Re: [PATCH] MATCH: Move `a <= CST1 ? MAX : a` optimization to match
On Mon, May 8, 2023 at 12:21 AM Andrew Pinski via Gcc-patches
wrote:
>
> This moves the `a <= CST1 ? MAX : a` optimization
> from phiopt to match. It just adds a new pattern to match.pd.
>
> There is one more change needed before being able to remove
> minmax_replacement from phiopt.
>
> A few notes on the testsuite changes:
> * phi-opt-5.c is now able to optimize at phiopt1 so remove
> the xfail.
> * pr66726-4.c can be optimized during fold before phiopt1
> so need to change the scanning.
> * pr66726-5.c needs two phiopt passes currently to optimize
> to the right thing, it needed 2 phiopt passes before, the cast
> from int to unsigned char is the reason.
> * pr66726-6.c is what the original pr66726-4.c was testing
> before the fold was able to optimize it.
>
> OK? Bootstrapped and tested on x86_64-linux-gnu.
OK.
> gcc/ChangeLog:
>
> * match.pd (`(a CMP CST1) ? max : a`): New
> pattern.
>
> gcc/testsuite/ChangeLog:
>
> * gcc.dg/tree-ssa/phi-opt-5.c: Remove last xfail.
> * gcc.dg/tree-ssa/pr66726-4.c: Change how scanning
> works.
> * gcc.dg/tree-ssa/pr66726-5.c: New test.
> * gcc.dg/tree-ssa/pr66726-6.c: New test.
> ---
> gcc/match.pd | 18 +++
> gcc/testsuite/gcc.dg/tree-ssa/phi-opt-5.c | 2 +-
> gcc/testsuite/gcc.dg/tree-ssa/pr66726-4.c | 5 +++-
> gcc/testsuite/gcc.dg/tree-ssa/pr66726-5.c | 28 +++
> gcc/testsuite/gcc.dg/tree-ssa/pr66726-6.c | 17 ++
> 5 files changed, 68 insertions(+), 2 deletions(-)
> create mode 100644 gcc/testsuite/gcc.dg/tree-ssa/pr66726-5.c
> create mode 100644 gcc/testsuite/gcc.dg/tree-ssa/pr66726-6.c
>
> diff --git a/gcc/match.pd b/gcc/match.pd
> index ceae1c34abc..a55ede838cd 100644
> --- a/gcc/match.pd
> +++ b/gcc/match.pd
> @@ -4954,6 +4954,24 @@ DEFINE_INT_AND_FLOAT_ROUND_FN (RINT)
> (if (code == MAX_EXPR)
>(minmax (max @1 @2) @4)))
>
> +/* Optimize (a CMP CST1) ? max : a */
> +(for cmp(gt ge lt le)
> + minmax (min min max max)
> + (simplify
> + (cond (cmp @0 @1) (minmax:c@2 @0 @3) @4)
> + (with
> +{
> + tree_code code = minmax_from_comparison (cmp, @0, @1, @0, @4);
> +}
> +(if ((cmp == LT_EXPR || cmp == LE_EXPR)
> +&& code == MIN_EXPR
> + && integer_nonzerop (fold_build2 (LE_EXPR, boolean_type_node, @3,
> @1)))
> + (min @2 @4)
> + (if ((cmp == GT_EXPR || cmp == GE_EXPR)
> + && code == MAX_EXPR
> + && integer_nonzerop (fold_build2 (GE_EXPR, boolean_type_node, @3,
> @1)))
> + (max @2 @4))
> +
> /* X != C1 ? -X : C2 simplifies to -X when -C1 == C2. */
> (simplify
> (cond (ne @0 INTEGER_CST@1) (negate@3 @0) INTEGER_CST@2)
> diff --git a/gcc/testsuite/gcc.dg/tree-ssa/phi-opt-5.c
> b/gcc/testsuite/gcc.dg/tree-ssa/phi-opt-5.c
> index 5f78a1ba6dc..e78d9d8b83d 100644
> --- a/gcc/testsuite/gcc.dg/tree-ssa/phi-opt-5.c
> +++ b/gcc/testsuite/gcc.dg/tree-ssa/phi-opt-5.c
> @@ -39,7 +39,7 @@ float repl2 (float vary)
>
> /* phiopt1 confused by predictors. */
> /* { dg-final { scan-tree-dump "vary.*MAX_EXPR.*0\\.0" "phiopt1" } } */
> -/* { dg-final { scan-tree-dump "vary.*MIN_EXPR.*1\\.0" "phiopt1" { xfail
> *-*-* } } } */
> +/* { dg-final { scan-tree-dump "vary.*MIN_EXPR.*1\\.0" "phiopt1" } } */
> /* { dg-final { scan-tree-dump "vary.*MAX_EXPR.*0\\.0" "phiopt2"} } */
> /* { dg-final { scan-tree-dump "vary.*MIN_EXPR.*1\\.0" "phiopt2"} } */
>
> diff --git a/gcc/testsuite/gcc.dg/tree-ssa/pr66726-4.c
> b/gcc/testsuite/gcc.dg/tree-ssa/pr66726-4.c
> index 4e43522f3a3..930ad5fb79f 100644
> --- a/gcc/testsuite/gcc.dg/tree-ssa/pr66726-4.c
> +++ b/gcc/testsuite/gcc.dg/tree-ssa/pr66726-4.c
> @@ -9,4 +9,7 @@ foo (unsigned char *p, int i)
>*p = SAT (i);
> }
>
> -/* { dg-final { scan-tree-dump-times "COND_EXPR .*and PHI .*converted to
> straightline code" 1 "phiopt1" } } */
> +/* fold could optimize SAT before phiopt1 so only match on the
> + MIN/MAX here. */
> +/* { dg-final { scan-tree-dump-times "= MIN_EXPR" 1 "phiopt1" } } */
> +/* { dg-final { scan-tree-dump-times "= MAX_EXPR" 1 "phiopt1" } } */
> diff --git a/gcc/testsuite/gcc.dg/tree-ssa/pr66726-5.c
> b/gcc/testsuite/gcc.dg/tree-ssa/pr66726-5.c
> new file mode 100644
> index 000..4b5066cdb6b
> --- /dev/null
> +++ b/gcc/testsuite/gcc.dg/tree-ssa/pr66726-5.c
> @@ -0,0 +1,28 @@
> +/* { dg-do compile } */
> +/* { dg-options "-O2 -fdump-tree-phiopt1-details -fdump-tree-phiopt2-details
> -fdump-tree-optimized" } */
> +
> +#define SAT(x) (x < 0 ? 0 : (x > 255 ? 255 : x))
> +
> +unsigned char
> +foo (unsigned char *p, int i)
> +{
> + if (i < 0)
> +return 0;
> + {
> +int t;
> +if (i > 255)
> + t = 255;
> +else
> + t = i;
> +return t;
> + }
> +}
> +
> +/* Because of the way PHIOPT works, it only does the merging of BBs after it
> is done so we get the case were we can't
> + optimize the above until phiopt2 right now. */
> +/* { dg-final {
[PATCH] MATCH: Move `a <= CST1 ? MAX : a` optimization to match
This moves the `a <= CST1 ? MAX : a` optimization
from phiopt to match. It just adds a new pattern to match.pd.
There is one more change needed before being able to remove
minmax_replacement from phiopt.
A few notes on the testsuite changes:
* phi-opt-5.c is now able to optimize at phiopt1 so remove
the xfail.
* pr66726-4.c can be optimized during fold before phiopt1
so need to change the scanning.
* pr66726-5.c needs two phiopt passes currently to optimize
to the right thing, it needed 2 phiopt passes before, the cast
from int to unsigned char is the reason.
* pr66726-6.c is what the original pr66726-4.c was testing
before the fold was able to optimize it.
OK? Bootstrapped and tested on x86_64-linux-gnu.
gcc/ChangeLog:
* match.pd (`(a CMP CST1) ? max : a`): New
pattern.
gcc/testsuite/ChangeLog:
* gcc.dg/tree-ssa/phi-opt-5.c: Remove last xfail.
* gcc.dg/tree-ssa/pr66726-4.c: Change how scanning
works.
* gcc.dg/tree-ssa/pr66726-5.c: New test.
* gcc.dg/tree-ssa/pr66726-6.c: New test.
---
gcc/match.pd | 18 +++
gcc/testsuite/gcc.dg/tree-ssa/phi-opt-5.c | 2 +-
gcc/testsuite/gcc.dg/tree-ssa/pr66726-4.c | 5 +++-
gcc/testsuite/gcc.dg/tree-ssa/pr66726-5.c | 28 +++
gcc/testsuite/gcc.dg/tree-ssa/pr66726-6.c | 17 ++
5 files changed, 68 insertions(+), 2 deletions(-)
create mode 100644 gcc/testsuite/gcc.dg/tree-ssa/pr66726-5.c
create mode 100644 gcc/testsuite/gcc.dg/tree-ssa/pr66726-6.c
diff --git a/gcc/match.pd b/gcc/match.pd
index ceae1c34abc..a55ede838cd 100644
--- a/gcc/match.pd
+++ b/gcc/match.pd
@@ -4954,6 +4954,24 @@ DEFINE_INT_AND_FLOAT_ROUND_FN (RINT)
(if (code == MAX_EXPR)
(minmax (max @1 @2) @4)))
+/* Optimize (a CMP CST1) ? max : a */
+(for cmp(gt ge lt le)
+ minmax (min min max max)
+ (simplify
+ (cond (cmp @0 @1) (minmax:c@2 @0 @3) @4)
+ (with
+{
+ tree_code code = minmax_from_comparison (cmp, @0, @1, @0, @4);
+}
+(if ((cmp == LT_EXPR || cmp == LE_EXPR)
+&& code == MIN_EXPR
+ && integer_nonzerop (fold_build2 (LE_EXPR, boolean_type_node, @3,
@1)))
+ (min @2 @4)
+ (if ((cmp == GT_EXPR || cmp == GE_EXPR)
+ && code == MAX_EXPR
+ && integer_nonzerop (fold_build2 (GE_EXPR, boolean_type_node, @3,
@1)))
+ (max @2 @4))
+
/* X != C1 ? -X : C2 simplifies to -X when -C1 == C2. */
(simplify
(cond (ne @0 INTEGER_CST@1) (negate@3 @0) INTEGER_CST@2)
diff --git a/gcc/testsuite/gcc.dg/tree-ssa/phi-opt-5.c
b/gcc/testsuite/gcc.dg/tree-ssa/phi-opt-5.c
index 5f78a1ba6dc..e78d9d8b83d 100644
--- a/gcc/testsuite/gcc.dg/tree-ssa/phi-opt-5.c
+++ b/gcc/testsuite/gcc.dg/tree-ssa/phi-opt-5.c
@@ -39,7 +39,7 @@ float repl2 (float vary)
/* phiopt1 confused by predictors. */
/* { dg-final { scan-tree-dump "vary.*MAX_EXPR.*0\\.0" "phiopt1" } } */
-/* { dg-final { scan-tree-dump "vary.*MIN_EXPR.*1\\.0" "phiopt1" { xfail *-*-*
} } } */
+/* { dg-final { scan-tree-dump "vary.*MIN_EXPR.*1\\.0" "phiopt1" } } */
/* { dg-final { scan-tree-dump "vary.*MAX_EXPR.*0\\.0" "phiopt2"} } */
/* { dg-final { scan-tree-dump "vary.*MIN_EXPR.*1\\.0" "phiopt2"} } */
diff --git a/gcc/testsuite/gcc.dg/tree-ssa/pr66726-4.c
b/gcc/testsuite/gcc.dg/tree-ssa/pr66726-4.c
index 4e43522f3a3..930ad5fb79f 100644
--- a/gcc/testsuite/gcc.dg/tree-ssa/pr66726-4.c
+++ b/gcc/testsuite/gcc.dg/tree-ssa/pr66726-4.c
@@ -9,4 +9,7 @@ foo (unsigned char *p, int i)
*p = SAT (i);
}
-/* { dg-final { scan-tree-dump-times "COND_EXPR .*and PHI .*converted to
straightline code" 1 "phiopt1" } } */
+/* fold could optimize SAT before phiopt1 so only match on the
+ MIN/MAX here. */
+/* { dg-final { scan-tree-dump-times "= MIN_EXPR" 1 "phiopt1" } } */
+/* { dg-final { scan-tree-dump-times "= MAX_EXPR" 1 "phiopt1" } } */
diff --git a/gcc/testsuite/gcc.dg/tree-ssa/pr66726-5.c
b/gcc/testsuite/gcc.dg/tree-ssa/pr66726-5.c
new file mode 100644
index 000..4b5066cdb6b
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/tree-ssa/pr66726-5.c
@@ -0,0 +1,28 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -fdump-tree-phiopt1-details -fdump-tree-phiopt2-details
-fdump-tree-optimized" } */
+
+#define SAT(x) (x < 0 ? 0 : (x > 255 ? 255 : x))
+
+unsigned char
+foo (unsigned char *p, int i)
+{
+ if (i < 0)
+return 0;
+ {
+int t;
+if (i > 255)
+ t = 255;
+else
+ t = i;
+return t;
+ }
+}
+
+/* Because of the way PHIOPT works, it only does the merging of BBs after it
is done so we get the case were we can't
+ optimize the above until phiopt2 right now. */
+/* { dg-final { scan-tree-dump-times "COND_EXPR .*and PHI .*converted to
straightline code" 2 "phiopt1" { xfail *-*-* } } } */
+/* { dg-final { scan-tree-dump-times "COND_EXPR .*and PHI .*converted to
straightline code" 0 "phiopt2" { xfail *-*-* } } } */
+/* { dg-final { scan-tree-dump-times "= MIN_EXPR" 1 "phiopt1" } } */
+/* { dg-final {
