Hi All,
I've re-spun the patch with the changes requested.
This is only done when not honoring signaling NaNs.
This transormation is done at expand time by using
a new optab "xorsign". If the optab is not available
then copysign is expanded as normal.
Bootstrapped on both aarch64-none-linux-gnu and x86_64 with no issues.
Regression done on aarch64-none-linux-gnu and no regressions.
Ok for trunk?
gcc/
2017-07-10 Tamar Christina <[email protected]>
Andrew Pinski <[email protected]>
PR middle-end/19706
* expr.c (is_copysign_call_with_1): New.
(maybe_expand_mult_copysign): Likewise.
(expand_expr_real_2): Expand copysign.
* optabs.def (xorsign_optab): New.
________________________________________
From: Andrew Pinski <[email protected]>
Sent: Monday, July 10, 2017 12:21:29 AM
To: Tamar Christina
Cc: GCC Patches; nd; [email protected]; [email protected]; [email protected]
Subject: Re: [GCC][PATCH][mid-end] Optimize x * copysign (1.0, y) [Patch (1/2)]
On Mon, Jun 12, 2017 at 12:56 AM, Tamar Christina
<[email protected]> wrote:
> Hi All,
>
> this patch implements a optimization rewriting
>
> x * copysign (1.0, y) and
> x * copysign (-1.0, y)
>
> to:
>
> x ^ (y & (1 << sign_bit_position))
>
> This is done by creating a special builtin during matching and generate the
> appropriate instructions during expand. This new builtin is called XORSIGN.
>
> The expansion of xorsign depends on if the backend has an appropriate optab
> available. If this is not the case then we use a modified version of the
> existing
> copysign which does not take the abs value of the first argument as a fall
> back.
>
> This patch is a revival of a previous patch
> https://gcc.gnu.org/ml/gcc-patches/2015-10/msg00069.html
>
> Bootstrapped on both aarch64-none-linux-gnu and x86_64 with no issues.
> Regression done on aarch64-none-linux-gnu and no regressions.
Note this is also PR 19706.
Thanks,
Andrew
>
> Ok for trunk?
>
> gcc/
> 2017-06-07 Tamar Christina <[email protected]>
>
> * builtins.def (BUILT_IN_XORSIGN, BUILT_IN_XORSIGNF): New.
> (BUILT_IN_XORSIGNL, BUILT_IN_XORSIGN_FLOAT_NX): Likewise.
> * match.pd (mult (COPYSIGN:s real_onep @0) @1): New simplifier.
> (mult (COPYSIGN:s real_mus_onep @0) @1): Likewise.
> (copysigns @0 (negate @1)): Likewise.
> * builtins.c (expand_builtin_copysign): Promoted local to argument.
> (expand_builtin): Added CASE_FLT_FN_FLOATN_NX (BUILT_IN_XORSIGN) and
> CASE_FLT_FN (BUILT_IN_XORSIGN).
> (BUILT_IN_COPYSIGN): Updated function call.
> * optabs.h (expand_copysign): New bool.
> (expand_xorsign): New.
> * optabs.def (xorsign_optab): New.
> * optabs.c (expand_copysign): New parameter.
> * fortran/f95-lang.c (xorsignl, xorsign, xorsignf): New.
> * fortran/mathbuiltins.def (XORSIGN): New.
>
> gcc/testsuite/
> 2017-06-07 Tamar Christina <[email protected]>
>
> * gcc.dg/tree-ssa/xorsign.c: New.
> * gcc.dg/xorsign_exec.c: New.
> * gcc.dg/vec-xorsign_exec.c: New.
> * gcc.dg/tree-ssa/reassoc-39.c (f2, f3): Updated constant to 2.
diff --git a/gcc/expr.c b/gcc/expr.c
index 5febf07929d0add0ad0ae1356baef008524f0c7c..0193231bc857bdea3e02b2845e62883e1b5c291b 100644
--- a/gcc/expr.c
+++ b/gcc/expr.c
@@ -8182,6 +8182,86 @@ expand_cond_expr_using_cmove (tree treeop0 ATTRIBUTE_UNUSED,
return NULL_RTX;
}
+/* Check to see if the CALL statement is an invocation of copysign
+ with 1. being the first argument. */
+static bool
+is_copysign_call_with_1 (gimple *call)
+{
+ if (!is_gimple_call (call))
+ return false;
+
+ enum combined_fn code = gimple_call_combined_fn (call);
+
+ if (code == CFN_LAST)
+ return false;
+
+ gcall *c = as_a<gcall*> (call);
+
+ if (builtin_fn_p (code))
+ {
+ switch (as_builtin_fn (code))
+ {
+ CASE_FLT_FN (BUILT_IN_COPYSIGN):
+ CASE_FLT_FN_FLOATN_NX (BUILT_IN_COPYSIGN):
+ return real_onep (gimple_call_arg (c, 0));
+ default:
+ return false;
+ }
+ }
+
+ if (internal_fn_p (code))
+ {
+ switch (as_internal_fn (code))
+ {
+ case IFN_COPYSIGN:
+ return real_onep (gimple_call_arg (c, 0));
+ default:
+ return false;
+ }
+ }
+
+ return false;
+}
+
+/* Try to expand the pattern x * copysign (1, y) into xorsign (x, y).
+ This only happens when the the xorsign optab is defined, if the
+ pattern is not a xorsign pattern or if expension failes NULL_RTX is
+ returned, otherwise the RTX from the optab expansion is returned. */
+static rtx
+maybe_expand_mult_copysign (tree treeop0, tree treeop1, rtx target)
+{
+ tree type = TREE_TYPE (treeop0);
+ rtx op0, op1;
+
+ if (HONOR_SNANS (type))
+ return NULL_RTX;
+
+ if (TREE_CODE (treeop0) == SSA_NAME && TREE_CODE (treeop1) == SSA_NAME)
+ {
+ gimple *call0 = SSA_NAME_DEF_STMT (treeop0);
+ if (!is_copysign_call_with_1 (call0))
+ {
+ /* IPA sometimes inlines and then extracts the function again,
+ resulting in an incorrect order, so check both ways. */
+ call0 = SSA_NAME_DEF_STMT (treeop1);
+ if (!is_copysign_call_with_1 (call0))
+ return NULL_RTX;
+
+ treeop1 = treeop0;
+ }
+
+ gcall *c = as_a<gcall*> (call0);
+ treeop0 = gimple_call_arg (c, 1);
+
+ expand_operands (treeop1, treeop0, NULL_RTX, &op0, &op1, EXPAND_NORMAL);
+
+ return expand_binop (TYPE_MODE (type), xorsign_optab, op0, op1,
+ target, 0, OPTAB_DIRECT);
+ }
+
+ return NULL_RTX;
+}
+
rtx
expand_expr_real_2 (sepops ops, rtx target, machine_mode tmode,
enum expand_modifier modifier)
@@ -8791,6 +8871,10 @@ expand_expr_real_2 (sepops ops, rtx target, machine_mode tmode,
if (modifier == EXPAND_STACK_PARM)
target = 0;
+ temp = maybe_expand_mult_copysign (treeop0, treeop1, target);
+ if (temp)
+ return temp;
+
expand_operands (treeop0, treeop1, subtarget, &op0, &op1, EXPAND_NORMAL);
return REDUCE_BIT_FIELD (expand_mult (mode, op0, op1, target, unsignedp));
diff --git a/gcc/optabs.def b/gcc/optabs.def
index 504c655be0210a72e7f0f34cde0131e21ccf8089..507af9ea81c42eba98780ef326c22847fdd2c043 100644
--- a/gcc/optabs.def
+++ b/gcc/optabs.def
@@ -253,6 +253,7 @@ OPTAB_D (asin_optab, "asin$a2")
OPTAB_D (atan2_optab, "atan2$a3")
OPTAB_D (atan_optab, "atan$a2")
OPTAB_D (copysign_optab, "copysign$F$a3")
+OPTAB_D (xorsign_optab, "xorsign$F$a3")
OPTAB_D (cos_optab, "cos$a2")
OPTAB_D (exp10_optab, "exp10$a2")
OPTAB_D (exp2_optab, "exp2$a2")
