Don't assume it's AVX_U128_CLEAN after call_insn whose abi.mode_clobber(V4DImode...

If the function desn't clobber any sse registers or only clobber
128-bit part, then vzeroupper isn't issued before the function exit.
the status not CLEAN but ANY after the function.

Also for sibling_call, it's safe to issue an vzeroupper. Also there
could be missing vzeroupper since there's no mode_exit for
sibling_call_p.

gcc/ChangeLog:

	PR target/112891
	* config/i386/i386.cc (ix86_avx_u128_mode_after): Return
	AVX_U128_ANY if callee_abi doesn't clobber all_sse_regs to
	align with ix86_avx_u128_mode_needed.
	(ix86_avx_u128_mode_needed): Return AVX_U128_ClEAN for
	sibling_call.

gcc/testsuite/ChangeLog:

	* gcc.target/i386/pr112891.c: New test.
	* gcc.target/i386/pr112891-2.c: New test.

(cherry picked from commit fc189a08f5b7ad5889bd4c6b320c1dd99dd5d642)

diff --git a/gcc/config/i386/i386.cc b/gcc/config/i386/i386.cc
index 807e2a2ac5a750ed868b2d5b69bdf6e33c6733ad..7ace3702b1c162f165e75bb5de4facbddfa37ac7 100644 (file)
--- a/gcc/config/i386/i386.cc
+++ b/gcc/config/i386/i386.cc
@@ -14416,8 +14416,12 @@ ix86_avx_u128_mode_needed (rtx_insn *insn)
         modes wider than 256 bits.  It's only safe to issue a
         vzeroupper if all SSE registers are clobbered.  */
       const function_abi &abi = insn_callee_abi (insn);
-      if (!hard_reg_set_subset_p (reg_class_contents[SSE_REGS],
-                                 abi.mode_clobbers (V4DImode)))
+      /* Should be safe to issue an vzeroupper before sibling_call_p.
+        Also there not mode_exit for sibling_call, so there could be
+        missing vzeroupper for that.  */
+      if (!(SIBLING_CALL_P (insn)
+           || hard_reg_set_subset_p (reg_class_contents[SSE_REGS],
+                                     abi.mode_clobbers (V4DImode))))
        return AVX_U128_ANY;
 
       return AVX_U128_CLEAN;
@@ -14555,7 +14559,19 @@ ix86_avx_u128_mode_after (int mode, rtx_insn *insn)
       bool avx_upper_reg_found = false;
       note_stores (insn, ix86_check_avx_upper_stores, &avx_upper_reg_found);
 
-      return avx_upper_reg_found ? AVX_U128_DIRTY : AVX_U128_CLEAN;
+      if (avx_upper_reg_found)
+       return AVX_U128_DIRTY;
+
+      /* If the function desn't clobber any sse registers or only clobber
+        128-bit part, Then vzeroupper isn't issued before the function exit.
+        the status not CLEAN but ANY after the function.  */
+      const function_abi &abi = insn_callee_abi (insn);
+      if (!(SIBLING_CALL_P (insn)
+           || hard_reg_set_subset_p (reg_class_contents[SSE_REGS],
+                                     abi.mode_clobbers (V4DImode))))
+       return AVX_U128_ANY;
+
+      return  AVX_U128_CLEAN;
     }
 
   /* Otherwise, return current mode.  Remember that if insn

diff --git a/gcc/testsuite/gcc.target/i386/pr112891-2.c b/gcc/testsuite/gcc.target/i386/pr112891-2.c
new file mode 100644 (file)
index 0000000..164c398
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/pr112891-2.c
@@ -0,0 +1,30 @@
+/* { dg-do compile } */
+/* { dg-options "-mavx2 -O3" } */
+/* { dg-final { scan-assembler-times "vzeroupper" 1 } } */
+
+void
+__attribute__((noinline))
+bar (double* a)
+{
+  a[0] = 1.0;
+  a[1] = 2.0;
+}
+
+double
+__attribute__((noinline))
+foo (double* __restrict a, double* b)
+{
+  a[0] += b[0];
+  a[1] += b[1];
+  a[2] += b[2];
+  a[3] += b[3];
+  bar (b);
+  return a[5] + b[5];
+}
+
+double
+foo1 (double* __restrict a, double* b)
+{
+  double c = foo (a, b);
+  return __builtin_exp (c);
+}

diff --git a/gcc/testsuite/gcc.target/i386/pr112891.c b/gcc/testsuite/gcc.target/i386/pr112891.c
new file mode 100644 (file)
index 0000000..dbf6c67
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/pr112891.c
@@ -0,0 +1,29 @@
+/* { dg-do compile } */
+/* { dg-options "-mavx2 -O3" } */
+/* { dg-final { scan-assembler-times "vzeroupper" 1 } } */
+
+void
+__attribute__((noinline))
+bar (double* a)
+{
+  a[0] = 1.0;
+  a[1] = 2.0;
+}
+
+void
+__attribute__((noinline))
+foo (double* __restrict a, double* b)
+{
+  a[0] += b[0];
+  a[1] += b[1];
+  a[2] += b[2];
+  a[3] += b[3];
+  bar (b);
+}
+
+double
+foo1 (double* __restrict a, double* b)
+{
+  foo (a, b);
+  return __builtin_exp (b[1]);
+}