Hello,
This patch inlines strlen when optimizing for speed.
A strlen body is now inlined as:
mov r4,r0
tst #3,r0
bf/s .L6
mov r4,r1
mov #0,r3
.L4:
mov.l @r1+,r2
cmp/str r3,r2
bf .L4
add #-4,r1
.L6:
mov.b @r1+,r2
tst r2,r2
bf/s .L6
sett
mov r1,r0
rts
subc r4,r0
A few percent performance improvement here and there for regexp based
benchmarks, but worth to highlight is a 70% speedup for eembc
networking/qos that now nicely combines sequences like !strncmp(*av,
"any", strlen(*av))
No regressions for sh-none-elf. OK for trunk ?
Many thanks
Christian
2013-11-05 Christian Bruel <christian.br...@st.com>
* gcc/config/sh/sh-mem.cc (sh_expand_strlen): New function.
* gcc/config/sh/sh-protos.h (sh_expand_strlen): Declare.
* gcc/config/sh/sh.md (strlensi): New pattern.
(UNSPEC_BUILTIN_STRLEN): Define.
2013-11-05 Christian Bruel <christian.br...@st.com>
* gcc.target/sh/strlen.c: New test.
diff --exclude='*~' --exclude=.svn -ruN gcc/config/sh/sh.md ../../gnu_trunk.test/gcc/gcc/config/sh/sh.md
--- gcc/config/sh/sh.md 2013-11-05 12:28:38.000000000 +0100
+++ ../../gnu_trunk.test/gcc/gcc/config/sh/sh.md 2013-11-05 11:16:00.000000000 +0100
@@ -161,6 +161,9 @@
;; (unspec [OFFSET ANCHOR] UNSPEC_PCREL_SYMOFF) == OFFSET - (ANCHOR - .).
(UNSPEC_PCREL_SYMOFF 46)
+ ;; Misc builtins
+ (UNSPEC_BUILTIN_STRLEN 47)
+
;; These are used with unspec_volatile.
(UNSPECV_BLOCKAGE 0)
(UNSPECV_ALIGN 1)
@@ -12081,6 +12084,20 @@
FAIL;
})
+(define_expand "strlensi"
+ [(set (match_operand:SI 0 "register_operand")
+ (unspec:SI [(match_operand:BLK 1 "memory_operand")
+ (match_operand:SI 2 "immediate_operand")
+ (match_operand:SI 3 "immediate_operand")]
+ UNSPEC_BUILTIN_STRLEN))]
+ "TARGET_SH1 && optimize"
+{
+ if (! optimize_insn_for_size_p () && sh_expand_strlen (operands))
+ DONE;
+ else
+ FAIL;
+})
+
;; -------------------------------------------------------------------------
;; Floating point instructions.
diff --exclude='*~' --exclude=.svn -ruN gcc/config/sh/sh-mem.cc ../../gnu_trunk.test/gcc/gcc/config/sh/sh-mem.cc
--- gcc/config/sh/sh-mem.cc 2013-11-05 12:30:33.000000000 +0100
+++ ../../gnu_trunk.test/gcc/gcc/config/sh/sh-mem.cc 2013-11-04 15:34:05.000000000 +0100
@@ -469,3 +469,83 @@
return true;
}
+
+/* Emit code to perform a strlen
+
+ OPERANDS[0] is the destination.
+ OPERANDS[1] is the string.
+ OPERANDS[2] is the char to search.
+ OPERANDS[3] is the alignment. */
+bool
+sh_expand_strlen (rtx *operands)
+{
+ rtx addr1 = operands[1];
+ rtx start_addr = copy_addr_to_reg (XEXP (addr1, 0));
+ rtx end_addr = gen_reg_rtx (Pmode);
+ rtx tmp0 = gen_reg_rtx (SImode);
+ rtx tmp1 = gen_reg_rtx (SImode);
+ rtx L_return = gen_label_rtx ();
+ rtx L_loop_byte = gen_label_rtx ();
+
+ rtx jump;
+ rtx L_loop_long = gen_label_rtx ();
+ rtx L_end_loop_long = gen_label_rtx ();
+
+ int align = INTVAL (operands[3]);
+
+ emit_move_insn (operands[0], GEN_INT (-1));
+
+ /* remember start of string. */
+ emit_move_insn (end_addr, start_addr);
+
+ if (align < 4)
+ {
+ emit_insn (gen_tstsi_t (GEN_INT (3), start_addr));
+ jump = emit_jump_insn (gen_branch_false (L_loop_byte));
+ add_int_reg_note (jump, REG_BR_PROB, prob_likely);
+ }
+
+ emit_move_insn (tmp0, operands[2]);
+
+ addr1 = adjust_automodify_address (addr1, SImode, start_addr, 0);
+
+ /*start long loop. */
+ emit_label (L_loop_long);
+
+ /* tmp1 is aligned, OK to load. */
+ emit_move_insn (tmp1, addr1);
+ emit_move_insn (start_addr, plus_constant (Pmode, start_addr, 4));
+
+ /* Is there a 0 byte ? */
+ emit_insn (gen_cmpstr_t (tmp0, tmp1));
+
+ jump = emit_jump_insn (gen_branch_false (L_loop_long));
+ add_int_reg_note (jump, REG_BR_PROB, prob_likely);
+ /* end loop. */
+
+ emit_label (L_end_loop_long);
+
+ emit_move_insn (start_addr, plus_constant (Pmode, start_addr, -4));
+
+ /* start byte loop. */
+ addr1 = adjust_address (addr1, QImode, 0);
+
+ emit_label (L_loop_byte);
+
+ emit_insn (gen_extendqisi2 (tmp1, addr1));
+ emit_move_insn (start_addr, plus_constant (Pmode, start_addr, 1));
+
+ emit_insn (gen_cmpeqsi_t (tmp1, const0_rtx));
+ jump = emit_jump_insn (gen_branch_false (L_loop_byte));
+ add_int_reg_note (jump, REG_BR_PROB, prob_likely);
+
+ /* end loop. */
+
+ emit_label (L_return);
+
+ emit_insn (gen_addsi3 (end_addr, end_addr, GEN_INT (1)));
+
+ emit_insn (gen_subsi3 (operands[0], start_addr, end_addr));
+
+ return true;
+}
diff --exclude='*~' --exclude=.svn -ruN gcc/config/sh/sh-protos.h ../../gnu_trunk.test/gcc/gcc/config/sh/sh-protos.h
--- gcc/config/sh/sh-protos.h 2013-11-05 12:47:44.000000000 +0100
+++ ../../gnu_trunk.test/gcc/gcc/config/sh/sh-protos.h 2013-11-05 10:14:48.000000000 +0100
@@ -118,6 +118,7 @@
extern void prepare_move_operands (rtx[], enum machine_mode mode);
extern bool sh_expand_cmpstr (rtx *);
extern bool sh_expand_cmpnstr (rtx *);
+extern bool sh_expand_strlen (rtx *);
extern enum rtx_code prepare_cbranch_operands (rtx *, enum machine_mode mode,
enum rtx_code comparison);
extern void expand_cbranchsi4 (rtx *operands, enum rtx_code comparison, int);
diff --exclude='*~' --exclude=.svn -ruN gcc/testsuite/ChangeLog ../../gnu_trunk.test/gcc/gcc/testsuite/ChangeLog
diff --exclude='*~' --exclude=.svn -ruN gcc/testsuite/gcc.target/sh/strlen.c ../../gnu_trunk.test/gcc/gcc/testsuite/gcc.target/sh/strlen.c
--- gcc/testsuite/gcc.target/sh/strlen.c 1970-01-01 01:00:00.000000000 +0100
+++ ../../gnu_trunk.test/gcc/gcc/testsuite/gcc.target/sh/strlen.c 2013-11-05 09:45:43.000000000 +0100
@@ -0,0 +1,19 @@
+/* Check that the __builtin_strlen function is inlined with cmp/str
+ when optimizing for speed. */
+/* { dg-do compile { target "sh*-*-*" } } */
+/* { dg-options "-O2" } */
+/* { dg-skip-if "" { "sh*-*-*" } { "-m5*" } { "" } } */
+/* { dg-final { scan-assembler-not "jmp" } } */
+/* { dg-final { scan-assembler-times "cmp/str" 2 } } */
+/* { dg-final { scan-assembler-times "tst\t#3" 1 } } */
+
+test00 (const char *s1)
+{
+ return __builtin_strlen (s1);
+}
+
+/* Check that no test for alignment is needed. */
+test03(const char *s1)
+{
+ return __builtin_strlen (__builtin_assume_aligned (s1, 4));
+}
