middle-end: optimize fneg (fabs (x)) to copysign (x, -1) [PR109154]

This patch transforms fneg (fabs (x)) into copysign (x, -1) which is more
canonical and allows a target to expand this sequence efficiently.  Such
sequences are common in scientific code working with gradients.

There is an existing canonicalization of copysign (x, -1) to fneg (fabs (x))
which I remove since this is a less efficient form.  The testsuite is also
updated in light of this.

gcc/ChangeLog:

	PR tree-optimization/109154
	* match.pd: Add new neg+abs rule, remove inverse copysign rule.

gcc/testsuite/ChangeLog:

	PR tree-optimization/109154
	* gcc.dg/fold-copysign-1.c: Updated.
	* gcc.dg/pr55152-2.c: Updated.
	* gcc.dg/tree-ssa/abs-4.c: Updated.
	* gcc.dg/tree-ssa/backprop-6.c: Updated.
	* gcc.dg/tree-ssa/copy-sign-2.c: Updated.
	* gcc.dg/tree-ssa/mult-abs-2.c: Updated.
	* gcc.target/aarch64/fneg-abs_1.c: New test.
	* gcc.target/aarch64/fneg-abs_2.c: New test.
	* gcc.target/aarch64/fneg-abs_3.c: New test.
	* gcc.target/aarch64/fneg-abs_4.c: New test.
	* gcc.target/aarch64/sve/fneg-abs_1.c: New test.
	* gcc.target/aarch64/sve/fneg-abs_2.c: New test.
	* gcc.target/aarch64/sve/fneg-abs_3.c: New test.
	* gcc.target/aarch64/sve/fneg-abs_4.c: New test.

15 files changed, 303 insertions, 12 deletions

diff --git a/gcc/match.pd b/gcc/match.pd
index 68a1587..5928acb 100644
--- a/gcc/match.pd
+++ b/gcc/match.pd
@@ -1118,14 +1118,18 @@ DEFINE_INT_AND_FLOAT_ROUND_FN (RINT)
    (hypots @0 (copysigns @1 @2))
    (hypots @0 @1))))
 
-/* copysign(x, CST) -> [-]abs (x).  */
+/* copysign(x, CST) -> abs (x).  */
 (for copysigns (COPYSIGN_ALL)
  (simplify
   (copysigns @0 REAL_CST@1)
-  (if (REAL_VALUE_NEGATIVE (TREE_REAL_CST (@1)))
-   (negate (abs @0))
+  (if (!REAL_VALUE_NEGATIVE (TREE_REAL_CST (@1)))
    (abs @0))))
 
+/* Transform fneg (fabs (X)) -> copysign (X, -1).  */
+(simplify
+ (negate (abs @0))
+ (IFN_COPYSIGN @0 { build_minus_one_cst (type); }))
+
 /* copysign(copysign(x, y), z) -> copysign(x, z).  */
 (for copysigns (COPYSIGN_ALL)
  (simplify
diff --git a/gcc/testsuite/gcc.dg/fold-copysign-1.c b/gcc/testsuite/gcc.dg/fold-copysign-1.c
index f17d65c..f9cafd1 100644
--- a/gcc/testsuite/gcc.dg/fold-copysign-1.c
+++ b/gcc/testsuite/gcc.dg/fold-copysign-1.c
@@ -12,5 +12,5 @@ double bar (double x)
   return __builtin_copysign (x, minuszero);
 }
 
-/* { dg-final { scan-tree-dump-times "= -" 1 "cddce1" } } */
-/* { dg-final { scan-tree-dump-times "= ABS_EXPR" 2 "cddce1" } } */
+/* { dg-final { scan-tree-dump-times "__builtin_copysign" 1 "cddce1" } } */
+/* { dg-final { scan-tree-dump-times "= ABS_EXPR" 1 "cddce1" } } */
diff --git a/gcc/testsuite/gcc.dg/pr55152-2.c b/gcc/testsuite/gcc.dg/pr55152-2.c
index 54db0f2..605f202 100644
--- a/gcc/testsuite/gcc.dg/pr55152-2.c
+++ b/gcc/testsuite/gcc.dg/pr55152-2.c
@@ -10,4 +10,5 @@ int f(int a)
   return (a<-a)?a:-a;
 }
 
-/* { dg-final { scan-tree-dump-times "ABS_EXPR" 2 "optimized" } } */
+/* { dg-final { scan-tree-dump-times "\.COPYSIGN" 1 "optimized" } } */
+/* { dg-final { scan-tree-dump-times "ABS_EXPR" 1 "optimized" } } */
diff --git a/gcc/testsuite/gcc.dg/tree-ssa/abs-4.c b/gcc/testsuite/gcc.dg/tree-ssa/abs-4.c
index 6197519..e1b825f 100644
--- a/gcc/testsuite/gcc.dg/tree-ssa/abs-4.c
+++ b/gcc/testsuite/gcc.dg/tree-ssa/abs-4.c
@@ -9,5 +9,6 @@ long double abs_ld(long double x) { return __builtin_signbit(x) ? x : -x; }
 
 /* __builtin_signbit(x) ? x : -x. Should be convert into - ABS_EXP<x> */
 /* { dg-final { scan-tree-dump-not "signbit" "optimized"} } */
-/* { dg-final { scan-tree-dump-times "= ABS_EXPR" 3 "optimized"} } */
-/* { dg-final { scan-tree-dump-times "= -" 3 "optimized"} } */
+/* { dg-final { scan-tree-dump-times "= ABS_EXPR" 1 "optimized"} } */
+/* { dg-final { scan-tree-dump-times "= -" 1 "optimized"} } */
+/* { dg-final { scan-tree-dump-times "= \.COPYSIGN" 2 "optimized"} } */
diff --git a/gcc/testsuite/gcc.dg/tree-ssa/backprop-6.c b/gcc/testsuite/gcc.dg/tree-ssa/backprop-6.c
index 31f0571..c3a1386 100644
--- a/gcc/testsuite/gcc.dg/tree-ssa/backprop-6.c
+++ b/gcc/testsuite/gcc.dg/tree-ssa/backprop-6.c
@@ -26,5 +26,6 @@ TEST_FUNCTION (float, f)
 TEST_FUNCTION (double, )
 TEST_FUNCTION (long double, l)
 
-/* { dg-final { scan-tree-dump-times {Deleting[^\n]* = -} 6 "backprop" } } */
-/* { dg-final { scan-tree-dump-times {Deleting[^\n]* = ABS_EXPR <} 3 "backprop" } } */
+/* { dg-final { scan-tree-dump-times {Deleting[^\n]* = -} 4 "backprop" } } */
+/* { dg-final { scan-tree-dump-times {Deleting[^\n]* = \.COPYSIGN} 2 "backprop" } } */
+/* { dg-final { scan-tree-dump-times {Deleting[^\n]* = ABS_EXPR <} 1 "backprop" } } */
diff --git a/gcc/testsuite/gcc.dg/tree-ssa/copy-sign-2.c b/gcc/testsuite/gcc.dg/tree-ssa/copy-sign-2.c
index de52c5f..e5d565c 100644
--- a/gcc/testsuite/gcc.dg/tree-ssa/copy-sign-2.c
+++ b/gcc/testsuite/gcc.dg/tree-ssa/copy-sign-2.c
@@ -10,4 +10,5 @@ float f1(float x)
   float t = __builtin_copysignf (1.0f, -x);
   return x * t;
 }
-/* { dg-final { scan-tree-dump-times "ABS" 2 "optimized"} } */
+/* { dg-final { scan-tree-dump-times "ABS" 1 "optimized"} } */
+/* { dg-final { scan-tree-dump-times ".COPYSIGN" 1 "optimized"} } */
diff --git a/gcc/testsuite/gcc.dg/tree-ssa/mult-abs-2.c b/gcc/testsuite/gcc.dg/tree-ssa/mult-abs-2.c
index a41f1ba..a22896b 100644
--- a/gcc/testsuite/gcc.dg/tree-ssa/mult-abs-2.c
+++ b/gcc/testsuite/gcc.dg/tree-ssa/mult-abs-2.c
@@ -34,4 +34,5 @@ float i1(float x)
 {
   return x * (x <= 0.f ? 1.f : -1.f);
 }
-/* { dg-final { scan-tree-dump-times "ABS" 8 "gimple"} } */
+/* { dg-final { scan-tree-dump-times "ABS" 4 "gimple"} } */
+/* { dg-final { scan-tree-dump-times "\.COPYSIGN" 4 "gimple"} } */
diff --git a/gcc/testsuite/gcc.target/aarch64/fneg-abs_1.c b/gcc/testsuite/gcc.target/aarch64/fneg-abs_1.c
new file mode 100644
index 0000000..f823013
--- /dev/null
+++ b/gcc/testsuite/gcc.target/aarch64/fneg-abs_1.c
@@ -0,0 +1,39 @@
+/* { dg-do compile } */
+/* { dg-options "-O3" } */
+/* { dg-final { check-function-bodies "**" "" "" { target lp64 } } } */
+
+#pragma GCC target "+nosve"
+
+#include <arm_neon.h>
+
+/*
+** t1:
+**	orr	v[0-9]+.2s, #128, lsl #24
+**	ret
+*/
+float32x2_t t1 (float32x2_t a)
+{
+  return vneg_f32 (vabs_f32 (a));
+}
+
+/*
+** t2:
+**	orr	v[0-9]+.4s, #128, lsl #24
+**	ret
+*/
+float32x4_t t2 (float32x4_t a)
+{
+  return vnegq_f32 (vabsq_f32 (a));
+}
+
+/*
+** t3:
+**	adrp	x0, .LC[0-9]+
+**	ldr	q[0-9]+, \[x0, #:lo12:.LC0\]
+**	orr	v[0-9]+.16b, v[0-9]+.16b, v[0-9]+.16b
+**	ret
+*/
+float64x2_t t3 (float64x2_t a)
+{
+  return vnegq_f64 (vabsq_f64 (a));
+}
diff --git a/gcc/testsuite/gcc.target/aarch64/fneg-abs_2.c b/gcc/testsuite/gcc.target/aarch64/fneg-abs_2.c
new file mode 100644
index 0000000..1411211
--- /dev/null
+++ b/gcc/testsuite/gcc.target/aarch64/fneg-abs_2.c
@@ -0,0 +1,31 @@
+/* { dg-do compile } */
+/* { dg-options "-O3" } */
+/* { dg-final { check-function-bodies "**" "" "" { target lp64 } } } */
+
+#pragma GCC target "+nosve"
+
+#include <arm_neon.h>
+#include <math.h>
+
+/*
+** f1:
+**	movi	v[0-9]+.2s, 0x80, lsl 24
+**	orr	v[0-9]+.8b, v[0-9]+.8b, v[0-9]+.8b
+**	ret
+*/
+float32_t f1 (float32_t a)
+{
+  return -fabsf (a);
+}
+
+/*
+** f2:
+**	mov	x0, -9223372036854775808
+**	fmov	d[0-9]+, x0
+**	orr	v[0-9]+.8b, v[0-9]+.8b, v[0-9]+.8b
+**	ret
+*/
+float64_t f2 (float64_t a)
+{
+  return -fabs (a);
+}
diff --git a/gcc/testsuite/gcc.target/aarch64/fneg-abs_3.c b/gcc/testsuite/gcc.target/aarch64/fneg-abs_3.c
new file mode 100644
index 0000000..b465217
--- /dev/null
+++ b/gcc/testsuite/gcc.target/aarch64/fneg-abs_3.c
@@ -0,0 +1,36 @@
+/* { dg-do compile } */
+/* { dg-options "-O3" } */
+/* { dg-final { check-function-bodies "**" "" "" { target lp64 } } } */
+
+#pragma GCC target "+nosve"
+
+#include <arm_neon.h>
+#include <math.h>
+
+/*
+** f1:
+**	...
+**	ldr	q[0-9]+, \[x0\]
+**	orr	v[0-9]+.4s, #128, lsl #24
+**	str	q[0-9]+, \[x0\], 16
+**	...
+*/
+void f1 (float32_t *a, int n)
+{
+  for (int i = 0; i < (n & -8); i++)
+   a[i] = -fabsf (a[i]);
+}
+
+/*
+** f2:
+**	...
+**	ldr	q[0-9]+, \[x0\]
+**	orr	v[0-9]+.16b, v[0-9]+.16b, v[0-9]+.16b
+**	str	q[0-9]+, \[x0\], 16
+**	...
+*/
+void f2 (float64_t *a, int n)
+{
+  for (int i = 0; i < (n & -8); i++)
+   a[i] = -fabs (a[i]);
+}
diff --git a/gcc/testsuite/gcc.target/aarch64/fneg-abs_4.c b/gcc/testsuite/gcc.target/aarch64/fneg-abs_4.c
new file mode 100644
index 0000000..10879de
--- /dev/null
+++ b/gcc/testsuite/gcc.target/aarch64/fneg-abs_4.c
@@ -0,0 +1,39 @@
+/* { dg-do compile } */
+/* { dg-options "-O3" } */
+/* { dg-final { check-function-bodies "**" "" "" { target lp64 } } } */
+
+#pragma GCC target "+nosve"
+
+#include <string.h>
+
+/*
+** negabs:
+**	mov	x0, -9223372036854775808
+**	fmov	d[0-9]+, x0
+**	orr	v[0-9]+.8b, v[0-9]+.8b, v[0-9]+.8b
+**	ret
+*/
+double negabs (double x)
+{
+   unsigned long long y;
+   memcpy (&y, &x, sizeof(double));
+   y = y | (1UL << 63);
+   memcpy (&x, &y, sizeof(double));
+   return x;
+}
+
+/*
+** negabsf:
+**	movi	v[0-9]+.2s, 0x80, lsl 24
+**	orr	v[0-9]+.8b, v[0-9]+.8b, v[0-9]+.8b
+**	ret
+*/
+float negabsf (float x)
+{
+   unsigned int y;
+   memcpy (&y, &x, sizeof(float));
+   y = y | (1U << 31);
+   memcpy (&x, &y, sizeof(float));
+   return x;
+}
+
diff --git a/gcc/testsuite/gcc.target/aarch64/sve/fneg-abs_1.c b/gcc/testsuite/gcc.target/aarch64/sve/fneg-abs_1.c
new file mode 100644
index 0000000..0c7664e
--- /dev/null
+++ b/gcc/testsuite/gcc.target/aarch64/sve/fneg-abs_1.c
@@ -0,0 +1,37 @@
+/* { dg-do compile } */
+/* { dg-options "-O3" } */
+/* { dg-final { check-function-bodies "**" "" "" { target lp64 } } } */
+
+#include <arm_neon.h>
+
+/*
+** t1:
+**	orr	v[0-9]+.2s, #128, lsl #24
+**	ret
+*/
+float32x2_t t1 (float32x2_t a)
+{
+  return vneg_f32 (vabs_f32 (a));
+}
+
+/*
+** t2:
+**	orr	v[0-9]+.4s, #128, lsl #24
+**	ret
+*/
+float32x4_t t2 (float32x4_t a)
+{
+  return vnegq_f32 (vabsq_f32 (a));
+}
+
+/*
+** t3:
+**	adrp	x0, .LC[0-9]+
+**	ldr	q[0-9]+, \[x0, #:lo12:.LC0\]
+**	orr	v[0-9]+.16b, v[0-9]+.16b, v[0-9]+.16b
+**	ret
+*/
+float64x2_t t3 (float64x2_t a)
+{
+  return vnegq_f64 (vabsq_f64 (a));
+}
diff --git a/gcc/testsuite/gcc.target/aarch64/sve/fneg-abs_2.c b/gcc/testsuite/gcc.target/aarch64/sve/fneg-abs_2.c
new file mode 100644
index 0000000..a60cd31
--- /dev/null
+++ b/gcc/testsuite/gcc.target/aarch64/sve/fneg-abs_2.c
@@ -0,0 +1,29 @@
+/* { dg-do compile } */
+/* { dg-options "-O3" } */
+/* { dg-final { check-function-bodies "**" "" "" { target lp64 } } } */
+
+#include <arm_neon.h>
+#include <math.h>
+
+/*
+** f1:
+**	movi	v[0-9]+.2s, 0x80, lsl 24
+**	orr	v[0-9]+.8b, v[0-9]+.8b, v[0-9]+.8b
+**	ret
+*/
+float32_t f1 (float32_t a)
+{
+  return -fabsf (a);
+}
+
+/*
+** f2:
+**	mov	x0, -9223372036854775808
+**	fmov	d[0-9]+, x0
+**	orr	v[0-9]+.8b, v[0-9]+.8b, v[0-9]+.8b
+**	ret
+*/
+float64_t f2 (float64_t a)
+{
+  return -fabs (a);
+}
diff --git a/gcc/testsuite/gcc.target/aarch64/sve/fneg-abs_3.c b/gcc/testsuite/gcc.target/aarch64/sve/fneg-abs_3.c
new file mode 100644
index 0000000..1bf3432
--- /dev/null
+++ b/gcc/testsuite/gcc.target/aarch64/sve/fneg-abs_3.c
@@ -0,0 +1,34 @@
+/* { dg-do compile } */
+/* { dg-options "-O3" } */
+/* { dg-final { check-function-bodies "**" "" "" { target lp64 } } } */
+
+#include <arm_neon.h>
+#include <math.h>
+
+/*
+** f1:
+**	...
+**	ld1w	z[0-9]+.s, p[0-9]+/z, \[x0, x2, lsl 2\]
+**	orr	z[0-9]+.s, z[0-9]+.s, #0x80000000
+**	st1w	z[0-9]+.s, p[0-9]+, \[x0, x2, lsl 2\]
+**	...
+*/
+void f1 (float32_t *a, int n)
+{
+  for (int i = 0; i < (n & -8); i++)
+   a[i] = -fabsf (a[i]);
+}
+
+/*
+** f2:
+**	...
+**	ld1d	z[0-9]+.d, p[0-9]+/z, \[x0, x2, lsl 3\]
+**	orr	z[0-9]+.d, z[0-9]+.d, #0x8000000000000000
+**	st1d	z[0-9]+.d, p[0-9]+, \[x0, x2, lsl 3\]
+**	...
+*/
+void f2 (float64_t *a, int n)
+{
+  for (int i = 0; i < (n & -8); i++)
+   a[i] = -fabs (a[i]);
+}
diff --git a/gcc/testsuite/gcc.target/aarch64/sve/fneg-abs_4.c b/gcc/testsuite/gcc.target/aarch64/sve/fneg-abs_4.c
new file mode 100644
index 0000000..21f2a8d
--- /dev/null
+++ b/gcc/testsuite/gcc.target/aarch64/sve/fneg-abs_4.c
@@ -0,0 +1,37 @@
+/* { dg-do compile } */
+/* { dg-options "-O3" } */
+/* { dg-final { check-function-bodies "**" "" "" { target lp64 } } } */
+
+#include <string.h>
+
+/*
+** negabs:
+**	mov	x0, -9223372036854775808
+**	fmov	d[0-9]+, x0
+**	orr	v[0-9]+.8b, v[0-9]+.8b, v[0-9]+.8b
+**	ret
+*/
+double negabs (double x)
+{
+   unsigned long long y;
+   memcpy (&y, &x, sizeof(double));
+   y = y | (1UL << 63);
+   memcpy (&x, &y, sizeof(double));
+   return x;
+}
+
+/*
+** negabsf:
+**	movi	v[0-9]+.2s, 0x80, lsl 24
+**	orr	v[0-9]+.8b, v[0-9]+.8b, v[0-9]+.8b
+**	ret
+*/
+float negabsf (float x)
+{
+   unsigned int y;
+   memcpy (&y, &x, sizeof(float));
+   y = y | (1U << 31);
+   memcpy (&x, &y, sizeof(float));
+   return x;
+}
+