gcc/0076-LoongArch-Use-force_reg-instead-of-gen_reg_rtx-emit_.patch

From be149d7f6527df6b16f3f9f8aec1e488466a71f1 Mon Sep 17 00:00:00 2001
From: Xi Ruoyao <xry111@xry111.site>
Date: Tue, 19 Dec 2023 04:48:03 +0800
Subject: [PATCH 076/188] LoongArch: Use force_reg instead of gen_reg_rtx +
 emit_move_insn in vec_init expander [PR113033]

Jakub says:

    Then that seems like a bug in the loongarch vec_init pattern(s).
    Those really don't have a predicate in any of the backends on the
    input operand, so they need to force_reg it if it is something it
    can't handle. I've looked e.g. at i386 vec_init and that is exactly
    what it does, see the various tests + force_reg calls in
    ix86_expand_vector_init*.

So replace gen_reg_rtx + emit_move_insn with force_reg to fix PR 113033.

gcc/ChangeLog:

	PR target/113033
	* config/loongarch/loongarch.cc
	(loongarch_expand_vector_init_same): Replace gen_reg_rtx +
	emit_move_insn with force_reg.
	(loongarch_expand_vector_init): Likewise.

gcc/testsuite/ChangeLog:

	PR target/113033
	* gcc.target/loongarch/pr113033.c: New test.
---
 gcc/config/loongarch/loongarch.cc             | 38 ++++++-------------
 gcc/testsuite/gcc.target/loongarch/pr113033.c | 23 +++++++++++
 2 files changed, 35 insertions(+), 26 deletions(-)
 create mode 100644 gcc/testsuite/gcc.target/loongarch/pr113033.c

diff --git a/gcc/config/loongarch/loongarch.cc b/gcc/config/loongarch/loongarch.cc
index a22601d88..000d2d623 100644
--- a/gcc/config/loongarch/loongarch.cc
+++ b/gcc/config/loongarch/loongarch.cc
@@ -10745,7 +10745,7 @@ loongarch_expand_vector_init_same (rtx target, rtx vals, unsigned nvar)
 	  gcc_unreachable ();
 	}
     }
-  temp = gen_reg_rtx (imode);
+
   if (imode == GET_MODE (same))
     temp2 = same;
   else if (GET_MODE_SIZE (imode) >= UNITS_PER_WORD)
@@ -10770,7 +10770,8 @@ loongarch_expand_vector_init_same (rtx target, rtx vals, unsigned nvar)
       else
 	temp2 = lowpart_subreg (imode, same, GET_MODE (same));
     }
-  emit_move_insn (temp, temp2);
+
+  temp = force_reg (imode, temp2);
 
   switch (vmode)
     {
@@ -10992,35 +10993,29 @@ loongarch_expand_vector_init (rtx target, rtx vals)
 			 to reduce the number of instructions.  */
 		      if (i == 1)
 			{
-			  op0 = gen_reg_rtx (imode);
-			  emit_move_insn (op0, val_hi[0]);
-			  op1 = gen_reg_rtx (imode);
-			  emit_move_insn (op1, val_hi[1]);
+			  op0 = force_reg (imode, val_hi[0]);
+			  op1 = force_reg (imode, val_hi[1]);
 			  emit_insn (
 			    loongarch_vec_repl2_256 (target_hi, op0, op1));
 			}
 		      else if (i > 1)
 			{
-			  op0 = gen_reg_rtx (imode);
-			  emit_move_insn (op0, val_hi[i]);
+			  op0 = force_reg (imode, val_hi[i]);
 			  emit_insn (
 			    loongarch_vec_set256 (target_hi, op0, GEN_INT (i)));
 			}
 		    }
 		  else
 		    {
+		      op0 = force_reg (imode, val_hi[i]);
 		      /* Assign the lowest element of val_hi to all elements
 			 of target_hi.  */
 		      if (i == 0)
 			{
-			  op0 = gen_reg_rtx (imode);
-			  emit_move_insn (op0, val_hi[0]);
 			  emit_insn (loongarch_vec_repl1_256 (target_hi, op0));
 			}
 		      else if (!rtx_equal_p (val_hi[i], val_hi[0]))
 			{
-			  op0 = gen_reg_rtx (imode);
-			  emit_move_insn (op0, val_hi[i]);
 			  emit_insn (
 			    loongarch_vec_set256 (target_hi, op0, GEN_INT (i)));
 			}
@@ -11028,18 +11023,15 @@ loongarch_expand_vector_init (rtx target, rtx vals)
 		}
 	      if (!lo_same && !half_same)
 		{
+		  op0 = force_reg (imode, val_lo[i]);
 		  /* Assign the lowest element of val_lo to all elements
 		     of target_lo.  */
 		  if (i == 0)
 		    {
-		      op0 = gen_reg_rtx (imode);
-		      emit_move_insn (op0, val_lo[0]);
 		      emit_insn (loongarch_vec_repl1_128 (target_lo, op0));
 		    }
 		  else if (!rtx_equal_p (val_lo[i], val_lo[0]))
 		    {
-		      op0 = gen_reg_rtx (imode);
-		      emit_move_insn (op0, val_lo[i]);
 		      emit_insn (
 			loongarch_vec_set128 (target_lo, op0, GEN_INT (i)));
 		    }
@@ -11071,16 +11063,13 @@ loongarch_expand_vector_init (rtx target, rtx vals)
 		     reduce the number of instructions.  */
 		  if (i == 1)
 		    {
-		      op0 = gen_reg_rtx (imode);
-		      emit_move_insn (op0, val[0]);
-		      op1 = gen_reg_rtx (imode);
-		      emit_move_insn (op1, val[1]);
+		      op0 = force_reg (imode, val[0]);
+		      op1 = force_reg (imode, val[1]);
 		      emit_insn (loongarch_vec_repl2_128 (target, op0, op1));
 		    }
 		  else if (i > 1)
 		    {
-		      op0 = gen_reg_rtx (imode);
-		      emit_move_insn (op0, val[i]);
+		      op0 = force_reg (imode, val[i]);
 		      emit_insn (
 			loongarch_vec_set128 (target, op0, GEN_INT (i)));
 		    }
@@ -11093,18 +11082,15 @@ loongarch_expand_vector_init (rtx target, rtx vals)
 			loongarch_vec_mirror (target, target, const0_rtx));
 		      return;
 		    }
+		  op0 = force_reg (imode, val[i]);
 		  /* Assign the lowest element of val to all elements of
 		     target.  */
 		  if (i == 0)
 		    {
-		      op0 = gen_reg_rtx (imode);
-		      emit_move_insn (op0, val[0]);
 		      emit_insn (loongarch_vec_repl1_128 (target, op0));
 		    }
 		  else if (!rtx_equal_p (val[i], val[0]))
 		    {
-		      op0 = gen_reg_rtx (imode);
-		      emit_move_insn (op0, val[i]);
 		      emit_insn (
 			loongarch_vec_set128 (target, op0, GEN_INT (i)));
 		    }
diff --git a/gcc/testsuite/gcc.target/loongarch/pr113033.c b/gcc/testsuite/gcc.target/loongarch/pr113033.c
new file mode 100644
index 000000000..4ccd037d8
--- /dev/null
+++ b/gcc/testsuite/gcc.target/loongarch/pr113033.c
@@ -0,0 +1,23 @@
+/* PR target/113033: ICE with vector left rotate */
+/* { dg-do compile } */
+/* { dg-options "-O2 -mlasx" } */
+
+typedef unsigned __attribute__ ((vector_size (16))) v4si;
+typedef unsigned __attribute__ ((vector_size (32))) v8si;
+typedef unsigned long long __attribute__ ((vector_size (16))) v2di;
+typedef unsigned long long __attribute__ ((vector_size (32))) v4di;
+
+#define TEST(tp) \
+extern tp data_##tp; \
+tp \
+test_##tp (int x) \
+{ \
+  const int bit = sizeof (data_##tp[0]) * __CHAR_BIT__; \
+  data_##tp = data_##tp << (x & (bit - 1)) \
+	      | data_##tp >> (bit - x & (bit - 1)); \
+}
+
+TEST (v4si)
+TEST (v8si)
+TEST (v2di)
+TEST (v4di)
-- 
2.43.0