[gcc r17-3334] match.pd: turn more conditional bit_iors unconditional [PR124667]

https://gcc.gnu.org/g:656bb1d9e9637028f917310e6c7688a0f1e99758

commit r17-3334-g656bb1d9e9637028f917310e6c7688a0f1e99758
Author: Daniel Barboza <[email protected]>
Date:   Tue Aug 11 08:20:40 2026 -0300

    match.pd: turn more conditional bit_iors unconditional [PR124667]
    
    Add patterns to handle the case where we're checking if a bit is set and
    setting it in case it's not.  Similar to the work done in PR64567 but in
    this case the bit is a result of a 1 << val lshift:
    
    (A & BIT) EQ 0 ? A | BIT : A , BIT = 1 << val => A | BIT
    (A & BIT) NE 0 ? A : A | BIT , BIT = 1 << val => A | BIT
    
    Following Andrea's suggestion we're also handling the variants that
    results in just 'A' if we switch the conditionals:
    
    (A & BIT) EQ 0 ? A | BIT : A , BIT = 1 << val => A | BIT
    (A & BIT) NE 0 ? A | BIT : A , BIT = 1 << val => A
    
    (A & BIT) NE 0 ? A : A | BIT , BIT = 1 << val => A | BIT
    (A & BIT) EQ 0 ? A : A | BIT , BIT = 1 << val => A
    
    We're also adding cases where a full bitmask is tested, i.e.:
    
    (A & MASK) EQ MASK ? A : A | MASK => A | MASK
    (A & MASK) NE MASK ? A : A | MASK => A
    
    (A & MASK) NE MASK ? A | MASK : A => A | MASK
    (A & MASK) EQ MASK ? A | MASK : A => A
    
    Note that for these simplifications we're not limited to a bit/pow2
    value like the zero comparisons, which don't work with multiple bits
    because there's no guarantees to preserve the 'non-zero' cases. E.g.:
    "(A & 0xF) == 0 ? A | 0xF : A" can't be simplified to just "A | 0xF"
    because there's a whole range of A lower bits (1,2...E) that would be
    turned to 0xF in the simplification - bits that would be preserved in
    the original pattern. This is the same scenario discussed before in
    PR64567.
    
    Bootstrapped and regression tested in x86_64, aarch64 and riscv64.
    
            PR tree-optimization/124667
    
    gcc/ChangeLog:
    
            * match.pd(`(A & BIT) EQ|NE 0 ? A | BIT : A`): New
            pattern.
            (`(A & BIT) EQ|NE 0 ? A : A | BIT`): New pattern.
            (`(A & MASK) EQ|NE MASK ? A : A | MASK`): New pattern.
            (`(A & MASK) EQ|NE MASK ? A | MASK : A`): New pattern.
            (`A | (((A >> N) & 1) << N)`): New pattern.
    
    gcc/testsuite/ChangeLog:
    
            * gcc.dg/tree-ssa/pr124667-2.c: New test.
            * gcc.dg/tree-ssa/pr124667.c: New test.

Diff:
---
 gcc/match.pd                               | 102 +++++++++++++++++++++++++++
 gcc/testsuite/gcc.dg/tree-ssa/pr124667-2.c |  67 ++++++++++++++++++
 gcc/testsuite/gcc.dg/tree-ssa/pr124667.c   | 107 +++++++++++++++++++++++++++++
 3 files changed, 276 insertions(+)

diff --git a/gcc/match.pd b/gcc/match.pd
index 02684d8a302b..18d295ad4cbc 100644
--- a/gcc/match.pd
+++ b/gcc/match.pd
@@ -6406,6 +6406,108 @@ DEFINE_INT_AND_FLOAT_ROUND_FN (RINT)
   (if (wi::to_wide (@2) == ~wi::to_wide (@1))
    @3))
 
+/* PR124667: Similar to PR64567 above but with the bit given
+   by an (1 << val) lshift.  Note that this shift pattern
+   guarantees that this is a single bit operation.
+
+   The same pattern, if using '!=' instead of '==', will
+   result in just 'A'.
+
+   (A & (1 << val)) == 0 ? A |= (1 << val) : A => A |= (1 << val)
+   (A & (1 << val)) != 0 ? A |= (1 << val) : A => A;  */
+(for neeq (eq ne)
+ (simplify
+  (cond
+   (neeq (bit_and:c @0 (lshift@1 integer_onep @2)) integer_zerop)
+	 (bit_ior:c@3 @0 @1)
+	 @0)
+    (if (neeq == EQ_EXPR)
+     @3
+     @0))
+
+/* PR124667: NE variant of the previous match with switched true/false
+   legs:
+
+   (A & (1 << val)) != 0 ? A : A |= (1 << val) => A |= (1 << val)
+   (A & (1 << val)) == 0 ? A : A |= (1 << val) => A;  */
+ (simplify
+  (cond
+   (neeq (bit_and:c @0 (lshift@1 integer_onep @2)) integer_zerop)
+	 @0
+	 (bit_ior:c@3 @0 @1))
+    (if (neeq == NE_EXPR)
+     @3
+     @0))
+
+/* PR124667: a bitmask set simplification that is possible as
+   long as the whole bitmask is being checked.  Switching the
+   comparison from '==' to '!=' results in 'A':
+
+   (A & B) == B ? A : A |= B  => A |= B
+   (A & B) != B ? A : A |= B  => A;  */
+ (simplify
+  (cond
+   (neeq:c (bit_and @0 @1) @1)
+	   @0
+	   (bit_ior@2 @0 @1))
+    (if (neeq == EQ_EXPR)
+     @2
+     @0))
+
+/* PR124667: similar from above with true/false legs switched:
+
+   (A & B) != B ? A |= B : A => A | B.
+   (A & B) == B ? A |= B : A => A;  */
+(simplify
+ (cond
+  (neeq:c (bit_and @0 @1) @1)
+	  (bit_ior@2 @0 @1)
+	  @0)
+   (if (neeq == NE_EXPR)
+    @2
+    @0)))
+
+/* PR124667: these also reduces to just "A":
+   ((A >> val) & 1) == 0 ?  A : (A | (1 << val))
+   ((A >> val) & 1) != 0 ?  (A | (1 << val)) : A;
+
+   For both cases the zero_one patterns in lines 4860-4890
+   will turn both into the following 'original':
+
+   intD.7 bitshiftD.4489 = 1 << bitD.4485;
+   arrD.4488 = arrD.4488 >> bitD.4485 & 1) * bitshiftD.4489 | arrD.4488;
+
+   And it'll appear back in phiopt as:
+
+   _1 = arrD.4482;
+   _2 = _1 >> bit_7;
+   _3 = _2 & 1;
+   _4 = _3 << bit_7;
+   _6 = _1 | _4;
+
+   I.e. it'll drop the 'mult' and lshift the zero_one result from the
+   bit check.  The 3 middle stmts can be reduced to:
+
+   _3 = 1 << bit_7;
+   _4 = _1 & _3;
+
+   Resulting in:
+
+   _1 = arrD.4482;
+   _3 = 1 << bit_7;
+   _4 = _1 & _3
+   _6 = _1 | _4;
+
+   Which will reduce to just _1.  Simplifying the middle stmts has the
+   advantage of also benefitting other optimizations as well.  Note
+   that this transformation is valid with all CST masks, not just
+   '1'.  */
+(simplify
+  (lshift
+    (bit_and:c (rshift @0 @1) INTEGER_CST@2)
+     @1)
+  (bit_and @0 (lshift @2 @1)))
+
 #if GIMPLE
 (match (nop_atomic_bit_test_and_p @0 @1 @4)
  (bit_and (convert?@4 (ATOMIC_FETCH_OR_XOR_N @2 INTEGER_CST@0 @3))
diff --git a/gcc/testsuite/gcc.dg/tree-ssa/pr124667-2.c b/gcc/testsuite/gcc.dg/tree-ssa/pr124667-2.c
new file mode 100644
index 000000000000..aa7ac22e07d3
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/tree-ssa/pr124667-2.c
@@ -0,0 +1,67 @@
+/* { dg-additional-options -O2 } */
+/* { dg-additional-options -fdump-tree-optimized } */
+
+int test1 (int n, int bit)
+{
+  int arr[16];
+  int bitshift = 1 << bit;
+
+  arr[n] = (arr[n] & bitshift) == 0 ? arr[n] : arr[n] | bitshift;
+
+  return arr[n];
+}
+
+int test1_alt (int n, int bit)
+{
+  int arr[16];
+  int bitshift = 1 << bit;
+
+  arr[n] = (arr[n] & bitshift) != 0 ? arr[n] | bitshift : arr[n];
+
+  return arr[n];
+}
+
+int test2 (int n, int bit)
+{
+  int arr[16];
+  int bitshift = 1 << bit;
+
+  arr[n] = ((arr[n] >> bit) & 1) == 0 ? arr[n] : arr[n] | bitshift;
+
+  return arr[n];
+}
+
+int test2_alt (int n, int bit)
+{
+  int arr[16];
+  int bitshift = 1 << bit;
+
+  arr[n] = ((arr[n] >> bit) & 1) != 0 ? arr[n] | bitshift : arr[n];
+
+  return arr[n];
+}
+
+int test3 (int n)
+{
+  int arr[16];
+  int bits = 0xF;
+
+  arr[n] = (arr[n] & bits) == bits ? arr[n] | bits : arr[n];
+
+  return arr[n];
+}
+
+int test3_alt (int n)
+{
+  int arr[16];
+  int bits = 0xF;
+
+  arr[n] = (arr[n] & bits) != bits ? arr[n] : arr[n] | bits;
+
+  return arr[n];
+}
+
+/* { dg-final { scan-tree-dump-times " \\| " 0 optimized } } */
+/* { dg-final { scan-tree-dump-times " \& " 0 optimized } } */
+/* { dg-final { scan-tree-dump-times " << " 0 optimized } } */
+/* { dg-final { scan-tree-dump-times " >> " 0 optimized } } */
diff --git a/gcc/testsuite/gcc.dg/tree-ssa/pr124667.c b/gcc/testsuite/gcc.dg/tree-ssa/pr124667.c
new file mode 100644
index 000000000000..9bdbe05a00d9
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/tree-ssa/pr124667.c
@@ -0,0 +1,107 @@
+/* { dg-additional-options -O2 } */
+/* { dg-additional-options -fdump-tree-optimized } */
+
+int bitset1 (int n, int bit)
+{
+  int arr[16];
+  int bitshift = 1 << bit;
+
+  if ((arr[n] & bitshift) == 0)
+    arr[n] |= bitshift;
+
+  return arr[n];
+}
+
+int bitset1_alt (int n, int bit)
+{
+  int arr[16];
+  int bitshift = 1 << bit;
+
+  arr[n] = (arr[n] & bitshift) != 0 ? arr[n] : arr[n] | bitshift;
+
+  return arr[n];
+}
+
+int bitset1b (int n, int bit)
+{
+  int arr[16];
+  int bitshift = 1 << bit;
+
+  if ((bitshift & arr[n]) == 0)
+    arr[n] |= bitshift;
+
+  return arr[n];
+}
+
+int bitset1b_alt (int n, int bit)
+{
+  int arr[16];
+  int bitshift = 1 << bit;
+
+  arr[n] = (bitshift & arr[n]) != 0 ? arr[n] : bitshift | arr[n];
+
+  return arr[n];
+}
+
+int bitset2 (int n)
+{
+  int arr[16];
+  int bits = 0xF;
+
+  if ((arr[n] & bits) != bits)
+    arr[n] |= bits;
+
+  return arr[n];
+}
+
+int bitset2_alt (int n)
+{
+  int arr[16];
+  int bits = 0xF;
+
+  arr[n] = (arr[n] & bits) == bits ?  arr[n]: arr[n] | bits;
+
+  return arr[n];
+}
+
+int bitset2b (int n)
+{
+  int arr[16];
+  int bits = 0xF;
+
+  if ((bits & arr[n]) != bits)
+    arr[n] |= bits;
+
+  return arr[n];
+}
+
+int bitset2b_alt (int n)
+{
+  int arr[16];
+  int bits = 0xF;
+
+  arr[n] = (bits & arr[n]) == bits ?  arr[n]: bits | arr[n];
+
+  return arr[n];
+}
+
+/* A negative test to ensure we're not optimizing something
+   we shouldn't. */
+int bitset_nosimplify (int n)
+{
+  int arr[16];
+
+  int bits = 0xF;
+
+  /* We can't make the bit_ior unconditional here because the
+     cond matches for multiple values aside from '0xF' in
+     which the value wouldn't be touched, e.g. for arr[n] = 0x1
+     "arr[n] & bits" is also non-zero and the value wouldn't be
+     changed.  */
+  if ((arr[n] & bits) == 0)
+    arr[n] |= bits;
+
+  return arr[n];
+}
+
+/* { dg-final { scan-tree-dump-times "goto" 2 optimized } } */