[0], current_addr, start_addr));
 
   return true;