aarch64: Fix SVE2 BCAX pattern [PR97730]

This patch adds a missing not to the SVE2 BCAX (Bitwise clear and
exclusive or) pattern, fixing the PR. Since SVE doesn't have an
unpredicated not instruction, we need to use a (vacuously) predicated
not here.

To ensure that the predicate is instantiated correctly (to all 1s) for
the intrinsics, we pull out a separate expander from the define_insn.

From the ISA reference [1]:
> Bitwise AND elements of the second source vector with the
> corresponding inverted elements of the third source vector, then
> exclusive OR the results with corresponding elements of the first
> source vector.

[1] : https://developer.arm.com/docs/ddi0602/g/a64-sve-instructions-alphabetic-order/bcax-bitwise-clear-and-exclusive-or

gcc/ChangeLog:

	PR target/97730
	* config/aarch64/aarch64-sve2.md (@aarch64_sve2_bcax<mode>):
	Change to define_expand, add missing (trivially-predicated) not
	rtx to fix wrong code bug.
	(*aarch64_sve2_bcax<mode>): New.

gcc/testsuite/ChangeLog:

	PR target/97730
	* gcc.target/aarch64/sve2/bcax_1.c (OP): Add missing bitwise not
	to match correct bcax semantics.
	* gcc.dg/vect/pr97730.c: New test.

diff --git a/gcc/config/aarch64/aarch64-sve2.md b/gcc/config/aarch64/aarch64-sve2.md
index 0cafd0b..12dc9aa 100644 (file)
--- a/gcc/config/aarch64/aarch64-sve2.md
+++ b/gcc/config/aarch64/aarch64-sve2.md
@@ -786,17 +786,42 @@
 ;; -------------------------------------------------------------------------
 
 ;; Unpredicated exclusive OR of AND.
-(define_insn "@aarch64_sve2_bcax<mode>"
+(define_expand "@aarch64_sve2_bcax<mode>"
+  [(set (match_operand:SVE_FULL_I 0 "register_operand")
+       (xor:SVE_FULL_I
+         (and:SVE_FULL_I
+           (unspec:SVE_FULL_I
+             [(match_dup 4)
+              (not:SVE_FULL_I
+                (match_operand:SVE_FULL_I 3 "register_operand"))]
+             UNSPEC_PRED_X)
+           (match_operand:SVE_FULL_I 2 "register_operand"))
+         (match_operand:SVE_FULL_I 1 "register_operand")))]
+  "TARGET_SVE2"
+  {
+    operands[4] = CONSTM1_RTX (<VPRED>mode);
+  }
+)
+
+(define_insn_and_rewrite "*aarch64_sve2_bcax<mode>"
   [(set (match_operand:SVE_FULL_I 0 "register_operand" "=w, ?&w")
        (xor:SVE_FULL_I
          (and:SVE_FULL_I
-           (match_operand:SVE_FULL_I 2 "register_operand" "w, w")
-           (match_operand:SVE_FULL_I 3 "register_operand" "w, w"))
+           (unspec:SVE_FULL_I
+             [(match_operand 4)
+              (not:SVE_FULL_I
+                (match_operand:SVE_FULL_I 3 "register_operand" "w, w"))]
+             UNSPEC_PRED_X)
+           (match_operand:SVE_FULL_I 2 "register_operand" "w, w"))
          (match_operand:SVE_FULL_I 1 "register_operand" "0, w")))]
   "TARGET_SVE2"
   "@
   bcax\t%0.d, %0.d, %2.d, %3.d
   movprfx\t%0, %1\;bcax\t%0.d, %0.d, %2.d, %3.d"
+  "&& !CONSTANT_P (operands[4])"
+  {
+    operands[4] = CONSTM1_RTX (<VPRED>mode);
+  }
   [(set_attr "movprfx" "*,yes")]
 )
 

diff --git a/gcc/testsuite/gcc.dg/vect/pr97730.c b/gcc/testsuite/gcc.dg/vect/pr97730.c
new file mode 100644 (file)
index 0000000..af4bca4
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/vect/pr97730.c
@@ -0,0 +1,12 @@
+/* { dg-additional-options "-O1" } */
+unsigned b = 0xce8e5a48, c = 0xb849691a;
+unsigned a[8080];
+int main() {
+  a[0] = b;
+  c = c;
+  unsigned f = 0xb1e8;
+  for (int h = 0; h < 5; h++)
+    a[h] = (b & c) ^ f;
+  if (a[0] != 0x8808f9e0)
+    __builtin_abort();
+}

diff --git a/gcc/testsuite/gcc.target/aarch64/sve2/bcax_1.c b/gcc/testsuite/gcc.target/aarch64/sve2/bcax_1.c
index 4b0d5a9..7c31afc 100644 (file)
--- a/gcc/testsuite/gcc.target/aarch64/sve2/bcax_1.c
+++ b/gcc/testsuite/gcc.target/aarch64/sve2/bcax_1.c
@@ -1,7 +1,7 @@
 /* { dg-do compile } */
 /* { dg-options "-O2 -ftree-vectorize -fdump-tree-vect-details --save-temps" } */
 
-#define OP(x,y,z) ((x) ^ ((y) & (z)))
+#define OP(x,y,z) ((x) ^ (~(y) & (z)))
 
 #include "bitsel_1.c"