From a2f5e6f38fe7b5b32a252643b00dd2d7ab0e3fac Mon Sep 17 00:00:00 2001
From: Richard Sandiford <richard.sandiford@arm.com>
Date: Tue, 12 May 2020 09:01:10 +0100
Subject: [PATCH 19/35] [Backport] tree: Add vector_element_bits(_tree)
 [PR94980 1/3]

Reference: https://gcc.gnu.org/git/gitweb.cgi?p=gcc.git;h=d17a896da1e898928d337596d029f0ece0039d55

A lot of code that wants to know the number of bits in a vector
element gets that information from the element's TYPE_SIZE,
which is always equal to TYPE_SIZE_UNIT * BITS_PER_UNIT.
This doesn't work for SVE and AVX512-style packed boolean vectors,
where several elements can occupy a single byte.

This patch introduces a new pair of helpers for getting the true
(possibly sub-byte) size.  I made a token attempt to convert obvious
element size calculations, but I'm sure I missed some.

2020-05-12  Richard Sandiford  <richard.sandiford@arm.com>

gcc/
	PR tree-optimization/94980
	* tree.h (vector_element_bits, vector_element_bits_tree): Declare.
	* tree.c (vector_element_bits, vector_element_bits_tree): New.
	* match.pd: Use the new functions instead of determining the
	vector element size directly from TYPE_SIZE(_UNIT).
	* tree-vect-data-refs.c (vect_gather_scatter_fn_p): Likewise.
	* tree-vect-patterns.c (vect_recog_mask_conversion_pattern): Likewise.
	* tree-vect-stmts.c (vect_is_simple_cond): Likewise.
	* tree-vect-generic.c (expand_vector_piecewise): Likewise.
	(expand_vector_conversion): Likewise.
	(expand_vector_addition): Likewise for a TYPE_SIZE_UNIT used as
	a divisor.  Convert the dividend to bits to compensate.
	* tree-vect-loop.c (vectorizable_live_operation): Call
	vector_element_bits instead of open-coding it.
---
 gcc/ChangeLog             | 17 +++++++++++++++++
 gcc/match.pd              |  2 +-
 gcc/tree-vect-data-refs.c |  2 +-
 gcc/tree-vect-generic.c   | 19 +++++++------------
 gcc/tree-vect-loop.c      |  4 +---
 gcc/tree-vect-patterns.c  |  3 +--
 gcc/tree-vect-stmts.c     |  3 +--
 gcc/tree.c                | 24 ++++++++++++++++++++++++
 gcc/tree.h                |  2 ++
 9 files changed, 55 insertions(+), 21 deletions(-)

diff --git a/gcc/ChangeLog b/gcc/ChangeLog
index 3b1384e70..07aea9b86 100644
--- a/gcc/ChangeLog
+++ b/gcc/ChangeLog
@@ -1,3 +1,20 @@
+2020-05-12  Richard Sandiford  <richard.sandiford@arm.com>
+
+	PR tree-optimization/94980
+	* tree.h (vector_element_bits, vector_element_bits_tree): Declare.
+	* tree.c (vector_element_bits, vector_element_bits_tree): New.
+	* match.pd: Use the new functions instead of determining the
+	vector element size directly from TYPE_SIZE(_UNIT).
+	* tree-vect-data-refs.c (vect_gather_scatter_fn_p): Likewise.
+	* tree-vect-patterns.c (vect_recog_mask_conversion_pattern): Likewise.
+	* tree-vect-stmts.c (vect_is_simple_cond): Likewise.
+	* tree-vect-generic.c (expand_vector_piecewise): Likewise.
+	(expand_vector_conversion): Likewise.
+	(expand_vector_addition): Likewise for a TYPE_SIZE_UNIT used as
+	a divisor.  Convert the dividend to bits to compensate.
+	* tree-vect-loop.c (vectorizable_live_operation): Call
+	vector_element_bits instead of open-coding it.
+
 2021-04-08  Release Manager
 
 	* GCC 10.3.0 released.
diff --git a/gcc/match.pd b/gcc/match.pd
index 5899eea95..79a0228d2 100644
--- a/gcc/match.pd
+++ b/gcc/match.pd
@@ -6236,7 +6236,7 @@ DEFINE_INT_AND_FLOAT_ROUND_FN (RINT)
       }
       (if (ins)
        (bit_insert { op0; } { ins; }
-         { bitsize_int (at * tree_to_uhwi (TYPE_SIZE (TREE_TYPE (type)))); })
+         { bitsize_int (at * vector_element_bits (type)); })
        (if (changed)
         (vec_perm { op0; } { op1; } { op2; }))))))))))
 
diff --git a/gcc/tree-vect-data-refs.c b/gcc/tree-vect-data-refs.c
index d78b06455..e4466a4f3 100644
--- a/gcc/tree-vect-data-refs.c
+++ b/gcc/tree-vect-data-refs.c
@@ -3709,7 +3709,7 @@ vect_gather_scatter_fn_p (vec_info *vinfo, bool read_p, bool masked_p,
 			  tree *offset_vectype_out)
 {
   unsigned int memory_bits = tree_to_uhwi (TYPE_SIZE (memory_type));
-  unsigned int element_bits = tree_to_uhwi (TYPE_SIZE (TREE_TYPE (vectype)));
+  unsigned int element_bits = vector_element_bits (vectype);
   if (element_bits != memory_bits)
     /* For now the vector elements must be the same width as the
        memory elements.  */
diff --git a/gcc/tree-vect-generic.c b/gcc/tree-vect-generic.c
index c10492034..37c3956a4 100644
--- a/gcc/tree-vect-generic.c
+++ b/gcc/tree-vect-generic.c
@@ -276,8 +276,7 @@ expand_vector_piecewise (gimple_stmt_iterator *gsi, elem_op_func f,
   tree part_width = TYPE_SIZE (inner_type);
   tree index = bitsize_int (0);
   int nunits = nunits_for_known_piecewise_op (type);
-  int delta = tree_to_uhwi (part_width)
-	      / tree_to_uhwi (TYPE_SIZE (TREE_TYPE (type)));
+  int delta = tree_to_uhwi (part_width) / vector_element_bits (type);
   int i;
   location_t loc = gimple_location (gsi_stmt (*gsi));
 
@@ -357,8 +356,7 @@ expand_vector_addition (gimple_stmt_iterator *gsi,
 			elem_op_func f, elem_op_func f_parallel,
 			tree type, tree a, tree b, enum tree_code code)
 {
-  int parts_per_word = UNITS_PER_WORD
-	  	       / tree_to_uhwi (TYPE_SIZE_UNIT (TREE_TYPE (type)));
+  int parts_per_word = BITS_PER_WORD / vector_element_bits (type);
 
   if (INTEGRAL_TYPE_P (TREE_TYPE (type))
       && parts_per_word >= 4
@@ -1733,19 +1731,17 @@ expand_vector_conversion (gimple_stmt_iterator *gsi)
   optab optab1 = unknown_optab;
 
   gcc_checking_assert (VECTOR_TYPE_P (ret_type) && VECTOR_TYPE_P (arg_type));
-  gcc_checking_assert (tree_fits_uhwi_p (TYPE_SIZE (TREE_TYPE (ret_type))));
-  gcc_checking_assert (tree_fits_uhwi_p (TYPE_SIZE (TREE_TYPE (arg_type))));
   if (INTEGRAL_TYPE_P (TREE_TYPE (ret_type))
       && SCALAR_FLOAT_TYPE_P (TREE_TYPE (arg_type)))
     code = FIX_TRUNC_EXPR;
   else if (INTEGRAL_TYPE_P (TREE_TYPE (arg_type))
 	   && SCALAR_FLOAT_TYPE_P (TREE_TYPE (ret_type)))
     code = FLOAT_EXPR;
-  if (tree_to_uhwi (TYPE_SIZE (TREE_TYPE (ret_type)))
-      < tree_to_uhwi (TYPE_SIZE (TREE_TYPE (arg_type))))
+  unsigned int ret_elt_bits = vector_element_bits (ret_type);
+  unsigned int arg_elt_bits = vector_element_bits (arg_type);
+  if (ret_elt_bits < arg_elt_bits)
     modifier = NARROW;
-  else if (tree_to_uhwi (TYPE_SIZE (TREE_TYPE (ret_type)))
-	   > tree_to_uhwi (TYPE_SIZE (TREE_TYPE (arg_type))))
+  else if (ret_elt_bits > arg_elt_bits)
     modifier = WIDEN;
 
   if (modifier == NONE && (code == FIX_TRUNC_EXPR || code == FLOAT_EXPR))
@@ -1908,8 +1904,7 @@ expand_vector_conversion (gimple_stmt_iterator *gsi)
 	      tree part_width = TYPE_SIZE (compute_type);
 	      tree index = bitsize_int (0);
 	      int nunits = nunits_for_known_piecewise_op (arg_type);
-	      int delta = tree_to_uhwi (part_width)
-			  / tree_to_uhwi (TYPE_SIZE (TREE_TYPE (arg_type)));
+	      int delta = tree_to_uhwi (part_width) / arg_elt_bits;
 	      int i;
 	      location_t loc = gimple_location (gsi_stmt (*gsi));
 
diff --git a/gcc/tree-vect-loop.c b/gcc/tree-vect-loop.c
index 899b56087..7990e31de 100644
--- a/gcc/tree-vect-loop.c
+++ b/gcc/tree-vect-loop.c
@@ -8059,9 +8059,7 @@ vectorizable_live_operation (stmt_vec_info stmt_info,
 	: gimple_get_lhs (stmt);
   lhs_type = TREE_TYPE (lhs);
 
-  bitsize = (VECTOR_BOOLEAN_TYPE_P (vectype)
-	     ? bitsize_int (TYPE_PRECISION (TREE_TYPE (vectype)))
-	     : TYPE_SIZE (TREE_TYPE (vectype)));
+  bitsize = vector_element_bits_tree (vectype);
   vec_bitsize = TYPE_SIZE (vectype);
 
   /* Get the vectorized lhs of STMT and the lane to use (counted in bits).  */
diff --git a/gcc/tree-vect-patterns.c b/gcc/tree-vect-patterns.c
index 84d7ddb17..b076740ef 100644
--- a/gcc/tree-vect-patterns.c
+++ b/gcc/tree-vect-patterns.c
@@ -4406,8 +4406,7 @@ vect_recog_mask_conversion_pattern (stmt_vec_info stmt_vinfo, tree *type_out)
 		  || dt == vect_constant_def))
 	    {
 	      tree wide_scalar_type = build_nonstandard_integer_type
-		(tree_to_uhwi (TYPE_SIZE (TREE_TYPE (vectype1))),
-		 TYPE_UNSIGNED (rhs1_type));
+		(vector_element_bits (vectype1), TYPE_UNSIGNED (rhs1_type));
 	      tree vectype3 = get_vectype_for_scalar_type (vinfo,
 							   wide_scalar_type);
 	      if (expand_vec_cond_expr_p (vectype1, vectype3, TREE_CODE (rhs1)))
diff --git a/gcc/tree-vect-stmts.c b/gcc/tree-vect-stmts.c
index 4636b7ba2..0bdf9a547 100644
--- a/gcc/tree-vect-stmts.c
+++ b/gcc/tree-vect-stmts.c
@@ -10717,8 +10717,7 @@ vect_is_simple_cond (tree cond, vec_info *vinfo, slp_tree slp_node,
 	      && tree_int_cst_lt (TYPE_SIZE (scalar_type),
 				  TYPE_SIZE (TREE_TYPE (vectype))))
 	    scalar_type = build_nonstandard_integer_type
-	      (tree_to_uhwi (TYPE_SIZE (TREE_TYPE (vectype))),
-	       TYPE_UNSIGNED (scalar_type));
+	      (vector_element_bits (vectype), TYPE_UNSIGNED (scalar_type));
 	  *comp_vectype = get_vectype_for_scalar_type (vinfo, scalar_type,
 						       slp_node);
 	}
diff --git a/gcc/tree.c b/gcc/tree.c
index 3e6647ae0..9a0cedf10 100644
--- a/gcc/tree.c
+++ b/gcc/tree.c
@@ -13892,6 +13892,30 @@ vector_type_mode (const_tree t)
   return mode;
 }
 
+/* Return the size in bits of each element of vector type TYPE.  */
+
+unsigned int
+vector_element_bits (const_tree type)
+{
+  gcc_checking_assert (VECTOR_TYPE_P (type));
+  if (VECTOR_BOOLEAN_TYPE_P (type))
+    return vector_element_size (tree_to_poly_uint64 (TYPE_SIZE (type)),
+				TYPE_VECTOR_SUBPARTS (type));
+  return tree_to_uhwi (TYPE_SIZE (TREE_TYPE (type)));
+}
+
+/* Calculate the size in bits of each element of vector type TYPE
+   and return the result as a tree of type bitsizetype.  */
+
+tree
+vector_element_bits_tree (const_tree type)
+{
+  gcc_checking_assert (VECTOR_TYPE_P (type));
+  if (VECTOR_BOOLEAN_TYPE_P (type))
+    return bitsize_int (vector_element_bits (type));
+  return TYPE_SIZE (TREE_TYPE (type));
+}
+
 /* Verify that basic properties of T match TV and thus T can be a variant of
    TV.  TV should be the more specified variant (i.e. the main variant).  */
 
diff --git a/gcc/tree.h b/gcc/tree.h
index bddc6e528..c66207fa0 100644
--- a/gcc/tree.h
+++ b/gcc/tree.h
@@ -1996,6 +1996,8 @@ class auto_suppress_location_wrappers
 
 extern machine_mode element_mode (const_tree);
 extern machine_mode vector_type_mode (const_tree);
+extern unsigned int vector_element_bits (const_tree);
+extern tree vector_element_bits_tree (const_tree);
 
 /* The "canonical" type for this type node, which is used by frontends to
    compare the type for equality with another type.  If two types are
-- 
2.27.0.windows.1