Re: [PATCH] MATCH: [PR110937/PR100798] (a ? ~b : b) should be optimized to b ^ -(a)
On Thu, 10 Aug 2023 at 20:52, Andrew Pinski wrote: > On Thu, Aug 10, 2023 at 6:39 AM Christophe Lyon via Gcc-patches > wrote: > > > > Hi Andrew, > > > > > > On Wed, 9 Aug 2023 at 21:20, Andrew Pinski via Gcc-patches < > > gcc-patches@gcc.gnu.org> wrote: > > > > > This adds a simple match pattern for this case. > > > I noticed it a couple of different places. > > > One while I was looking at code generation of a parser and > > > also while I was looking at locations where bitwise_inverted_equal_p > > > should be used more. > > > > > > Committed as approved after bootstrapped and tested on x86_64-linux-gnu > > > with no regressions. > > > > > > PR tree-optimization/110937 > > > PR tree-optimization/100798 > > > > > > gcc/ChangeLog: > > > > > > * match.pd (`a ? ~b : b`): Handle this > > > case. > > > > > > gcc/testsuite/ChangeLog: > > > > > > * gcc.dg/tree-ssa/bool-14.c: New test. > > > * gcc.dg/tree-ssa/bool-15.c: New test. > > > * gcc.dg/tree-ssa/phi-opt-33.c: New test. > > > * gcc.dg/tree-ssa/20030709-2.c: Update testcase > > > so `a ? -1 : 0` is not used to hit the match > > > pattern. > > > > > > > Our CI noticed that your patch introduced regressions as follows on > aarch64: > > > > Running gcc:gcc.target/aarch64/aarch64.exp ... > > FAIL: gcc.target/aarch64/cond_op_imm_1.c scan-assembler csinv\tw[0-9]*.* > > FAIL: gcc.target/aarch64/cond_op_imm_1.c scan-assembler csinv\tx[0-9]*.* > > > > Running gcc:gcc.target/aarch64/sve/aarch64-sve.exp ... > > FAIL: gcc.target/aarch64/sve/cond_unary_5.c scan-assembler-not \\tmov\\tz > > FAIL: gcc.target/aarch64/sve/cond_unary_5.c scan-assembler-times > > \\tneg\\tz[0-9]+\\.b, p[0-7]/m, 3 > > FAIL: gcc.target/aarch64/sve/cond_unary_5.c scan-assembler-times > > \\tneg\\tz[0-9]+\\.h, p[0-7]/m, 2 > > FAIL: gcc.target/aarch64/sve/cond_unary_5.c scan-assembler-times > > \\tneg\\tz[0-9]+\\.s, p[0-7]/m, 1 > > FAIL: gcc.target/aarch64/sve/cond_unary_5.c scan-assembler-times > > \\tnot\\tz[0-9]+\\.b, p[0-7]/m, 3 > > FAIL: gcc.target/aarch64/sve/cond_unary_5.c scan-assembler-times > > \\tnot\\tz[0-9]+\\.h, p[0-7]/m, 2 > > FAIL: gcc.target/aarch64/sve/cond_unary_5.c scan-assembler-times > > \\tnot\\tz[0-9]+\\.s, p[0-7]/m, 1 > > > > Hopefully you'll just need to update the testcases (I didn't check > > manually, I think you can easily reproduce this on aarch64?) > > I have a few ideas of how to fix this properly inside isel without > changing the testcases. I will start working on that starting > tomorrow. > In the meantime can you file a bug report? So we don't lose track of > the regression? > > Hi Andrew, Sure, I've just filed: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=110986 Thanks, Christophe Thanks, > Andrew > > > > > Thanks, > > > > Christophe > > > > > > > > > > > --- > > > gcc/match.pd | 14 ++ > > > gcc/testsuite/gcc.dg/tree-ssa/20030709-2.c | 5 +++-- > > > gcc/testsuite/gcc.dg/tree-ssa/bool-14.c| 15 +++ > > > gcc/testsuite/gcc.dg/tree-ssa/bool-15.c| 18 ++ > > > gcc/testsuite/gcc.dg/tree-ssa/phi-opt-33.c | 13 + > > > 5 files changed, 63 insertions(+), 2 deletions(-) > > > create mode 100644 gcc/testsuite/gcc.dg/tree-ssa/bool-14.c > > > create mode 100644 gcc/testsuite/gcc.dg/tree-ssa/bool-15.c > > > create mode 100644 gcc/testsuite/gcc.dg/tree-ssa/phi-opt-33.c > > > > > > diff --git a/gcc/match.pd b/gcc/match.pd > > > index 9b4819e5be7..fc630b63563 100644 > > > --- a/gcc/match.pd > > > +++ b/gcc/match.pd > > > @@ -6460,6 +6460,20 @@ DEFINE_INT_AND_FLOAT_ROUND_FN (RINT) > > >(if (cmp == NE_EXPR) > > > { constant_boolean_node (true, type); }))) > > > > > > +#if GIMPLE > > > +/* a?~t:t -> (-(a))^t */ > > > +(simplify > > > + (cond @0 @1 @2) > > > + (if (INTEGRAL_TYPE_P (type) > > > + && bitwise_inverted_equal_p (@1, @2)) > > > + (with { > > > +auto prec = TYPE_PRECISION (type); > > > +auto unsign = TYPE_UNSIGNED (type); > > > +tree inttype = build_nonstandard_integer_type (prec, unsign); > > > + } > > > + (convert (bit_xor (negate (convert:inttype @0)) (convert:inttype > > > @2)) > > > +#endif > > > + > > > /* Simplify pointer equality compares using PTA. */ > > > (for neeq (ne eq) > > > (simplify > > > diff --git a/gcc/testsuite/gcc.dg/tree-ssa/20030709-2.c > > > b/gcc/testsuite/gcc.dg/tree-ssa/20030709-2.c > > > index 5009cd69cfe..78938f919d4 100644 > > > --- a/gcc/testsuite/gcc.dg/tree-ssa/20030709-2.c > > > +++ b/gcc/testsuite/gcc.dg/tree-ssa/20030709-2.c > > > @@ -29,15 +29,16 @@ union tree_node > > > }; > > > int make_decl_rtl (tree, int); > > > void * > > > -get_alias_set (t) > > > +get_alias_set (t, t1) > > > tree t; > > > + void *t1; > > > { > > >long set; > > >if (t->decl.rtl) > > > return (t->decl.rtl->fld[1].rtmem > > > ? 0 > > > : (((t->decl.rtl ? t->decl.rtl:
Re: [PATCH] MATCH: [PR110937/PR100798] (a ? ~b : b) should be optimized to b ^ -(a)
On Thu, Aug 10, 2023 at 6:39 AM Christophe Lyon via Gcc-patches wrote: > > Hi Andrew, > > > On Wed, 9 Aug 2023 at 21:20, Andrew Pinski via Gcc-patches < > gcc-patches@gcc.gnu.org> wrote: > > > This adds a simple match pattern for this case. > > I noticed it a couple of different places. > > One while I was looking at code generation of a parser and > > also while I was looking at locations where bitwise_inverted_equal_p > > should be used more. > > > > Committed as approved after bootstrapped and tested on x86_64-linux-gnu > > with no regressions. > > > > PR tree-optimization/110937 > > PR tree-optimization/100798 > > > > gcc/ChangeLog: > > > > * match.pd (`a ? ~b : b`): Handle this > > case. > > > > gcc/testsuite/ChangeLog: > > > > * gcc.dg/tree-ssa/bool-14.c: New test. > > * gcc.dg/tree-ssa/bool-15.c: New test. > > * gcc.dg/tree-ssa/phi-opt-33.c: New test. > > * gcc.dg/tree-ssa/20030709-2.c: Update testcase > > so `a ? -1 : 0` is not used to hit the match > > pattern. > > > > Our CI noticed that your patch introduced regressions as follows on aarch64: > > Running gcc:gcc.target/aarch64/aarch64.exp ... > FAIL: gcc.target/aarch64/cond_op_imm_1.c scan-assembler csinv\tw[0-9]*.* > FAIL: gcc.target/aarch64/cond_op_imm_1.c scan-assembler csinv\tx[0-9]*.* > > Running gcc:gcc.target/aarch64/sve/aarch64-sve.exp ... > FAIL: gcc.target/aarch64/sve/cond_unary_5.c scan-assembler-not \\tmov\\tz > FAIL: gcc.target/aarch64/sve/cond_unary_5.c scan-assembler-times > \\tneg\\tz[0-9]+\\.b, p[0-7]/m, 3 > FAIL: gcc.target/aarch64/sve/cond_unary_5.c scan-assembler-times > \\tneg\\tz[0-9]+\\.h, p[0-7]/m, 2 > FAIL: gcc.target/aarch64/sve/cond_unary_5.c scan-assembler-times > \\tneg\\tz[0-9]+\\.s, p[0-7]/m, 1 > FAIL: gcc.target/aarch64/sve/cond_unary_5.c scan-assembler-times > \\tnot\\tz[0-9]+\\.b, p[0-7]/m, 3 > FAIL: gcc.target/aarch64/sve/cond_unary_5.c scan-assembler-times > \\tnot\\tz[0-9]+\\.h, p[0-7]/m, 2 > FAIL: gcc.target/aarch64/sve/cond_unary_5.c scan-assembler-times > \\tnot\\tz[0-9]+\\.s, p[0-7]/m, 1 > > Hopefully you'll just need to update the testcases (I didn't check > manually, I think you can easily reproduce this on aarch64?) I have a few ideas of how to fix this properly inside isel without changing the testcases. I will start working on that starting tomorrow. In the meantime can you file a bug report? So we don't lose track of the regression? Thanks, Andrew > > Thanks, > > Christophe > > > > > > --- > > gcc/match.pd | 14 ++ > > gcc/testsuite/gcc.dg/tree-ssa/20030709-2.c | 5 +++-- > > gcc/testsuite/gcc.dg/tree-ssa/bool-14.c| 15 +++ > > gcc/testsuite/gcc.dg/tree-ssa/bool-15.c| 18 ++ > > gcc/testsuite/gcc.dg/tree-ssa/phi-opt-33.c | 13 + > > 5 files changed, 63 insertions(+), 2 deletions(-) > > create mode 100644 gcc/testsuite/gcc.dg/tree-ssa/bool-14.c > > create mode 100644 gcc/testsuite/gcc.dg/tree-ssa/bool-15.c > > create mode 100644 gcc/testsuite/gcc.dg/tree-ssa/phi-opt-33.c > > > > diff --git a/gcc/match.pd b/gcc/match.pd > > index 9b4819e5be7..fc630b63563 100644 > > --- a/gcc/match.pd > > +++ b/gcc/match.pd > > @@ -6460,6 +6460,20 @@ DEFINE_INT_AND_FLOAT_ROUND_FN (RINT) > >(if (cmp == NE_EXPR) > > { constant_boolean_node (true, type); }))) > > > > +#if GIMPLE > > +/* a?~t:t -> (-(a))^t */ > > +(simplify > > + (cond @0 @1 @2) > > + (if (INTEGRAL_TYPE_P (type) > > + && bitwise_inverted_equal_p (@1, @2)) > > + (with { > > +auto prec = TYPE_PRECISION (type); > > +auto unsign = TYPE_UNSIGNED (type); > > +tree inttype = build_nonstandard_integer_type (prec, unsign); > > + } > > + (convert (bit_xor (negate (convert:inttype @0)) (convert:inttype > > @2)) > > +#endif > > + > > /* Simplify pointer equality compares using PTA. */ > > (for neeq (ne eq) > > (simplify > > diff --git a/gcc/testsuite/gcc.dg/tree-ssa/20030709-2.c > > b/gcc/testsuite/gcc.dg/tree-ssa/20030709-2.c > > index 5009cd69cfe..78938f919d4 100644 > > --- a/gcc/testsuite/gcc.dg/tree-ssa/20030709-2.c > > +++ b/gcc/testsuite/gcc.dg/tree-ssa/20030709-2.c > > @@ -29,15 +29,16 @@ union tree_node > > }; > > int make_decl_rtl (tree, int); > > void * > > -get_alias_set (t) > > +get_alias_set (t, t1) > > tree t; > > + void *t1; > > { > >long set; > >if (t->decl.rtl) > > return (t->decl.rtl->fld[1].rtmem > > ? 0 > > : (((t->decl.rtl ? t->decl.rtl: (make_decl_rtl (t, 0), > > t->decl.rtl)))->fld[1]).rtmem); > > - return (void*)-1; > > + return t1; > > } > > > > /* There should be precisely one load of ->decl.rtl. If there is > > diff --git a/gcc/testsuite/gcc.dg/tree-ssa/bool-14.c > > b/gcc/testsuite/gcc.dg/tree-ssa/bool-14.c > > new file mode 100644 > > index 000..0149380a63b > > --- /dev/null > > +++ b/gcc/testsuite/gcc.dg/tree-ssa/bool-14.c > > @@ -0,0 +1,15 @@ > >
Re: [PATCH] MATCH: [PR110937/PR100798] (a ? ~b : b) should be optimized to b ^ -(a)
Hi Andrew, On Wed, 9 Aug 2023 at 21:20, Andrew Pinski via Gcc-patches < gcc-patches@gcc.gnu.org> wrote: > This adds a simple match pattern for this case. > I noticed it a couple of different places. > One while I was looking at code generation of a parser and > also while I was looking at locations where bitwise_inverted_equal_p > should be used more. > > Committed as approved after bootstrapped and tested on x86_64-linux-gnu > with no regressions. > > PR tree-optimization/110937 > PR tree-optimization/100798 > > gcc/ChangeLog: > > * match.pd (`a ? ~b : b`): Handle this > case. > > gcc/testsuite/ChangeLog: > > * gcc.dg/tree-ssa/bool-14.c: New test. > * gcc.dg/tree-ssa/bool-15.c: New test. > * gcc.dg/tree-ssa/phi-opt-33.c: New test. > * gcc.dg/tree-ssa/20030709-2.c: Update testcase > so `a ? -1 : 0` is not used to hit the match > pattern. > Our CI noticed that your patch introduced regressions as follows on aarch64: Running gcc:gcc.target/aarch64/aarch64.exp ... FAIL: gcc.target/aarch64/cond_op_imm_1.c scan-assembler csinv\tw[0-9]*.* FAIL: gcc.target/aarch64/cond_op_imm_1.c scan-assembler csinv\tx[0-9]*.* Running gcc:gcc.target/aarch64/sve/aarch64-sve.exp ... FAIL: gcc.target/aarch64/sve/cond_unary_5.c scan-assembler-not \\tmov\\tz FAIL: gcc.target/aarch64/sve/cond_unary_5.c scan-assembler-times \\tneg\\tz[0-9]+\\.b, p[0-7]/m, 3 FAIL: gcc.target/aarch64/sve/cond_unary_5.c scan-assembler-times \\tneg\\tz[0-9]+\\.h, p[0-7]/m, 2 FAIL: gcc.target/aarch64/sve/cond_unary_5.c scan-assembler-times \\tneg\\tz[0-9]+\\.s, p[0-7]/m, 1 FAIL: gcc.target/aarch64/sve/cond_unary_5.c scan-assembler-times \\tnot\\tz[0-9]+\\.b, p[0-7]/m, 3 FAIL: gcc.target/aarch64/sve/cond_unary_5.c scan-assembler-times \\tnot\\tz[0-9]+\\.h, p[0-7]/m, 2 FAIL: gcc.target/aarch64/sve/cond_unary_5.c scan-assembler-times \\tnot\\tz[0-9]+\\.s, p[0-7]/m, 1 Hopefully you'll just need to update the testcases (I didn't check manually, I think you can easily reproduce this on aarch64?) Thanks, Christophe > --- > gcc/match.pd | 14 ++ > gcc/testsuite/gcc.dg/tree-ssa/20030709-2.c | 5 +++-- > gcc/testsuite/gcc.dg/tree-ssa/bool-14.c| 15 +++ > gcc/testsuite/gcc.dg/tree-ssa/bool-15.c| 18 ++ > gcc/testsuite/gcc.dg/tree-ssa/phi-opt-33.c | 13 + > 5 files changed, 63 insertions(+), 2 deletions(-) > create mode 100644 gcc/testsuite/gcc.dg/tree-ssa/bool-14.c > create mode 100644 gcc/testsuite/gcc.dg/tree-ssa/bool-15.c > create mode 100644 gcc/testsuite/gcc.dg/tree-ssa/phi-opt-33.c > > diff --git a/gcc/match.pd b/gcc/match.pd > index 9b4819e5be7..fc630b63563 100644 > --- a/gcc/match.pd > +++ b/gcc/match.pd > @@ -6460,6 +6460,20 @@ DEFINE_INT_AND_FLOAT_ROUND_FN (RINT) >(if (cmp == NE_EXPR) > { constant_boolean_node (true, type); }))) > > +#if GIMPLE > +/* a?~t:t -> (-(a))^t */ > +(simplify > + (cond @0 @1 @2) > + (if (INTEGRAL_TYPE_P (type) > + && bitwise_inverted_equal_p (@1, @2)) > + (with { > +auto prec = TYPE_PRECISION (type); > +auto unsign = TYPE_UNSIGNED (type); > +tree inttype = build_nonstandard_integer_type (prec, unsign); > + } > + (convert (bit_xor (negate (convert:inttype @0)) (convert:inttype > @2)) > +#endif > + > /* Simplify pointer equality compares using PTA. */ > (for neeq (ne eq) > (simplify > diff --git a/gcc/testsuite/gcc.dg/tree-ssa/20030709-2.c > b/gcc/testsuite/gcc.dg/tree-ssa/20030709-2.c > index 5009cd69cfe..78938f919d4 100644 > --- a/gcc/testsuite/gcc.dg/tree-ssa/20030709-2.c > +++ b/gcc/testsuite/gcc.dg/tree-ssa/20030709-2.c > @@ -29,15 +29,16 @@ union tree_node > }; > int make_decl_rtl (tree, int); > void * > -get_alias_set (t) > +get_alias_set (t, t1) > tree t; > + void *t1; > { >long set; >if (t->decl.rtl) > return (t->decl.rtl->fld[1].rtmem > ? 0 > : (((t->decl.rtl ? t->decl.rtl: (make_decl_rtl (t, 0), > t->decl.rtl)))->fld[1]).rtmem); > - return (void*)-1; > + return t1; > } > > /* There should be precisely one load of ->decl.rtl. If there is > diff --git a/gcc/testsuite/gcc.dg/tree-ssa/bool-14.c > b/gcc/testsuite/gcc.dg/tree-ssa/bool-14.c > new file mode 100644 > index 000..0149380a63b > --- /dev/null > +++ b/gcc/testsuite/gcc.dg/tree-ssa/bool-14.c > @@ -0,0 +1,15 @@ > +/* { dg-do compile } */ > +/* { dg-options "-O2 -fdump-tree-optimized-raw" } */ > +/* PR tree-optimization/110937 */ > + > +_Bool f2(_Bool a, _Bool b) > +{ > +if (a) > + return !b; > +return b; > +} > + > +/* We should be able to remove the conditional and convert it to an xor. > */ > +/* { dg-final { scan-tree-dump-not "gimple_cond " "optimized" } } */ > +/* { dg-final { scan-tree-dump-not "gimple_phi " "optimized" } } */ > +/* { dg-final { scan-tree-dump-times "bit_xor_expr, " 1 "optimized" } } */ > diff --git
[PATCH] MATCH: [PR110937/PR100798] (a ? ~b : b) should be optimized to b ^ -(a)
This adds a simple match pattern for this case. I noticed it a couple of different places. One while I was looking at code generation of a parser and also while I was looking at locations where bitwise_inverted_equal_p should be used more. Committed as approved after bootstrapped and tested on x86_64-linux-gnu with no regressions. PR tree-optimization/110937 PR tree-optimization/100798 gcc/ChangeLog: * match.pd (`a ? ~b : b`): Handle this case. gcc/testsuite/ChangeLog: * gcc.dg/tree-ssa/bool-14.c: New test. * gcc.dg/tree-ssa/bool-15.c: New test. * gcc.dg/tree-ssa/phi-opt-33.c: New test. * gcc.dg/tree-ssa/20030709-2.c: Update testcase so `a ? -1 : 0` is not used to hit the match pattern. --- gcc/match.pd | 14 ++ gcc/testsuite/gcc.dg/tree-ssa/20030709-2.c | 5 +++-- gcc/testsuite/gcc.dg/tree-ssa/bool-14.c| 15 +++ gcc/testsuite/gcc.dg/tree-ssa/bool-15.c| 18 ++ gcc/testsuite/gcc.dg/tree-ssa/phi-opt-33.c | 13 + 5 files changed, 63 insertions(+), 2 deletions(-) create mode 100644 gcc/testsuite/gcc.dg/tree-ssa/bool-14.c create mode 100644 gcc/testsuite/gcc.dg/tree-ssa/bool-15.c create mode 100644 gcc/testsuite/gcc.dg/tree-ssa/phi-opt-33.c diff --git a/gcc/match.pd b/gcc/match.pd index 9b4819e5be7..fc630b63563 100644 --- a/gcc/match.pd +++ b/gcc/match.pd @@ -6460,6 +6460,20 @@ DEFINE_INT_AND_FLOAT_ROUND_FN (RINT) (if (cmp == NE_EXPR) { constant_boolean_node (true, type); }))) +#if GIMPLE +/* a?~t:t -> (-(a))^t */ +(simplify + (cond @0 @1 @2) + (if (INTEGRAL_TYPE_P (type) + && bitwise_inverted_equal_p (@1, @2)) + (with { +auto prec = TYPE_PRECISION (type); +auto unsign = TYPE_UNSIGNED (type); +tree inttype = build_nonstandard_integer_type (prec, unsign); + } + (convert (bit_xor (negate (convert:inttype @0)) (convert:inttype @2)) +#endif + /* Simplify pointer equality compares using PTA. */ (for neeq (ne eq) (simplify diff --git a/gcc/testsuite/gcc.dg/tree-ssa/20030709-2.c b/gcc/testsuite/gcc.dg/tree-ssa/20030709-2.c index 5009cd69cfe..78938f919d4 100644 --- a/gcc/testsuite/gcc.dg/tree-ssa/20030709-2.c +++ b/gcc/testsuite/gcc.dg/tree-ssa/20030709-2.c @@ -29,15 +29,16 @@ union tree_node }; int make_decl_rtl (tree, int); void * -get_alias_set (t) +get_alias_set (t, t1) tree t; + void *t1; { long set; if (t->decl.rtl) return (t->decl.rtl->fld[1].rtmem ? 0 : (((t->decl.rtl ? t->decl.rtl: (make_decl_rtl (t, 0), t->decl.rtl)))->fld[1]).rtmem); - return (void*)-1; + return t1; } /* There should be precisely one load of ->decl.rtl. If there is diff --git a/gcc/testsuite/gcc.dg/tree-ssa/bool-14.c b/gcc/testsuite/gcc.dg/tree-ssa/bool-14.c new file mode 100644 index 000..0149380a63b --- /dev/null +++ b/gcc/testsuite/gcc.dg/tree-ssa/bool-14.c @@ -0,0 +1,15 @@ +/* { dg-do compile } */ +/* { dg-options "-O2 -fdump-tree-optimized-raw" } */ +/* PR tree-optimization/110937 */ + +_Bool f2(_Bool a, _Bool b) +{ +if (a) + return !b; +return b; +} + +/* We should be able to remove the conditional and convert it to an xor. */ +/* { dg-final { scan-tree-dump-not "gimple_cond " "optimized" } } */ +/* { dg-final { scan-tree-dump-not "gimple_phi " "optimized" } } */ +/* { dg-final { scan-tree-dump-times "bit_xor_expr, " 1 "optimized" } } */ diff --git a/gcc/testsuite/gcc.dg/tree-ssa/bool-15.c b/gcc/testsuite/gcc.dg/tree-ssa/bool-15.c new file mode 100644 index 000..1f496663863 --- /dev/null +++ b/gcc/testsuite/gcc.dg/tree-ssa/bool-15.c @@ -0,0 +1,18 @@ +/* { dg-do compile } */ +/* { dg-options "-O2 -fdump-tree-optimized-raw" } */ +/* PR tree-optimization/110937 */ + +_Bool f2(int x, int y, int w, int z) +{ + _Bool a = x == y; + _Bool b = w == z; + if (a) +return !b; + return b; +} + +/* We should be able to remove the conditional and convert it to an xor. */ +/* { dg-final { scan-tree-dump-not "gimple_cond " "optimized" } } */ +/* { dg-final { scan-tree-dump-not "gimple_phi " "optimized" } } */ +/* { dg-final { scan-tree-dump-not "ne_expr, " "optimized" } } */ +/* { dg-final { scan-tree-dump-times "bit_xor_expr, " 1 "optimized" } } */ diff --git a/gcc/testsuite/gcc.dg/tree-ssa/phi-opt-33.c b/gcc/testsuite/gcc.dg/tree-ssa/phi-opt-33.c new file mode 100644 index 000..b79fe44187a --- /dev/null +++ b/gcc/testsuite/gcc.dg/tree-ssa/phi-opt-33.c @@ -0,0 +1,13 @@ +/* { dg-do compile } */ +/* { dg-options "-O2 -fdump-tree-optimized-raw" } */ +/* PR tree-optimization/100798 */ + +int f(int a, int t) +{ + return (a=='s' ? ~t : t); +} + +/* This should be convert into t^-(a=='s'). */ +/* { dg-final { scan-tree-dump-times "bit_xor_expr, " 1 "optimized" } } */ +/* { dg-final { scan-tree-dump-times "negate_expr, " 1 "optimized" } } */ +/* { dg-final { scan-tree-dump-not "bit_not_expr, " "optimized" } }
Re: [PATCH] MATCH: [PR110937/PR100798] (a ? ~b : b) should be optimized to b ^ -(a)
On Tue, Aug 8, 2023 at 12:44 AM Richard Biener via Gcc-patches wrote: > > On Tue, Aug 8, 2023 at 2:55 AM Andrew Pinski via Gcc-patches > wrote: > > > > This adds a simple match pattern for this case. > > I noticed it a couple of different places. > > One while I was looking at code generation of a parser and > > also while I was looking at locations where bitwise_inverted_equal_p > > should be used more. > > > > OK? Bootstrapped and tested on x86_64-linux-gnu with no regressions. > > > > PR tree-optimization/110937 > > PR tree-optimization/100798 > > > > gcc/ChangeLog: > > > > * match.pd (`a ? ~b : b`): Handle this > > case. > > > > gcc/testsuite/ChangeLog: > > > > * gcc.dg/tree-ssa/bool-14.c: New test. > > * gcc.dg/tree-ssa/bool-15.c: New test. > > * gcc.dg/tree-ssa/phi-opt-33.c: New test. > > * gcc.dg/tree-ssa/20030709-2.c: Update testcase > > so `a ? -1 : 0` is not used to hit the match > > pattern. > > --- > > gcc/match.pd | 13 + > > gcc/testsuite/gcc.dg/tree-ssa/20030709-2.c | 5 +++-- > > gcc/testsuite/gcc.dg/tree-ssa/bool-14.c| 15 +++ > > gcc/testsuite/gcc.dg/tree-ssa/bool-15.c| 18 ++ > > gcc/testsuite/gcc.dg/tree-ssa/phi-opt-33.c | 13 + > > 5 files changed, 62 insertions(+), 2 deletions(-) > > create mode 100644 gcc/testsuite/gcc.dg/tree-ssa/bool-14.c > > create mode 100644 gcc/testsuite/gcc.dg/tree-ssa/bool-15.c > > create mode 100644 gcc/testsuite/gcc.dg/tree-ssa/phi-opt-33.c > > > > diff --git a/gcc/match.pd b/gcc/match.pd > > index 9b4819e5be7..f887c517c81 100644 > > --- a/gcc/match.pd > > +++ b/gcc/match.pd > > @@ -6460,6 +6460,19 @@ DEFINE_INT_AND_FLOAT_ROUND_FN (RINT) > >(if (cmp == NE_EXPR) > > { constant_boolean_node (true, type); }))) > > > > +#if GIMPLE > > +/* a?~t:t -> (-(a))^t */ > > +(simplify > > + (cond @0 @1 @2) > > + (if (bitwise_inverted_equal_p (@1, @2)) > > I'm not sure if that can ever match a not INTEGRAL_TYPE_P > but we can have vector typed @1 and @2 and then the > TYPE_PRECISION ask below would be wrong. So can you > add > > INTEGRAL_TYPE_P (type) > && bitwise_in... > > if only for clarity? > > > + (with { > > +auto prec = TYPE_PRECISION (type); > > +auto unsign = TYPE_UNSIGNED (type); > > +tree inttype = build_nonstandard_integer_type (prec, unsign); > > + } > > + (convert (bit_xor (negate (convert:inttype @0)) (convert:inttype > > @2)) > > so we don't get to know which of @1 or @2 is "simpler" (the not > explicitely inverted > operand), I suppose that's the disadvantage of using bitwise_inverted_equal_p. > I'll note that if you make bitwise_inverted_equal_p a match you'd need a :c on > the 'cond' but otherwise complexity would be the same as match patterns are > not > "inlined". Right, The disadvantage is definitely not knowing which is "simpler". And I found a testcase which shows that but I suspect we can fix that. ``` int f(int a, int t) { int t1 = ~t; return (a=='s' ? t : t1); } ``` Basically we are missing transforming: ~(-(cast)(cmp)) into -(cast)(cmp`) Filed as PR 110949 . > > In any case, OK with the INTEGRAL_TYPE_P check. Will update the patch and commit it after a bootstrap/test. Thanks, Andrew > > Thanks, > Richard. > > > +#endif > > + > > /* Simplify pointer equality compares using PTA. */ > > (for neeq (ne eq) > > (simplify > > diff --git a/gcc/testsuite/gcc.dg/tree-ssa/20030709-2.c > > b/gcc/testsuite/gcc.dg/tree-ssa/20030709-2.c > > index 5009cd69cfe..78938f919d4 100644 > > --- a/gcc/testsuite/gcc.dg/tree-ssa/20030709-2.c > > +++ b/gcc/testsuite/gcc.dg/tree-ssa/20030709-2.c > > @@ -29,15 +29,16 @@ union tree_node > > }; > > int make_decl_rtl (tree, int); > > void * > > -get_alias_set (t) > > +get_alias_set (t, t1) > > tree t; > > + void *t1; > > { > >long set; > >if (t->decl.rtl) > > return (t->decl.rtl->fld[1].rtmem > > ? 0 > > : (((t->decl.rtl ? t->decl.rtl: (make_decl_rtl (t, 0), > > t->decl.rtl)))->fld[1]).rtmem); > > - return (void*)-1; > > + return t1; > > } > > > > /* There should be precisely one load of ->decl.rtl. If there is > > diff --git a/gcc/testsuite/gcc.dg/tree-ssa/bool-14.c > > b/gcc/testsuite/gcc.dg/tree-ssa/bool-14.c > > new file mode 100644 > > index 000..0149380a63b > > --- /dev/null > > +++ b/gcc/testsuite/gcc.dg/tree-ssa/bool-14.c > > @@ -0,0 +1,15 @@ > > +/* { dg-do compile } */ > > +/* { dg-options "-O2 -fdump-tree-optimized-raw" } */ > > +/* PR tree-optimization/110937 */ > > + > > +_Bool f2(_Bool a, _Bool b) > > +{ > > +if (a) > > + return !b; > > +return b; > > +} > > + > > +/* We should be able to remove the conditional and convert it to an xor. */ > > +/* { dg-final { scan-tree-dump-not "gimple_cond " "optimized" } } */ > > +/* { dg-final { scan-tree-dump-not "gimple_phi " "optimized" } }
Re: [PATCH] MATCH: [PR110937/PR100798] (a ? ~b : b) should be optimized to b ^ -(a)
On Tue, Aug 8, 2023 at 2:55 AM Andrew Pinski via Gcc-patches wrote: > > This adds a simple match pattern for this case. > I noticed it a couple of different places. > One while I was looking at code generation of a parser and > also while I was looking at locations where bitwise_inverted_equal_p > should be used more. > > OK? Bootstrapped and tested on x86_64-linux-gnu with no regressions. > > PR tree-optimization/110937 > PR tree-optimization/100798 > > gcc/ChangeLog: > > * match.pd (`a ? ~b : b`): Handle this > case. > > gcc/testsuite/ChangeLog: > > * gcc.dg/tree-ssa/bool-14.c: New test. > * gcc.dg/tree-ssa/bool-15.c: New test. > * gcc.dg/tree-ssa/phi-opt-33.c: New test. > * gcc.dg/tree-ssa/20030709-2.c: Update testcase > so `a ? -1 : 0` is not used to hit the match > pattern. > --- > gcc/match.pd | 13 + > gcc/testsuite/gcc.dg/tree-ssa/20030709-2.c | 5 +++-- > gcc/testsuite/gcc.dg/tree-ssa/bool-14.c| 15 +++ > gcc/testsuite/gcc.dg/tree-ssa/bool-15.c| 18 ++ > gcc/testsuite/gcc.dg/tree-ssa/phi-opt-33.c | 13 + > 5 files changed, 62 insertions(+), 2 deletions(-) > create mode 100644 gcc/testsuite/gcc.dg/tree-ssa/bool-14.c > create mode 100644 gcc/testsuite/gcc.dg/tree-ssa/bool-15.c > create mode 100644 gcc/testsuite/gcc.dg/tree-ssa/phi-opt-33.c > > diff --git a/gcc/match.pd b/gcc/match.pd > index 9b4819e5be7..f887c517c81 100644 > --- a/gcc/match.pd > +++ b/gcc/match.pd > @@ -6460,6 +6460,19 @@ DEFINE_INT_AND_FLOAT_ROUND_FN (RINT) >(if (cmp == NE_EXPR) > { constant_boolean_node (true, type); }))) > > +#if GIMPLE > +/* a?~t:t -> (-(a))^t */ > +(simplify > + (cond @0 @1 @2) > + (if (bitwise_inverted_equal_p (@1, @2)) I'm not sure if that can ever match a not INTEGRAL_TYPE_P but we can have vector typed @1 and @2 and then the TYPE_PRECISION ask below would be wrong. So can you add INTEGRAL_TYPE_P (type) && bitwise_in... if only for clarity? > + (with { > +auto prec = TYPE_PRECISION (type); > +auto unsign = TYPE_UNSIGNED (type); > +tree inttype = build_nonstandard_integer_type (prec, unsign); > + } > + (convert (bit_xor (negate (convert:inttype @0)) (convert:inttype @2)) so we don't get to know which of @1 or @2 is "simpler" (the not explicitely inverted operand), I suppose that's the disadvantage of using bitwise_inverted_equal_p. I'll note that if you make bitwise_inverted_equal_p a match you'd need a :c on the 'cond' but otherwise complexity would be the same as match patterns are not "inlined". In any case, OK with the INTEGRAL_TYPE_P check. Thanks, Richard. > +#endif > + > /* Simplify pointer equality compares using PTA. */ > (for neeq (ne eq) > (simplify > diff --git a/gcc/testsuite/gcc.dg/tree-ssa/20030709-2.c > b/gcc/testsuite/gcc.dg/tree-ssa/20030709-2.c > index 5009cd69cfe..78938f919d4 100644 > --- a/gcc/testsuite/gcc.dg/tree-ssa/20030709-2.c > +++ b/gcc/testsuite/gcc.dg/tree-ssa/20030709-2.c > @@ -29,15 +29,16 @@ union tree_node > }; > int make_decl_rtl (tree, int); > void * > -get_alias_set (t) > +get_alias_set (t, t1) > tree t; > + void *t1; > { >long set; >if (t->decl.rtl) > return (t->decl.rtl->fld[1].rtmem > ? 0 > : (((t->decl.rtl ? t->decl.rtl: (make_decl_rtl (t, 0), > t->decl.rtl)))->fld[1]).rtmem); > - return (void*)-1; > + return t1; > } > > /* There should be precisely one load of ->decl.rtl. If there is > diff --git a/gcc/testsuite/gcc.dg/tree-ssa/bool-14.c > b/gcc/testsuite/gcc.dg/tree-ssa/bool-14.c > new file mode 100644 > index 000..0149380a63b > --- /dev/null > +++ b/gcc/testsuite/gcc.dg/tree-ssa/bool-14.c > @@ -0,0 +1,15 @@ > +/* { dg-do compile } */ > +/* { dg-options "-O2 -fdump-tree-optimized-raw" } */ > +/* PR tree-optimization/110937 */ > + > +_Bool f2(_Bool a, _Bool b) > +{ > +if (a) > + return !b; > +return b; > +} > + > +/* We should be able to remove the conditional and convert it to an xor. */ > +/* { dg-final { scan-tree-dump-not "gimple_cond " "optimized" } } */ > +/* { dg-final { scan-tree-dump-not "gimple_phi " "optimized" } } */ > +/* { dg-final { scan-tree-dump-times "bit_xor_expr, " 1 "optimized" } } */ > diff --git a/gcc/testsuite/gcc.dg/tree-ssa/bool-15.c > b/gcc/testsuite/gcc.dg/tree-ssa/bool-15.c > new file mode 100644 > index 000..1f496663863 > --- /dev/null > +++ b/gcc/testsuite/gcc.dg/tree-ssa/bool-15.c > @@ -0,0 +1,18 @@ > +/* { dg-do compile } */ > +/* { dg-options "-O2 -fdump-tree-optimized-raw" } */ > +/* PR tree-optimization/110937 */ > + > +_Bool f2(int x, int y, int w, int z) > +{ > + _Bool a = x == y; > + _Bool b = w == z; > + if (a) > +return !b; > + return b; > +} > + > +/* We should be able to remove the conditional and convert it to an xor. */ > +/* { dg-final { scan-tree-dump-not "gimple_cond "
[PATCH] MATCH: [PR110937/PR100798] (a ? ~b : b) should be optimized to b ^ -(a)
This adds a simple match pattern for this case. I noticed it a couple of different places. One while I was looking at code generation of a parser and also while I was looking at locations where bitwise_inverted_equal_p should be used more. OK? Bootstrapped and tested on x86_64-linux-gnu with no regressions. PR tree-optimization/110937 PR tree-optimization/100798 gcc/ChangeLog: * match.pd (`a ? ~b : b`): Handle this case. gcc/testsuite/ChangeLog: * gcc.dg/tree-ssa/bool-14.c: New test. * gcc.dg/tree-ssa/bool-15.c: New test. * gcc.dg/tree-ssa/phi-opt-33.c: New test. * gcc.dg/tree-ssa/20030709-2.c: Update testcase so `a ? -1 : 0` is not used to hit the match pattern. --- gcc/match.pd | 13 + gcc/testsuite/gcc.dg/tree-ssa/20030709-2.c | 5 +++-- gcc/testsuite/gcc.dg/tree-ssa/bool-14.c| 15 +++ gcc/testsuite/gcc.dg/tree-ssa/bool-15.c| 18 ++ gcc/testsuite/gcc.dg/tree-ssa/phi-opt-33.c | 13 + 5 files changed, 62 insertions(+), 2 deletions(-) create mode 100644 gcc/testsuite/gcc.dg/tree-ssa/bool-14.c create mode 100644 gcc/testsuite/gcc.dg/tree-ssa/bool-15.c create mode 100644 gcc/testsuite/gcc.dg/tree-ssa/phi-opt-33.c diff --git a/gcc/match.pd b/gcc/match.pd index 9b4819e5be7..f887c517c81 100644 --- a/gcc/match.pd +++ b/gcc/match.pd @@ -6460,6 +6460,19 @@ DEFINE_INT_AND_FLOAT_ROUND_FN (RINT) (if (cmp == NE_EXPR) { constant_boolean_node (true, type); }))) +#if GIMPLE +/* a?~t:t -> (-(a))^t */ +(simplify + (cond @0 @1 @2) + (if (bitwise_inverted_equal_p (@1, @2)) + (with { +auto prec = TYPE_PRECISION (type); +auto unsign = TYPE_UNSIGNED (type); +tree inttype = build_nonstandard_integer_type (prec, unsign); + } + (convert (bit_xor (negate (convert:inttype @0)) (convert:inttype @2)) +#endif + /* Simplify pointer equality compares using PTA. */ (for neeq (ne eq) (simplify diff --git a/gcc/testsuite/gcc.dg/tree-ssa/20030709-2.c b/gcc/testsuite/gcc.dg/tree-ssa/20030709-2.c index 5009cd69cfe..78938f919d4 100644 --- a/gcc/testsuite/gcc.dg/tree-ssa/20030709-2.c +++ b/gcc/testsuite/gcc.dg/tree-ssa/20030709-2.c @@ -29,15 +29,16 @@ union tree_node }; int make_decl_rtl (tree, int); void * -get_alias_set (t) +get_alias_set (t, t1) tree t; + void *t1; { long set; if (t->decl.rtl) return (t->decl.rtl->fld[1].rtmem ? 0 : (((t->decl.rtl ? t->decl.rtl: (make_decl_rtl (t, 0), t->decl.rtl)))->fld[1]).rtmem); - return (void*)-1; + return t1; } /* There should be precisely one load of ->decl.rtl. If there is diff --git a/gcc/testsuite/gcc.dg/tree-ssa/bool-14.c b/gcc/testsuite/gcc.dg/tree-ssa/bool-14.c new file mode 100644 index 000..0149380a63b --- /dev/null +++ b/gcc/testsuite/gcc.dg/tree-ssa/bool-14.c @@ -0,0 +1,15 @@ +/* { dg-do compile } */ +/* { dg-options "-O2 -fdump-tree-optimized-raw" } */ +/* PR tree-optimization/110937 */ + +_Bool f2(_Bool a, _Bool b) +{ +if (a) + return !b; +return b; +} + +/* We should be able to remove the conditional and convert it to an xor. */ +/* { dg-final { scan-tree-dump-not "gimple_cond " "optimized" } } */ +/* { dg-final { scan-tree-dump-not "gimple_phi " "optimized" } } */ +/* { dg-final { scan-tree-dump-times "bit_xor_expr, " 1 "optimized" } } */ diff --git a/gcc/testsuite/gcc.dg/tree-ssa/bool-15.c b/gcc/testsuite/gcc.dg/tree-ssa/bool-15.c new file mode 100644 index 000..1f496663863 --- /dev/null +++ b/gcc/testsuite/gcc.dg/tree-ssa/bool-15.c @@ -0,0 +1,18 @@ +/* { dg-do compile } */ +/* { dg-options "-O2 -fdump-tree-optimized-raw" } */ +/* PR tree-optimization/110937 */ + +_Bool f2(int x, int y, int w, int z) +{ + _Bool a = x == y; + _Bool b = w == z; + if (a) +return !b; + return b; +} + +/* We should be able to remove the conditional and convert it to an xor. */ +/* { dg-final { scan-tree-dump-not "gimple_cond " "optimized" } } */ +/* { dg-final { scan-tree-dump-not "gimple_phi " "optimized" } } */ +/* { dg-final { scan-tree-dump-not "ne_expr, " "optimized" } } */ +/* { dg-final { scan-tree-dump-times "bit_xor_expr, " 1 "optimized" } } */ diff --git a/gcc/testsuite/gcc.dg/tree-ssa/phi-opt-33.c b/gcc/testsuite/gcc.dg/tree-ssa/phi-opt-33.c new file mode 100644 index 000..b79fe44187a --- /dev/null +++ b/gcc/testsuite/gcc.dg/tree-ssa/phi-opt-33.c @@ -0,0 +1,13 @@ +/* { dg-do compile } */ +/* { dg-options "-O2 -fdump-tree-optimized-raw" } */ +/* PR tree-optimization/100798 */ + +int f(int a, int t) +{ + return (a=='s' ? ~t : t); +} + +/* This should be convert into t^-(a=='s'). */ +/* { dg-final { scan-tree-dump-times "bit_xor_expr, " 1 "optimized" } } */ +/* { dg-final { scan-tree-dump-times "negate_expr, " 1 "optimized" } } */ +/* { dg-final { scan-tree-dump-not "bit_not_expr, " "optimized" } } */ -- 2.31.1