match: Fix the `popcnt(a&b) + popcnt(a|b)` patthern for types [PR111913]
Checks
Commit Message
So this pattern needs a little help on the gimple side of things to know what
the type popcount should be. For most builtins, the type is the same as the input
but popcount and others are not. And when using it with another outer expression,
genmatch needs some slight help to know that the return type was type rather than
the argument type.
Bootstrapped and tested on x86_64-linux-gnu with no regressions.
PR tree-optimization/111913
gcc/ChangeLog:
* match.pd (`popcount(X&Y) + popcount(X|Y)`): Add the resulting
type for popcount.
gcc/testsuite/ChangeLog:
* gcc.c-torture/compile/fold-popcount-1.c: New test.
* gcc.dg/fold-popcount-8a.c: New test.
---
gcc/match.pd | 2 +-
.../gcc.c-torture/compile/fold-popcount-1.c | 13 ++++++++
gcc/testsuite/gcc.dg/fold-popcount-8a.c | 33 +++++++++++++++++++
3 files changed, 47 insertions(+), 1 deletion(-)
create mode 100644 gcc/testsuite/gcc.c-torture/compile/fold-popcount-1.c
create mode 100644 gcc/testsuite/gcc.dg/fold-popcount-8a.c
Comments
On Tue, Oct 24, 2023 at 1:04 AM Andrew Pinski <pinskia@gmail.com> wrote:
>
> So this pattern needs a little help on the gimple side of things to know what
> the type popcount should be. For most builtins, the type is the same as the input
> but popcount and others are not. And when using it with another outer expression,
> genmatch needs some slight help to know that the return type was type rather than
> the argument type.
>
> Bootstrapped and tested on x86_64-linux-gnu with no regressions.
OK.
> PR tree-optimization/111913
>
> gcc/ChangeLog:
>
> * match.pd (`popcount(X&Y) + popcount(X|Y)`): Add the resulting
> type for popcount.
>
> gcc/testsuite/ChangeLog:
>
> * gcc.c-torture/compile/fold-popcount-1.c: New test.
> * gcc.dg/fold-popcount-8a.c: New test.
> ---
> gcc/match.pd | 2 +-
> .../gcc.c-torture/compile/fold-popcount-1.c | 13 ++++++++
> gcc/testsuite/gcc.dg/fold-popcount-8a.c | 33 +++++++++++++++++++
> 3 files changed, 47 insertions(+), 1 deletion(-)
> create mode 100644 gcc/testsuite/gcc.c-torture/compile/fold-popcount-1.c
> create mode 100644 gcc/testsuite/gcc.dg/fold-popcount-8a.c
>
> diff --git a/gcc/match.pd b/gcc/match.pd
> index ce8d159d260..f725a685863 100644
> --- a/gcc/match.pd
> +++ b/gcc/match.pd
> @@ -8600,7 +8600,7 @@ DEFINE_INT_AND_FLOAT_ROUND_FN (RINT)
> /* popcount(X&Y) + popcount(X|Y) is popcount(x) + popcount(Y). */
> (simplify
> (plus:c (POPCOUNT:s (bit_and:s @0 @1)) (POPCOUNT:s (bit_ior:cs @0 @1)))
> - (plus (POPCOUNT @0) (POPCOUNT @1)))
> + (plus (POPCOUNT:type @0) (POPCOUNT:type @1)))
>
> /* popcount(X) + popcount(Y) - popcount(X&Y) is popcount(X|Y). */
> /* popcount(X) + popcount(Y) - popcount(X|Y) is popcount(X&Y). */
> diff --git a/gcc/testsuite/gcc.c-torture/compile/fold-popcount-1.c b/gcc/testsuite/gcc.c-torture/compile/fold-popcount-1.c
> new file mode 100644
> index 00000000000..d3d3a2976e0
> --- /dev/null
> +++ b/gcc/testsuite/gcc.c-torture/compile/fold-popcount-1.c
> @@ -0,0 +1,13 @@
> +/* PR tree-optimization/111913 */
> +
> +int f(unsigned int x, unsigned int y)
> +{
> + return __builtin_popcount (x&y) + __builtin_popcount (y|x--);
> +}
> +
> +int f2(unsigned int x, unsigned int y)
> +{
> + int t = __builtin_popcount (x&y);
> + int t1 = __builtin_popcount (x|y);
> + return t + t1;
> +}
> diff --git a/gcc/testsuite/gcc.dg/fold-popcount-8a.c b/gcc/testsuite/gcc.dg/fold-popcount-8a.c
> new file mode 100644
> index 00000000000..3001522f259
> --- /dev/null
> +++ b/gcc/testsuite/gcc.dg/fold-popcount-8a.c
> @@ -0,0 +1,33 @@
> +/* { dg-do compile } */
> +/* { dg-options "-O2 -fdump-tree-optimized" } */
> +
> +int foo1(unsigned int x, unsigned int y)
> +{
> + int t = __builtin_popcount (x&y);
> + int t1 = __builtin_popcount (x|y);
> + return t + t1;
> +}
> +
> +int foo2(unsigned int x, unsigned int y)
> +{
> + int t1 = __builtin_popcount (x|y);
> + int t = __builtin_popcount (x&y);
> + return t + t1;
> +}
> +
> +int foo3(unsigned int y, unsigned int x)
> +{
> + int t = __builtin_popcount (x&y);
> + int t1 = __builtin_popcount (x|y);
> + return t + t1;
> +}
> +
> +int foo4(unsigned int y, unsigned int x)
> +{
> + int t1 = __builtin_popcount (x|y);
> + int t = __builtin_popcount (x&y);
> + return t + t1;
> +}
> +
> +/* { dg-final { scan-tree-dump-not " & " "optimized" } } */
> +/* { dg-final { scan-tree-dump-not " \\| " "optimized" } } */
> --
> 2.39.3
>
@@ -8600,7 +8600,7 @@ DEFINE_INT_AND_FLOAT_ROUND_FN (RINT)
/* popcount(X&Y) + popcount(X|Y) is popcount(x) + popcount(Y). */
(simplify
(plus:c (POPCOUNT:s (bit_and:s @0 @1)) (POPCOUNT:s (bit_ior:cs @0 @1)))
- (plus (POPCOUNT @0) (POPCOUNT @1)))
+ (plus (POPCOUNT:type @0) (POPCOUNT:type @1)))
/* popcount(X) + popcount(Y) - popcount(X&Y) is popcount(X|Y). */
/* popcount(X) + popcount(Y) - popcount(X|Y) is popcount(X&Y). */
new file mode 100644
@@ -0,0 +1,13 @@
+/* PR tree-optimization/111913 */
+
+int f(unsigned int x, unsigned int y)
+{
+ return __builtin_popcount (x&y) + __builtin_popcount (y|x--);
+}
+
+int f2(unsigned int x, unsigned int y)
+{
+ int t = __builtin_popcount (x&y);
+ int t1 = __builtin_popcount (x|y);
+ return t + t1;
+}
new file mode 100644
@@ -0,0 +1,33 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -fdump-tree-optimized" } */
+
+int foo1(unsigned int x, unsigned int y)
+{
+ int t = __builtin_popcount (x&y);
+ int t1 = __builtin_popcount (x|y);
+ return t + t1;
+}
+
+int foo2(unsigned int x, unsigned int y)
+{
+ int t1 = __builtin_popcount (x|y);
+ int t = __builtin_popcount (x&y);
+ return t + t1;
+}
+
+int foo3(unsigned int y, unsigned int x)
+{
+ int t = __builtin_popcount (x&y);
+ int t1 = __builtin_popcount (x|y);
+ return t + t1;
+}
+
+int foo4(unsigned int y, unsigned int x)
+{
+ int t1 = __builtin_popcount (x|y);
+ int t = __builtin_popcount (x&y);
+ return t + t1;
+}
+
+/* { dg-final { scan-tree-dump-not " & " "optimized" } } */
+/* { dg-final { scan-tree-dump-not " \\| " "optimized" } } */