/* Function sin vectorized with AVX2.

   Copyright (C) 2014-2018 Free Software Foundation, Inc.

   This file is part of the GNU C Library.

   The GNU C Library is free software; you can redistribute it and/or

   modify it under the terms of the GNU Lesser General Public

   License as published by the Free Software Foundation; either

   version 2.1 of the License, or (at your option) any later version.

   The GNU C Library is distributed in the hope that it will be useful,

   but WITHOUT ANY WARRANTY; without even the implied warranty of

   MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU

   Lesser General Public License for more details.

   You should have received a copy of the GNU Lesser General Public

   License along with the GNU C Library; if not, see

   <http://www.gnu.org/licenses/>.  */

#include <sysdep.h>

#include "svml_d_trig_data.h"

	.text

ENTRY (_ZGVdN4v_sin_avx2)

/* ALGORITHM DESCRIPTION:

      ( low accuracy ( < 4ulp ) or enhanced performance

      ( half of correct mantissa ) implementation )

     Argument representation:

     arg = N*Pi + R

     Result calculation:

     sin(arg) = sin(N*Pi + R) = (-1)^N * sin(R)

     sin(R) is approximated by corresponding polynomial

 */

        pushq     %rbp

        cfi_adjust_cfa_offset (8)

        cfi_rel_offset (%rbp, 0)

        movq      %rsp, %rbp

        cfi_def_cfa_register (%rbp)

        andq      $-64, %rsp

        subq      $448, %rsp

        movq      __svml_d_trig_data@GOTPCREL(%rip), %rax

        vmovdqa   %ymm0, %ymm4

        vmovupd __dAbsMask(%rax), %ymm2

        vmovupd __dInvPI(%rax), %ymm6

        vmovupd __dRShifter(%rax), %ymm5

        vmovupd __dPI1_FMA(%rax), %ymm7

/*

  ARGUMENT RANGE REDUCTION:

  X' = |X|

 */

        vandpd    %ymm2, %ymm4, %ymm3

/* Y = X'*InvPi + RS : right shifter add */

        vfmadd213pd %ymm5, %ymm3, %ymm6

/* N = Y - RS : right shifter sub */

        vsubpd    %ymm5, %ymm6, %ymm1

/* SignRes = Y<<63 : shift LSB to MSB place for result sign */

        vpsllq    $63, %ymm6, %ymm5

/* R = X' - N*Pi1 */

        vmovapd   %ymm3, %ymm0

        vfnmadd231pd %ymm1, %ymm7, %ymm0

        vcmpnle_uqpd __dRangeVal(%rax), %ymm3, %ymm3

/* R = R - N*Pi2 */

        vfnmadd231pd __dPI2_FMA(%rax), %ymm1, %ymm0

/* R = R - N*Pi3 */

        vfnmadd132pd __dPI3_FMA(%rax), %ymm0, %ymm1

/*

  POLYNOMIAL APPROXIMATION:

  R2 = R*R

 */

        vmulpd    %ymm1, %ymm1, %ymm0

/* R = R^SignRes : update sign of reduced argument */

        vxorpd    %ymm5, %ymm1, %ymm6

        vmovupd   __dC7_sin(%rax), %ymm1

        vfmadd213pd __dC6_sin(%rax), %ymm0, %ymm1

        vfmadd213pd __dC5_sin(%rax), %ymm0, %ymm1

        vfmadd213pd __dC4_sin(%rax), %ymm0, %ymm1

/* Poly = C3+R2*(C4+R2*(C5+R2*(C6+R2*C7))) */

        vfmadd213pd __dC3_sin(%rax), %ymm0, %ymm1

/* Poly = R2*(C1+R2*(C2+R2*Poly)) */

        vfmadd213pd __dC2_sin(%rax), %ymm0, %ymm1

        vfmadd213pd __dC1_sin(%rax), %ymm0, %ymm1

/* SignX - sign bit of X */

        vandnpd   %ymm4, %ymm2, %ymm7

        vmulpd    %ymm0, %ymm1, %ymm2

/* Poly = Poly*R + R */

        vfmadd213pd %ymm6, %ymm6, %ymm2

        vmovmskpd %ymm3, %ecx

/*

  RECONSTRUCTION:

  Final sign setting: Res = Poly^SignX

 */

        vxorpd    %ymm7, %ymm2, %ymm0

        testl     %ecx, %ecx

        jne       .LBL_1_3

.LBL_1_2:

        cfi_remember_state

        movq      %rbp, %rsp

        cfi_def_cfa_register (%rsp)

        popq      %rbp

        cfi_adjust_cfa_offset (-8)

        cfi_restore (%rbp)

        ret

.LBL_1_3:

        cfi_restore_state

        vmovupd   %ymm4, 320(%rsp)

        vmovupd   %ymm0, 384(%rsp)

        je        .LBL_1_2

        xorb      %dl, %dl

        xorl      %eax, %eax

        vmovups   %ymm8, 224(%rsp)

        vmovups   %ymm9, 192(%rsp)

        vmovups   %ymm10, 160(%rsp)

        vmovups   %ymm11, 128(%rsp)

        vmovups   %ymm12, 96(%rsp)

        vmovups   %ymm13, 64(%rsp)

        vmovups   %ymm14, 32(%rsp)

        vmovups   %ymm15, (%rsp)

        movq      %rsi, 264(%rsp)

        movq      %rdi, 256(%rsp)

        movq      %r12, 296(%rsp)

        cfi_offset_rel_rsp (12, 296)

        movb      %dl, %r12b

        movq      %r13, 288(%rsp)

        cfi_offset_rel_rsp (13, 288)

        movl      %ecx, %r13d

        movq      %r14, 280(%rsp)

        cfi_offset_rel_rsp (14, 280)

        movl      %eax, %r14d

        movq      %r15, 272(%rsp)

        cfi_offset_rel_rsp (15, 272)

        cfi_remember_state

.LBL_1_6:

        btl       %r14d, %r13d

        jc        .LBL_1_12

.LBL_1_7:

        lea       1(%r14), %esi

        btl       %esi, %r13d

        jc        .LBL_1_10

.LBL_1_8:

        incb      %r12b

        addl      $2, %r14d

        cmpb      $16, %r12b

        jb        .LBL_1_6

        vmovups   224(%rsp), %ymm8

        vmovups   192(%rsp), %ymm9

        vmovups   160(%rsp), %ymm10

        vmovups   128(%rsp), %ymm11

        vmovups   96(%rsp), %ymm12

        vmovups   64(%rsp), %ymm13

        vmovups   32(%rsp), %ymm14

        vmovups   (%rsp), %ymm15

        vmovupd   384(%rsp), %ymm0

        movq      264(%rsp), %rsi

        movq      256(%rsp), %rdi

        movq      296(%rsp), %r12

        cfi_restore (%r12)

        movq      288(%rsp), %r13

        cfi_restore (%r13)

        movq      280(%rsp), %r14

        cfi_restore (%r14)

        movq      272(%rsp), %r15

        cfi_restore (%r15)

        jmp       .LBL_1_2

.LBL_1_10:

        cfi_restore_state

        movzbl    %r12b, %r15d

        shlq      $4, %r15

        vmovsd    328(%rsp,%r15), %xmm0

        vzeroupper

        call      JUMPTARGET(sin)

        vmovsd    %xmm0, 392(%rsp,%r15)

        jmp       .LBL_1_8

.LBL_1_12:

        movzbl    %r12b, %r15d

        shlq      $4, %r15

        vmovsd    320(%rsp,%r15), %xmm0

        vzeroupper

        call      JUMPTARGET(sin)

        vmovsd    %xmm0, 384(%rsp,%r15)

        jmp       .LBL_1_7

END (_ZGVdN4v_sin_avx2)