There were more omissions in how zero_one_operation works with the new
way of processing negates in the context of multiplication chains.
Bootstrapped on x86_64-unknown-linux-gnu, testing in progress. CPU 2006
build in progress as well.
Richard.
2016-05-24 Richard Biener <rguent...@suse.de>
PR tree-optimization/71230
* tree-ssa-reassoc.c (zero_one_operation): Handle negate special ops.
* gcc.dg/torture/pr71230.c: New testcase.
* g++.dg/torture/pr71230.C: Likewise.
Index: gcc/tree-ssa-reassoc.c
===================================================================
*** gcc/tree-ssa-reassoc.c (revision 236630)
--- gcc/tree-ssa-reassoc.c (working copy)
*************** zero_one_operation (tree *def, enum tree
*** 1189,1200 ****
{
tree name;
! if (opcode == MULT_EXPR
! && stmt_is_power_of_op (stmt, op))
{
! if (decrement_power (stmt) == 1)
! propagate_op_to_single_use (op, stmt, def);
! return;
}
name = gimple_assign_rhs1 (stmt);
--- 1191,1210 ----
{
tree name;
! if (opcode == MULT_EXPR)
{
! if (stmt_is_power_of_op (stmt, op))
! {
! if (decrement_power (stmt) == 1)
! propagate_op_to_single_use (op, stmt, def);
! return;
! }
! else if (gimple_assign_rhs_code (stmt) == NEGATE_EXPR
! && gimple_assign_rhs1 (stmt) == op)
! {
! propagate_op_to_single_use (op, stmt, def);
! return;
! }
}
name = gimple_assign_rhs1 (stmt);
*************** zero_one_operation (tree *def, enum tree
*** 1213,1219 ****
}
/* We might have a multiply of two __builtin_pow* calls, and
! the operand might be hiding in the rightmost one. */
if (opcode == MULT_EXPR
&& gimple_assign_rhs_code (stmt) == opcode
&& TREE_CODE (gimple_assign_rhs2 (stmt)) == SSA_NAME
--- 1223,1230 ----
}
/* We might have a multiply of two __builtin_pow* calls, and
! the operand might be hiding in the rightmost one. Likewise
! this can happen for a negate. */
if (opcode == MULT_EXPR
&& gimple_assign_rhs_code (stmt) == opcode
&& TREE_CODE (gimple_assign_rhs2 (stmt)) == SSA_NAME
*************** zero_one_operation (tree *def, enum tree
*** 1226,1231 ****
--- 1237,1249 ----
propagate_op_to_single_use (op, stmt2, def);
return;
}
+ else if (is_gimple_assign (stmt2)
+ && gimple_assign_rhs_code (stmt2) == NEGATE_EXPR
+ && gimple_assign_rhs1 (stmt2) == op)
+ {
+ propagate_op_to_single_use (op, stmt2, def);
+ return;
+ }
}
/* Continue walking the chain. */
Index: gcc/testsuite/gcc.dg/torture/pr71230.c
===================================================================
*** gcc/testsuite/gcc.dg/torture/pr71230.c (revision 0)
--- gcc/testsuite/gcc.dg/torture/pr71230.c (working copy)
***************
*** 0 ****
--- 1,25 ----
+ /* { dg-do compile } */
+ /* { dg-additional-options "-ffast-math" } */
+
+ void metric_carttosphere(int *cctk_lsh, double txz, double tyz, double txx,
+ double tzz, double sint, double cosp, double cost,
+ double tyy, double sinp, double txy, double *grp,
+ double *grq, double *r)
+ {
+ int i;
+ for(i=0; i<cctk_lsh[0]*cctk_lsh[1]*cctk_lsh[2]; i++)
+ {
+ grq[i] = (cost*tyy*((sinp)*(sinp))*sint+
+ 2*cosp*cost*txy*sinp*sint-
+ cost*tzz*sint+
+ ((cosp)*(cosp))*cost*txx*sint+
+ 2*((cost)*(cost))*tyz*sinp-
+ tyz*sinp+
+ 2*cosp*((cost)*(cost))*txz-
+ cosp*txz)*r[i];
+ grp[i] = ((-txy*((sinp)*(sinp))+
+ (cosp*tyy-cosp*txx)*sinp+
+ ((cosp)*(cosp))*txy)*sint-
+ cost*txz*sinp+cosp*cost*tyz);
+ }
+ }
Index: gcc/testsuite/g++.dg/torture/pr71230.C
===================================================================
--- gcc/testsuite/g++.dg/torture/pr71230.C (revision 0)
+++ gcc/testsuite/g++.dg/torture/pr71230.C (working copy)
@@ -0,0 +1,31 @@
+// { dg-do compile }
+// { dg-additional-options "-ffast-math" }
+
+template <int rank, int dim> class Tensor;
+template <int dim> class Point {
+public:
+ Point (const double x, const double y, const double z);
+ double operator () (const unsigned int index) const;
+};
+template <int celldim, int dim> class TriaObjectAccessor {
+ Point<dim> & vertex (const unsigned int i) const;
+ Point<dim> barycenter (double, double, double, double, double) const;
+};
+template <> Point<3> TriaObjectAccessor<3, 3>::barycenter (double s6, double
s7, double s1, double s2, double s3) const
+{
+ const double x[8] = {
+ vertex(0)(0), vertex(1)(0), vertex(2)(0), vertex(3)(0),
vertex(4)(0), vertex(5)(0), vertex(6)(0), vertex(7)(0) };
+ const double y[8] = {
+ vertex(0)(1), vertex(1)(1), vertex(2)(1), vertex(3)(1),
vertex(4)(1), vertex(5)(1), vertex(6)(1), vertex(7)(1) };
+ const double z[8] = {
+ vertex(0)(2), vertex(1)(2), vertex(2)(2), vertex(3)(2),
vertex(4)(2), vertex(5)(2), vertex(6)(2), vertex(7)(2) };
+ double s4, s5, s8;
+ const double unknown0 = s1*s2;
+ const double unknown1 = s1*s2;
+ s8 = -z[2]*x[1]*y[2]*z[5]+z[2]*y[1]*x[2]*z[5]-z[2]*z[1]*x[2]*y[5]+z[2]*z
[1]*x[5]*y[2]+2.0*y[5]*x[7]*z[4]*z[4]-y[1]*x[2]*z[0]*z[0]+x[0]*y[3]*z[7]*z[7]
-2.0*z[5]*z[5]*x[4]*y[1]+2.0*z[5]*z[5]*x[1]*y[4]+z[5]*z[5]*x[0]*y[4]-2.0*z[2]*z
[2]*x[1]*y[3]+2.0*z[2]*z[2]*x[3]*y[1]-x[0]*y[4]*z[7]*z[7]-y[0]*x[3]*z[7]*z[7]+x
[1]*y[0]*z[5]*z[5];
+ s5 = s8+z[2]*x[6]*y[2]*z[5]-z[2]*x[5]*y[2]*z[6]-z[2]*x[2]*y[3]*z[7]-x[2]*
y[3]*z[7]*z[7]+2.0*z[2]*x[2]*y[3]*z[1]-z[2]*y[2]*x[3]*z[0]+z[2]*y[2]*x[0]*z[3]-
z[2]*x[2]*y[0]*z[3]-z[7]*y[2]*x[7]*z[3]+z[7]*z[2]*x[7]*y[3]+z[7]*x[2]*y[7]*z[3]
+z[6]*y[1]*x[2]*z[5]-z[6]*x[1]*y[2]*z[5]+z[5]*x[1]*y[5]*z[2]+s6+s7;
+ s4 = 1/s5;
+ s2 = s3*s4;
+ const double unknown2 = s1*s2;
+ return Point<3> (unknown0, unknown1, unknown2);
+}
