[gcc r11-9202] [PR102842] Consider all outputs in generation of matching reloads

[gcc r11-9202] [PR102842] Consider all outputs in generation of matching reloads

[Vladimir Makarov]

https://gcc.gnu.org/g:41bea618a77dca8c1c13a3d7b883976a25d83373

commit r11-9202-g41bea618a77dca8c1c13a3d7b883976a25d83373
Author: Vladimir N. Makarov <vmakarov@redhat.com>
Date:   Tue Oct 26 14:03:42 2021 -0400

    [PR102842] Consider all outputs in generation of matching reloads
    
    Without considering all output insn operands (not only processed
    before), in rare cases LRA can use the same hard register for
    different outputs of the insn on different assignment subpasses.  The
    patch fixes the problem.
    
    gcc/ChangeLog:
    
            PR rtl-optimization/102842
            * lra-constraints.c (match_reload): Ignore out in checking values
            of outs.
            (curr_insn_transform): Collect outputs before doing reloads of operands.
    
    gcc/testsuite/ChangeLog:
    
            PR rtl-optimization/102842
            * g++.target/arm/pr102842.C: New test.

Diff:
---
 gcc/lra-constraints.c                   | 17 +++++------------
 gcc/testsuite/g++.target/arm/pr102842.C | 30 ++++++++++++++++++++++++++++++
 2 files changed, 35 insertions(+), 12 deletions(-)

diff --git a/gcc/lra-constraints.c b/gcc/lra-constraints.c
index aaacc4eabed..da84466917d 100644
--- a/gcc/lra-constraints.c
+++ b/gcc/lra-constraints.c
@@ -1102,7 +1102,7 @@ match_reload (signed char out, signed char *ins, signed char *outs,
 	  for (i = 0; outs[i] >= 0; i++)
 	    {
 	      rtx other_out_rtx = *curr_id->operand_loc[outs[i]];
-	      if (REG_P (other_out_rtx)
+	      if (outs[i] != out && REG_P (other_out_rtx)
 		  && (regno_val_use_in (REGNO (in_rtx), other_out_rtx)
 		      != NULL_RTX))
 		{
@@ -4388,7 +4388,10 @@ curr_insn_transform (bool check_only_p)
       }
 
   n_outputs = 0;
-  outputs[0] = -1;
+  for (i = 0; i < n_operands; i++)
+    if (curr_static_id->operand[i].type == OP_OUT)
+      outputs[n_outputs++] = i;
+  outputs[n_outputs] = -1;
   for (i = 0; i < n_operands; i++)
     {
       int regno;
@@ -4463,8 +4466,6 @@ curr_insn_transform (bool check_only_p)
 		     lra-lives.c.  */
 		  match_reload (i, goal_alt_matched[i], outputs, goal_alt[i], &before,
 				&after, TRUE);
-		  outputs[n_outputs++] = i;
-		  outputs[n_outputs] = -1;
 		}
 	      continue;
 	    }
@@ -4642,14 +4643,6 @@ curr_insn_transform (bool check_only_p)
 	   process_alt_operands decides that it is possible.  */
 	gcc_unreachable ();
 
-      /* Memorise processed outputs so that output remaining to be processed
-	 can avoid using the same register value (see match_reload).  */
-      if (curr_static_id->operand[i].type == OP_OUT)
-	{
-	  outputs[n_outputs++] = i;
-	  outputs[n_outputs] = -1;
-	}
-
       if (optional_p)
 	{
 	  rtx reg = op;
diff --git a/gcc/testsuite/g++.target/arm/pr102842.C b/gcc/testsuite/g++.target/arm/pr102842.C
new file mode 100644
index 00000000000..a2bac66091a
--- /dev/null
+++ b/gcc/testsuite/g++.target/arm/pr102842.C
@@ -0,0 +1,30 @@
+/* PR rtl-optimization/102842 */
+/* { dg-do compile } */
+/* { dg-options "-fPIC  -O2 -fno-omit-frame-pointer -mthumb -march=armv7-a+fp" } */
+
+struct Plane {
+  using T = float;
+  T *Row();
+};
+using ImageF = Plane;
+long long Mirror_x;
+struct EnsurePaddingInPlaceRowByRow {
+  void Process() {
+    switch (strategy_) {
+    case kSlow:
+      float *row = img_.Row();
+      long long xsize = x1_;
+      while (Mirror_x >= xsize)
+        if (Mirror_x)
+          Mirror_x = 2 * xsize - 1;
+      *row = Mirror_x;
+    }
+  }
+  ImageF img_;
+  unsigned x1_;
+  enum { kSlow } strategy_;
+};
+void FinalizeImageRect() {
+  EnsurePaddingInPlaceRowByRow ensure_padding;
+  ensure_padding.Process();
+}