[PATCH v3] zero_extend(not) -> xor optimization [PR112398]

This patch adds optimization of the following patterns:

  (zero_extend:M (subreg:N (not:O==M (X:Q==M)))) ->
  (xor:M (zero_extend:M (subreg:N (X:M)), mask))
  ... where the mask is GET_MODE_MASK (N).

For the cases when X:M doesn't have any non-zero bits outside of mode N,
(zero_extend:M (subreg:N (X:M)) could be simplified to just (X:M)
and whole optimization will be:

  (zero_extend:M (subreg:N (not:M (X:M)))) ->
  (xor:M (X:M, mask))

Patch targets to handle code patterns like:
  not   a0,a0
  andi  a0,a0,0xff
to be optimized to:
  xori  a0,a0,255

	PR rtl-optimization/112398
	PR rtl-optimization/117476

gcc/ChangeLog:

	* simplify-rtx.cc (simplify_context::simplify_unary_operation_1):
	Simplify ZERO_EXTEND (SUBREG (NOT X)) to XOR (X, GET_MODE_MASK(SUBREG))
	when X doesn't have any non-zero bits outside of SUBREG mode.

gcc/testsuite/ChangeLog:

	* gcc.target/riscv/pr112398.c: New test.
	* gcc.dg/torture/pr117476-1.c: New test. From Zhendong Su.
	* gcc.dg/torture/pr117476-2.c: New test. From Zdenek Sojka.

diff --git a/gcc/simplify-rtx.cc b/gcc/simplify-rtx.cc
index 893c5f6e1ae0b0579da3f98bda4f7d48487b8a84..86b3f3319285c5316f77bdd7d840e8b914e0884c 100644 (file)
--- a/gcc/simplify-rtx.cc
+++ b/gcc/simplify-rtx.cc
@@ -1842,6 +1842,29 @@ simplify_context::simplify_unary_operation_1 (rtx_code code, machine_mode mode,
              & ~GET_MODE_MASK (op_mode)) == 0)
        return SUBREG_REG (op);
 
+      /* Trying to optimize:
+        (zero_extend:M (subreg:N (not:M (X:M)))) ->
+        (xor:M (zero_extend:M (subreg:N (X:M)), mask))
+        where the mask is GET_MODE_MASK (N).
+        For the cases when X:M doesn't have any non-zero bits
+        outside of mode N, (zero_extend:M (subreg:N (X:M))
+        will be simplified to just (X:M)
+        and whole optimization will be -> (xor:M (X:M, mask)).  */
+      if (partial_subreg_p (op)
+         && GET_CODE (XEXP (op, 0)) == NOT
+         && GET_MODE (XEXP (op, 0)) == mode
+         && subreg_lowpart_p (op)
+         && HWI_COMPUTABLE_MODE_P (mode)
+         && is_a <scalar_int_mode> (GET_MODE (op), &op_mode)
+         && (nonzero_bits (XEXP (XEXP (op, 0), 0), mode)
+             & ~GET_MODE_MASK (op_mode)) == 0)
+      {
+       unsigned HOST_WIDE_INT mask = GET_MODE_MASK (op_mode);
+       return simplify_gen_binary (XOR, mode,
+                                   XEXP (XEXP (op, 0), 0),
+                                   gen_int_mode (mask, mode));
+      }
+
 #if defined(POINTERS_EXTEND_UNSIGNED)
       /* As we do not know which address space the pointer is referring to,
         we can do this only if the target does not support different pointer

diff --git a/gcc/testsuite/gcc.dg/torture/pr117476-1.c b/gcc/testsuite/gcc.dg/torture/pr117476-1.c
new file mode 100644 (file)
index 0000000..d295562
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/torture/pr117476-1.c
@@ -0,0 +1,12 @@
+/* PR rtl-optimization/117476.
+   First case checking out of mode N non-zero bits. */
+/* { dg-do run } */
+
+int c = 0x1FF;
+
+int main()
+{
+  if (((c ^ 0xFF) & 0xFF) != 0)
+    __builtin_abort();
+  return 0;
+}

diff --git a/gcc/testsuite/gcc.dg/torture/pr117476-2.c b/gcc/testsuite/gcc.dg/torture/pr117476-2.c
new file mode 100644 (file)
index 0000000..1973ebc
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/torture/pr117476-2.c
@@ -0,0 +1,20 @@
+/* PR rtl-optimization/117476.
+   Second case checking skipping of TI mode. */
+/* { dg-do run } */
+/* { dg-require-effective-target int128 } */
+
+unsigned __int128 g;
+
+void
+foo ()
+{
+  g += __builtin_add_overflow_p (~g, 0, 0ul);
+}
+
+int
+main ()
+{
+  foo();
+  if (!g)
+    __builtin_abort();
+}

diff --git a/gcc/testsuite/gcc.target/riscv/pr112398.c b/gcc/testsuite/gcc.target/riscv/pr112398.c
new file mode 100644 (file)
index 0000000..624a665
--- /dev/null
+++ b/gcc/testsuite/gcc.target/riscv/pr112398.c
@@ -0,0 +1,14 @@
+/* { dg-do compile } */
+/* { dg-options "-march=rv64gc -mabi=lp64d" } */
+/* { dg-skip-if "" { *-*-* } { "-O0" "-Og" } } */
+
+#include <stdint.h>
+
+uint8_t neg_u8 (const uint8_t src)
+{
+  return ~src;
+}
+
+/* { dg-final { scan-assembler-times "xori\t" 1 } } */
+/* { dg-final { scan-assembler-not "not\t" } } */
+/* { dg-final { scan-assembler-not "andi\t" } } */