Commit 4261463d by Tamar Christina Committed by Tamar Christina

re PR middle-end/19706 (Recognize common Fortran usages of copysign.)

2017-08-08  Tamar Christina  <tamar.christina@arm.com>

	PR middle-end/19706
	* config/aarch64/aarch64.md (xorsign<mode>3): New optabs.
	* config/aarch64/aarch64-builtins.c
	(aarch64_builtin_vectorized_function): Added CASE_CFN_XORSIGN.
	* config/aarch64/aarch64-simd-builtins.def: Added xorsign BINOP.
	* config/aarch64/aarch64-simd.md: Added xorsign<mode>3.

gcc/testsuite/
2017-08-08  Tamar Christina  <tamar.christina@arm.com>

	* gcc.target/aarch64/xorsign.c: New.
	* gcc.target/aarch64/xorsign_exec.c: New.
	* gcc.target/aarch64/vect-xorsign_exec.c: New.

From-SVN: r250957
parent 336a06a1
2017-08-08 Tamar Christina <tamar.christina@arm.com>
PR middle-end/19706
* config/aarch64/aarch64.md (xorsign<mode>3): New optabs.
* config/aarch64/aarch64-builtins.c
(aarch64_builtin_vectorized_function): Added CASE_CFN_XORSIGN.
* config/aarch64/aarch64-simd-builtins.def: Added xorsign BINOP.
* config/aarch64/aarch64-simd.md: Added xorsign<mode>3
2017-08-08 Tamar Christina <tamar.christina@arm.com>
Andrew Pinski <pinskia@gmail.com>
PR middle-end/19706
......
......@@ -351,6 +351,35 @@
}
)
(define_expand "xorsign<mode>3"
[(match_operand:VHSDF 0 "register_operand")
(match_operand:VHSDF 1 "register_operand")
(match_operand:VHSDF 2 "register_operand")]
"TARGET_SIMD"
{
machine_mode imode = <V_cmp_result>mode;
rtx v_bitmask = gen_reg_rtx (imode);
rtx op1x = gen_reg_rtx (imode);
rtx op2x = gen_reg_rtx (imode);
rtx arg1 = lowpart_subreg (imode, operands[1], <MODE>mode);
rtx arg2 = lowpart_subreg (imode, operands[2], <MODE>mode);
int bits = GET_MODE_UNIT_BITSIZE (<MODE>mode) - 1;
emit_move_insn (v_bitmask,
aarch64_simd_gen_const_vector_dup (<V_cmp_result>mode,
HOST_WIDE_INT_M1U << bits));
emit_insn (gen_and<v_cmp_result>3 (op2x, v_bitmask, arg2));
emit_insn (gen_xor<v_cmp_result>3 (op1x, arg1, op2x));
emit_move_insn (operands[0],
lowpart_subreg (<MODE>mode, op1x, imode));
DONE;
}
)
(define_expand "copysign<mode>3"
[(match_operand:VHSDF 0 "register_operand")
(match_operand:VHSDF 1 "register_operand")
......
......@@ -5178,6 +5178,42 @@
}
)
;; For xorsign (x, y), we want to generate:
;;
;; LDR d2, #1<<63
;; AND v3.8B, v1.8B, v2.8B
;; EOR v0.8B, v0.8B, v3.8B
;;
(define_expand "xorsign<mode>3"
[(match_operand:GPF 0 "register_operand")
(match_operand:GPF 1 "register_operand")
(match_operand:GPF 2 "register_operand")]
"TARGET_FLOAT && TARGET_SIMD"
{
machine_mode imode = <V_cmp_result>mode;
rtx mask = gen_reg_rtx (imode);
rtx op1x = gen_reg_rtx (imode);
rtx op2x = gen_reg_rtx (imode);
int bits = GET_MODE_BITSIZE (<MODE>mode) - 1;
emit_move_insn (mask, GEN_INT (trunc_int_for_mode (HOST_WIDE_INT_M1U << bits,
imode)));
emit_insn (gen_and<v_cmp_result>3 (op2x, mask,
lowpart_subreg (imode, operands[2],
<MODE>mode)));
emit_insn (gen_xor<v_cmp_result>3 (op1x,
lowpart_subreg (imode, operands[1],
<MODE>mode),
op2x));
emit_move_insn (operands[0],
lowpart_subreg (<MODE>mode, op1x, imode));
DONE;
}
)
;; -------------------------------------------------------------------
;; Reload support
;; -------------------------------------------------------------------
......
2017-08-08 Tamar Christina <tamar.christina@arm.com>
* gcc.target/aarch64/xorsign.c: New.
* gcc.target/aarch64/xorsign_exec.c: New.
* gcc.target/aarch64/vect-xorsign_exec.c: New.
2017-08-08 Bill Schmidt <wschmidt@linux.vnet.ibm.com>
PR tree-optimization/81354
......
/* { dg-do run } */
/* { dg-options "-O2 -ftree-vectorize -fdump-tree-vect-details" } */
extern void abort ();
#define N 16
float a[N] = {-0.1f, -3.2f, -6.3f, -9.4f,
-12.5f, -15.6f, -18.7f, -21.8f,
24.9f, 27.1f, 30.2f, 33.3f,
36.4f, 39.5f, 42.6f, 45.7f};
float b[N] = {-1.2f, 3.4f, -5.6f, 7.8f,
-9.0f, 1.0f, -2.0f, 3.0f,
-4.0f, -5.0f, 6.0f, 7.0f,
-8.0f, -9.0f, 10.0f, 11.0f};
float r[N];
double ad[N] = {-0.1d, -3.2d, -6.3d, -9.4d,
-12.5d, -15.6d, -18.7d, -21.8d,
24.9d, 27.1d, 30.2d, 33.3d,
36.4d, 39.5d, 42.6d, 45.7d};
double bd[N] = {-1.2d, 3.4d, -5.6d, 7.8d,
-9.0d, 1.0d, -2.0d, 3.0d,
-4.0d, -5.0d, 6.0d, 7.0d,
-8.0d, -9.0d, 10.0d, 11.0d};
double rd[N];
int
main (void)
{
int i;
for (i = 0; i < N; i++)
r[i] = a[i] * __builtin_copysignf (1.0f, b[i]);
/* check results: */
for (i = 0; i < N; i++)
if (r[i] != a[i] * __builtin_copysignf (1.0f, b[i]))
abort ();
for (i = 0; i < N; i++)
rd[i] = ad[i] * __builtin_copysign (1.0d, bd[i]);
/* check results: */
for (i = 0; i < N; i++)
if (rd[i] != ad[i] * __builtin_copysign (1.0d, bd[i]))
abort ();
return 0;
}
/* { dg-final { scan-tree-dump-times "vectorized 2 loops" 1 "vect" } } */
/* { dg-final { scan-assembler "\[ \t\]?eor\[ \t\]?" } } */
/* { dg-final { scan-assembler "\[ \t\]?and\[ \t\]?" } } */
/* { dg-final { scan-assembler-not "copysign" } } */
/* { dg-final { scan-assembler-not "\[ \t\]?orr\[ \t\]?" } } */
/* { dg-final { scan-assembler-not "\[ \t\]?fmul\[ \t\]?" } } */
/* { dg-do compile } */
/* { dg-options "-O3" } */
double
check_d_pos (double x, double y)
{
return x * __builtin_copysign (1.0, y);
}
float
check_f_pos (float x, float y)
{
return x * __builtin_copysignf (1.0f, y);
}
long double
check_l_pos (long double x, long double y)
{
return x * __builtin_copysignl (1.0, y);
}
/* --------------- */
double
check_d_neg (double x, double y)
{
return x * __builtin_copysign (-1.0, y);
}
float
check_f_neg (float x, float y)
{
return x * __builtin_copysignf (-1.0f, y);
}
long double
check_l_neg (long double x, long double y)
{
return x * __builtin_copysignl (-1.0, y);
}
/* --------------- */
double
check_d_pos_rev (double x, double y)
{
return __builtin_copysign (1.0, y) * x;
}
float
check_f_pos_rev (float x, float y)
{
return __builtin_copysignf (1.0f, y) * x;
}
long double
check_l_pos_rev (long double x, long double y)
{
return __builtin_copysignl (1.0, y) * x;
}
/* --------------- */
double
check_d_neg_rev (double x, double y)
{
return __builtin_copysign (-1.0, y) * x;
}
float
check_f_neg_rev (float x, float y)
{
return __builtin_copysignf (-1.0f, y) * x;
}
long double
check_l_neg_rev (long double x, long double y)
{
return __builtin_copysignl (-1.0, y) * x;
}
/* { dg-final { scan-assembler "\[ \t\]?eor\[ \t\]?" } } */
/* { dg-final { scan-assembler "\[ \t\]?and\[ \t\]?" } } */
/* { dg-final { scan-assembler-not "copysign" } } */
/* { dg-final { scan-assembler-not "\[ \t\]?orr\[ \t\]?" } } */
/* { dg-final { scan-assembler-not "\[ \t\]?fmul\[ \t\]?" } } */
/* { dg-do run } */
/* { dg-options "-O -ffast-math" } */
#include <math.h>
extern void abort(void);
static double x = 2.0;
static float y = 2.0;
int main()
{
if ((2.5 * __builtin_copysign(1.0d, x)) != 2.5)
abort();
if ((2.5 * __builtin_copysign(1.0f, y)) != 2.5)
abort();
if ((2.5 * __builtin_copysignf(1.0d, -x)) != -2.5)
abort();
if ((2.5 * __builtin_copysignf(1.0f, -y)) != -2.5)
abort();
return 0;
}
Markdown is supported
0% or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment