Message ID | 20160428154237.GS26501@tucnak.zalov.cz |
---|---|
State | New |
Headers | show |
On Thu, Apr 28, 2016 at 5:42 PM, Jakub Jelinek <jakub@redhat.com> wrote: > Hi! > > Optimizing atomic_fetch_add followed by comparison into just testing > the flags of the lock; sub is handled by a peephole2, which works usually > fine, except that for -Os we have another peephole2 that transforms > movl $-1, %reg into orl $-1, %reg and that causes the above mentioned > peephole2 not to trigger anymore. > > Fixed by adding a peephole2 even for this case. > > Bootstrapped/regtested on x86_64-linux and i686-linux, ok for trunk? > > 2016-04-28 Jakub Jelinek <jakub@redhat.com> > > PR target/70821 > * config/i386/sync.md (define_peephole2 *atomic_fetch_add_cmp<mode>): > Add new peephole2 where the first insn is *mov<mode>_or instead of > *mov<mode>_internal. > > * gcc.target/i386/pr70821.c: New test. OK. Thanks, Uros. > > --- gcc/config/i386/sync.md.jj 2016-01-04 14:55:56.000000000 +0100 > +++ gcc/config/i386/sync.md 2016-04-28 09:40:28.265764880 +0200 > @@ -467,6 +467,36 @@ (define_peephole2 > (plus:SWI (match_dup 1) > (match_dup 2)))])]) > > +;; Likewise, but for the -Os special case of *mov<mode>_or. > +(define_peephole2 > + [(parallel [(set (match_operand:SWI 0 "register_operand") > + (match_operand:SWI 2 "constm1_operand")) > + (clobber (reg:CC FLAGS_REG))]) > + (parallel [(set (match_dup 0) > + (unspec_volatile:SWI > + [(match_operand:SWI 1 "memory_operand") > + (match_operand:SI 4 "const_int_operand")] > + UNSPECV_XCHG)) > + (set (match_dup 1) > + (plus:SWI (match_dup 1) > + (match_dup 0))) > + (clobber (reg:CC FLAGS_REG))]) > + (set (reg:CCZ FLAGS_REG) > + (compare:CCZ (match_dup 0) > + (match_operand:SWI 3 "const_int_operand")))] > + "peep2_reg_dead_p (3, operands[0]) > + && (unsigned HOST_WIDE_INT) INTVAL (operands[2]) > + == -(unsigned HOST_WIDE_INT) INTVAL (operands[3]) > + && !reg_overlap_mentioned_p (operands[0], operands[1])" > + [(parallel [(set (reg:CCZ FLAGS_REG) > + (compare:CCZ > + (unspec_volatile:SWI [(match_dup 1) (match_dup 4)] > + UNSPECV_XCHG) > + (match_dup 3))) > + (set (match_dup 1) > + (plus:SWI (match_dup 1) > + (match_dup 2)))])]) > + > (define_insn "*atomic_fetch_add_cmp<mode>" > [(set (reg:CCZ FLAGS_REG) > (compare:CCZ > --- gcc/testsuite/gcc.target/i386/pr70821.c.jj 2016-04-28 09:56:06.239893613 +0200 > +++ gcc/testsuite/gcc.target/i386/pr70821.c 2016-04-28 09:55:23.000000000 +0200 > @@ -0,0 +1,16 @@ > +/* PR target/70821 */ > +/* { dg-do compile } */ > +/* { dg-options "-Os" } */ > +/* { dg-additional-options "-march=i686" { target ia32 } } */ > + > +void bar (void); > + > +void > +foo (int *p) > +{ > + if (__atomic_sub_fetch (p, 1, __ATOMIC_SEQ_CST)) > + bar (); > +} > + > +/* { dg-final { scan-assembler "lock;? dec" } } */ > +/* { dg-final { scan-assembler-not "lock;? xadd" } } */ > > Jakub
--- gcc/config/i386/sync.md.jj 2016-01-04 14:55:56.000000000 +0100 +++ gcc/config/i386/sync.md 2016-04-28 09:40:28.265764880 +0200 @@ -467,6 +467,36 @@ (define_peephole2 (plus:SWI (match_dup 1) (match_dup 2)))])]) +;; Likewise, but for the -Os special case of *mov<mode>_or. +(define_peephole2 + [(parallel [(set (match_operand:SWI 0 "register_operand") + (match_operand:SWI 2 "constm1_operand")) + (clobber (reg:CC FLAGS_REG))]) + (parallel [(set (match_dup 0) + (unspec_volatile:SWI + [(match_operand:SWI 1 "memory_operand") + (match_operand:SI 4 "const_int_operand")] + UNSPECV_XCHG)) + (set (match_dup 1) + (plus:SWI (match_dup 1) + (match_dup 0))) + (clobber (reg:CC FLAGS_REG))]) + (set (reg:CCZ FLAGS_REG) + (compare:CCZ (match_dup 0) + (match_operand:SWI 3 "const_int_operand")))] + "peep2_reg_dead_p (3, operands[0]) + && (unsigned HOST_WIDE_INT) INTVAL (operands[2]) + == -(unsigned HOST_WIDE_INT) INTVAL (operands[3]) + && !reg_overlap_mentioned_p (operands[0], operands[1])" + [(parallel [(set (reg:CCZ FLAGS_REG) + (compare:CCZ + (unspec_volatile:SWI [(match_dup 1) (match_dup 4)] + UNSPECV_XCHG) + (match_dup 3))) + (set (match_dup 1) + (plus:SWI (match_dup 1) + (match_dup 2)))])]) + (define_insn "*atomic_fetch_add_cmp<mode>" [(set (reg:CCZ FLAGS_REG) (compare:CCZ --- gcc/testsuite/gcc.target/i386/pr70821.c.jj 2016-04-28 09:56:06.239893613 +0200 +++ gcc/testsuite/gcc.target/i386/pr70821.c 2016-04-28 09:55:23.000000000 +0200 @@ -0,0 +1,16 @@ +/* PR target/70821 */ +/* { dg-do compile } */ +/* { dg-options "-Os" } */ +/* { dg-additional-options "-march=i686" { target ia32 } } */ + +void bar (void); + +void +foo (int *p) +{ + if (__atomic_sub_fetch (p, 1, __ATOMIC_SEQ_CST)) + bar (); +} + +/* { dg-final { scan-assembler "lock;? dec" } } */ +/* { dg-final { scan-assembler-not "lock;? xadd" } } */