From 29a71fc5cbfc3b5e4649abf51740daed5ea243bd Mon Sep 17 00:00:00 2001
From: Richard Sandiford <richard.sandiford@arm.com>
Date: Tue, 5 Dec 2023 09:20:55 +0000
Subject: [PATCH 134/157] [Backport][SME] lra: Updates of biggest mode for hard
 regs [PR112278]

Reference: https://gcc.gnu.org/git/?p=gcc.git;a=commit;h=6e2e0ce6795c863e295eb33559f8dc0500297da3

LRA keeps track of the biggest mode for both hard registers and
pseudos.  The updates assume that the modes are ordered, i.e. that
we can tell whether one is no bigger than the other at compile time.

That is (or at least seemed to be) a reasonable restriction for pseudos.
But it isn't necessarily so for hard registers, since the uses of hard
registers can be logically distinct.  The testcase is an example of this.

The biggest mode of hard registers is also special for other reasons.
As the existing comment says:

  /* A reg can have a biggest_mode of VOIDmode if it was only ever seen as
     part of a multi-word register.  In that case, just use the reg_rtx
     mode.  Do the same also if the biggest mode was larger than a register
     or we can not compare the modes.  Otherwise, limit the size to that of
     the biggest access in the function or to the natural mode at least.  */

This patch applies the same approach to the updates.

gcc/
	PR rtl-optimization/112278
	* lra-int.h (lra_update_biggest_mode): New function.
	* lra-coalesce.cc (merge_pseudos): Use it.
	* lra-lives.cc (process_bb_lives): Likewise.
	* lra.cc (new_insn_reg): Likewise.

gcc/testsuite/
	PR rtl-optimization/112278
	* gcc.target/aarch64/sve/pr112278.c: New test.
---
 gcc/lra-coalesce.cc                             |  4 +---
 gcc/lra-int.h                                   | 15 +++++++++++++++
 gcc/lra-lives.cc                                |  4 +---
 gcc/lra.cc                                      |  5 ++---
 gcc/testsuite/gcc.target/aarch64/sve/pr112278.c | 15 +++++++++++++++
 5 files changed, 34 insertions(+), 9 deletions(-)
 create mode 100644 gcc/testsuite/gcc.target/aarch64/sve/pr112278.c

diff --git a/gcc/lra-coalesce.cc b/gcc/lra-coalesce.cc
index c82934569..901a44663 100644
--- a/gcc/lra-coalesce.cc
+++ b/gcc/lra-coalesce.cc
@@ -112,9 +112,7 @@ merge_pseudos (int regno1, int regno2)
     = (lra_merge_live_ranges
        (lra_reg_info[first].live_ranges,
 	lra_copy_live_range_list (lra_reg_info[first2].live_ranges)));
-  if (partial_subreg_p (lra_reg_info[first].biggest_mode,
-			lra_reg_info[first2].biggest_mode))
-    lra_reg_info[first].biggest_mode = lra_reg_info[first2].biggest_mode;
+  lra_update_biggest_mode (first, lra_reg_info[first2].biggest_mode);
 }
 
 /* Change pseudos in *LOC on their coalescing group
diff --git a/gcc/lra-int.h b/gcc/lra-int.h
index 04baefef3..040e87d11 100644
--- a/gcc/lra-int.h
+++ b/gcc/lra-int.h
@@ -525,4 +525,19 @@ lra_assign_reg_val (int from, int to)
   lra_reg_info[to].offset = lra_reg_info[from].offset;
 }
 
+/* Update REGNO's biggest recorded mode so that it includes a reference
+   in mode MODE.  */
+inline void
+lra_update_biggest_mode (int regno, machine_mode mode)
+{
+  if (!ordered_p (GET_MODE_SIZE (lra_reg_info[regno].biggest_mode),
+		  GET_MODE_SIZE (mode)))
+    {
+      gcc_checking_assert (HARD_REGISTER_NUM_P (regno));
+      lra_reg_info[regno].biggest_mode = reg_raw_mode[regno];
+    }
+  else if (partial_subreg_p (lra_reg_info[regno].biggest_mode, mode))
+    lra_reg_info[regno].biggest_mode = mode;
+}
+
 #endif /* GCC_LRA_INT_H */
diff --git a/gcc/lra-lives.cc b/gcc/lra-lives.cc
index a755464ee..fb4a12304 100644
--- a/gcc/lra-lives.cc
+++ b/gcc/lra-lives.cc
@@ -770,9 +770,7 @@ process_bb_lives (basic_block bb, int &curr_point, bool dead_insn_p)
 	{
 	  int regno = reg->regno;
 
-	  if (partial_subreg_p (lra_reg_info[regno].biggest_mode,
-				reg->biggest_mode))
-	    lra_reg_info[regno].biggest_mode = reg->biggest_mode;
+	  lra_update_biggest_mode (regno, reg->biggest_mode);
 	  if (HARD_REGISTER_NUM_P (regno))
 	    lra_hard_reg_usage[regno] += freq;
 	}
diff --git a/gcc/lra.cc b/gcc/lra.cc
index 1444cb759..8fda432f1 100644
--- a/gcc/lra.cc
+++ b/gcc/lra.cc
@@ -559,9 +559,8 @@ new_insn_reg (rtx_insn *insn, int regno, enum op_type type,
   lra_insn_reg *ir = lra_insn_reg_pool.allocate ();
   ir->type = type;
   ir->biggest_mode = mode;
-  if (NONDEBUG_INSN_P (insn)
-      && partial_subreg_p (lra_reg_info[regno].biggest_mode, mode))
-    lra_reg_info[regno].biggest_mode = mode;
+  if (NONDEBUG_INSN_P (insn))
+    lra_update_biggest_mode (regno, mode);
   ir->subreg_p = subreg_p;
   ir->early_clobber_alts = early_clobber_alts;
   ir->regno = regno;
diff --git a/gcc/testsuite/gcc.target/aarch64/sve/pr112278.c b/gcc/testsuite/gcc.target/aarch64/sve/pr112278.c
new file mode 100644
index 000000000..4f56add2b
--- /dev/null
+++ b/gcc/testsuite/gcc.target/aarch64/sve/pr112278.c
@@ -0,0 +1,15 @@
+#include <arm_neon.h>
+#include <arm_sve.h>
+
+void
+f (void)
+{
+  {
+    register svint8_t v0 asm ("z0");
+    asm volatile ("" : "=w" (v0));
+  }
+  {
+    register int8x8x4_t v0 asm ("v0");
+    asm volatile ("" : "=w" (v0));
+  }
+}
-- 
2.33.0