From 45063c0506a00f2673049d46f12a6061dca4692f Mon Sep 17 00:00:00 2001
From: liuhongt <hongtao.liu@intel.com>
Date: Thu, 13 May 2021 13:08:16 +0800
Subject: [PATCH] Fix ICE [PR target/100549]

When arg0 is same as arg1 in __builtin_ia32_pcmpgtw,
gimple_build (&stmts, GT_EXPR, cmp_type, arg0, arg1) will simplify the
comparison to vector constant 0, no stmts is generated, which causes
ICE in gsi_insert_before (gsi, stmts, GSI_SAME_STMT). So use
gsi_insert_seq_before instead which will handle NULL seq.

gcc/ChangeLog:

	PR target/100549
	* config/i386/i386.c (ix86_gimple_fold_builtin): Use
	gsi_insert_seq_before instead.

gcc/testsuite/ChangeLog:

	PR target/100549
	* gcc.target/i386/pr100549.c: New test.
---
 gcc/config/i386/i386.c                   |   4 +-
 gcc/testsuite/gcc.target/i386/pr100549.c | 108 +++++++++++++++++++++++++++++++
 2 files changed, 110 insertions(+), 2 deletions(-)
 create mode 100644 gcc/testsuite/gcc.target/i386/pr100549.c

diff --git a/gcc/config/i386/i386.c b/gcc/config/i386/i386.c
index 6a1f574..befe69e 100644
--- a/gcc/config/i386/i386.c
+++ b/gcc/config/i386/i386.c
@@ -18000,8 +18000,8 @@ ix86_gimple_fold_builtin (gimple_stmt_iterator *gsi)
 	tree cmp_type = truth_type_for (type);
 	gimple_seq stmts = NULL;
 	tree cmp = gimple_build (&stmts, tcode, cmp_type, arg0, arg1);
-	gsi_insert_before (gsi, stmts, GSI_SAME_STMT);
-	gimple *g = gimple_build_assign (gimple_call_lhs (stmt),
+	gsi_insert_seq_before (gsi, stmts, GSI_SAME_STMT);
+	gimple* g = gimple_build_assign (gimple_call_lhs (stmt),
 					 VEC_COND_EXPR, cmp,
 					 minus_one_vec, zero_vec);
 	gimple_set_location (g, loc);
diff --git a/gcc/testsuite/gcc.target/i386/pr100549.c b/gcc/testsuite/gcc.target/i386/pr100549.c
new file mode 100644
index 0000000..83bba3c
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/pr100549.c
@@ -0,0 +1,108 @@
+/* PR target/100549  */
+/* { dg-do compile } */
+/* { dg-options "-O -mavx2" } */
+
+typedef char v16qi __attribute__ ((vector_size (16)));
+typedef char v32qi __attribute__ ((vector_size (32)));
+typedef short v8hi __attribute__ ((vector_size (16)));
+typedef short v16hi __attribute__ ((vector_size (32)));
+typedef int v4si __attribute__ ((vector_size (16)));
+typedef int v8si __attribute__ ((vector_size (32)));
+typedef long long v2di __attribute__ ((vector_size (16)));
+typedef long long v4di __attribute__ ((vector_size (32)));
+
+v16qi
+f1 (v16qi a)
+{
+  return __builtin_ia32_pcmpeqb128 (a, a);
+}
+
+v8hi
+f2 (v8hi a)
+{
+  return __builtin_ia32_pcmpeqw128 (a, a);
+}
+
+v4si
+f3 (v4si a)
+{
+  return __builtin_ia32_pcmpeqd128 (a, a);
+}
+
+v2di
+f4 (v2di a)
+{
+  return __builtin_ia32_pcmpeqq (a, a);
+}
+
+v16qi
+f5 (v16qi a)
+{
+  return __builtin_ia32_pcmpgtb128 (a, a);
+}
+
+v8hi
+f6 (v8hi a)
+{
+  return __builtin_ia32_pcmpgtw128 (a, a);
+}
+
+v4si
+f7 (v4si a)
+{
+  return __builtin_ia32_pcmpgtd128 (a, a);
+}
+
+v2di
+f8 (v2di a)
+{
+  return __builtin_ia32_pcmpgtq (a, a);
+}
+
+v32qi
+f9 (v32qi a)
+{
+  return __builtin_ia32_pcmpeqb256 (a, a);
+}
+
+v16hi
+f10 (v16hi a)
+{
+  return __builtin_ia32_pcmpeqw256 (a, a);
+}
+
+v8si
+f11 (v8si a)
+{
+  return __builtin_ia32_pcmpeqd256 (a, a);
+}
+
+v4di
+f12 (v4di a)
+{
+  return __builtin_ia32_pcmpeqq256 (a, a);
+}
+
+v32qi
+f13 (v32qi a)
+{
+  return __builtin_ia32_pcmpgtb256 (a, a);
+}
+
+v16hi
+f14 (v16hi a)
+{
+  return __builtin_ia32_pcmpgtw256 (a, a);
+}
+
+v8si
+f15 (v8si a)
+{
+  return __builtin_ia32_pcmpgtd256 (a, a);
+}
+
+v4di
+f16 (v4di a)
+{
+  return __builtin_ia32_pcmpgtq256 (a, a);
+}
-- 
2.7.4