[PR96264] LRA: Check output insn hard regs when updating available rematerialization after the insn

 Insn for rematerialization can contain a clobbered hard register.  We
can not move such insn through another insn setting up the same hard
register.  The patch adds such check.

gcc/ChangeLog:

	PR rtl-optimization/96264
	* lra-remat.c (reg_overlap_for_remat_p): Check also output insn
	hard regs.

gcc/testsuite/ChangeLog:

	PR rtl-optimization/96264
	* gcc.target/powerpc/pr96264.c: New.

2 files changed, 37 insertions, 4 deletions

diff --git a/gcc/lra-remat.c b/gcc/lra-remat.c
index 8bd9ffa..d983731 100644
--- a/gcc/lra-remat.c
+++ b/gcc/lra-remat.c
@@ -651,7 +651,11 @@ calculate_local_reg_remat_bb_data (void)
 
 
 
-/* Return true if REG overlaps an input operand of INSN.  */
+/* Return true if REG overlaps an input operand or non-input hard register of
+   INSN.  Basically the function returns false if we can move rematerialization
+   candidate INSN through another insn with output REG or dead input REG (we
+   consider it to avoid extending reg live range) with possible output pseudo
+   renaming in INSN.  */
 static bool
 reg_overlap_for_remat_p (lra_insn_reg *reg, rtx_insn *insn)
 {
@@ -675,10 +679,11 @@ reg_overlap_for_remat_p (lra_insn_reg *reg, rtx_insn *insn)
 	 reg2 != NULL;
 	 reg2 = reg2->next)
       {
-	if (reg2->type != OP_IN)
-	  continue;
-	unsigned regno2 = reg2->regno;
 	int nregs2;
+	unsigned regno2 = reg2->regno;
+
+	if (reg2->type != OP_IN && regno2 >= FIRST_PSEUDO_REGISTER)
+	  continue;
 
 	if (regno2 >= FIRST_PSEUDO_REGISTER && reg_renumber[regno2] >= 0)
 	  regno2 = reg_renumber[regno2];
diff --git a/gcc/testsuite/gcc.target/powerpc/pr96264.c b/gcc/testsuite/gcc.target/powerpc/pr96264.c
new file mode 100644
index 0000000..e89979b
--- /dev/null
+++ b/gcc/testsuite/gcc.target/powerpc/pr96264.c
@@ -0,0 +1,28 @@
+/* { dg-do run } */
+/* { dg-options "-Os -fno-forward-propagate -fschedule-insns -fno-tree-ter -Wno-psabi" } */
+/* { dg-require-effective-target p8vector_hw } */
+
+typedef unsigned char __attribute__ ((__vector_size__ (64))) v512u8;
+typedef unsigned short u16;
+typedef unsigned short __attribute__ ((__vector_size__ (64))) v512u16;
+typedef unsigned __int128 __attribute__ ((__vector_size__ (64))) v512u128;
+
+v512u16 d;
+v512u128 f;
+
+v512u8
+foo (u16 e)
+{
+  v512u128 g = f - -e;
+  d = (5 / (d + 1)) < e;
+  return (v512u8) g;
+}
+
+int
+main (void)
+{
+  v512u8 x = foo (2);
+  for (unsigned i = 0; i < sizeof (x); i++)
+    if (x[i] != (i % 16 ? 0 : 2))
+      __builtin_abort ();
+}