[committed] vect: Fix ncopies calculation for emulated gather/scatter [PR103494]

[Richard Sandiford]

I was too eager about removing ncopies calculations in g:10833849b55.
When emulating gather/scatter, the offset ncopies can be different from
the data ncopies.  This patch restores the original calculation.

Tested on aarch64-linux-gnu and x86_64-linux-gnu.  Pushed as obvious,
since it's essentially reverting part of my earlier patch (except for
obvious adjustments to keep slp_node).

Richard


gcc/
	PR tree-optimization/103494
	* tree-vect-stmts.c (vect_get_gather_scatter_ops): Remove ncopies
	argument and calculate ncopies from gs_info->offset_vectype
	where necessary.
	(vectorizable_store, vectorizable_load): Update accordingly.

gcc/testsuite/
	PR tree-optimization/103494
	* gcc.dg/vect/pr103494.c: New test.
	* g++.dg/vect/pr103494.cc: Likewise.
---
 gcc/testsuite/g++.dg/vect/pr103494.cc | 26 ++++++++++++++++++++++++++
 gcc/testsuite/gcc.dg/vect/pr103494.c  | 14 ++++++++++++++
 gcc/tree-vect-stmts.c                 | 21 ++++++++++++---------
 3 files changed, 52 insertions(+), 9 deletions(-)
 create mode 100644 gcc/testsuite/g++.dg/vect/pr103494.cc
 create mode 100644 gcc/testsuite/gcc.dg/vect/pr103494.c

diff --git a/gcc/testsuite/g++.dg/vect/pr103494.cc b/gcc/testsuite/g++.dg/vect/pr103494.cc
new file mode 100644
index 00000000000..c0b078105c2
--- /dev/null
+++ b/gcc/testsuite/g++.dg/vect/pr103494.cc
@@ -0,0 +1,26 @@
+/* { dg-do compile } */
+/* { dg-additional-options "-O3" } */
+
+void glFinish();
+struct _Vector_base {
+  struct {
+    unsigned _M_start;
+  } _M_impl;
+};
+class vector : _Vector_base {
+public:
+  vector(long) {}
+  unsigned *data() { return &_M_impl._M_start; }
+};
+void *PutBitsIndexedImpl_color_table;
+int PutBitsIndexedImpl_dstRectHeight;
+char *PutBitsIndexedImpl_src_ptr;
+void PutBitsIndexedImpl() {
+  vector unpacked_buf(PutBitsIndexedImpl_dstRectHeight);
+  unsigned *dst_ptr = unpacked_buf.data();
+  for (int x; x; x++) {
+    char i = *PutBitsIndexedImpl_src_ptr++;
+    dst_ptr[x] = static_cast<int *>(PutBitsIndexedImpl_color_table)[i];
+  }
+  glFinish();
+}
diff --git a/gcc/testsuite/gcc.dg/vect/pr103494.c b/gcc/testsuite/gcc.dg/vect/pr103494.c
new file mode 100644
index 00000000000..b544bf2379c
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/vect/pr103494.c
@@ -0,0 +1,14 @@
+/* { dg-do compile } */
+/* { dg-additional-options "-O3" } */
+
+typedef int T1;
+typedef signed char T2;
+
+T1
+f (T1 *d, T2 *x, int n)
+{
+  unsigned char res = 0;
+  for (int i = 0; i < n; ++i)
+    res += d[x[i]];
+  return res;
+}
diff --git a/gcc/tree-vect-stmts.c b/gcc/tree-vect-stmts.c
index 8642acbc0b4..9726450ab2d 100644
--- a/gcc/tree-vect-stmts.c
+++ b/gcc/tree-vect-stmts.c
@@ -2962,8 +2962,7 @@ vect_build_gather_load_calls (vec_info *vinfo, stmt_vec_info stmt_info,
 static void
 vect_get_gather_scatter_ops (loop_vec_info loop_vinfo,
 			     class loop *loop, stmt_vec_info stmt_info,
-			     slp_tree slp_node, unsigned int ncopies,
-			     gather_scatter_info *gs_info,
+			     slp_tree slp_node, gather_scatter_info *gs_info,
 			     tree *dataref_ptr, vec<tree> *vec_offset)
 {
   gimple_seq stmts = NULL;
@@ -2978,9 +2977,13 @@ vect_get_gather_scatter_ops (loop_vec_info loop_vinfo,
   if (slp_node)
     vect_get_slp_defs (SLP_TREE_CHILDREN (slp_node)[0], vec_offset);
   else
-    vect_get_vec_defs_for_operand (loop_vinfo, stmt_info, ncopies,
-				   gs_info->offset, vec_offset,
-				   gs_info->offset_vectype);
+    {
+      unsigned ncopies
+	= vect_get_num_copies (loop_vinfo, gs_info->offset_vectype);
+      vect_get_vec_defs_for_operand (loop_vinfo, stmt_info, ncopies,
+				     gs_info->offset, vec_offset,
+				     gs_info->offset_vectype);
+    }
 }
 
 /* Prepare to implement a grouped or strided load or store using
@@ -8149,8 +8152,8 @@ vectorizable_store (vec_info *vinfo,
 	  else if (STMT_VINFO_GATHER_SCATTER_P (stmt_info))
 	    {
 	      vect_get_gather_scatter_ops (loop_vinfo, loop, stmt_info,
-					   slp_node, ncopies, &gs_info,
-					   &dataref_ptr, &vec_offsets);
+					   slp_node, &gs_info, &dataref_ptr,
+					   &vec_offsets);
 	      vec_offset = vec_offsets[0];
 	    }
 	  else
@@ -9454,8 +9457,8 @@ vectorizable_load (vec_info *vinfo,
 	  else if (STMT_VINFO_GATHER_SCATTER_P (stmt_info))
 	    {
 	      vect_get_gather_scatter_ops (loop_vinfo, loop, stmt_info,
-					   slp_node, ncopies, &gs_info,
-					   &dataref_ptr, &vec_offsets);
+					   slp_node, &gs_info, &dataref_ptr,
+					   &vec_offsets);
 	    }
 	  else
 	    dataref_ptr
-- 
2.25.1