Fix regression from x86 multi-epilogue tuning

With the avx512_two_epilogues tuning enabled for zen4 and zen5
the gcc.target/i386/vect-epilogues-5.c testcase below regresses
and ends up using AVX2 sized vectors for the masked epilogue
rather than AVX512 sized vectors.  The following patch rectifies
this and adds coverage for the intended behavior.

	* config/i386/i386.cc (ix86_vector_costs::finish_cost):
	Do not suggest a first epilogue mode for AVX512 sized
	main loops with X86_TUNE_AVX512_TWO_EPILOGUES as that
	interferes with using a masked epilogue.

	* gcc.target/i386/vect-epilogues-1.c: New testcase.
	* gcc.target/i386/vect-epilogues-2.c: Likewise.
	* gcc.target/i386/vect-epilogues-3.c: Likewise.
	* gcc.target/i386/vect-epilogues-4.c: Likewise.
	* gcc.target/i386/vect-epilogues-5.c: Likewise.

(cherry picked from commit 75c7f90bfe6fa8e6c1a70b784e98a3412861646d)

6 files changed, 73 insertions, 7 deletions

diff --git a/gcc/config/i386/i386.cc b/gcc/config/i386/i386.cc
index 38df84f..a6f0a58 100644
--- a/gcc/config/i386/i386.cc
+++ b/gcc/config/i386/i386.cc
@@ -25545,14 +25545,10 @@ ix86_vector_costs::finish_cost (const vector_costs *scalar_costs)
   /* When X86_TUNE_AVX512_TWO_EPILOGUES is enabled arrange for both
      a AVX2 and a SSE epilogue for AVX512 vectorized loops.  */
   if (loop_vinfo
+      && LOOP_VINFO_EPILOGUE_P (loop_vinfo)
+      && GET_MODE_SIZE (loop_vinfo->vector_mode) == 32
       && ix86_tune_features[X86_TUNE_AVX512_TWO_EPILOGUES])
-    {
-      if (GET_MODE_SIZE (loop_vinfo->vector_mode) == 64)
-	m_suggested_epilogue_mode = V32QImode;
-      else if (LOOP_VINFO_EPILOGUE_P (loop_vinfo)
-	       && GET_MODE_SIZE (loop_vinfo->vector_mode) == 32)
-	m_suggested_epilogue_mode = V16QImode;
-    }
+    m_suggested_epilogue_mode = V16QImode;
   /* When a 128bit SSE vectorized epilogue still has a VF of 16 or larger
      enable a 64bit SSE epilogue.  */
   if (loop_vinfo
diff --git a/gcc/testsuite/gcc.target/i386/vect-epilogues-1.c b/gcc/testsuite/gcc.target/i386/vect-epilogues-1.c
new file mode 100644
index 0000000..a7f5f12
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/vect-epilogues-1.c
@@ -0,0 +1,14 @@
+/* { dg-do compile } */
+/* { dg-options "-O3 -mavx2 -mno-avx512f -mtune=generic -fdump-tree-vect-optimized" } */
+
+int test (signed char *data, int n)
+{
+  int sum = 0;
+  for (int i = 0; i < n; ++i)
+    sum += data[i];
+  return sum;
+}
+
+/* { dg-final { scan-tree-dump "loop vectorized using 32 byte vectors" "vect" } } */
+/* { dg-final { scan-tree-dump "loop vectorized using 16 byte vectors" "vect" } } */
+/* { dg-final { scan-tree-dump "loop vectorized using 8 byte vectors" "vect" { target { ! ia32 } } } } */
diff --git a/gcc/testsuite/gcc.target/i386/vect-epilogues-2.c b/gcc/testsuite/gcc.target/i386/vect-epilogues-2.c
new file mode 100644
index 0000000..d6c06ed
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/vect-epilogues-2.c
@@ -0,0 +1,15 @@
+/* { dg-do compile } */
+/* { dg-options "-O3 -mavx512bw -mtune=generic -fdump-tree-vect-optimized" } */
+
+int test (signed char *data, int n)
+{
+  int sum = 0;
+  for (int i = 0; i < n; ++i)
+    sum += data[i];
+  return sum;
+}
+
+/* { dg-final { scan-tree-dump "loop vectorized using 64 byte vectors" "vect" } } */
+/* { dg-final { scan-tree-dump "loop vectorized using 32 byte vectors" "vect" } } */
+/* { dg-final { scan-tree-dump-not "loop vectorized using 16 byte vectors" "vect" } } */
+/* { dg-final { scan-tree-dump-not "loop vectorized using 8 byte vectors" "vect" } } */
diff --git a/gcc/testsuite/gcc.target/i386/vect-epilogues-3.c b/gcc/testsuite/gcc.target/i386/vect-epilogues-3.c
new file mode 100644
index 0000000..0ee610f
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/vect-epilogues-3.c
@@ -0,0 +1,15 @@
+/* { dg-do compile } */
+/* { dg-options "-O3 -mavx512bw -mtune=znver4 -fdump-tree-vect-optimized" } */
+
+int test (signed char *data, int n)
+{
+  int sum = 0;
+  for (int i = 0; i < n; ++i)
+    sum += data[i];
+  return sum;
+}
+
+/* { dg-final { scan-tree-dump "loop vectorized using 64 byte vectors" "vect" } } */
+/* { dg-final { scan-tree-dump "loop vectorized using 32 byte vectors" "vect" } } */
+/* { dg-final { scan-tree-dump "loop vectorized using 16 byte vectors" "vect" } } */
+/* { dg-final { scan-tree-dump "loop vectorized using 8 byte vectors" "vect" { target { ! ia32 } } } } */
diff --git a/gcc/testsuite/gcc.target/i386/vect-epilogues-4.c b/gcc/testsuite/gcc.target/i386/vect-epilogues-4.c
new file mode 100644
index 0000000..498db6b
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/vect-epilogues-4.c
@@ -0,0 +1,13 @@
+/* { dg-do compile } */
+/* { dg-options "-O3 -mavx512bw -mtune=generic --param vect-partial-vector-usage=1 -fdump-tree-vect-optimized" } */
+
+int test (signed char *data, int n)
+{
+  int sum = 0;
+  for (int i = 0; i < n; ++i)
+    sum += data[i];
+  return sum;
+}
+
+/* { dg-final { scan-tree-dump-times "loop vectorized using 64 byte vectors" 2 "vect" } } */
+/* { dg-final { scan-tree-dump-not "loop vectorized using 32 byte vectors" "vect" } } */
diff --git a/gcc/testsuite/gcc.target/i386/vect-epilogues-5.c b/gcc/testsuite/gcc.target/i386/vect-epilogues-5.c
new file mode 100644
index 0000000..6772cab
--- /dev/null
+++ b/gcc/testsuite/gcc.target/i386/vect-epilogues-5.c
@@ -0,0 +1,13 @@
+/* { dg-do compile } */
+/* { dg-options "-O3 -mavx512bw -mtune=znver4 --param vect-partial-vector-usage=1 -fdump-tree-vect-optimized" } */
+
+int test (signed char *data, int n)
+{
+  int sum = 0;
+  for (int i = 0; i < n; ++i)
+    sum += data[i];
+  return sum;
+}
+
+/* { dg-final { scan-tree-dump-times "loop vectorized using 64 byte vectors" 2 "vect" } } */
+/* { dg-final { scan-tree-dump-not "loop vectorized using 32 byte vectors" "vect" } } */