On Mon, Jul 31, 2023 at 7:35 AM Andrew Pinski via Gcc-patches
<[email protected]> wrote:
>
> I noticed that there are patterns that optimize
> `(X CMP1 CST1) AND/IOR (X CMP2 CST2)` and we can easily extend
> them to support the `(X CMP1 Y) AND/IOR (X CMP2 Y)` by saying they
> compare equal. This allows for this kind of optimization for integral
> and pointer types (which have the same semantics).
>
> OK? Bootstrapped and tested on x86_64-linux-gnu with no regressions.
OK.
Thanks,
Richard.
> gcc/ChangeLog:
>
> PR tree-optimization/106164
> * match.pd: Extend the `(X CMP1 CST1) AND/IOR (X CMP2 CST2)`
> patterns to support `(X CMP1 Y) AND/IOR (X CMP2 Y)`.
>
> gcc/testsuite/ChangeLog:
>
> PR tree-optimization/106164
> * gcc.dg/tree-ssa/cmpbit-1.c: New test.
> ---
> gcc/match.pd | 66 +++++++++++++++++++-----
> gcc/testsuite/gcc.dg/tree-ssa/cmpbit-1.c | 38 ++++++++++++++
> 2 files changed, 90 insertions(+), 14 deletions(-)
> create mode 100644 gcc/testsuite/gcc.dg/tree-ssa/cmpbit-1.c
>
> diff --git a/gcc/match.pd b/gcc/match.pd
> index 73eb249f704..00af5d99119 100644
> --- a/gcc/match.pd
> +++ b/gcc/match.pd
> @@ -2799,14 +2799,24 @@ DEFINE_INT_AND_FLOAT_ROUND_FN (RINT)
>
> /* Convert (X == CST1) && (X OP2 CST2) to a known value
> based on CST1 OP2 CST2. Similarly for (X != CST1). */
> +/* Convert (X == Y) && (X OP2 Y) to a known value if X is an integral type.
> + Similarly for (X != Y). */
>
> (for code1 (eq ne)
> (for code2 (eq ne lt gt le ge)
> (simplify
> - (bit_and:c (code1@3 @0 INTEGER_CST@1) (code2@4 @0 INTEGER_CST@2))
> + (bit_and:c (code1@3 @0 @1) (code2@4 @0 @2))
> + (if ((TREE_CODE (@1) == INTEGER_CST
> + && TREE_CODE (@2) == INTEGER_CST)
> + || ((INTEGRAL_TYPE_P (TREE_TYPE (@1))
> + || POINTER_TYPE_P (TREE_TYPE (@1)))
> + && operand_equal_p (@1, @2)))
> (with
> {
> - int cmp = tree_int_cst_compare (@1, @2);
> + int cmp = 0;
> + if (TREE_CODE (@1) == INTEGER_CST
> + && TREE_CODE (@2) == INTEGER_CST)
> + cmp = tree_int_cst_compare (@1, @2);
> bool val;
> switch (code2)
> {
> @@ -2822,17 +2832,26 @@ DEFINE_INT_AND_FLOAT_ROUND_FN (RINT)
> (switch
> (if (code1 == EQ_EXPR && val) @3)
> (if (code1 == EQ_EXPR && !val) { constant_boolean_node (false, type);
> })
> - (if (code1 == NE_EXPR && !val) @4))))))
> + (if (code1 == NE_EXPR && !val) @4)))))))
>
> -/* Convert (X OP1 CST1) && (X OP2 CST2). */
> +/* Convert (X OP1 CST1) && (X OP2 CST2).
> + Convert (X OP1 Y) && (X OP2 Y). */
>
> (for code1 (lt le gt ge)
> (for code2 (lt le gt ge)
> (simplify
> - (bit_and (code1:c@3 @0 INTEGER_CST@1) (code2:c@4 @0 INTEGER_CST@2))
> + (bit_and (code1:c@3 @0 @1) (code2:c@4 @0 @2))
> + (if ((TREE_CODE (@1) == INTEGER_CST
> + && TREE_CODE (@2) == INTEGER_CST)
> + || ((INTEGRAL_TYPE_P (TREE_TYPE (@1))
> + || POINTER_TYPE_P (TREE_TYPE (@1)))
> + && operand_equal_p (@1, @2)))
> (with
> {
> - int cmp = tree_int_cst_compare (@1, @2);
> + int cmp = 0;
> + if (TREE_CODE (@1) == INTEGER_CST
> + && TREE_CODE (@2) == INTEGER_CST)
> + cmp = tree_int_cst_compare (@1, @2);
> }
> (switch
> /* Choose the more restrictive of two < or <= comparisons. */
> @@ -2861,18 +2880,28 @@ DEFINE_INT_AND_FLOAT_ROUND_FN (RINT)
> && (code1 == GT_EXPR || code1 == GE_EXPR)
> && (code2 == LT_EXPR || code2 == LE_EXPR))
> { constant_boolean_node (false, type); })
> - )))))
> + ))))))
>
> /* Convert (X == CST1) || (X OP2 CST2) to a known value
> based on CST1 OP2 CST2. Similarly for (X != CST1). */
> +/* Convert (X == Y) || (X OP2 Y) to a known value if X is an integral type.
> + Similarly for (X != Y). */
>
> (for code1 (eq ne)
> (for code2 (eq ne lt gt le ge)
> (simplify
> - (bit_ior:c (code1@3 @0 INTEGER_CST@1) (code2@4 @0 INTEGER_CST@2))
> + (bit_ior:c (code1@3 @0 @1) (code2@4 @0 @2))
> + (if ((TREE_CODE (@1) == INTEGER_CST
> + && TREE_CODE (@2) == INTEGER_CST)
> + || ((INTEGRAL_TYPE_P (TREE_TYPE (@1))
> + || POINTER_TYPE_P (TREE_TYPE (@1)))
> + && operand_equal_p (@1, @2)))
> (with
> {
> - int cmp = tree_int_cst_compare (@1, @2);
> + int cmp = 0;
> + if (TREE_CODE (@1) == INTEGER_CST
> + && TREE_CODE (@2) == INTEGER_CST)
> + cmp = tree_int_cst_compare (@1, @2);
> bool val;
> switch (code2)
> {
> @@ -2888,17 +2917,26 @@ DEFINE_INT_AND_FLOAT_ROUND_FN (RINT)
> (switch
> (if (code1 == EQ_EXPR && val) @4)
> (if (code1 == NE_EXPR && val) { constant_boolean_node (true, type); })
> - (if (code1 == NE_EXPR && !val) @3))))))
> + (if (code1 == NE_EXPR && !val) @3)))))))
>
> -/* Convert (X OP1 CST1) || (X OP2 CST2). */
> +/* Convert (X OP1 CST1) || (X OP2 CST2).
> + Convert (X OP1 Y) || (X OP2 Y). */
>
> (for code1 (lt le gt ge)
> (for code2 (lt le gt ge)
> (simplify
> - (bit_ior (code1@3 @0 INTEGER_CST@1) (code2@4 @0 INTEGER_CST@2))
> + (bit_ior (code1@3 @0 @1) (code2@4 @0 @2))
> + (if ((TREE_CODE (@1) == INTEGER_CST
> + && TREE_CODE (@2) == INTEGER_CST)
> + || ((INTEGRAL_TYPE_P (TREE_TYPE (@1))
> + || POINTER_TYPE_P (TREE_TYPE (@1)))
> + && operand_equal_p (@1, @2)))
> (with
> {
> - int cmp = tree_int_cst_compare (@1, @2);
> + int cmp = 0;
> + if (TREE_CODE (@1) == INTEGER_CST
> + && TREE_CODE (@2) == INTEGER_CST)
> + cmp = tree_int_cst_compare (@1, @2);
> }
> (switch
> /* Choose the more restrictive of two < or <= comparisons. */
> @@ -2927,7 +2965,7 @@ DEFINE_INT_AND_FLOAT_ROUND_FN (RINT)
> && (code1 == GT_EXPR || code1 == GE_EXPR)
> && (code2 == LT_EXPR || code2 == LE_EXPR))
> { constant_boolean_node (true, type); })
> - )))))
> + ))))))
>
> /* We can't reassociate at all for saturating types. */
> (if (!TYPE_SATURATING (type))
> diff --git a/gcc/testsuite/gcc.dg/tree-ssa/cmpbit-1.c
> b/gcc/testsuite/gcc.dg/tree-ssa/cmpbit-1.c
> new file mode 100644
> index 00000000000..c219e047ba8
> --- /dev/null
> +++ b/gcc/testsuite/gcc.dg/tree-ssa/cmpbit-1.c
> @@ -0,0 +1,38 @@
> +/* { dg-do compile } */
> +/* { dg-options "-O1 -fno-tree-reassoc -fdump-tree-optimized-raw" } */
> +_Bool f(int a, int b)
> +{
> + _Bool c = a > b;
> + _Bool d = a >= b;
> + return c & d;
> +}
> +
> +_Bool f1(int a, int b)
> +{
> + _Bool c = a > b;
> + _Bool d = a >= b;
> + return c | d;
> +}
> +
> +_Bool g(int a, int b)
> +{
> + _Bool c = a < b;
> + _Bool d = a <= b;
> + return c & d;
> +}
> +
> +_Bool g1(int a, int b)
> +{
> + _Bool c = a < b;
> + _Bool d = a <= b;
> + return c | d;
> +}
> +
> +
> +/* We should be able to optimize these without reassociation too. */
> +/* { dg-final { scan-tree-dump-not "bit_and_expr," "optimized" } } */
> +/* { dg-final { scan-tree-dump-not "bit_ior_expr," "optimized" } } */
> +/* { dg-final { scan-tree-dump-times "gt_expr," 1 "optimized" } } */
> +/* { dg-final { scan-tree-dump-times "ge_expr," 1 "optimized" } } */
> +/* { dg-final { scan-tree-dump-times "lt_expr," 1 "optimized" } } */
> +/* { dg-final { scan-tree-dump-times "le_expr," 1 "optimized" } } */
> --
> 2.31.1
>
