[PATCH] tree-optimization/100253 - fix bogus aligned vectorized loads/stores

[PATCH] tree-optimization/100253 - fix bogus aligned vectorized loads/stores

[Richard Biener]

At some point DR_MISALIGNMENT was supposed to be -1 when the
access was not element aligned.  That's obviously not true at this
point so this adjusts both store and load vectorizing to no longer
assume this which in turn allows simplifying the code.

Bootstrapped and tested on x86_64-unknown-linux-gnu, pushed to
trunk sofar.

2021-04-29  Richard Biener  <rguenther@suse.de>

	PR tree-optimization/100253
	* tree-vect-stmts.c (vectorizable_load): Do not assume
	element alignment when DR_MISALIGNMENT is -1.
	(vectorizable_store): Likewise.

	* g++.dg/pr100253.C: New testcase.
---
 gcc/testsuite/g++.dg/pr100253.C | 33 +++++++++++++++++++++++++++++++++
 gcc/tree-vect-stmts.c           | 18 ++++--------------
 2 files changed, 37 insertions(+), 14 deletions(-)
 create mode 100644 gcc/testsuite/g++.dg/pr100253.C

diff --git a/gcc/testsuite/g++.dg/pr100253.C b/gcc/testsuite/g++.dg/pr100253.C
new file mode 100644
index 00000000000..0102caa7df8
--- /dev/null
+++ b/gcc/testsuite/g++.dg/pr100253.C
@@ -0,0 +1,33 @@
+/* { dg-do run } */
+/* { dg-options "-O2 -fno-tree-bit-ccp -ftree-slp-vectorize" } */
+
+#include <vector>
+
+struct T
+{
+};
+
+struct S
+{
+  std::vector < std::vector < T > > v;
+  char x;
+  char y[16];
+  char z[16];
+};
+
+S s, g[1];
+
+void
+foo (char *buf)
+{
+  s = g[*buf];
+}
+
+char c;
+
+int
+main ()
+{
+  foo (&c);
+  return 0;
+}
diff --git a/gcc/tree-vect-stmts.c b/gcc/tree-vect-stmts.c
index 4c01e82ff39..bd2a1c89e67 100644
--- a/gcc/tree-vect-stmts.c
+++ b/gcc/tree-vect-stmts.c
@@ -8166,6 +8166,7 @@ vectorizable_store (vec_info *vinfo,
 		  && TREE_CODE (dataref_ptr) == SSA_NAME)
 		set_ptr_info_alignment (get_ptr_info (dataref_ptr), align,
 					misalign);
+	      align = least_bit_hwi (misalign | align);
 
 	      if (memory_access_type == VMAT_CONTIGUOUS_REVERSE)
 		{
@@ -8187,7 +8188,6 @@ vectorizable_store (vec_info *vinfo,
 	      /* Arguments are ready.  Create the new vector stmt.  */
 	      if (final_mask)
 		{
-		  align = least_bit_hwi (misalign | align);
 		  tree ptr = build_int_cst (ref_type, align * BITS_PER_UNIT);
 		  gcall *call
 		    = gimple_build_call_internal (IFN_MASK_STORE, 4,
@@ -8202,7 +8202,6 @@ vectorizable_store (vec_info *vinfo,
 		  tree final_len
 		    = vect_get_loop_len (loop_vinfo, loop_lens,
 					 vec_num * ncopies, vec_num * j + i);
-		  align = least_bit_hwi (misalign | align);
 		  tree ptr = build_int_cst (ref_type, align * BITS_PER_UNIT);
 		  machine_mode vmode = TYPE_MODE (vectype);
 		  opt_machine_mode new_ovmode
@@ -8241,14 +8240,10 @@ vectorizable_store (vec_info *vinfo,
 					  : build_int_cst (ref_type, 0));
 		  if (aligned_access_p (first_dr_info))
 		    ;
-		  else if (DR_MISALIGNMENT (first_dr_info) == -1)
-		    TREE_TYPE (data_ref)
-		      = build_aligned_type (TREE_TYPE (data_ref),
-					    align * BITS_PER_UNIT);
 		  else
 		    TREE_TYPE (data_ref)
 		      = build_aligned_type (TREE_TYPE (data_ref),
-					    TYPE_ALIGN (elem_type));
+					    align * BITS_PER_UNIT);
 		  vect_copy_ref_info (data_ref, DR_REF (first_dr_info->dr));
 		  new_stmt = gimple_build_assign (data_ref, vec_oprnd);
 		  vect_finish_stmt_generation (vinfo, stmt_info, new_stmt, gsi);
@@ -9452,10 +9447,10 @@ vectorizable_load (vec_info *vinfo,
 			&& TREE_CODE (dataref_ptr) == SSA_NAME)
 		      set_ptr_info_alignment (get_ptr_info (dataref_ptr),
 					      align, misalign);
+		    align = least_bit_hwi (misalign | align);
 
 		    if (final_mask)
 		      {
-			align = least_bit_hwi (misalign | align);
 			tree ptr = build_int_cst (ref_type,
 						  align * BITS_PER_UNIT);
 			gcall *call
@@ -9472,7 +9467,6 @@ vectorizable_load (vec_info *vinfo,
 			  = vect_get_loop_len (loop_vinfo, loop_lens,
 					       vec_num * ncopies,
 					       vec_num * j + i);
-			align = least_bit_hwi (misalign | align);
 			tree ptr = build_int_cst (ref_type,
 						  align * BITS_PER_UNIT);
 			gcall *call
@@ -9548,14 +9542,10 @@ vectorizable_load (vec_info *vinfo,
 			  = fold_build2 (MEM_REF, ltype, dataref_ptr, offset);
 			if (alignment_support_scheme == dr_aligned)
 			  ;
-			else if (DR_MISALIGNMENT (first_dr_info) == -1)
-			  TREE_TYPE (data_ref)
-			    = build_aligned_type (TREE_TYPE (data_ref),
-						  align * BITS_PER_UNIT);
 			else
 			  TREE_TYPE (data_ref)
 			    = build_aligned_type (TREE_TYPE (data_ref),
-						  TYPE_ALIGN (elem_type));
+						  align * BITS_PER_UNIT);
 			if (ltype != vectype)
 			  {
 			    vect_copy_ref_info (data_ref,
-- 
2.26.2