This patch adds code to the cse_sincos pass to expand builtin cabs (x)
into sqrt (r*r + i*i), where r = realpart(x) and i = imagpart(x). This
is usually handled by fold_builtin_cabs; however, PR49302 shows a case
where compile flags of -O0 -flto combined with link flags of -O2
-ffast-math allow cabs to leak through.
Test case gcc.dg/lto/20110201-1_0.c indicates that cabs is not
guaranteed to be implemented in libm, so -lm is not specified for the
test. This patch does not present a perfect solution, in that it will
produce a builtin call to sqrt for targets that don't have a hardware
sqrt instruction. Although sqrt should always be provided by libm, this
test case will fail since -lm is not specified. Note that this is not
new behavior introduced by the patch, so this is probably OK; it just
restores what was happening prior to the pow/powi fixes for PR46728.
The test case has been verified fixed on x86_64-linux, and verified to
fail only with an unsatisfied reference to sqrt on powerpc64-linux.
Bootstrapped and regtested on both platforms.
OK for trunk?
Thanks,
Bill
2011-06-08 Bill Schmidt <wschm...@linux.vnet.ibm.com>
PR lto/49302
* tree-ssa-math-opts.c (build_and_insert_ref): New.
(gimple_expand_builtin_cabs): New.
(execute_cse_sincos): Add case for BUILT_IN_CABS.
Index: gcc/tree-ssa-math-opts.c
===================================================================
--- gcc/tree-ssa-math-opts.c (revision 174765)
+++ gcc/tree-ssa-math-opts.c (working copy)
@@ -1070,6 +1070,22 @@ build_and_insert_binop (gimple_stmt_iterator *gsi,
return result;
}
+/* Build a gimple reference operation with the given CODE and argument
+ ARG, assigning the result to a new SSA name for variable TARGET.
+ Insert the statement prior to GSI's current position, and return
+ the fresh SSA name.*/
+
+static inline tree
+build_and_insert_ref (gimple_stmt_iterator *gsi, location_t loc, tree type,
+ tree target, enum tree_code code, tree arg0)
+{
+ tree result = make_ssa_name (target, NULL);
+ gimple stmt = gimple_build_assign (result, build1 (code, type, arg0));
+ gimple_set_location (stmt, loc);
+ gsi_insert_before (gsi, stmt, GSI_SAME_STMT);
+ return result;
+}
+
/* ARG0 and ARG1 are the two arguments to a pow builtin call in GSI
with location info LOC. If possible, create an equivalent and
less expensive sequence of statements prior to GSI, and return an
@@ -1306,6 +1322,41 @@ gimple_expand_builtin_pow (gimple_stmt_iterator *g
return NULL_TREE;
}
+/* ARG is the argument to a cabs builtin call in GSI with location info
+ LOC. Create a sequence of statements prior to GSI that calculates
+ sqrt(R*R + I*I), where R and I are the real and imaginary components
+ of ARG, respectively. Return an expression holding the result. */
+
+static tree
+gimple_expand_builtin_cabs (gimple_stmt_iterator *gsi, location_t loc, tree
arg)
+{
+ tree target, real_part, imag_part, addend1, addend2, sum, result, sqrtfn;
+ tree type = TREE_TYPE (arg);
+
+ gcc_assert (TREE_CODE (type) == COMPLEX_TYPE);
+ type = TREE_TYPE (type);
+ sqrtfn = mathfn_built_in (type, BUILT_IN_SQRT);
+
+ if (!sqrtfn)
+ return NULL_TREE;
+
+ target = create_tmp_var (type, "cabs");
+ add_referenced_var (target);
+
+ real_part = build_and_insert_ref (gsi, loc, type, target,
+ REALPART_EXPR, arg);
+ addend1 = build_and_insert_binop (gsi, loc, target, MULT_EXPR,
+ real_part, real_part);
+ imag_part = build_and_insert_ref (gsi, loc, type, target,
+ IMAGPART_EXPR, arg);
+ addend2 = build_and_insert_binop (gsi, loc, target, MULT_EXPR,
+ imag_part, imag_part);
+ sum = build_and_insert_binop (gsi, loc, target, PLUS_EXPR, addend1, addend2);
+ result = build_and_insert_call (gsi, loc, &target, sqrtfn, sum);
+
+ return result;
+}
+
/* Go through all calls to sin, cos and cexpi and call execute_cse_sincos_1
on the SSA_NAME argument of each of them. Also expand powi(x,n) into
an optimal number of multiplies, when n is a constant. */
@@ -1388,6 +1439,34 @@ execute_cse_sincos (void)
}
break;
+ CASE_FLT_FN (BUILT_IN_CABS):
+ /* This code is usually redundant with fold_builtin_cabs.
+ There is a possible edge case where compile flags
+ include -O0 -flto, while link flags include -O2
+ -ffast-math. In this case, the fold does not occur
+ and cabs can leak through. Since it is not guaranteed
+ to be implemented in libm on all targets, we need to
+ lower it here.
+
+ See test case gcc.dg/lto/20110201-1_0.c. */
+ if (!flag_unsafe_math_optimizations
+ || !optimize_function_for_speed_p (cfun))
+ break;
+
+ arg0 = gimple_call_arg (stmt, 0);
+ loc = gimple_location (stmt);
+ result = gimple_expand_builtin_cabs (&gsi, loc, arg0);
+
+ if (result)
+ {
+ tree lhs = gimple_get_lhs (stmt);
+ gimple new_stmt = gimple_build_assign (lhs, result);
+ gimple_set_location (new_stmt, loc);
+ unlink_stmt_vdef (stmt);
+ gsi_replace (&gsi, new_stmt, true);
+ }
+ break;
+
default:;
}
}
