Hi,
I decided to split my previous patch into two different patches, one
for floating point and one for integer. This is the floating point
version as we can use copysign here which should allow for more cases
to be optimized and even by a phiopt which uses match-and-simplify (I
hope to be able to submit that during stage 1).
This patch adds the following transformations:
Transform (X > 0.0 ? 1.0 : -1.0) into copysign(1, X).
Transform (X >= 0.0 ? 1.0 : -1.0) into copysign(1, X).
Transform (X < 0.0 ? 1.0 : -1.0) into copysign(1,-X).
Transform (X <= 0.0 ? 1.0 : -1.0) into copysign(1,-X).
Transform (X > 0.0 ? -1.0 : 1.0) into copysign(1,-X).
Transform (X >= 0.0 ? -1.0 : 1.0) into copysign(1,-X).
Transform (X < 0.0 ? -1.0 : 1.0) into copysign(1,X).
Transform (X <= 0.0 ? -1.0 : 1.0) into copysign(1,X).
Transform X * copysign (1.0, X) into abs(X).
Transform X * copysign (1.0, -X) into -abs(X).
Transform copysign (-1.0, X) into copysign (1.0, X).
The last one is there so if someone decides to writes -1.0 instead of
1.0 in the code we would get the optimization still.
OK? Bootstrapped and tested on aarch64-linux-gnu with no regressions.
Thanks,
Andrew Pinski
ChangeLog:
* match.pd (X >/>=/</<= 0 ? 1.0 : -1.0): New patterns.
(X * copysign (1.0, X)): New pattern.
(X * copysign (1.0, -X)): New pattern.
(copysign (-1.0, X)): New pattern.
testsuite/ChangeLog:
* gcc.dg/tree-ssa/copy-sign-1.c: New testcase.
* gcc.dg/tree-ssa/copy-sign-2.c: New testcase.
* gcc.dg/tree-ssa/mult-abs-2.c: New testcase.
Index: match.pd
===================================================================
--- match.pd (revision 249626)
+++ match.pd (working copy)
@@ -155,6 +155,57 @@
|| !COMPLEX_FLOAT_TYPE_P (type)))
(negate @0)))
+(for cmp (gt ge lt le)
+ outp (convert convert negate negate)
+ outn (negate negate convert convert)
+ /* Transform (X > 0.0 ? 1.0 : -1.0) into copysign(1, X). */
+ /* Transform (X >= 0.0 ? 1.0 : -1.0) into copysign(1, X). */
+ /* Transform (X < 0.0 ? 1.0 : -1.0) into copysign(1,-X). */
+ /* Transform (X <= 0.0 ? 1.0 : -1.0) into copysign(1,-X). */
+ (simplify
+ (cond (cmp @0 real_zerop) real_onep real_minus_onep)
+ (if (!HONOR_NANS (type) && !HONOR_SIGNED_ZEROS (type)
+ && types_match (type, TREE_TYPE (@0)))
+ (switch
+ (if (types_match (type, float_type_node))
+ (BUILT_IN_COPYSIGNF { build_one_cst (type); } (outp @0)))
+ (if (types_match (type, double_type_node))
+ (BUILT_IN_COPYSIGN { build_one_cst (type); } (outp @0)))
+ (if (types_match (type, long_double_type_node))
+ (BUILT_IN_COPYSIGNL { build_one_cst (type); } (outp @0))))))
+ /* Transform (X > 0.0 ? -1.0 : 1.0) into copysign(1,-X). */
+ /* Transform (X >= 0.0 ? -1.0 : 1.0) into copysign(1,-X). */
+ /* Transform (X < 0.0 ? -1.0 : 1.0) into copysign(1,X). */
+ /* Transform (X <= 0.0 ? -1.0 : 1.0) into copysign(1,X). */
+ (simplify
+ (cond (cmp @0 real_zerop) real_minus_onep real_onep)
+ (if (!HONOR_NANS (type) && !HONOR_SIGNED_ZEROS (type)
+ && types_match (type, TREE_TYPE (@0)))
+ (switch
+ (if (types_match (type, float_type_node))
+ (BUILT_IN_COPYSIGNF { build_one_cst (type); } (outn @0)))
+ (if (types_match (type, double_type_node))
+ (BUILT_IN_COPYSIGN { build_one_cst (type); } (outn @0)))
+ (if (types_match (type, long_double_type_node))
+ (BUILT_IN_COPYSIGNL { build_one_cst (type); } (outn @0)))))))
+
+/* Transform X * copysign (1.0, X) into abs(X). */
+(simplify
+ (mult:c @0 (COPYSIGN real_onep @0))
+ (if (!HONOR_NANS (type) && !HONOR_SIGNED_ZEROS (type))
+ (abs @0)))
+
+/* Transform X * copysign (1.0, -X) into -abs(X). */
+(simplify
+ (mult:c @0 (COPYSIGN real_onep (negate @0)))
+ (if (!HONOR_NANS (type) && !HONOR_SIGNED_ZEROS (type))
+ (negate (abs @0))))
+
+/* Transform copysign (-1.0, X) into copysign (1.0, X). */
+(simplify
+ (COPYSIGN real_minus_onep @0)
+ (COPYSIGN { build_one_cst (type); } @0))
+
/* X * 1, X / 1 -> X. */
(for op (mult trunc_div ceil_div floor_div round_div exact_div)
(simplify
Index: testsuite/gcc.dg/tree-ssa/copy-sign-1.c
===================================================================
--- testsuite/gcc.dg/tree-ssa/copy-sign-1.c (nonexistent)
+++ testsuite/gcc.dg/tree-ssa/copy-sign-1.c (working copy)
@@ -0,0 +1,35 @@
+/* { dg-options "-O2 -ffast-math -fdump-tree-gimple" } */
+/* { dg-do compile } */
+float f(float x)
+{
+ return (x > 0.f ? -1.f : 1.f);
+}
+float f1(float x)
+{
+ return (x > 0.f ? 1.f : -1.f);
+}
+float g(float x)
+{
+ return (x >= 0.f ? -1.f : 1.f);
+}
+float g1(float x)
+{
+ return (x >= 0.f ? 1.f : -1.f);
+}
+float h(float x)
+{
+ return (x < 0.f ? -1.f : 1.f);
+}
+float h1(float x)
+{
+ return (x < 0.f ? 1.f : -1.f);
+}
+float i(float x)
+{
+ return (x <= 0.f ? -1.f : 1.f);
+}
+float i1(float x)
+{
+ return (x <= 0.f ? 1.f : -1.f);
+}
+/* { dg-final { scan-tree-dump-times "copysign" 8 "gimple"} } */
Index: testsuite/gcc.dg/tree-ssa/copy-sign-2.c
===================================================================
--- testsuite/gcc.dg/tree-ssa/copy-sign-2.c (nonexistent)
+++ testsuite/gcc.dg/tree-ssa/copy-sign-2.c (working copy)
@@ -0,0 +1,13 @@
+/* { dg-options "-O2 -ffast-math -fdump-tree-optimized" } */
+/* { dg-do compile } */
+float f(float x)
+{
+ float t = __builtin_copysignf (1.0f, x);
+ return x * t;
+}
+float f1(float x)
+{
+ float t = __builtin_copysignf (1.0f, -x);
+ return x * t;
+}
+/* { dg-final { scan-tree-dump-times "ABS" 2 "optimized"} } */
Index: testsuite/gcc.dg/tree-ssa/mult-abs-2.c
===================================================================
--- testsuite/gcc.dg/tree-ssa/mult-abs-2.c (nonexistent)
+++ testsuite/gcc.dg/tree-ssa/mult-abs-2.c (working copy)
@@ -0,0 +1,35 @@
+/* { dg-options "-O2 -ffast-math -fdump-tree-gimple" } */
+/* { dg-do compile } */
+float f(float x)
+{
+ return x * (x > 0.f ? -1.f : 1.f);
+}
+float f1(float x)
+{
+ return x * (x > 0.f ? 1.f : -1.f);
+}
+float g(float x)
+{
+ return x * (x >= 0.f ? -1.f : 1.f);
+}
+float g1(float x)
+{
+ return x * (x >= 0.f ? 1.f : -1.f);
+}
+float h(float x)
+{
+ return x * (x < 0.f ? -1.f : 1.f);
+}
+float h1(float x)
+{
+ return x * (x < 0.f ? 1.f : -1.f);
+}
+float i(float x)
+{
+ return x * (x <= 0.f ? -1.f : 1.f);
+}
+float i1(float x)
+{
+ return x * (x <= 0.f ? 1.f : -1.f);
+}
+/* { dg-final { scan-tree-dump-times "ABS" 8 "gimple"} } */
