middle-end: Convert bitclear <imm> + cmp<cc> #0 into cm<cc2> <imm2>

This optimizes the case where a mask Y which fulfills ~Y + 1 == pow2 is used to
clear a some bits and then compared against 0 into one without the masking and
a compare against a different bit immediate.

We can do this for all unsigned compares and for signed we can do it for
comparisons of EQ and NE:

(x & (~255)) == 0 becomes x <= 255. Which for leaves it to the target to
optimally deal with the comparison.

This transformation has to be done in the mid-end because in RTL you don't have
the signs of the comparison operands and if the target needs an immediate this
should be floated outside of the loop.

The RTL loop invariant hoisting is done before split1.

i.e.

void fun1(int32_t *x, int n)
{
    for (int i = 0; i < (n & -16); i++)
      x[i] = (x[i]&(~255)) == 0;
}

now generates:

.L3:
        ldr     q0, [x0]
        cmhs    v0.4s, v2.4s, v0.4s
        and     v0.16b, v1.16b, v0.16b
        str     q0, [x0], 16
        cmp     x0, x1
        bne     .L3

and floats the immediate out of the loop.

instead of:

.L3:
        ldr     q0, [x0]
        bic     v0.4s, #255
        cmeq    v0.4s, v0.4s, #0
        and     v0.16b, v1.16b, v0.16b
        str     q0, [x0], 16
        cmp     x0, x1
        bne     .L3

In order to not break IVopts and CSE I have added a
requirement for the scalar version to be single use.

gcc/ChangeLog:

	* tree.c (bitmask_inv_cst_vector_p): New.
	* tree.h (bitmask_inv_cst_vector_p): New.
	* match.pd: Use it in new bitmask compare pattern.

gcc/testsuite/ChangeLog:

	* gcc.dg/bic-bitmask-10.c: New test.
	* gcc.dg/bic-bitmask-11.c: New test.
	* gcc.dg/bic-bitmask-12.c: New test.
	* gcc.dg/bic-bitmask-13.c: New test.
	* gcc.dg/bic-bitmask-14.c: New test.
	* gcc.dg/bic-bitmask-15.c: New test.
	* gcc.dg/bic-bitmask-16.c: New test.
	* gcc.dg/bic-bitmask-17.c: New test.
	* gcc.dg/bic-bitmask-18.c: New test.
	* gcc.dg/bic-bitmask-19.c: New test.
	* gcc.dg/bic-bitmask-2.c: New test.
	* gcc.dg/bic-bitmask-20.c: New test.
	* gcc.dg/bic-bitmask-21.c: New test.
	* gcc.dg/bic-bitmask-22.c: New test.
	* gcc.dg/bic-bitmask-23.c: New test.
	* gcc.dg/bic-bitmask-3.c: New test.
	* gcc.dg/bic-bitmask-4.c: New test.
	* gcc.dg/bic-bitmask-5.c: New test.
	* gcc.dg/bic-bitmask-6.c: New test.
	* gcc.dg/bic-bitmask-7.c: New test.
	* gcc.dg/bic-bitmask-8.c: New test.
	* gcc.dg/bic-bitmask-9.c: New test.
	* gcc.dg/bic-bitmask.h: New test.
	* gcc.target/aarch64/bic-bitmask-1.c: New test.

1 files changed, 20 insertions, 1 deletions

diff --git a/gcc/match.pd b/gcc/match.pd
index 60b4ad5f706..3e54e2cf5a6 100644
--- a/gcc/match.pd
+++ b/gcc/match.pd
@@ -38,7 +38,8 @@ along with GCC; see the file COPYING3.  If not see
    uniform_integer_cst_p
    HONOR_NANS
    uniform_vector_p
-   expand_vec_cmp_expr_p)
+   expand_vec_cmp_expr_p
+   bitmask_inv_cst_vector_p)
 
 /* Operator lists.  */
 (define_operator_list tcc_comparison
@@ -5207,6 +5208,24 @@ DEFINE_INT_AND_FLOAT_ROUND_FN (RINT)
       (eqcmp (bit_and @1 { wide_int_to_tree (ty, mask - rhs); })
 	     { build_zero_cst (ty); }))))))
 
+/* Transform comparisons of the form (X & Y) CMP 0 to X CMP2 Z
+   where ~Y + 1 == pow2 and Z = ~Y.  */
+(for cst (VECTOR_CST INTEGER_CST)
+ (for cmp (le eq ne ge gt)
+      icmp (le le gt le gt)
+ (simplify
+  (cmp (bit_and:c@2 @0 cst@1) integer_zerop)
+   (with { tree csts = bitmask_inv_cst_vector_p (@1); }
+     (switch
+      (if (csts && TYPE_UNSIGNED (TREE_TYPE (@1))
+	   && (VECTOR_TYPE_P (TREE_TYPE (@1)) || single_use (@2)))
+       (icmp @0 { csts; }))
+      (if (csts && !TYPE_UNSIGNED (TREE_TYPE (@1))
+	   && (cmp == EQ_EXPR || cmp == NE_EXPR)
+	   && (VECTOR_TYPE_P (TREE_TYPE (@1)) || single_use (@2)))
+       (with { tree utype = unsigned_type_for (TREE_TYPE (@1)); }
+	(icmp (convert:utype @0) { csts; }))))))))
+
 /* -A CMP -B -> B CMP A.  */
 (for cmp (tcc_comparison)
      scmp (swapped_tcc_comparison)