X-Git-Url: http://git.sourceforge.jp/view?p=pf3gnuchains%2Fgcc-fork.git;a=blobdiff_plain;f=gcc%2Ftree-vect-generic.c;h=cb64065f2e84759b04dd7e6e62b82d6145f38155;hp=9919389dfc3f45a3bfed7d21d792a4f8078cd024;hb=70d2aaaa4527221ce952bdc3253a788be0d8c875;hpb=75a70cf95f65fe9204b15ad9aba31c571381d224
diff --git a/gcc/tree-vect-generic.c b/gcc/tree-vect-generic.c
index 9919389dfc3..cb64065f2e8 100644
--- a/gcc/tree-vect-generic.c
+++ b/gcc/tree-vect-generic.c
@@ -1,18 +1,19 @@
/* Lower vector operations to scalar operations.
- Copyright (C) 2004, 2005, 2006, 2007 Free Software Foundation, Inc.
+ Copyright (C) 2004, 2005, 2006, 2007, 2008, 2009, 2010, 2011, 2012
+ Free Software Foundation, Inc.
This file is part of GCC.
-
+
GCC is free software; you can redistribute it and/or modify it
under the terms of the GNU General Public License as published by the
Free Software Foundation; either version 3, or (at your option) any
later version.
-
+
GCC is distributed in the hope that it will be useful, but WITHOUT
ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License
for more details.
-
+
You should have received a copy of the GNU General Public License
along with GCC; see the file COPYING3. If not see
. */
@@ -22,12 +23,6 @@ along with GCC; see the file COPYING3. If not see
#include "coretypes.h"
#include "tree.h"
#include "tm.h"
-#include "rtl.h"
-#include "expr.h"
-#include "insn-codes.h"
-#include "diagnostic.h"
-#include "optabs.h"
-#include "machmode.h"
#include "langhooks.h"
#include "tree-flow.h"
#include "gimple.h"
@@ -35,6 +30,14 @@ along with GCC; see the file COPYING3. If not see
#include "tree-pass.h"
#include "flags.h"
#include "ggc.h"
+#include "diagnostic.h"
+
+/* Need to include rtl.h, expr.h, etc. for optabs. */
+#include "expr.h"
+#include "optabs.h"
+
+
+static void expand_vector_operations_1 (gimple_stmt_iterator *);
/* Build a constant of type TYPE, made of VALUE's bits replicated
@@ -122,9 +125,35 @@ static tree
do_binop (gimple_stmt_iterator *gsi, tree inner_type, tree a, tree b,
tree bitpos, tree bitsize, enum tree_code code)
{
+ if (TREE_CODE (TREE_TYPE (a)) == VECTOR_TYPE)
+ a = tree_vec_extract (gsi, inner_type, a, bitsize, bitpos);
+ if (TREE_CODE (TREE_TYPE (b)) == VECTOR_TYPE)
+ b = tree_vec_extract (gsi, inner_type, b, bitsize, bitpos);
+ return gimplify_build2 (gsi, code, inner_type, a, b);
+}
+
+/* Construct expression (A[BITPOS] code B[BITPOS]) ? -1 : 0
+
+ INNER_TYPE is the type of A and B elements
+
+ returned expression is of signed integer type with the
+ size equal to the size of INNER_TYPE. */
+static tree
+do_compare (gimple_stmt_iterator *gsi, tree inner_type, tree a, tree b,
+ tree bitpos, tree bitsize, enum tree_code code)
+{
+ tree comp_type;
+
a = tree_vec_extract (gsi, inner_type, a, bitsize, bitpos);
b = tree_vec_extract (gsi, inner_type, b, bitsize, bitpos);
- return gimplify_build2 (gsi, code, inner_type, a, b);
+
+ comp_type = build_nonstandard_integer_type
+ (GET_MODE_BITSIZE (TYPE_MODE (inner_type)), 0);
+
+ return gimplify_build3 (gsi, COND_EXPR, comp_type,
+ fold_build2 (code, boolean_type_node, a, b),
+ build_int_cst (comp_type, -1),
+ build_int_cst (comp_type, 0));
}
/* Expand vector addition to scalars. This does bit twiddling
@@ -208,10 +237,18 @@ expand_vector_piecewise (gimple_stmt_iterator *gsi, elem_op_func f,
int delta = tree_low_cst (part_width, 1)
/ tree_low_cst (TYPE_SIZE (TREE_TYPE (type)), 1);
int i;
+ location_t loc = gimple_location (gsi_stmt (*gsi));
+
+ if (types_compatible_p (gimple_expr_type (gsi_stmt (*gsi)), type))
+ warning_at (loc, OPT_Wvector_operation_performance,
+ "vector operation will be expanded piecewise");
+ else
+ warning_at (loc, OPT_Wvector_operation_performance,
+ "vector operation will be expanded in parallel");
v = VEC_alloc(constructor_elt, gc, (nunits + delta - 1) / delta);
for (i = 0; i < nunits;
- i += delta, index = int_const_binop (PLUS_EXPR, index, part_width, 0))
+ i += delta, index = int_const_binop (PLUS_EXPR, index, part_width))
{
tree result = f (gsi, inner_type, a, b, index, part_width, code);
constructor_elt *ce = VEC_quick_push (constructor_elt, v, NULL);
@@ -233,6 +270,7 @@ expand_vector_parallel (gimple_stmt_iterator *gsi, elem_op_func f, tree type,
tree result, compute_type;
enum machine_mode mode;
int n_words = tree_low_cst (TYPE_SIZE_UNIT (type), 1) / UNITS_PER_WORD;
+ location_t loc = gimple_location (gsi_stmt (*gsi));
/* We have three strategies. If the type is already correct, just do
the operation an element at a time. Else, if the vector is wider than
@@ -257,6 +295,9 @@ expand_vector_parallel (gimple_stmt_iterator *gsi, elem_op_func f, tree type,
mode = mode_for_size (tree_low_cst (TYPE_SIZE (type), 1), MODE_INT, 0);
compute_type = lang_hooks.types.type_for_mode (mode, 1);
result = f (gsi, compute_type, a, b, NULL_TREE, NULL_TREE, code);
+ warning_at (loc, OPT_Wvector_operation_performance,
+ "vector operation will be expanded with a "
+ "single scalar operation");
}
return result;
@@ -286,6 +327,73 @@ expand_vector_addition (gimple_stmt_iterator *gsi,
a, b, code);
}
+/* Check if vector VEC consists of all the equal elements and
+ that the number of elements corresponds to the type of VEC.
+ The function returns first element of the vector
+ or NULL_TREE if the vector is not uniform. */
+static tree
+uniform_vector_p (tree vec)
+{
+ tree first, t, els;
+ unsigned i;
+
+ if (vec == NULL_TREE)
+ return NULL_TREE;
+
+ if (TREE_CODE (vec) == VECTOR_CST)
+ {
+ els = TREE_VECTOR_CST_ELTS (vec);
+ first = TREE_VALUE (els);
+ els = TREE_CHAIN (els);
+
+ for (t = els; t; t = TREE_CHAIN (t))
+ if (!operand_equal_p (first, TREE_VALUE (t), 0))
+ return NULL_TREE;
+
+ return first;
+ }
+
+ else if (TREE_CODE (vec) == CONSTRUCTOR)
+ {
+ first = error_mark_node;
+
+ FOR_EACH_CONSTRUCTOR_VALUE (CONSTRUCTOR_ELTS (vec), i, t)
+ {
+ if (i == 0)
+ {
+ first = t;
+ continue;
+ }
+ if (!operand_equal_p (first, t, 0))
+ return NULL_TREE;
+ }
+ if (i != TYPE_VECTOR_SUBPARTS (TREE_TYPE (vec)))
+ return NULL_TREE;
+
+ return first;
+ }
+
+ return NULL_TREE;
+}
+
+/* Try to expand vector comparison expression OP0 CODE OP1 by
+ querying optab if the following expression:
+ VEC_COND_EXPR< OP0 CODE OP1, {-1,...}, {0,...}>
+ can be expanded. */
+static tree
+expand_vector_comparison (gimple_stmt_iterator *gsi, tree type, tree op0,
+ tree op1, enum tree_code code)
+{
+ tree t;
+ if (! expand_vec_cond_expr_p (type, TREE_TYPE (op0)))
+ t = expand_vector_piecewise (gsi, do_compare, type,
+ TREE_TYPE (TREE_TYPE (op0)), op0, op1, code);
+ else
+ t = NULL_TREE;
+
+ return t;
+}
+
static tree
expand_vector_operation (gimple_stmt_iterator *gsi, tree type, tree compute_type,
gimple assign, enum tree_code code)
@@ -306,8 +414,8 @@ expand_vector_operation (gimple_stmt_iterator *gsi, tree type, tree compute_type
case PLUS_EXPR:
case MINUS_EXPR:
if (!TYPE_OVERFLOW_TRAPS (type))
- return expand_vector_addition (gsi, do_binop, do_plus_minus, type,
- gimple_assign_rhs1 (assign),
+ return expand_vector_addition (gsi, do_binop, do_plus_minus, type,
+ gimple_assign_rhs1 (assign),
gimple_assign_rhs2 (assign), code);
break;
@@ -328,8 +436,27 @@ expand_vector_operation (gimple_stmt_iterator *gsi, tree type, tree compute_type
case BIT_NOT_EXPR:
return expand_vector_parallel (gsi, do_unop, type,
gimple_assign_rhs1 (assign),
- NULL_TREE, code);
+ NULL_TREE, code);
+ case EQ_EXPR:
+ case NE_EXPR:
+ case GT_EXPR:
+ case LT_EXPR:
+ case GE_EXPR:
+ case LE_EXPR:
+ case UNEQ_EXPR:
+ case UNGT_EXPR:
+ case UNLT_EXPR:
+ case UNGE_EXPR:
+ case UNLE_EXPR:
+ case LTGT_EXPR:
+ case ORDERED_EXPR:
+ case UNORDERED_EXPR:
+ {
+ tree rhs1 = gimple_assign_rhs1 (assign);
+ tree rhs2 = gimple_assign_rhs2 (assign);
+ return expand_vector_comparison (gsi, type, rhs1, rhs2, code);
+ }
default:
break;
}
@@ -344,13 +471,13 @@ expand_vector_operation (gimple_stmt_iterator *gsi, tree type, tree compute_type
gimple_assign_rhs2 (assign), code);
}
-/* Return a type for the widest vector mode whose components are of mode
- INNER_MODE, or NULL_TREE if none is found.
- SATP is true for saturating fixed-point types. */
+/* Return a type for the widest vector mode whose components are of type
+ TYPE, or NULL_TREE if none is found. */
static tree
-type_for_widest_vector_mode (enum machine_mode inner_mode, optab op, int satp)
+type_for_widest_vector_mode (tree type, optab op)
{
+ enum machine_mode inner_mode = TYPE_MODE (type);
enum machine_mode best_mode = VOIDmode, mode;
int best_nunits = 0;
@@ -370,19 +497,232 @@ type_for_widest_vector_mode (enum machine_mode inner_mode, optab op, int satp)
for (; mode != VOIDmode; mode = GET_MODE_WIDER_MODE (mode))
if (GET_MODE_INNER (mode) == inner_mode
&& GET_MODE_NUNITS (mode) > best_nunits
- && optab_handler (op, mode)->insn_code != CODE_FOR_nothing)
+ && optab_handler (op, mode) != CODE_FOR_nothing)
best_mode = mode, best_nunits = GET_MODE_NUNITS (mode);
if (best_mode == VOIDmode)
return NULL_TREE;
else
+ return build_vector_type_for_mode (type, best_mode);
+}
+
+
+/* Build a reference to the element of the vector VECT. Function
+ returns either the element itself, either BIT_FIELD_REF, or an
+ ARRAY_REF expression.
+
+ GSI is requred to insert temporary variables while building a
+ refernece to the element of the vector VECT.
+
+ PTMPVEC is a pointer to the temporary variable for caching
+ purposes. In case when PTMPVEC is NULL new temporary variable
+ will be created. */
+static tree
+vector_element (gimple_stmt_iterator *gsi, tree vect, tree idx, tree *ptmpvec)
+{
+ tree vect_type, vect_elt_type;
+ gimple asgn;
+ tree tmpvec;
+ tree arraytype;
+ bool need_asgn = true;
+ unsigned int elements;
+
+ vect_type = TREE_TYPE (vect);
+ vect_elt_type = TREE_TYPE (vect_type);
+ elements = TYPE_VECTOR_SUBPARTS (vect_type);
+
+ if (TREE_CODE (idx) == INTEGER_CST)
{
- /* For fixed-point modes, we need to pass satp as the 2nd parameter. */
- if (ALL_FIXED_POINT_MODE_P (best_mode))
- return lang_hooks.types.type_for_mode (best_mode, satp);
+ unsigned HOST_WIDE_INT index;
- return lang_hooks.types.type_for_mode (best_mode, 1);
+ /* Given that we're about to compute a binary modulus,
+ we don't care about the high bits of the value. */
+ index = TREE_INT_CST_LOW (idx);
+ if (!host_integerp (idx, 1) || index >= elements)
+ {
+ index &= elements - 1;
+ idx = build_int_cst (TREE_TYPE (idx), index);
+ }
+
+ /* When lowering a vector statement sequence do some easy
+ simplification by looking through intermediate vector results. */
+ if (TREE_CODE (vect) == SSA_NAME)
+ {
+ gimple def_stmt = SSA_NAME_DEF_STMT (vect);
+ if (is_gimple_assign (def_stmt)
+ && (gimple_assign_rhs_code (def_stmt) == VECTOR_CST
+ || gimple_assign_rhs_code (def_stmt) == CONSTRUCTOR))
+ vect = gimple_assign_rhs1 (def_stmt);
+ }
+
+ if (TREE_CODE (vect) == VECTOR_CST)
+ {
+ unsigned i;
+ tree vals = TREE_VECTOR_CST_ELTS (vect);
+ for (i = 0; vals; vals = TREE_CHAIN (vals), ++i)
+ if (i == index)
+ return TREE_VALUE (vals);
+ return build_zero_cst (vect_elt_type);
+ }
+ else if (TREE_CODE (vect) == CONSTRUCTOR)
+ {
+ unsigned i;
+ tree elt_i, elt_v;
+
+ FOR_EACH_CONSTRUCTOR_ELT (CONSTRUCTOR_ELTS (vect), i, elt_i, elt_v)
+ if (operand_equal_p (elt_i, idx, 0))
+ return elt_v;
+ return build_zero_cst (vect_elt_type);
+ }
+ else
+ {
+ tree size = TYPE_SIZE (vect_elt_type);
+ tree pos = fold_build2 (MULT_EXPR, bitsizetype, bitsize_int (index),
+ size);
+ return fold_build3 (BIT_FIELD_REF, vect_elt_type, vect, size, pos);
+ }
+ }
+
+ if (!ptmpvec)
+ tmpvec = create_tmp_var (vect_type, "vectmp");
+ else if (!*ptmpvec)
+ tmpvec = *ptmpvec = create_tmp_var (vect_type, "vectmp");
+ else
+ {
+ tmpvec = *ptmpvec;
+ need_asgn = false;
+ }
+
+ if (need_asgn)
+ {
+ TREE_ADDRESSABLE (tmpvec) = 1;
+ asgn = gimple_build_assign (tmpvec, vect);
+ gsi_insert_before (gsi, asgn, GSI_SAME_STMT);
+ }
+
+ arraytype = build_array_type_nelts (vect_elt_type, elements);
+ return build4 (ARRAY_REF, vect_elt_type,
+ build1 (VIEW_CONVERT_EXPR, arraytype, tmpvec),
+ idx, NULL_TREE, NULL_TREE);
+}
+
+/* Check if VEC_PERM_EXPR within the given setting is supported
+ by hardware, or lower it piecewise.
+
+ When VEC_PERM_EXPR has the same first and second operands:
+ VEC_PERM_EXPR the lowered version would be
+ {v0[mask[0]], v0[mask[1]], ...}
+ MASK and V0 must have the same number of elements.
+
+ Otherwise VEC_PERM_EXPR is lowered to
+ {mask[0] < len(v0) ? v0[mask[0]] : v1[mask[0]], ...}
+ V0 and V1 must have the same type. MASK, V0, V1 must have the
+ same number of arguments. */
+
+static void
+lower_vec_perm (gimple_stmt_iterator *gsi)
+{
+ gimple stmt = gsi_stmt (*gsi);
+ tree mask = gimple_assign_rhs3 (stmt);
+ tree vec0 = gimple_assign_rhs1 (stmt);
+ tree vec1 = gimple_assign_rhs2 (stmt);
+ tree vect_type = TREE_TYPE (vec0);
+ tree mask_type = TREE_TYPE (mask);
+ tree vect_elt_type = TREE_TYPE (vect_type);
+ tree mask_elt_type = TREE_TYPE (mask_type);
+ unsigned int elements = TYPE_VECTOR_SUBPARTS (vect_type);
+ VEC(constructor_elt,gc) *v;
+ tree constr, t, si, i_val;
+ tree vec0tmp = NULL_TREE, vec1tmp = NULL_TREE, masktmp = NULL_TREE;
+ bool two_operand_p = !operand_equal_p (vec0, vec1, 0);
+ location_t loc = gimple_location (gsi_stmt (*gsi));
+ unsigned i;
+
+ if (TREE_CODE (mask) == VECTOR_CST)
+ {
+ unsigned char *sel_int = XALLOCAVEC (unsigned char, elements);
+ tree vals = TREE_VECTOR_CST_ELTS (mask);
+
+ for (i = 0; i < elements; ++i, vals = TREE_CHAIN (vals))
+ sel_int[i] = TREE_INT_CST_LOW (TREE_VALUE (vals)) & (2 * elements - 1);
+
+ if (can_vec_perm_p (TYPE_MODE (vect_type), false, sel_int))
+ return;
+ }
+ else if (can_vec_perm_p (TYPE_MODE (vect_type), true, NULL))
+ return;
+
+ warning_at (loc, OPT_Wvector_operation_performance,
+ "vector shuffling operation will be expanded piecewise");
+
+ v = VEC_alloc (constructor_elt, gc, elements);
+ for (i = 0; i < elements; i++)
+ {
+ si = size_int (i);
+ i_val = vector_element (gsi, mask, si, &masktmp);
+
+ if (TREE_CODE (i_val) == INTEGER_CST)
+ {
+ unsigned HOST_WIDE_INT index;
+
+ index = TREE_INT_CST_LOW (i_val);
+ if (!host_integerp (i_val, 1) || index >= elements)
+ i_val = build_int_cst (mask_elt_type, index & (elements - 1));
+
+ if (two_operand_p && (index & elements) != 0)
+ t = vector_element (gsi, vec1, i_val, &vec1tmp);
+ else
+ t = vector_element (gsi, vec0, i_val, &vec0tmp);
+
+ t = force_gimple_operand_gsi (gsi, t, true, NULL_TREE,
+ true, GSI_SAME_STMT);
+ }
+ else
+ {
+ tree cond = NULL_TREE, v0_val;
+
+ if (two_operand_p)
+ {
+ cond = fold_build2 (BIT_AND_EXPR, mask_elt_type, i_val,
+ build_int_cst (mask_elt_type, elements));
+ cond = force_gimple_operand_gsi (gsi, cond, true, NULL_TREE,
+ true, GSI_SAME_STMT);
+ }
+
+ i_val = fold_build2 (BIT_AND_EXPR, mask_elt_type, i_val,
+ build_int_cst (mask_elt_type, elements - 1));
+ i_val = force_gimple_operand_gsi (gsi, i_val, true, NULL_TREE,
+ true, GSI_SAME_STMT);
+
+ v0_val = vector_element (gsi, vec0, i_val, &vec0tmp);
+ v0_val = force_gimple_operand_gsi (gsi, v0_val, true, NULL_TREE,
+ true, GSI_SAME_STMT);
+
+ if (two_operand_p)
+ {
+ tree v1_val;
+
+ v1_val = vector_element (gsi, vec1, i_val, &vec1tmp);
+ v1_val = force_gimple_operand_gsi (gsi, v1_val, true, NULL_TREE,
+ true, GSI_SAME_STMT);
+
+ cond = fold_build2 (EQ_EXPR, boolean_type_node,
+ cond, build_zero_cst (mask_elt_type));
+ cond = fold_build3 (COND_EXPR, vect_elt_type,
+ cond, v0_val, v1_val);
+ t = force_gimple_operand_gsi (gsi, cond, true, NULL_TREE,
+ true, GSI_SAME_STMT);
+ }
+ else
+ t = v0_val;
+ }
+
+ CONSTRUCTOR_APPEND_ELT (v, si, t);
}
+
+ constr = build_constructor (vect_type, v);
+ gimple_assign_set_rhs_from_tree (gsi, constr);
+ update_stmt (gsi_stmt (*gsi));
}
/* Process one statement. If we identify a vector operation, expand it. */
@@ -394,7 +734,7 @@ expand_vector_operations_1 (gimple_stmt_iterator *gsi)
tree lhs, rhs1, rhs2 = NULL, type, compute_type;
enum tree_code code;
enum machine_mode compute_mode;
- optab op;
+ optab op = NULL;
enum gimple_rhs_class rhs_class;
tree new_rhs;
@@ -403,11 +743,17 @@ expand_vector_operations_1 (gimple_stmt_iterator *gsi)
code = gimple_assign_rhs_code (stmt);
rhs_class = get_gimple_rhs_class (code);
+ lhs = gimple_assign_lhs (stmt);
+
+ if (code == VEC_PERM_EXPR)
+ {
+ lower_vec_perm (gsi);
+ return;
+ }
if (rhs_class != GIMPLE_UNARY_RHS && rhs_class != GIMPLE_BINARY_RHS)
return;
- lhs = gimple_assign_lhs (stmt);
rhs1 = gimple_assign_rhs1 (stmt);
type = gimple_expr_type (stmt);
if (rhs_class == GIMPLE_BINARY_RHS)
@@ -416,12 +762,12 @@ expand_vector_operations_1 (gimple_stmt_iterator *gsi)
if (TREE_CODE (type) != VECTOR_TYPE)
return;
- if (code == NOP_EXPR
+ if (code == NOP_EXPR
|| code == FLOAT_EXPR
|| code == FIX_TRUNC_EXPR
|| code == VIEW_CONVERT_EXPR)
return;
-
+
gcc_assert (code != CONVERT_EXPR);
/* The signedness is determined from input argument. */
@@ -431,29 +777,53 @@ expand_vector_operations_1 (gimple_stmt_iterator *gsi)
/* Choose between vector shift/rotate by vector and vector shift/rotate by
scalar */
- if (code == LSHIFT_EXPR
- || code == RSHIFT_EXPR
+ if (code == LSHIFT_EXPR
+ || code == RSHIFT_EXPR
|| code == LROTATE_EXPR
|| code == RROTATE_EXPR)
{
- /* If the 2nd argument is vector, we need a vector/vector shift */
- if (VECTOR_MODE_P (TYPE_MODE (TREE_TYPE (rhs2))))
- op = optab_for_tree_code (code, type, optab_vector);
+ optab opv;
+
+ /* Check whether we have vector {x,x,x,x} where x
+ could be a scalar variable or a constant. Transform
+ vector {x,x,x,x} ==> vector scalar. */
+ if (VECTOR_INTEGER_TYPE_P (TREE_TYPE (rhs2)))
+ {
+ tree first;
+ gimple def_stmt;
+
+ if ((TREE_CODE (rhs2) == VECTOR_CST
+ && (first = uniform_vector_p (rhs2)) != NULL_TREE)
+ || (TREE_CODE (rhs2) == SSA_NAME
+ && (def_stmt = SSA_NAME_DEF_STMT (rhs2))
+ && gimple_assign_single_p (def_stmt)
+ && (first = uniform_vector_p
+ (gimple_assign_rhs1 (def_stmt))) != NULL_TREE))
+ {
+ gimple_assign_set_rhs2 (stmt, first);
+ update_stmt (stmt);
+ rhs2 = first;
+ }
+ }
+
+ opv = optab_for_tree_code (code, type, optab_vector);
+ if (VECTOR_INTEGER_TYPE_P (TREE_TYPE (rhs2)))
+ op = opv;
else
{
- /* Try for a vector/scalar shift, and if we don't have one, see if we
- have a vector/vector shift */
- op = optab_for_tree_code (code, type, optab_scalar);
- if (!op
- || (op->handlers[(int) TYPE_MODE (type)].insn_code
- == CODE_FOR_nothing))
- op = optab_for_tree_code (code, type, optab_vector);
+ op = optab_for_tree_code (code, type, optab_scalar);
+
+ /* The rtl expander will expand vector/scalar as vector/vector
+ if necessary. Don't bother converting the stmt here. */
+ if (optab_handler (op, TYPE_MODE (type)) == CODE_FOR_nothing
+ && optab_handler (opv, TYPE_MODE (type)) != CODE_FOR_nothing)
+ return;
}
}
else
op = optab_for_tree_code (code, type, optab_default);
- /* For widening/narrowing vector operations, the relevant type is of the
+ /* For widening/narrowing vector operations, the relevant type is of the
arguments, not the widened result. VEC_UNPACK_FLOAT_*_EXPR is
calculated in the same way above. */
if (code == WIDEN_SUM_EXPR
@@ -463,7 +833,9 @@ expand_vector_operations_1 (gimple_stmt_iterator *gsi)
|| code == VEC_UNPACK_LO_EXPR
|| code == VEC_PACK_TRUNC_EXPR
|| code == VEC_PACK_SAT_EXPR
- || code == VEC_PACK_FIX_TRUNC_EXPR)
+ || code == VEC_PACK_FIX_TRUNC_EXPR
+ || code == VEC_WIDEN_LSHIFT_HI_EXPR
+ || code == VEC_WIDEN_LSHIFT_LO_EXPR)
type = TREE_TYPE (rhs1);
/* Optabs will try converting a negation into a subtraction, so
@@ -476,13 +848,16 @@ expand_vector_operations_1 (gimple_stmt_iterator *gsi)
/* For very wide vectors, try using a smaller vector mode. */
compute_type = type;
- if (TYPE_MODE (type) == BLKmode && op)
+ if (!VECTOR_MODE_P (TYPE_MODE (type)) && op)
{
tree vector_compute_type
- = type_for_widest_vector_mode (TYPE_MODE (TREE_TYPE (type)), op,
- TYPE_SATURATING (TREE_TYPE (type)));
- if (vector_compute_type != NULL_TREE)
- compute_type = vector_compute_type;
+ = type_for_widest_vector_mode (TREE_TYPE (type), op);
+ if (vector_compute_type != NULL_TREE
+ && (TYPE_VECTOR_SUBPARTS (vector_compute_type)
+ < TYPE_VECTOR_SUBPARTS (compute_type))
+ && (optab_handler (op, TYPE_MODE (vector_compute_type))
+ != CODE_FOR_nothing))
+ compute_type = vector_compute_type;
}
/* If we are breaking a BLKmode vector into smaller pieces,
@@ -491,14 +866,9 @@ expand_vector_operations_1 (gimple_stmt_iterator *gsi)
if (compute_type == type)
{
compute_mode = TYPE_MODE (compute_type);
- if ((GET_MODE_CLASS (compute_mode) == MODE_VECTOR_INT
- || GET_MODE_CLASS (compute_mode) == MODE_VECTOR_FLOAT
- || GET_MODE_CLASS (compute_mode) == MODE_VECTOR_FRACT
- || GET_MODE_CLASS (compute_mode) == MODE_VECTOR_UFRACT
- || GET_MODE_CLASS (compute_mode) == MODE_VECTOR_ACCUM
- || GET_MODE_CLASS (compute_mode) == MODE_VECTOR_UACCUM)
+ if (VECTOR_MODE_P (compute_mode)
&& op != NULL
- && optab_handler (op, compute_mode)->insn_code != CODE_FOR_nothing)
+ && optab_handler (op, compute_mode) != CODE_FOR_nothing)
return;
else
/* There is no operation in hardware, so fall back to scalars. */
@@ -507,6 +877,11 @@ expand_vector_operations_1 (gimple_stmt_iterator *gsi)
gcc_assert (code != VEC_LSHIFT_EXPR && code != VEC_RSHIFT_EXPR);
new_rhs = expand_vector_operation (gsi, type, compute_type, stmt, code);
+
+ /* Leave expression untouched for later expansion. */
+ if (new_rhs == NULL_TREE)
+ return;
+
if (!useless_type_conversion_p (TREE_TYPE (lhs), TREE_TYPE (new_rhs)))
new_rhs = gimplify_build1 (gsi, VIEW_CONVERT_EXPR, TREE_TYPE (lhs),
new_rhs);
@@ -515,17 +890,16 @@ expand_vector_operations_1 (gimple_stmt_iterator *gsi)
way to do it is change expand_vector_operation and its callees to
return a tree_code, RHS1 and RHS2 instead of a tree. */
gimple_assign_set_rhs_from_tree (gsi, new_rhs);
-
- gimple_set_modified (gsi_stmt (*gsi), true);
+ update_stmt (gsi_stmt (*gsi));
}
/* Use this to lower vector operations introduced by the vectorizer,
if it may need the bit-twiddling tricks implemented in this file. */
static bool
-gate_expand_vector_operations (void)
+gate_expand_vector_operations_ssa (void)
{
- return flag_tree_vectorize != 0;
+ return optimize == 0;
}
static unsigned int
@@ -533,56 +907,67 @@ expand_vector_operations (void)
{
gimple_stmt_iterator gsi;
basic_block bb;
+ bool cfg_changed = false;
FOR_EACH_BB (bb)
{
for (gsi = gsi_start_bb (bb); !gsi_end_p (gsi); gsi_next (&gsi))
{
expand_vector_operations_1 (&gsi);
- update_stmt_if_modified (gsi_stmt (gsi));
+ /* ??? If we do not cleanup EH then we will ICE in
+ verification. But in reality we have created wrong-code
+ as we did not properly transition EH info and edges to
+ the piecewise computations. */
+ if (maybe_clean_eh_stmt (gsi_stmt (gsi))
+ && gimple_purge_dead_eh_edges (bb))
+ cfg_changed = true;
}
}
- return 0;
+
+ return cfg_changed ? TODO_cleanup_cfg : 0;
}
-struct gimple_opt_pass pass_lower_vector =
+struct gimple_opt_pass pass_lower_vector =
{
{
GIMPLE_PASS,
"veclower", /* name */
- 0, /* gate */
+ gate_expand_vector_operations_ssa, /* gate */
expand_vector_operations, /* execute */
NULL, /* sub */
NULL, /* next */
0, /* static_pass_number */
- 0, /* tv_id */
+ TV_NONE, /* tv_id */
PROP_cfg, /* properties_required */
0, /* properties_provided */
0, /* properties_destroyed */
0, /* todo_flags_start */
- TODO_dump_func | TODO_ggc_collect
- | TODO_verify_stmts /* todo_flags_finish */
+ TODO_update_ssa /* todo_flags_finish */
+ | TODO_verify_ssa
+ | TODO_verify_stmts | TODO_verify_flow
+ | TODO_cleanup_cfg
}
};
-struct gimple_opt_pass pass_lower_vector_ssa =
+struct gimple_opt_pass pass_lower_vector_ssa =
{
{
GIMPLE_PASS,
"veclower2", /* name */
- gate_expand_vector_operations, /* gate */
+ 0, /* gate */
expand_vector_operations, /* execute */
NULL, /* sub */
NULL, /* next */
0, /* static_pass_number */
- 0, /* tv_id */
+ TV_NONE, /* tv_id */
PROP_cfg, /* properties_required */
0, /* properties_provided */
0, /* properties_destroyed */
0, /* todo_flags_start */
- TODO_dump_func | TODO_update_ssa /* todo_flags_finish */
+ TODO_update_ssa /* todo_flags_finish */
| TODO_verify_ssa
| TODO_verify_stmts | TODO_verify_flow
+ | TODO_cleanup_cfg
}
};