For function arguments/return, when it's BLK mode, it's put in a
parallel with an expr_list, and the expr_list contains the real mode
and registers.
Current ix86_check_avx_upper_register only checked for SSE_REG_P, and
failed to handle that. The patch extend the handle to each subrtx.

Bootstrapped and regtested on x86_64-pc-linux-gnu{-m32,}.
Ok for trunk?

gcc/ChangeLog:

        PR target/116512
        * config/i386/i386.cc (ix86_avx_u128_mode_entry): Iterate
        each subrtx for potential rtx parallel to check avx upper
        register.
        (ix86_avx_u128_mode_exit): Ditto.

gcc/testsuite/ChangeLog:

        * gcc.target/i386/pr116512.c: New test.
---
 gcc/config/i386/i386.cc                  | 28 ++++++++++++++++++++----
 gcc/testsuite/gcc.target/i386/pr116512.c | 26 ++++++++++++++++++++++
 2 files changed, 50 insertions(+), 4 deletions(-)
 create mode 100644 gcc/testsuite/gcc.target/i386/pr116512.c

diff --git a/gcc/config/i386/i386.cc b/gcc/config/i386/i386.cc
index 224a78cc832..94d1a14056e 100644
--- a/gcc/config/i386/i386.cc
+++ b/gcc/config/i386/i386.cc
@@ -15148,8 +15148,18 @@ ix86_avx_u128_mode_entry (void)
     {
       rtx incoming = DECL_INCOMING_RTL (arg);
 
-      if (incoming && ix86_check_avx_upper_register (incoming))
-       return AVX_U128_DIRTY;
+      if (incoming)
+       {
+         /* construct_container may return a parallel with expr_list
+            which contains the real reg and mode  */
+         subrtx_var_iterator::array_type array;
+         FOR_EACH_SUBRTX_VAR (iter, array, incoming, ALL)
+           {
+             rtx x = *iter;
+             if (ix86_check_avx_upper_register (x))
+               return AVX_U128_DIRTY;
+           }
+       }
     }
 
   return AVX_U128_CLEAN;
@@ -15184,8 +15194,18 @@ ix86_avx_u128_mode_exit (void)
 
   /* Exit mode is set to AVX_U128_DIRTY if there are 256bit
      or 512 bit modes used in the function return register. */
-  if (reg && ix86_check_avx_upper_register (reg))
-    return AVX_U128_DIRTY;
+  if (reg)
+    {
+      /* construct_container may return a parallel with expr_list
+        which contains the real reg and mode  */
+      subrtx_var_iterator::array_type array;
+      FOR_EACH_SUBRTX_VAR (iter, array, reg, ALL)
+       {
+         rtx x = *iter;
+         if (ix86_check_avx_upper_register (x))
+           return AVX_U128_DIRTY;
+       }
+    }
 
   /* Exit mode is set to AVX_U128_DIRTY if there are 256bit or 512bit
      modes used in function arguments, otherwise return AVX_U128_CLEAN.
diff --git a/gcc/testsuite/gcc.target/i386/pr116512.c 
b/gcc/testsuite/gcc.target/i386/pr116512.c
new file mode 100644
index 00000000000..c2bc6c91b64
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/pr116512.c
@@ -0,0 +1,26 @@
+/* { dg-do compile } */
+/* { dg-options "-march=x86-64-v4 -O2" } */
+/* { dg-final { scan-assembler-not "vzeroupper" { target { ! ia32 } } } } */
+
+#include <immintrin.h>
+
+struct B {
+  union {
+    __m512 f;
+    __m512i s;
+  };
+};
+
+struct B foo(int n) {
+  struct B res;
+  res.s = _mm512_set1_epi32(n);
+
+  return res;
+}
+
+__m512i bar(int n) {
+  struct B res;
+  res.s = _mm512_set1_epi32(n);
+
+  return res.s;
+}
-- 
2.31.1

Reply via email to