On Thu, Jul 25, 2024 at 4:16 AM Andrew Pinski <quic_apin...@quicinc.com> wrote:
>
> To better create rtl directly from gimple, we can use
> these already internal functions from the gimple.
>
> That is simplify `a & ~b` into BIT_ANDN.
> Likewise `a | ~b` into BIT_IORN.
> We only want to do this late after vectorization as some
> targets (e.g. aarch64 SVE) has BIT_IORN on scalars but not on
> some vector modes; even though the vectorizer could expand it back.
>
> Note a few testcases need to be changed to not look
> into optimized dump and catch them earlier.
> The modified testcases could catch BIT_ANDN and BIT_IORN so move the
> testing to forwprop2 before simplification happens.
>
> Built and tested on aarch64-linux-gnu with no regressions.
I think we want these only for ISEL as they happen way too often and will
disturb the IL too much in ways not handled by passes. not/and/or are
too important ops to "hide" from most of the gimple pipeline.
Richard.
> PR target/115086
>
> gcc/ChangeLog:
>
> * match.pd (`a & ~b`, `a | ~b`): New pattern.
> (BIT_ANDN/BIT_IORN with CST): New pattern.
>
> gcc/testsuite/ChangeLog:
>
> * gcc.target/aarch64/bic-cst-1.c: New test.
> * gcc.target/aarch64/bic_simd-1.c: New test.
> * gcc.dg/tree-ssa/bitops-1.c: Move testing from optimized to
> forwprop2.
> * gcc.dg/tree-ssa/bitops-6.c: Likewise.
> * gcc.dg/tree-ssa/cmpbit-4.c: Likewise.
> * gcc.dg/tree-ssa/pr110637-2.c: Likewise.
> * gcc.dg/tree-ssa/pr94880.c: Likewise.
> * gcc.dg/tree-ssa/pr96671-1.c: Likewise.
>
> Signed-off-by: Andrew Pinski <quic_apin...@quicinc.com>
> ---
> gcc/match.pd | 17 ++++++++++
> gcc/testsuite/gcc.dg/tree-ssa/bitops-1.c | 10 +++---
> gcc/testsuite/gcc.dg/tree-ssa/bitops-6.c | 12 +++----
> gcc/testsuite/gcc.dg/tree-ssa/bitops-8.c | 8 ++---
> gcc/testsuite/gcc.dg/tree-ssa/cmpbit-4.c | 12 +++----
> gcc/testsuite/gcc.dg/tree-ssa/pr110637-2.c | 8 ++---
> gcc/testsuite/gcc.dg/tree-ssa/pr94880.c | 6 ++--
> gcc/testsuite/gcc.dg/tree-ssa/pr96671-1.c | 8 ++---
> gcc/testsuite/gcc.target/aarch64/bic-cst-1.c | 31 ++++++++++++++++++
> gcc/testsuite/gcc.target/aarch64/bic_simd-1.c | 32 +++++++++++++++++++
> 10 files changed, 112 insertions(+), 32 deletions(-)
> create mode 100644 gcc/testsuite/gcc.target/aarch64/bic-cst-1.c
> create mode 100644 gcc/testsuite/gcc.target/aarch64/bic_simd-1.c
>
> diff --git a/gcc/match.pd b/gcc/match.pd
> index cf359b0ec0f..56f631dfeec 100644
> --- a/gcc/match.pd
> +++ b/gcc/match.pd
> @@ -9979,6 +9979,23 @@ and,
> (cond_op:s @1 @2 @3 @4 @5) @5)
> (cond_op (bit_and @1 @0) @2 @3 @4 @5)))
>
> +#if GIMPLE
> +/* Create bit_andc and bit_iorc internal functions. */
> +(for bitop (bit_and bit_ior)
> + bitopc (IFN_BIT_ANDN IFN_BIT_IORN)
> + (simplify
> + (bitop:c (bit_not:s @0) @1)
> + (if (canonicalize_math_after_vectorization_p ()
> + && direct_internal_fn_supported_p (as_internal_fn (bitopc),
> + type, OPTIMIZE_FOR_BOTH))
> + (bitopc @1 @0)))
> + /* If the second operand is a constant, then reduce it to a & ~cst if
> + the not simplifies. */
> + (simplify
> + (bitopc @0 CONSTANT_CLASS_P@1)
> + (bitop (bit_not! @1) @0)))
> +#endif
> +
> /* For pointers @0 and @2 and nonnegative constant offset @1, look for
> expressions like:
>
> diff --git a/gcc/testsuite/gcc.dg/tree-ssa/bitops-1.c
> b/gcc/testsuite/gcc.dg/tree-ssa/bitops-1.c
> index cf2823deb62..3a394b1f188 100644
> --- a/gcc/testsuite/gcc.dg/tree-ssa/bitops-1.c
> +++ b/gcc/testsuite/gcc.dg/tree-ssa/bitops-1.c
> @@ -1,5 +1,5 @@
> /* { dg-do run } */
> -/* { dg-options "-O -fdump-tree-optimized-raw" } */
> +/* { dg-options "-O -fdump-tree-forwprop2-raw" } */
>
> #define DECLS(n,VOL) \
> __attribute__((noinline,noclone)) \
> @@ -66,7 +66,7 @@ int main(){
> }
> }
>
> -/* { dg-final { scan-tree-dump-times "bit_not_expr" 12 "optimized"} } */
> -/* { dg-final { scan-tree-dump-times "bit_and_expr" 9 "optimized"} } */
> -/* { dg-final { scan-tree-dump-times "bit_ior_expr" 10 "optimized"} } */
> -/* { dg-final { scan-tree-dump-times "bit_xor_expr" 9 "optimized"} } */
> +/* { dg-final { scan-tree-dump-times "bit_not_expr, " 12 "forwprop2"} } */
> +/* { dg-final { scan-tree-dump-times "bit_and_expr, " 9 "forwprop2"} } */
> +/* { dg-final { scan-tree-dump-times "bit_ior_expr, " 10 "forwprop2"} } */
> +/* { dg-final { scan-tree-dump-times "bit_xor_expr, " 9 "forwprop2"} } */
> diff --git a/gcc/testsuite/gcc.dg/tree-ssa/bitops-6.c
> b/gcc/testsuite/gcc.dg/tree-ssa/bitops-6.c
> index e6ab2fd6c71..e08132e2ab5 100644
> --- a/gcc/testsuite/gcc.dg/tree-ssa/bitops-6.c
> +++ b/gcc/testsuite/gcc.dg/tree-ssa/bitops-6.c
> @@ -1,5 +1,5 @@
> /* { dg-do compile } */
> -/* { dg-options "-O2 -fdump-tree-optimized-raw" } */
> +/* { dg-options "-O2 -fdump-tree-forwprop2-raw" } */
> /* PR tree-optimization/111282 */
>
>
> @@ -25,9 +25,9 @@ int fcmp(int x, int y)
> return a & (b ^ !a); // (x == 2) & (y == 1)
> }
>
> -/* { dg-final { scan-tree-dump-not "bit_xor_expr, " "optimized" } } */
> -/* { dg-final { scan-tree-dump-times "bit_and_expr, " 4 "optimized" } } */
> -/* { dg-final { scan-tree-dump-times "bit_not_expr, " 1 "optimized" } } */
> -/* { dg-final { scan-tree-dump-not "ne_expr, " "optimized" } } */
> -/* { dg-final { scan-tree-dump-times "eq_expr, " 2 "optimized" } } */
> +/* { dg-final { scan-tree-dump-not "bit_xor_expr, " "forwprop2" } } */
> +/* { dg-final { scan-tree-dump-times "bit_and_expr, " 4 "forwprop2" } } */
> +/* { dg-final { scan-tree-dump-times "bit_not_expr, " 1 "forwprop2" } } */
> +/* { dg-final { scan-tree-dump-not "ne_expr, " "forwprop2" } } */
> +/* { dg-final { scan-tree-dump-times "eq_expr, " 2 "forwprop2" } } */
>
> diff --git a/gcc/testsuite/gcc.dg/tree-ssa/bitops-8.c
> b/gcc/testsuite/gcc.dg/tree-ssa/bitops-8.c
> index 40f756e4455..52c2f394222 100644
> --- a/gcc/testsuite/gcc.dg/tree-ssa/bitops-8.c
> +++ b/gcc/testsuite/gcc.dg/tree-ssa/bitops-8.c
> @@ -1,5 +1,5 @@
> /* { dg-do compile } */
> -/* { dg-options "-O2 -fdump-tree-optimized-raw" } */
> +/* { dg-options "-O2 -fdump-tree-forwprop2-raw" } */
> /* PR tree-optimization/115224 */
>
> int f1(int a, int b)
> @@ -9,7 +9,7 @@ int f1(int a, int b)
> return c | (a ^ b);
> // ~((a ^ 1) & b) or (a ^ -2) | ~b
> }
> -/* { dg-final { scan-tree-dump-times "bit_xor_expr, " 1 "optimized" } }
> */
> -/* { dg-final { scan-tree-dump-times "bit_ior_expr, " 1 "optimized" } }
> */
> -/* { dg-final { scan-tree-dump-times "bit_not_expr, " 1 "optimized" } }
> */
> +/* { dg-final { scan-tree-dump-times "bit_xor_expr, " 1 "forwprop2" } }
> */
> +/* { dg-final { scan-tree-dump-times "bit_ior_expr, " 1 "forwprop2" } }
> */
> +/* { dg-final { scan-tree-dump-times "bit_not_expr, " 1 "forwprop2" } }
> */
>
> diff --git a/gcc/testsuite/gcc.dg/tree-ssa/cmpbit-4.c
> b/gcc/testsuite/gcc.dg/tree-ssa/cmpbit-4.c
> index cdba5d623af..627dcc57cc7 100644
> --- a/gcc/testsuite/gcc.dg/tree-ssa/cmpbit-4.c
> +++ b/gcc/testsuite/gcc.dg/tree-ssa/cmpbit-4.c
> @@ -1,5 +1,5 @@
> /* { dg-do compile } */
> -/* { dg-options "-O2 -fdump-tree-optimized-raw" } */
> +/* { dg-options "-O2 -fdump-tree-forwprop2-raw" } */
>
> int g(int x, int y)
> {
> @@ -40,8 +40,8 @@ _Bool gbi0(int a, int b)
> }
>
> /* All of these should be optimized to `x & y` or `~x & y` */
> -/* { dg-final { scan-tree-dump-times "le_expr, " 3 "optimized" } } */
> -/* { dg-final { scan-tree-dump-times "gt_expr, " 1 "optimized" } } */
> -/* { dg-final { scan-tree-dump-not "bit_xor_expr, " "optimized" } } */
> -/* { dg-final { scan-tree-dump-times "bit_and_expr, " 6 "optimized" } } */
> -/* { dg-final { scan-tree-dump-times "bit_not_expr, " 2 "optimized" } } */
> +/* { dg-final { scan-tree-dump-times "le_expr, " 3 "forwprop2" } } */
> +/* { dg-final { scan-tree-dump-times "gt_expr, " 1 "forwprop2" } } */
> +/* { dg-final { scan-tree-dump-not "bit_xor_expr, " "forwprop2" } } */
> +/* { dg-final { scan-tree-dump-times "bit_and_expr, " 6 "forwprop2" } } */
> +/* { dg-final { scan-tree-dump-times "bit_not_expr, " 2 "forwprop2" } } */
> diff --git a/gcc/testsuite/gcc.dg/tree-ssa/pr110637-2.c
> b/gcc/testsuite/gcc.dg/tree-ssa/pr110637-2.c
> index f1c5b90353a..81d6a092508 100644
> --- a/gcc/testsuite/gcc.dg/tree-ssa/pr110637-2.c
> +++ b/gcc/testsuite/gcc.dg/tree-ssa/pr110637-2.c
> @@ -1,5 +1,5 @@
> /* { dg-do compile } */
> -/* { dg-options "-O1 -fdump-tree-optimized" } */
> +/* { dg-options "-O1 -fdump-tree-forwprop2" } */
> int f(int a)
> {
> int b = a & 1;
> @@ -8,6 +8,6 @@ int f(int a)
> }
>
> /* 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"} } */
> +/* { dg-final { scan-tree-dump-not " == " "forwprop2"} } */
> +/* { dg-final { scan-tree-dump-times "~a" 1 "forwprop2"} } */
> +/* { dg-final { scan-tree-dump-times " & 1" 1 "forwprop2"} } */
> diff --git a/gcc/testsuite/gcc.dg/tree-ssa/pr94880.c
> b/gcc/testsuite/gcc.dg/tree-ssa/pr94880.c
> index f7216618147..72a14b915a5 100644
> --- a/gcc/testsuite/gcc.dg/tree-ssa/pr94880.c
> +++ b/gcc/testsuite/gcc.dg/tree-ssa/pr94880.c
> @@ -1,8 +1,8 @@
> /* PR tree-optimization/94786 */
> /* { dg-do compile } */
> -/* { dg-options "-O2 -fdump-tree-optimized" } */
> -/* { dg-final { scan-tree-dump-times "= ~\[xy\]_" 4 "optimized" } } */
> -/* { dg-final { scan-tree-dump-times " & \[xy\]_" 4 "optimized" } } */
> +/* { dg-options "-O2 -fdump-tree-forwprop2" } */
> +/* { dg-final { scan-tree-dump-times "= ~\[xy\]_" 4 "forwprop2" } } */
> +/* { dg-final { scan-tree-dump-times " & \[xy\]_" 4 "forwprop2" } } */
>
> unsigned
> foo_u(unsigned x, unsigned y)
> diff --git a/gcc/testsuite/gcc.dg/tree-ssa/pr96671-1.c
> b/gcc/testsuite/gcc.dg/tree-ssa/pr96671-1.c
> index 42c5b27b53f..cf977b55cc2 100644
> --- a/gcc/testsuite/gcc.dg/tree-ssa/pr96671-1.c
> +++ b/gcc/testsuite/gcc.dg/tree-ssa/pr96671-1.c
> @@ -1,9 +1,9 @@
> /* PR tree-optimization/96671 */
> /* { dg-do compile } */
> -/* { dg-options "-O2 -fdump-tree-optimized" } */
> -/* { dg-final { scan-tree-dump-times " \\^ " 6 "optimized" } } */
> -/* { dg-final { scan-tree-dump-times " ~" 6 "optimized" } } */
> -/* { dg-final { scan-tree-dump-times " & " 6 "optimized" } } */
> +/* { dg-options "-O2 -fdump-tree-forwprop2" } */
> +/* { dg-final { scan-tree-dump-times " \\^ " 6 "forwprop2" } } */
> +/* { dg-final { scan-tree-dump-times " ~" 6 "forwprop2" } } */
> +/* { dg-final { scan-tree-dump-times " & " 6 "forwprop2" } } */
>
> int
> foo (int a, int b, int c)
> diff --git a/gcc/testsuite/gcc.target/aarch64/bic-cst-1.c
> b/gcc/testsuite/gcc.target/aarch64/bic-cst-1.c
> new file mode 100644
> index 00000000000..1c25de3ba84
> --- /dev/null
> +++ b/gcc/testsuite/gcc.target/aarch64/bic-cst-1.c
> @@ -0,0 +1,31 @@
> +/* { dg-do compile } */
> +/* { dg-additional-options "-O2 -fdump-tree-optimized" } */
> +/* { dg-final { check-function-bodies "**" "" "" { target { le } } } } */
> +
> +/**
> +**bar1:
> +** mov w([0-9]+), 4
> +** bic w0, w\1, w1
> +** ret
> +*/
> +int bar1(int a, int c)
> +{
> + int b = 4 & ~c;
> + return b;
> +}
> +
> +/**
> +**foo1:
> +** mov w([0-9]+), 4
> +** orn w0, w\1, w1
> +** ret
> +*/
> +int foo1(int a, int c)
> +{
> + int b = 4 | ~c;
> + return b;
> +}
> +
> +/* { dg-final { scan-tree-dump ".BIT_ANDN " "optimized" } } */
> +/* { dg-final { scan-tree-dump ".BIT_IORN " "optimized" } } */
> +
> diff --git a/gcc/testsuite/gcc.target/aarch64/bic_simd-1.c
> b/gcc/testsuite/gcc.target/aarch64/bic_simd-1.c
> new file mode 100644
> index 00000000000..e2a69272456
> --- /dev/null
> +++ b/gcc/testsuite/gcc.target/aarch64/bic_simd-1.c
> @@ -0,0 +1,32 @@
> +/* { dg-do compile } */
> +/* { dg-additional-options "-O2 -fdump-tree-optimized" } */
> +/* { dg-final { check-function-bodies "**" "" "" { target { le } } } } */
> +
> +/**
> +**bar1:
> +** movi v([0-9]+).2s, 0x4
> +** bic v0.8b, v\1.8b, v1.8b
> +** ret
> +*/
> +#define vect8 __attribute__((vector_size(8)))
> +vect8 int bar1(vect8 int a, vect8 int c)
> +{
> + vect8 int b = 4 & ~c;
> + return b;
> +}
> +
> +/**
> +**foo1:
> +** movi v([0-9]+).2s, 0x4
> +** orn v0.8b, v\1.8b, v1.8b
> +** ret
> +*/
> +vect8 int foo1(vect8 int a, vect8 int c)
> +{
> + vect8 int b = 4 | ~c;
> + return b;
> +}
> +
> +/* { dg-final { scan-tree-dump ".BIT_ANDN " "optimized" } } */
> +/* { dg-final { scan-tree-dump ".BIT_IORN " "optimized" } } */
> +
> --
> 2.43.0
>
