On Sat, Dec 2, 2023 at 7:38 AM Andrew Pinski <quic_apin...@quicinc.com> wrote:
>
> When I moved two_value to match.pd, I removed the check for the {0,+-1}
> as I had placed it after the {0,+-1} case for cond in match.pd.
> In the case of {0,+-1} and non boolean, before we would optmize those
> case to just `(convert)a` but after we would get `(convert)(a != 0)`
> which was not handled anyways to just `(convert)a`.
> So this adds a pattern to match `(convert)(zeroone != 0)` and simplify
> to `(convert)zeroone`.
>
> Also this optimizes (convert)(zeroone == 0) into (zeroone^1) if the
> type match. This can only be done on the gimple level as if zeroone
> was defined by (a&1), fold will convert (a&1)^1 back into
> `(convert)(zeroone == 0)` and an infinite loop will happen.
So fold converts (a&1)^1 to (convert)(a&1 == 0)? Can we fix (remove)
this instead or do we rely on that?
> Note the testcase pr69270.c needed a slight update due to not matching
> exactly a scan pattern, this update makes it more robust and will match
> before and afterwards and if there are other changes in this area too.
>
> Note the testcase gcc.target/i386/pr110790-2.c needs a slight update
> for better code generation in LP64 bit mode.
>
> Bootstrapped and tested on x86_64-linux-gnu with no regressions.
Otherwise OK.
Thanks,
Richard.
> gcc/ChangeLog:
>
> PR tree-optimization/111972
> PR tree-optimization/110637
> * match.pd (`(convert)(zeroone !=/== CST)`): Match
> and simplify to ((convert)zeroone){,^1}.
>
> gcc/testsuite/ChangeLog:
>
> * gcc.dg/tree-ssa/pr110637-1.c: New test.
> * gcc.dg/tree-ssa/pr110637-2.c: New test.
> * gcc.dg/tree-ssa/pr110637-3.c: New test.
> * gcc.dg/tree-ssa/pr111972-1.c: New test.
> * gcc.dg/tree-ssa/pr69270.c: Update testcase.
> * gcc.target/i386/pr110790-2.c: Update testcase.
>
> Signed-off-by: Andrew Pinski <quic_apin...@quicinc.com>
> ---
> gcc/match.pd | 21 +++++++++++++
> gcc/testsuite/gcc.dg/tree-ssa/pr110637-1.c | 10 +++++++
> gcc/testsuite/gcc.dg/tree-ssa/pr110637-2.c | 13 +++++++++
> gcc/testsuite/gcc.dg/tree-ssa/pr110637-3.c | 14 +++++++++
> gcc/testsuite/gcc.dg/tree-ssa/pr111972-1.c | 34 ++++++++++++++++++++++
> gcc/testsuite/gcc.dg/tree-ssa/pr69270.c | 4 +--
> gcc/testsuite/gcc.target/i386/pr110790-2.c | 16 ++++++++--
> 7 files changed, 108 insertions(+), 4 deletions(-)
> create mode 100644 gcc/testsuite/gcc.dg/tree-ssa/pr110637-1.c
> create mode 100644 gcc/testsuite/gcc.dg/tree-ssa/pr110637-2.c
> create mode 100644 gcc/testsuite/gcc.dg/tree-ssa/pr110637-3.c
> create mode 100644 gcc/testsuite/gcc.dg/tree-ssa/pr111972-1.c
>
> diff --git a/gcc/match.pd b/gcc/match.pd
> index 4d554ba4721..656b2c9edda 100644
> --- a/gcc/match.pd
> +++ b/gcc/match.pd
> @@ -3332,6 +3332,27 @@ DEFINE_INT_AND_FLOAT_ROUND_FN (RINT)
> (if (INTEGRAL_TYPE_P (TREE_TYPE (@0)) || POINTER_TYPE_P (TREE_TYPE (@0)))
> (rcmp @0 @1))))
>
> +/* (type)([0,1]@a != 0) -> (type)a
> + (type)([0,1]@a == 1) -> (type)a
> + (type)([0,1]@a == 0) -> a ^ 1
> + (type)([0,1]@a != 1) -> a ^ 1. */
> +(for eqne (eq ne)
> + (simplify
> + (convert (eqne zero_one_valued_p@0 INTEGER_CST@1))
> + (if ((integer_zerop (@1) || integer_onep (@1)))
> + (if ((eqne == EQ_EXPR) ^ integer_zerop (@1))
> + (convert @0)
> + /* a^1 can only be produced for gimple as
> + fold has the exact opposite transformation
> + for `(X & 1) ^ 1`.
> + See `Fold ~X & 1 as (X & 1) == 0.`
> + and `Fold (X ^ 1) & 1 as (X & 1) == 0.` in fold-const.cc.
> + Only do this if the types match as (type)(a == 0) is
> + canonical form normally, while `a ^ 1` is canonical when
> + there is no type change. */
> + (if (GIMPLE && types_match (type, TREE_TYPE (@0)))
> + (bit_xor @0 { build_one_cst (type); } ))))))
> +
> /* We can't reassociate at all for saturating types. */
> (if (!TYPE_SATURATING (type))
>
> diff --git a/gcc/testsuite/gcc.dg/tree-ssa/pr110637-1.c
> b/gcc/testsuite/gcc.dg/tree-ssa/pr110637-1.c
> new file mode 100644
> index 00000000000..3d03b0992a4
> --- /dev/null
> +++ b/gcc/testsuite/gcc.dg/tree-ssa/pr110637-1.c
> @@ -0,0 +1,10 @@
> +/* { dg-do compile } */
> +/* { dg-options "-O1 -fdump-tree-optimized" } */
> +int f(int a)
> +{
> + int b = (a & 1)!=0;
> + return b;
> +}
> +
> +/* This should be optimized to just return (a & 1); */
> +/* { dg-final { scan-tree-dump-not " == " "optimized"} } */
> diff --git a/gcc/testsuite/gcc.dg/tree-ssa/pr110637-2.c
> b/gcc/testsuite/gcc.dg/tree-ssa/pr110637-2.c
> new file mode 100644
> index 00000000000..f1c5b90353a
> --- /dev/null
> +++ b/gcc/testsuite/gcc.dg/tree-ssa/pr110637-2.c
> @@ -0,0 +1,13 @@
> +/* { dg-do compile } */
> +/* { dg-options "-O1 -fdump-tree-optimized" } */
> +int f(int a)
> +{
> + int b = a & 1;
> + int c = b == 0;
> + return c;
> +}
> +
> +/* This should be optimized to just return `(a&1) ^ 1` or `(~a) & 1`. */
> +/* { dg-final { scan-tree-dump-not " == " "optimized"} } */
> +/* { dg-final { scan-tree-dump-times "~a" 1 "optimized"} } */
> +/* { dg-final { scan-tree-dump-times " & 1" 1 "optimized"} } */
> diff --git a/gcc/testsuite/gcc.dg/tree-ssa/pr110637-3.c
> b/gcc/testsuite/gcc.dg/tree-ssa/pr110637-3.c
> new file mode 100644
> index 00000000000..ce80146d9df
> --- /dev/null
> +++ b/gcc/testsuite/gcc.dg/tree-ssa/pr110637-3.c
> @@ -0,0 +1,14 @@
> +/* { dg-do compile } */
> +/* { dg-options "-O1 -fdump-tree-optimized" } */
> +int f(int a)
> +{
> + int b = a & 1;
> + int c = b == 0;
> + int d = ~a;
> + int e = d & 1;
> + return c == e;
> +}
> +
> +/* This should be optimized to just `return 1` */
> +/* { dg-final { scan-tree-dump-not " == " "optimized"} } */
> +/* { dg-final { scan-tree-dump-times "return 1" 1 "optimized"} } */
> diff --git a/gcc/testsuite/gcc.dg/tree-ssa/pr111972-1.c
> b/gcc/testsuite/gcc.dg/tree-ssa/pr111972-1.c
> new file mode 100644
> index 00000000000..0611808ed50
> --- /dev/null
> +++ b/gcc/testsuite/gcc.dg/tree-ssa/pr111972-1.c
> @@ -0,0 +1,34 @@
> +/* { dg-do compile } */
> +/* { dg-options "-O1 -fdump-tree-phiopt" } */
> +double
> +foo() {
> + long n3 = 3450000, xtra = 7270;
> + long i,ix;
> + long j;
> + double Check;
> +
> + /* Section 3, Conditional jumps */
> + j = 0;
> + {
> + for (ix=0; ix<xtra; ix++)
> + {
> + for(i=0; i<n3; i++)
> + {
> + if(j==1) j = 2;
> + else j = 3;
> + if(j>2) j = 0;
> + else j = 1;
> + if(j<1) j = 1;
> + else j = 0;
> + }
> + }
> + }
> + Check = Check + (double)j;
> + return Check;
> +}
> +
> +/* the above if statements in loop should be optimized to just `j ^ 1`
> + and should not be (type)(j != 1). */
> +/* { dg-final { scan-tree-dump-not " != 1" "phiopt2"} } */
> +/* { dg-final { scan-tree-dump-times " \\^ 1" 1 "phiopt2"} } */
> +
> diff --git a/gcc/testsuite/gcc.dg/tree-ssa/pr69270.c
> b/gcc/testsuite/gcc.dg/tree-ssa/pr69270.c
> index 0d66cc4383f..b08ec9d6ddb 100644
> --- a/gcc/testsuite/gcc.dg/tree-ssa/pr69270.c
> +++ b/gcc/testsuite/gcc.dg/tree-ssa/pr69270.c
> @@ -7,8 +7,8 @@
> /* { dg-final { scan-tree-dump-times "Replaced .bufferstep_\[0-9\]+. with
> constant .1." 1 "dom3"} } */
>
> /* And some assignments ought to fold down to constants. */
> -/* { dg-final { scan-tree-dump-times "Folded to: _\[0-9\]+ = 1;" 1 "dom3"} }
> */
> -/* { dg-final { scan-tree-dump-times "Folded to: _\[0-9\]+ = 0;" 1 "dom3"} }
> */
> +/* { dg-final { scan-tree-dump-times "Folded to: (?:bufferstep)?_\[0-9\]+ =
> 1;" 1 "dom3"} } */
> +/* { dg-final { scan-tree-dump-times "Folded to: (?:bufferstep)?_\[0-9\]+ =
> 0;" 1 "dom3"} } */
>
> /* The XOR operations should have been optimized to constants. */
> /* { dg-final { scan-tree-dump-not "bit_xor" "dom3"} } */
> diff --git a/gcc/testsuite/gcc.target/i386/pr110790-2.c
> b/gcc/testsuite/gcc.target/i386/pr110790-2.c
> index 8b9d650c6e9..16c73cb7465 100644
> --- a/gcc/testsuite/gcc.target/i386/pr110790-2.c
> +++ b/gcc/testsuite/gcc.target/i386/pr110790-2.c
> @@ -9,5 +9,17 @@ refmpn_tstbit_bad (mp_srcptr ptr, unsigned long bit)
> return (((ptr)[(bit)/(32 - 0)] & (((mp_limb_t) 1L) << ((bit)%(32 - 0))))
> != 0);
> }
>
> -/* { dg-final { scan-assembler "bt\[ql\]" } } */
> -/* { dg-final { scan-assembler "setc" } } */
> +/* 32bit produces:
> + btl %eax, %edx
> + setc %al
> + movzbl %al, %eax
> + */
> +/* { dg-final { scan-assembler "bt\[ql\]" { target { ! lp64 } } } } */
> +/* { dg-final { scan-assembler "setc" { target { ! lp64 } } } } */
> +
> +/* 64bit produces:
> + shrq %cl, %rax
> + andl $1, %eax
> + */
> +/* { dg-final { scan-assembler-times "shrq" 2 { target { lp64 } } } } */
> +/* { dg-final { scan-assembler-times "andl" 2 { target { lp64 } } } } */
> --
> 2.39.3
>
