From 20482cfcc1d3b71e0aec57b5b48685bf0b5402ca Mon Sep 17 00:00:00 2001
From: Jakub Jelinek <jakub@redhat.com>
Date: Wed, 10 Feb 2021 19:50:11 +0100
Subject: [PATCH] i386: Fix ICEs due to simplify_gen_subreg returning NULL
 [PR99025]

In these patterns, we call simplify_gen_subreg on the input operand
to create paradoxical subregs that have 2x, 4x or 8x elements as the input
operand.  That works fine if the input operand is a REG, but when it is a
SUBREG, RTL doesn't allow SUBREG of SUBREG and so relies on simplify_subreg
actually simplifying it.  And e.g. if the input operand is a SUBREG that
changes the element mode (floating vs. non-floating) and then combined with
a paradoxical subreg (i.e. different size) this can easily fail, then
simplify_gen_subreg returns NULL but we still use it in instructions.

Fixed by forcing the operands into REG.

2021-02-10  Jakub Jelinek  <jakub@redhat.com>

	PR target/99025
	* config/i386/sse.md (fix<fixunssuffix>_truncv2sfv2di2,
	<insn>v8qiv8hi2, <insn>v8qiv8si2, <insn>v4qiv4si2, <insn>v4hiv4si2,
	<insn>v8qiv8di2, <insn>v4qiv4di2, <insn>v2qiv2di2, <insn>v4hiv4di2,
	<insn>v2hiv2di2, <insn>v2siv2di2): Force operands[1] into REG before
	calling simplify_gen_subreg on it.

	* gcc.target/i386/pr99025.c: New test.
---
 gcc/config/i386/sse.md                  | 11 +++++++++++
 gcc/testsuite/gcc.target/i386/pr99025.c | 17 +++++++++++++++++
 2 files changed, 28 insertions(+)
 create mode 100644 gcc/testsuite/gcc.target/i386/pr99025.c

diff --git a/gcc/config/i386/sse.md b/gcc/config/i386/sse.md
index 369a00d8f51..db5be59f5b7 100644
--- a/gcc/config/i386/sse.md
+++ b/gcc/config/i386/sse.md
@@ -6356,6 +6356,7 @@
 	  (match_operand:V2SF 1 "register_operand")))]
   "TARGET_AVX512DQ && TARGET_AVX512VL"
 {
+  operands[1] = force_reg (V2SFmode, operands[1]);
   operands[1] = simplify_gen_subreg (V4SFmode, operands[1], V2SFmode, 0);
   emit_insn (gen_avx512dq_fix<fixunssuffix>_truncv2sfv2di2
 	     (operands[0], operands[1]));
@@ -18013,6 +18014,7 @@
 {
   if (!MEM_P (operands[1]))
     {
+      operands[1] = force_reg (V8QImode, operands[1]);
       operands[1] = simplify_gen_subreg (V16QImode, operands[1], V8QImode, 0);
       emit_insn (gen_sse4_1_<code>v8qiv8hi2 (operands[0], operands[1]));
       DONE;
@@ -18090,6 +18092,7 @@
 {
   if (!MEM_P (operands[1]))
     {
+      operands[1] = force_reg (V8QImode, operands[1]);
       operands[1] = simplify_gen_subreg (V16QImode, operands[1], V8QImode, 0);
       emit_insn (gen_avx2_<code>v8qiv8si2 (operands[0], operands[1]));
       DONE;
@@ -18153,6 +18156,7 @@
 {
   if (!MEM_P (operands[1]))
     {
+      operands[1] = force_reg (V4QImode, operands[1]);
       operands[1] = simplify_gen_subreg (V16QImode, operands[1], V4QImode, 0);
       emit_insn (gen_sse4_1_<code>v4qiv4si2 (operands[0], operands[1]));
       DONE;
@@ -18279,6 +18283,7 @@
 {
   if (!MEM_P (operands[1]))
     {
+      operands[1] = force_reg (V4HImode, operands[1]);
       operands[1] = simplify_gen_subreg (V8HImode, operands[1], V4HImode, 0);
       emit_insn (gen_sse4_1_<code>v4hiv4si2 (operands[0], operands[1]));
       DONE;
@@ -18366,6 +18371,7 @@
 {
   if (!MEM_P (operands[1]))
     {
+      operands[1] = force_reg (V8QImode, operands[1]);
       operands[1] = simplify_gen_subreg (V16QImode, operands[1], V8QImode, 0);
       emit_insn (gen_avx512f_<code>v8qiv8di2 (operands[0], operands[1]));
       DONE;
@@ -18427,6 +18433,7 @@
 {
   if (!MEM_P (operands[1]))
     {
+      operands[1] = force_reg (V8QImode, operands[1]);
       operands[1] = simplify_gen_subreg (V16QImode, operands[1], V8QImode, 0);
       emit_insn (gen_avx2_<code>v4qiv4di2 (operands[0], operands[1]));
       DONE;
@@ -18453,6 +18460,7 @@
 	  (match_operand:V2QI 1 "register_operand")))]
   "TARGET_SSE4_1"
 {
+  operands[1] = force_reg (V2QImode, operands[1]);
   operands[1] = simplify_gen_subreg (V16QImode, operands[1], V2QImode, 0);
   emit_insn (gen_sse4_1_<code>v2qiv2di2 (operands[0], operands[1]));
   DONE;
@@ -18525,6 +18533,7 @@
 {
   if (!MEM_P (operands[1]))
     {
+      operands[1] = force_reg (V4HImode, operands[1]);
       operands[1] = simplify_gen_subreg (V8HImode, operands[1], V4HImode, 0);
       emit_insn (gen_avx2_<code>v4hiv4di2 (operands[0], operands[1]));
       DONE;
@@ -18586,6 +18595,7 @@
 {
   if (!MEM_P (operands[1]))
     {
+      operands[1] = force_reg (V2HImode, operands[1]);
       operands[1] = simplify_gen_subreg (V8HImode, operands[1], V2HImode, 0);
       emit_insn (gen_sse4_1_<code>v2hiv2di2 (operands[0], operands[1]));
       DONE;
@@ -18737,6 +18747,7 @@
 {
   if (!MEM_P (operands[1]))
     {
+      operands[1] = force_reg (V2SImode, operands[1]);
       operands[1] = simplify_gen_subreg (V4SImode, operands[1], V2SImode, 0);
       emit_insn (gen_sse4_1_<code>v2siv2di2 (operands[0], operands[1]));
       DONE;
diff --git a/gcc/testsuite/gcc.target/i386/pr99025.c b/gcc/testsuite/gcc.target/i386/pr99025.c
new file mode 100644
index 00000000000..288538d618a
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/pr99025.c
@@ -0,0 +1,17 @@
+/* PR target/99025 */
+/* { dg-do compile } */
+/* { dg-options "-O3 -msse4" } */
+
+long v[16];
+int w;
+union U { float u; int r; } x;
+
+void
+foo (float y)
+{
+  union U z;
+  x.u = w;
+  v[5] = x.r;
+  z.u = y;
+  v[6] = z.r;
+}
-- 
2.30.2