From a177be05f6952c3f7e62186d2e138d96c475b81a Mon Sep 17 00:00:00 2001
From: Richard Biener <rguenther@suse.de>
Date: Mon, 15 Jul 2024 13:50:58 +0200
Subject: [PATCH] tree-optimization/115843 - fix wrong-code with fully-masked
 loop and peeling

When AVX512 uses a fully masked loop and peeling we fail to create the
correct initial loop mask when the mask is composed of multiple
components in some cases.  The following fixes this by properly applying
the bias for the component to the shift amount.

	PR tree-optimization/115843
	* tree-vect-loop-manip.cc
	(vect_set_loop_condition_partial_vectors_avx512): Properly
	bias the shift of the initial mask for alignment peeling.

	* gcc.dg/vect/pr115843.c: New testcase.
---
 gcc/testsuite/gcc.dg/vect/pr115843.c | 41 ++++++++++++++++++++++++++++
 gcc/tree-vect-loop-manip.cc          |  8 ++++--
 2 files changed, 47 insertions(+), 2 deletions(-)
 create mode 100644 gcc/testsuite/gcc.dg/vect/pr115843.c

diff --git a/gcc/testsuite/gcc.dg/vect/pr115843.c b/gcc/testsuite/gcc.dg/vect/pr115843.c
new file mode 100644
index 000000000000..3dbb6c792788
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/vect/pr115843.c
@@ -0,0 +1,41 @@
+/* { dg-additional-options "-mavx512f --param vect-partial-vector-usage=2" { target avx512f_runtime } } */
+
+#include "tree-vect.h"
+
+typedef __UINT64_TYPE__ BITBOARD;
+BITBOARD KingPressureMask1[64], KingSafetyMask1[64];
+
+void __attribute__((noinline))
+foo()
+{
+  for (int i = 0; i < 64; i++)
+    {
+      if ((i & 7) == 0)
+	KingPressureMask1[i] = KingSafetyMask1[i + 1];
+      else if ((i & 7) == 7)
+	KingPressureMask1[i] = KingSafetyMask1[i - 1];
+      else
+	KingPressureMask1[i] = KingSafetyMask1[i];
+    }
+}
+
+BITBOARD verify[64]
+  = {1, 1, 2, 3, 4, 5, 6, 6, 9, 9, 10, 11, 12, 13, 14, 14, 17, 17, 18, 19,
+    20, 21, 22, 22, 25, 25, 26, 27, 28, 29, 30, 30, 33, 33, 34, 35, 36, 37, 38,
+    38, 41, 41, 42, 43, 44, 45, 46, 46, 49, 49, 50, 51, 52, 53, 54, 54, 57, 57,
+    58, 59, 60, 61, 62, 62};
+
+int main()
+{
+  check_vect ();
+
+#pragma GCC novector
+  for (int i = 0; i < 64; ++i)
+    KingSafetyMask1[i] = i;
+  foo ();
+#pragma GCC novector
+  for (int i = 0; i < 64; ++i)
+    if (KingPressureMask1[i] != verify[i])
+      __builtin_abort ();
+  return 0;
+}
diff --git a/gcc/tree-vect-loop-manip.cc b/gcc/tree-vect-loop-manip.cc
index ac13873cd88d..57dbcbe862cd 100644
--- a/gcc/tree-vect-loop-manip.cc
+++ b/gcc/tree-vect-loop-manip.cc
@@ -1149,10 +1149,14 @@ vect_set_loop_condition_partial_vectors_avx512 (class loop *loop,
 	      /* ???  But when the shift amount isn't constant this requires
 		 a round-trip to GRPs.  We could apply the bias to either
 		 side of the compare instead.  */
-	      tree shift = gimple_build (&preheader_seq, MULT_EXPR,
+	      tree shift = gimple_build (&preheader_seq, MINUS_EXPR,
 					 TREE_TYPE (niters_skip), niters_skip,
 					 build_int_cst (TREE_TYPE (niters_skip),
-							rgc.max_nscalars_per_iter));
+							bias));
+	      shift = gimple_build (&preheader_seq, MULT_EXPR,
+				    TREE_TYPE (niters_skip), shift,
+				    build_int_cst (TREE_TYPE (niters_skip),
+						   rgc.max_nscalars_per_iter));
 	      init_ctrl = gimple_build (&preheader_seq, LSHIFT_EXPR,
 					TREE_TYPE (init_ctrl),
 					init_ctrl, shift);
-- 
2.47.2