Commit 5b55e6e3 by Richard Biener Committed by Richard Biener

re PR tree-optimization/81082 (Failure to vectorise after reassociating index computation)

2018-01-26  Richard Biener  <rguenther@suse.de>

	PR tree-optimization/81082
	* fold-const.c (fold_plusminus_mult_expr): Do not perform the
	association if it requires casting to unsigned.
	* match.pd ((A * C) +- (B * C) -> (A+-B)): New patterns derived
	from fold_plusminus_mult_expr to catch important cases late when
	range info is available.

	* gcc.dg/vect/pr81082.c: New testcase.
	* gcc.dg/tree-ssa/loop-15.c: XFAIL the (int)((unsigned)n + -1U) * n + n
	simplification to n * n.

From-SVN: r257077
parent af2e3244
2018-01-26 Richard Biener <rguenther@suse.de>
PR tree-optimization/81082
* fold-const.c (fold_plusminus_mult_expr): Do not perform the
association if it requires casting to unsigned.
* match.pd ((A * C) +- (B * C) -> (A+-B)): New patterns derived
from fold_plusminus_mult_expr to catch important cases late when
range info is available.
2018-01-26 Rainer Orth <ro@CeBiTec.Uni-Bielefeld.DE>
* config/i386/sol2.h (USE_HIDDEN_LINKONCE): Remove.
......
......@@ -7097,7 +7097,7 @@ fold_plusminus_mult_expr (location_t loc, enum tree_code code, tree type,
/* Same may be zero and thus the operation 'code' may overflow. Likewise
same may be minus one and thus the multiplication may overflow. Perform
the operations in an unsigned type. */
the sum operation in an unsigned type. */
tree utype = unsigned_type_for (type);
tree tem = fold_build2_loc (loc, code, utype,
fold_convert_loc (loc, utype, alt0),
......@@ -7110,9 +7110,9 @@ fold_plusminus_mult_expr (location_t loc, enum tree_code code, tree type,
return fold_build2_loc (loc, MULT_EXPR, type,
fold_convert (type, tem), same);
return fold_convert_loc (loc, type,
fold_build2_loc (loc, MULT_EXPR, utype, tem,
fold_convert_loc (loc, utype, same)));
/* Do not resort to unsigned multiplication because
we lose the no-overflow property of the expression. */
return NULL_TREE;
}
/* Subroutine of native_encode_expr. Encode the INTEGER_CST
......
......@@ -1939,6 +1939,37 @@ DEFINE_INT_AND_FLOAT_ROUND_FN (RINT)
(minus (convert (view_convert:stype @1))
(convert (view_convert:stype @2)))))))
/* (A * C) +- (B * C) -> (A+-B) * C and (A * C) +- A -> A * (C+-1).
Modeled after fold_plusminus_mult_expr. */
(if (!TYPE_SATURATING (type)
&& (!FLOAT_TYPE_P (type) || flag_associative_math))
(for plusminus (plus minus)
(simplify
(plusminus (mult:cs @0 @1) (mult:cs @0 @2))
(if (!ANY_INTEGRAL_TYPE_P (type)
|| TYPE_OVERFLOW_WRAPS (type)
|| (INTEGRAL_TYPE_P (type)
&& tree_expr_nonzero_p (@0)
&& expr_not_equal_to (@0, wi::minus_one (TYPE_PRECISION (type)))))
(mult (plusminus @1 @2) @0)))
/* We cannot generate constant 1 for fract. */
(if (!ALL_FRACT_MODE_P (TYPE_MODE (type)))
(simplify
(plusminus @0 (mult:cs @0 @2))
(if (!ANY_INTEGRAL_TYPE_P (type)
|| TYPE_OVERFLOW_WRAPS (type)
|| (INTEGRAL_TYPE_P (type)
&& tree_expr_nonzero_p (@0)
&& expr_not_equal_to (@0, wi::minus_one (TYPE_PRECISION (type)))))
(mult (plusminus { build_one_cst (type); } @2) @0)))
(simplify
(plusminus (mult:cs @0 @2) @0)
(if (!ANY_INTEGRAL_TYPE_P (type)
|| TYPE_OVERFLOW_WRAPS (type)
|| (INTEGRAL_TYPE_P (type)
&& tree_expr_nonzero_p (@0)
&& expr_not_equal_to (@0, wi::minus_one (TYPE_PRECISION (type)))))
(mult (plusminus @2 { build_one_cst (type); }) @0))))))
/* Simplifications of MIN_EXPR, MAX_EXPR, fmin() and fmax(). */
......
2018-01-26 Richard Biener <rguenther@suse.de>
PR tree-optimization/81082
* gcc.dg/vect/pr81082.c: New testcase.
* gcc.dg/tree-ssa/loop-15.c: XFAIL the (int)((unsigned)n + -1U) * n + n
simplification to n * n.
2018-01-26 Rainer Orth <ro@CeBiTec.Uni-Bielefeld.DE>
* gcc.target/i386/mcount_pic.c: Only xfail get_pc_thunk scan on
......
......@@ -19,7 +19,7 @@ int bla(void)
}
/* Since the loop is removed, there should be no addition. */
/* { dg-final { scan-tree-dump-times " \\+ " 0 "optimized" } } */
/* { dg-final { scan-tree-dump-times " \\+ " 0 "optimized" { xfail *-*-* } } } */
/* { dg-final { scan-tree-dump-times " \\* " 1 "optimized" } } */
/* The if from the loop header copying remains in the code. */
......
/* { dg-do compile } */
/* { dg-require-effective-target vect_int } */
int
f (int *x, int b1, int b2, int b3)
{
int foo = 0;
for (int i1 = 0; i1 < b1; ++i1)
for (int i2 = 0; i2 < b2; ++i2)
for (int i3 = 0; i3 < b3; ++i3)
foo += x[i1 * b2 * b3 + i2 * b3 + (i3 - 1)];
return foo;
}
/* { dg-final { scan-tree-dump "vectorized 1 loops in function" "vect" } } */
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment