Vector sinf for x86_64 and tests.

Here is implementation of vectorized sinf containing SSE, AVX,
AVX2 and AVX512 versions according to Vector ABI
<https://groups.google.com/forum/#!topic/x86-64-abi/LmppCfN1rZ4>.

    * sysdeps/unix/sysv/linux/x86_64/libmvec.abilist: New symbols added.
    * sysdeps/x86/fpu/bits/math-vector.h: Added SIMD declaration for sinf.
    * sysdeps/x86_64/fpu/Makefile (libmvec-support): Added new files.
    * sysdeps/x86_64/fpu/Versions: New versions added.
    * sysdeps/x86_64/fpu/libm-test-ulps: Regenerated.
    * sysdeps/x86_64/fpu/multiarch/Makefile (libmvec-sysdep_routines): Added
    build of SSE, AVX2 and AVX512 IFUNC versions.
    * sysdeps/x86_64/fpu/multiarch/svml_s_sinf16_core.S: New file.
    * sysdeps/x86_64/fpu/multiarch/svml_s_sinf16_core_avx512.S: New file.
    * sysdeps/x86_64/fpu/multiarch/svml_s_sinf4_core.S: New file.
    * sysdeps/x86_64/fpu/multiarch/svml_s_sinf4_core_sse4.S: New file.
    * sysdeps/x86_64/fpu/multiarch/svml_s_sinf8_core.S: New file.
    * sysdeps/x86_64/fpu/multiarch/svml_s_sinf8_core_avx2.S: New file.
    * sysdeps/x86_64/fpu/svml_s_sinf16_core.S: New file.
    * sysdeps/x86_64/fpu/svml_s_sinf4_core.S: New file.
    * sysdeps/x86_64/fpu/svml_s_sinf8_core.S: New file.
    * sysdeps/x86_64/fpu/svml_s_sinf8_core_avx.S: New file.
    * sysdeps/x86_64/fpu/svml_s_sinf_data.S: New file.
    * sysdeps/x86_64/fpu/svml_s_sinf_data.h: New file.
    * sysdeps/x86_64/fpu/test-float-vlen16-wrappers.c: Vector sinf tests.
    * sysdeps/x86_64/fpu/test-float-vlen16.c: Likewise.
    * sysdeps/x86_64/fpu/test-float-vlen4-wrappers.c: Likewise.
    * sysdeps/x86_64/fpu/test-float-vlen4.c: Likewise.
    * sysdeps/x86_64/fpu/test-float-vlen8-avx2-wrappers.c: Likewise.
    * sysdeps/x86_64/fpu/test-float-vlen8-avx2.c: Likewise.
    * sysdeps/x86_64/fpu/test-float-vlen8-wrappers.c: Likewise.
    * sysdeps/x86_64/fpu/test-float-vlen8.c: Likewise.
    * NEWS: Mention addition of x86_64 vector sinf.

7 files changed, 1039 insertions, 1 deletions

diff --git a/sysdeps/x86_64/fpu/multiarch/Makefile b/sysdeps/x86_64/fpu/multiarch/Makefile
index 74da4cd4fe..61759b8d0b 100644
--- a/sysdeps/x86_64/fpu/multiarch/Makefile
+++ b/sysdeps/x86_64/fpu/multiarch/Makefile
@@ -57,5 +57,6 @@ libmvec-sysdep_routines += svml_d_cos2_core_sse4 svml_d_cos4_core_avx2 \
 			   svml_d_cos8_core_avx512 svml_d_sin2_core_sse4 \
 			   svml_d_sin4_core_avx2 svml_d_sin8_core_avx512 \
 			   svml_s_cosf4_core_sse4 svml_s_cosf8_core_avx2 \
-			   svml_s_cosf16_core_avx512
+			   svml_s_cosf16_core_avx512 svml_s_sinf4_core_sse4 \
+			   svml_s_sinf8_core_avx2 svml_s_sinf16_core_avx512
 endif
diff --git a/sysdeps/x86_64/fpu/multiarch/svml_s_sinf16_core.S b/sysdeps/x86_64/fpu/multiarch/svml_s_sinf16_core.S
new file mode 100644
index 0000000000..7ed637b8e6
--- /dev/null
+++ b/sysdeps/x86_64/fpu/multiarch/svml_s_sinf16_core.S
@@ -0,0 +1,39 @@
+/* Multiple versions of vectorized sinf.
+   Copyright (C) 2014-2015 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 <init-arch.h>
+
+	.text
+ENTRY (_ZGVeN16v_sinf)
+        .type   _ZGVeN16v_sinf, @gnu_indirect_function
+        cmpl    $0, KIND_OFFSET+__cpu_features(%rip)
+        jne     1
+        call    __init_cpu_features
+1:      leaq    _ZGVeN16v_sinf_skx(%rip), %rax
+        testl   $bit_AVX512DQ_Usable, __cpu_features+FEATURE_OFFSET+index_AVX512DQ_Usable(%rip)
+        jnz     3
+2:      leaq    _ZGVeN16v_sinf_knl(%rip), %rax
+        testl   $bit_AVX512F_Usable, __cpu_features+FEATURE_OFFSET+index_AVX512F_Usable(%rip)
+        jnz     3
+        leaq    _ZGVeN16v_sinf_avx2_wrapper(%rip), %rax
+3:      ret
+END (_ZGVeN16v_sinf)
+
+#define _ZGVeN16v_sinf _ZGVeN16v_sinf_avx2_wrapper
+#include "../svml_s_sinf16_core.S"
diff --git a/sysdeps/x86_64/fpu/multiarch/svml_s_sinf16_core_avx512.S b/sysdeps/x86_64/fpu/multiarch/svml_s_sinf16_core_avx512.S
new file mode 100644
index 0000000000..717267e76c
--- /dev/null
+++ b/sysdeps/x86_64/fpu/multiarch/svml_s_sinf16_core_avx512.S
@@ -0,0 +1,479 @@
+/* Function sinf vectorized with AVX-512. KNL and SKX versions.
+   Copyright (C) 2014-2015 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_s_sinf_data.h"
+#include "svml_s_wrapper_impl.h"
+
+	.text
+ENTRY(_ZGVeN16v_sinf_knl)
+#ifndef HAVE_AVX512_ASM_SUPPORT
+WRAPPER_IMPL_AVX512 _ZGVdN8v_sinf
+#else
+/*
+   ALGORITHM DESCRIPTION:
+
+   1) Range reduction to [-Pi/2; +Pi/2] interval
+      a) Grab sign from source argument and save it.
+      b) Remove sign using AND operation
+      c) Getting octant Y by 1/Pi multiplication
+      d) Add "Right Shifter" value
+      e) Treat obtained value as integer for destination sign setting.
+         Shift first bit of this value to the last (sign) position
+      f) Change destination sign if source sign is negative
+         using XOR operation.
+      g) Subtract "Right Shifter" value
+      h) Subtract Y*PI from X argument, where PI divided to 4 parts:
+         X = X - Y*PI1 - Y*PI2 - Y*PI3 - Y*PI4;
+   2) Polynomial (minimax for sin within [-Pi/2; +Pi/2] interval)
+      a) Calculate X^2 = X * X
+      b) Calculate polynomial:
+         R = X + X * X^2 * (A3 + x^2 * (A5 + ......
+   3) Destination sign setting
+      a) Set shifted destination sign using XOR operation:
+         R = XOR( R, S );
+ */
+        pushq     %rbp
+        cfi_adjust_cfa_offset (8)
+        cfi_rel_offset (%rbp, 0)
+        movq      %rsp, %rbp
+        cfi_def_cfa_register (%rbp)
+        andq      $-64, %rsp
+        subq      $1280, %rsp
+        movq      __svml_ssin_data@GOTPCREL(%rip), %rax
+
+/* Check for large and special values */
+        movl      $-1, %edx
+        vmovups __sAbsMask(%rax), %zmm4
+        vmovups __sInvPI(%rax), %zmm1
+
+/* b) Remove sign using AND operation */
+        vpandd    %zmm4, %zmm0, %zmm12
+        vmovups __sPI1_FMA(%rax), %zmm2
+        vmovups __sA9(%rax), %zmm7
+
+/*
+  f) Change destination sign if source sign is negative
+  using XOR operation.
+ */
+        vpandnd   %zmm0, %zmm4, %zmm11
+
+/*
+  h) Subtract Y*PI from X argument, where PI divided to 4 parts:
+  X = X - Y*PI1 - Y*PI2 - Y*PI3;
+ */
+        vmovaps   %zmm12, %zmm3
+
+/*
+  c) Getting octant Y by 1/Pi multiplication
+  d) Add "Right Shifter" value
+ */
+        vfmadd213ps __sRShifter(%rax), %zmm12, %zmm1
+        vcmpps    $22, __sRangeReductionVal(%rax), %zmm12, %k1
+        vpbroadcastd %edx, %zmm13{%k1}{z}
+
+/* g) Subtract "Right Shifter" value */
+        vsubps __sRShifter(%rax), %zmm1, %zmm5
+
+/*
+  e) Treat obtained value as integer for destination sign setting.
+  Shift first bit of this value to the last (sign) position
+ */
+        vpslld    $31, %zmm1, %zmm6
+        vptestmd  %zmm13, %zmm13, %k0
+        vfnmadd231ps %zmm5, %zmm2, %zmm3
+        kmovw     %k0, %ecx
+        vfnmadd231ps __sPI2_FMA(%rax), %zmm5, %zmm3
+        vfnmadd132ps __sPI3_FMA(%rax), %zmm3, %zmm5
+
+/*
+  2) Polynomial (minimax for sin within [-Pi/2; +Pi/2] interval)
+  a) Calculate X^2 = X * X
+  b) Calculate polynomial:
+  R = X + X * X^2 * (A3 + x^2 * (A5 + ......
+ */
+        vmulps    %zmm5, %zmm5, %zmm8
+        vpxord    %zmm6, %zmm5, %zmm9
+        vfmadd213ps __sA7(%rax), %zmm8, %zmm7
+        vfmadd213ps __sA5(%rax), %zmm8, %zmm7
+        vfmadd213ps __sA3(%rax), %zmm8, %zmm7
+        vmulps    %zmm8, %zmm7, %zmm10
+        vfmadd213ps %zmm9, %zmm9, %zmm10
+
+/*
+  3) Destination sign setting
+  a) Set shifted destination sign using XOR operation:
+  R = XOR( R, S );
+ */
+        vpxord    %zmm11, %zmm10, %zmm1
+        testl     %ecx, %ecx
+        jne       .LBL_1_3
+
+.LBL_1_2:
+        cfi_remember_state
+        vmovaps   %zmm1, %zmm0
+        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
+        vmovups   %zmm0, 1152(%rsp)
+        vmovups   %zmm1, 1216(%rsp)
+        je        .LBL_1_2
+
+        xorb      %dl, %dl
+        kmovw     %k4, 1048(%rsp)
+        xorl      %eax, %eax
+        kmovw     %k5, 1040(%rsp)
+        kmovw     %k6, 1032(%rsp)
+        kmovw     %k7, 1024(%rsp)
+        vmovups   %zmm16, 960(%rsp)
+        vmovups   %zmm17, 896(%rsp)
+        vmovups   %zmm18, 832(%rsp)
+        vmovups   %zmm19, 768(%rsp)
+        vmovups   %zmm20, 704(%rsp)
+        vmovups   %zmm21, 640(%rsp)
+        vmovups   %zmm22, 576(%rsp)
+        vmovups   %zmm23, 512(%rsp)
+        vmovups   %zmm24, 448(%rsp)
+        vmovups   %zmm25, 384(%rsp)
+        vmovups   %zmm26, 320(%rsp)
+        vmovups   %zmm27, 256(%rsp)
+        vmovups   %zmm28, 192(%rsp)
+        vmovups   %zmm29, 128(%rsp)
+        vmovups   %zmm30, 64(%rsp)
+        vmovups   %zmm31, (%rsp)
+        movq      %rsi, 1064(%rsp)
+        movq      %rdi, 1056(%rsp)
+        movq      %r12, 1096(%rsp)
+        cfi_offset_rel_rsp (12, 1096)
+        movb      %dl, %r12b
+        movq      %r13, 1088(%rsp)
+        cfi_offset_rel_rsp (13, 1088)
+        movl      %ecx, %r13d
+        movq      %r14, 1080(%rsp)
+        cfi_offset_rel_rsp (14, 1080)
+        movl      %eax, %r14d
+        movq      %r15, 1072(%rsp)
+        cfi_offset_rel_rsp (15, 1072)
+        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:
+        addb      $1, %r12b
+        addl      $2, %r14d
+        cmpb      $16, %r12b
+        jb        .LBL_1_6
+
+        kmovw     1048(%rsp), %k4
+        movq      1064(%rsp), %rsi
+        kmovw     1040(%rsp), %k5
+        movq      1056(%rsp), %rdi
+        kmovw     1032(%rsp), %k6
+        movq      1096(%rsp), %r12
+        cfi_restore (%r12)
+        movq      1088(%rsp), %r13
+        cfi_restore (%r13)
+        kmovw     1024(%rsp), %k7
+        vmovups   960(%rsp), %zmm16
+        vmovups   896(%rsp), %zmm17
+        vmovups   832(%rsp), %zmm18
+        vmovups   768(%rsp), %zmm19
+        vmovups   704(%rsp), %zmm20
+        vmovups   640(%rsp), %zmm21
+        vmovups   576(%rsp), %zmm22
+        vmovups   512(%rsp), %zmm23
+        vmovups   448(%rsp), %zmm24
+        vmovups   384(%rsp), %zmm25
+        vmovups   320(%rsp), %zmm26
+        vmovups   256(%rsp), %zmm27
+        vmovups   192(%rsp), %zmm28
+        vmovups   128(%rsp), %zmm29
+        vmovups   64(%rsp), %zmm30
+        vmovups   (%rsp), %zmm31
+        movq      1080(%rsp), %r14
+        cfi_restore (%r14)
+        movq      1072(%rsp), %r15
+        cfi_restore (%r15)
+        vmovups   1216(%rsp), %zmm1
+        jmp       .LBL_1_2
+
+.LBL_1_10:
+        cfi_restore_state
+        movzbl    %r12b, %r15d
+        vmovss    1156(%rsp,%r15,8), %xmm0
+        call      sinf@PLT
+        vmovss    %xmm0, 1220(%rsp,%r15,8)
+        jmp       .LBL_1_8
+
+.LBL_1_12:
+        movzbl    %r12b, %r15d
+        vmovss    1152(%rsp,%r15,8), %xmm0
+        call      sinf@PLT
+        vmovss    %xmm0, 1216(%rsp,%r15,8)
+        jmp       .LBL_1_7
+#endif
+END(_ZGVeN16v_sinf_knl)
+
+ENTRY (_ZGVeN16v_sinf_skx)
+#ifndef HAVE_AVX512_ASM_SUPPORT
+WRAPPER_IMPL_AVX512 _ZGVdN8v_sinf
+#else
+/*
+   ALGORITHM DESCRIPTION:
+
+   1) Range reduction to [-Pi/2; +Pi/2] interval
+      a) Grab sign from source argument and save it.
+      b) Remove sign using AND operation
+      c) Getting octant Y by 1/Pi multiplication
+      d) Add "Right Shifter" value
+      e) Treat obtained value as integer for destination sign setting.
+         Shift first bit of this value to the last (sign) position
+      f) Change destination sign if source sign is negative
+         using XOR operation.
+      g) Subtract "Right Shifter" value
+      h) Subtract Y*PI from X argument, where PI divided to 4 parts:
+         X = X - Y*PI1 - Y*PI2 - Y*PI3 - Y*PI4;
+   2) Polynomial (minimax for sin within [-Pi/2; +Pi/2] interval)
+      a) Calculate X^2 = X * X
+      b) Calculate polynomial:
+         R = X + X * X^2 * (A3 + x^2 * (A5 + ......
+   3) Destination sign setting
+      a) Set shifted destination sign using XOR operation:
+         R = XOR( R, S );
+  */
+
+        pushq     %rbp
+        cfi_adjust_cfa_offset (8)
+        cfi_rel_offset (%rbp, 0)
+        movq      %rsp, %rbp
+        cfi_def_cfa_register (%rbp)
+        andq      $-64, %rsp
+        subq      $1280, %rsp
+        movq      __svml_ssin_data@GOTPCREL(%rip), %rax
+
+/* Check for large and special values */
+        vmovups   .L_2il0floatpacket.11(%rip), %zmm14
+        vmovups __sAbsMask(%rax), %zmm5
+        vmovups __sInvPI(%rax), %zmm1
+        vmovups __sRShifter(%rax), %zmm2
+        vmovups __sPI1_FMA(%rax), %zmm3
+        vmovups __sA9(%rax), %zmm8
+
+/* b) Remove sign using AND operation */
+        vandps    %zmm5, %zmm0, %zmm13
+
+/*
+  f) Change destination sign if source sign is negative
+  using XOR operation.
+ */
+        vandnps   %zmm0, %zmm5, %zmm12
+
+/*
+  c) Getting octant Y by 1/Pi multiplication
+  d) Add "Right Shifter" value
+ */
+        vfmadd213ps %zmm2, %zmm13, %zmm1
+        vcmpps    $18, __sRangeReductionVal(%rax), %zmm13, %k1
+
+/*
+  e) Treat obtained value as integer for destination sign setting.
+  Shift first bit of this value to the last (sign) position
+ */
+        vpslld    $31, %zmm1, %zmm7
+
+/* g) Subtract "Right Shifter" value */
+        vsubps    %zmm2, %zmm1, %zmm6
+
+/*
+  h) Subtract Y*PI from X argument, where PI divided to 4 parts:
+  X = X - Y*PI1 - Y*PI2 - Y*PI3;
+ */
+        vmovaps   %zmm13, %zmm4
+        vfnmadd231ps %zmm6, %zmm3, %zmm4
+        vfnmadd231ps __sPI2_FMA(%rax), %zmm6, %zmm4
+        vfnmadd132ps __sPI3_FMA(%rax), %zmm4, %zmm6
+
+/*
+  2) Polynomial (minimax for sin within [-Pi/2; +Pi/2] interval)
+  a) Calculate X^2 = X * X
+  b) Calculate polynomial:
+  R = X + X * X^2 * (A3 + x^2 * (A5 + ......
+ */
+        vmulps    %zmm6, %zmm6, %zmm9
+        vxorps    %zmm7, %zmm6, %zmm10
+        vfmadd213ps __sA7(%rax), %zmm9, %zmm8
+        vfmadd213ps __sA5(%rax), %zmm9, %zmm8
+        vfmadd213ps __sA3(%rax), %zmm9, %zmm8
+        vmulps    %zmm9, %zmm8, %zmm11
+        vfmadd213ps %zmm10, %zmm10, %zmm11
+
+/*
+  3) Destination sign setting
+  a) Set shifted destination sign using XOR operation:
+  R = XOR( R, S );
+ */
+        vxorps    %zmm12, %zmm11, %zmm1
+        vpandnd   %zmm13, %zmm13, %zmm14{%k1}
+        vptestmd  %zmm14, %zmm14, %k0
+        kmovw     %k0, %ecx
+        testl     %ecx, %ecx
+        jne       .LBL_2_3
+
+.LBL_2_2:
+        cfi_remember_state
+        vmovaps   %zmm1, %zmm0
+        movq      %rbp, %rsp
+        cfi_def_cfa_register (%rsp)
+        popq      %rbp
+        cfi_adjust_cfa_offset (-8)
+        cfi_restore (%rbp)
+        ret
+
+.LBL_2_3:
+        cfi_restore_state
+        vmovups   %zmm0, 1152(%rsp)
+        vmovups   %zmm1, 1216(%rsp)
+        je        .LBL_2_2
+
+        xorb      %dl, %dl
+        xorl      %eax, %eax
+        kmovw     %k4, 1048(%rsp)
+        kmovw     %k5, 1040(%rsp)
+        kmovw     %k6, 1032(%rsp)
+        kmovw     %k7, 1024(%rsp)
+        vmovups   %zmm16, 960(%rsp)
+        vmovups   %zmm17, 896(%rsp)
+        vmovups   %zmm18, 832(%rsp)
+        vmovups   %zmm19, 768(%rsp)
+        vmovups   %zmm20, 704(%rsp)
+        vmovups   %zmm21, 640(%rsp)
+        vmovups   %zmm22, 576(%rsp)
+        vmovups   %zmm23, 512(%rsp)
+        vmovups   %zmm24, 448(%rsp)
+        vmovups   %zmm25, 384(%rsp)
+        vmovups   %zmm26, 320(%rsp)
+        vmovups   %zmm27, 256(%rsp)
+        vmovups   %zmm28, 192(%rsp)
+        vmovups   %zmm29, 128(%rsp)
+        vmovups   %zmm30, 64(%rsp)
+        vmovups   %zmm31, (%rsp)
+        movq      %rsi, 1064(%rsp)
+        movq      %rdi, 1056(%rsp)
+        movq      %r12, 1096(%rsp)
+        cfi_offset_rel_rsp (12, 1096)
+        movb      %dl, %r12b
+        movq      %r13, 1088(%rsp)
+        cfi_offset_rel_rsp (13, 1088)
+        movl      %ecx, %r13d
+        movq      %r14, 1080(%rsp)
+        cfi_offset_rel_rsp (14, 1080)
+        movl      %eax, %r14d
+        movq      %r15, 1072(%rsp)
+        cfi_offset_rel_rsp (15, 1072)
+        cfi_remember_state
+
+.LBL_2_6:
+        btl       %r14d, %r13d
+        jc        .LBL_2_12
+
+.LBL_2_7:
+        lea       1(%r14), %esi
+        btl       %esi, %r13d
+        jc        .LBL_2_10
+
+.LBL_2_8:
+        incb      %r12b
+        addl      $2, %r14d
+        cmpb      $16, %r12b
+        jb        .LBL_2_6
+
+        kmovw     1048(%rsp), %k4
+        kmovw     1040(%rsp), %k5
+        kmovw     1032(%rsp), %k6
+        kmovw     1024(%rsp), %k7
+        vmovups   960(%rsp), %zmm16
+        vmovups   896(%rsp), %zmm17
+        vmovups   832(%rsp), %zmm18
+        vmovups   768(%rsp), %zmm19
+        vmovups   704(%rsp), %zmm20
+        vmovups   640(%rsp), %zmm21
+        vmovups   576(%rsp), %zmm22
+        vmovups   512(%rsp), %zmm23
+        vmovups   448(%rsp), %zmm24
+        vmovups   384(%rsp), %zmm25
+        vmovups   320(%rsp), %zmm26
+        vmovups   256(%rsp), %zmm27
+        vmovups   192(%rsp), %zmm28
+        vmovups   128(%rsp), %zmm29
+        vmovups   64(%rsp), %zmm30
+        vmovups   (%rsp), %zmm31
+        vmovups   1216(%rsp), %zmm1
+        movq      1064(%rsp), %rsi
+        movq      1056(%rsp), %rdi
+        movq      1096(%rsp), %r12
+        cfi_restore (%r12)
+        movq      1088(%rsp), %r13
+        cfi_restore (%r13)
+        movq      1080(%rsp), %r14
+        cfi_restore (%r14)
+        movq      1072(%rsp), %r15
+        cfi_restore (%r15)
+        jmp       .LBL_2_2
+
+.LBL_2_10:
+        cfi_restore_state
+        movzbl    %r12b, %r15d
+        vmovss    1156(%rsp,%r15,8), %xmm0
+        vzeroupper
+        vmovss    1156(%rsp,%r15,8), %xmm0
+
+        call      sinf@PLT
+
+        vmovss    %xmm0, 1220(%rsp,%r15,8)
+        jmp       .LBL_2_8
+
+.LBL_2_12:
+        movzbl    %r12b, %r15d
+        vmovss    1152(%rsp,%r15,8), %xmm0
+        vzeroupper
+        vmovss    1152(%rsp,%r15,8), %xmm0
+
+        call      sinf@PLT
+
+        vmovss    %xmm0, 1216(%rsp,%r15,8)
+        jmp       .LBL_2_7
+#endif
+END (_ZGVeN16v_sinf_skx)
+
+	.section .rodata, "a"
+.L_2il0floatpacket.11:
+	.long	0xffffffff,0xffffffff,0xffffffff,0xffffffff,0xffffffff,0xffffffff,0xffffffff,0xffffffff,0xffffffff,0xffffffff,0xffffffff,0xffffffff,0xffffffff,0xffffffff,0xffffffff,0xffffffff
+	.type	.L_2il0floatpacket.11,@object
diff --git a/sysdeps/x86_64/fpu/multiarch/svml_s_sinf4_core.S b/sysdeps/x86_64/fpu/multiarch/svml_s_sinf4_core.S
new file mode 100644
index 0000000000..cf1e4df406
--- /dev/null
+++ b/sysdeps/x86_64/fpu/multiarch/svml_s_sinf4_core.S
@@ -0,0 +1,38 @@
+/* Multiple versions of vectorized sinf.
+   Copyright (C) 2014-2015 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 <init-arch.h>
+
+	.text
+ENTRY (_ZGVbN4v_sinf)
+        .type   _ZGVbN4v_sinf, @gnu_indirect_function
+        cmpl    $0, KIND_OFFSET+__cpu_features(%rip)
+        jne     1f
+        call    __init_cpu_features
+1:      leaq    _ZGVbN4v_sinf_sse4(%rip), %rax
+        testl   $bit_SSE4_1, __cpu_features+CPUID_OFFSET+index_SSE4_1(%rip)
+        jz      2f
+        ret
+2:      leaq    _ZGVbN4v_sinf_sse2(%rip), %rax
+        ret
+END (_ZGVbN4v_sinf)
+libmvec_hidden_def (_ZGVbN4v_sinf)
+
+#define _ZGVbN4v_sinf _ZGVbN4v_sinf_sse2
+#include "../svml_s_sinf4_core.S"
diff --git a/sysdeps/x86_64/fpu/multiarch/svml_s_sinf4_core_sse4.S b/sysdeps/x86_64/fpu/multiarch/svml_s_sinf4_core_sse4.S
new file mode 100644
index 0000000000..746e3efb2b
--- /dev/null
+++ b/sysdeps/x86_64/fpu/multiarch/svml_s_sinf4_core_sse4.S
@@ -0,0 +1,224 @@
+/* Function sinf vectorized with SSE4.
+   Copyright (C) 2014-2015 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_s_sinf_data.h"
+
+	.text
+ENTRY(_ZGVbN4v_sinf_sse4)
+/*
+   ALGORITHM DESCRIPTION:
+
+   1) Range reduction to [-Pi/2; +Pi/2] interval
+      a) Grab sign from source argument and save it.
+      b) Remove sign using AND operation
+      c) Getting octant Y by 1/Pi multiplication
+      d) Add "Right Shifter" value
+      e) Treat obtained value as integer for destination sign setting.
+         Shift first bit of this value to the last (sign) position
+      f) Change destination sign if source sign is negative
+         using XOR operation.
+      g) Subtract "Right Shifter" value
+      h) Subtract Y*PI from X argument, where PI divided to 4 parts:
+         X = X - Y*PI1 - Y*PI2 - Y*PI3 - Y*PI4;
+   2) Polynomial (minimax for sin within [-Pi/2; +Pi/2] interval)
+      a) Calculate X^2 = X * X
+      b) Calculate polynomial:
+         R = X + X * X^2 * (A3 + x^2 * (A5 + ......
+   3) Destination sign setting
+      a) Set shifted destination sign using XOR operation:
+         R = XOR( R, S );
+ */
+        pushq     %rbp
+        cfi_adjust_cfa_offset (8)
+        cfi_rel_offset (%rbp, 0)
+        movq      %rsp, %rbp
+        cfi_def_cfa_register (%rbp)
+        andq      $-64, %rsp
+        subq      $320, %rsp
+        movaps    %xmm0, %xmm5
+        movq      __svml_ssin_data@GOTPCREL(%rip), %rax
+        movups    __sAbsMask(%rax), %xmm2
+
+/* b) Remove sign using AND operation */
+        movaps    %xmm2, %xmm4
+
+/*
+  f) Change destination sign if source sign is negative
+  using XOR operation.
+ */
+        andnps    %xmm5, %xmm2
+        movups    __sInvPI(%rax), %xmm1
+        andps     %xmm5, %xmm4
+
+/* c) Getting octant Y by 1/Pi multiplication
+   d) Add "Right Shifter" value  */
+        mulps     %xmm4, %xmm1
+
+/* h) Subtract Y*PI from X argument, where PI divided to 4 parts:
+   X = X - Y*PI1 - Y*PI2 - Y*PI3 - Y*PI4  */
+        movaps    %xmm4, %xmm0
+
+/* Check for large and special values */
+        cmpnleps  __sRangeReductionVal(%rax), %xmm4
+        movups    __sRShifter(%rax), %xmm6
+        movups    __sPI1(%rax), %xmm7
+        addps     %xmm6, %xmm1
+        movmskps  %xmm4, %ecx
+
+/* e) Treat obtained value as integer for destination sign setting.
+   Shift first bit of this value to the last (sign) position  */
+        movaps    %xmm1, %xmm3
+
+/* g) Subtract "Right Shifter" value */
+        subps     %xmm6, %xmm1
+        mulps     %xmm1, %xmm7
+        pslld     $31, %xmm3
+        movups    __sPI2(%rax), %xmm6
+        subps     %xmm7, %xmm0
+        mulps     %xmm1, %xmm6
+        movups    __sPI3(%rax), %xmm7
+        subps     %xmm6, %xmm0
+        mulps     %xmm1, %xmm7
+        movups    __sPI4(%rax), %xmm6
+        subps     %xmm7, %xmm0
+        mulps     %xmm6, %xmm1
+        subps     %xmm1, %xmm0
+
+/* 2) Polynomial (minimax for sin within [-Pi/2; +Pi/2] interval)
+   a) Calculate X^2 = X * X
+   b) Calculate polynomial:
+   R = X + X * X^2 * (A3 + x^2 * (A5 + ...... */
+        movaps    %xmm0, %xmm1
+        mulps     %xmm0, %xmm1
+        xorps     %xmm3, %xmm0
+        movups    __sA9(%rax), %xmm3
+        mulps     %xmm1, %xmm3
+        addps     __sA7(%rax), %xmm3
+        mulps     %xmm1, %xmm3
+        addps     __sA5(%rax), %xmm3
+        mulps     %xmm1, %xmm3
+        addps     __sA3(%rax), %xmm3
+        mulps     %xmm3, %xmm1
+        mulps     %xmm0, %xmm1
+        addps     %xmm1, %xmm0
+
+/* 3) Destination sign setting
+   a) Set shifted destination sign using XOR operation:
+   R = XOR( R, S ); */
+        xorps     %xmm2, %xmm0
+        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
+        movups    %xmm5, 192(%rsp)
+        movups    %xmm0, 256(%rsp)
+        je        .LBL_1_2
+
+        xorb      %dl, %dl
+        xorl      %eax, %eax
+        movups    %xmm8, 112(%rsp)
+        movups    %xmm9, 96(%rsp)
+        movups    %xmm10, 80(%rsp)
+        movups    %xmm11, 64(%rsp)
+        movups    %xmm12, 48(%rsp)
+        movups    %xmm13, 32(%rsp)
+        movups    %xmm14, 16(%rsp)
+        movups    %xmm15, (%rsp)
+        movq      %rsi, 136(%rsp)
+        movq      %rdi, 128(%rsp)
+        movq      %r12, 168(%rsp)
+        cfi_offset_rel_rsp (12, 168)
+        movb      %dl, %r12b
+        movq      %r13, 160(%rsp)
+        cfi_offset_rel_rsp (13, 160)
+        movl      %ecx, %r13d
+        movq      %r14, 152(%rsp)
+        cfi_offset_rel_rsp (14, 152)
+        movl      %eax, %r14d
+        movq      %r15, 144(%rsp)
+        cfi_offset_rel_rsp (15, 144)
+        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
+
+        movups    112(%rsp), %xmm8
+        movups    96(%rsp), %xmm9
+        movups    80(%rsp), %xmm10
+        movups    64(%rsp), %xmm11
+        movups    48(%rsp), %xmm12
+        movups    32(%rsp), %xmm13
+        movups    16(%rsp), %xmm14
+        movups    (%rsp), %xmm15
+        movq      136(%rsp), %rsi
+        movq      128(%rsp), %rdi
+        movq      168(%rsp), %r12
+        cfi_restore (%r12)
+        movq      160(%rsp), %r13
+        cfi_restore (%r13)
+        movq      152(%rsp), %r14
+        cfi_restore (%r14)
+        movq      144(%rsp), %r15
+        cfi_restore (%r15)
+        movups    256(%rsp), %xmm0
+        jmp       .LBL_1_2
+
+.LBL_1_10:
+        cfi_restore_state
+        movzbl    %r12b, %r15d
+        movss     196(%rsp,%r15,8), %xmm0
+
+        call      sinf@PLT
+
+        movss     %xmm0, 260(%rsp,%r15,8)
+        jmp       .LBL_1_8
+
+.LBL_1_12:
+        movzbl    %r12b, %r15d
+        movss     192(%rsp,%r15,8), %xmm0
+
+        call      sinf@PLT
+
+        movss     %xmm0, 256(%rsp,%r15,8)
+        jmp       .LBL_1_7
+
+END(_ZGVbN4v_sinf_sse4)
diff --git a/sysdeps/x86_64/fpu/multiarch/svml_s_sinf8_core.S b/sysdeps/x86_64/fpu/multiarch/svml_s_sinf8_core.S
new file mode 100644
index 0000000000..b28bf3cabc
--- /dev/null
+++ b/sysdeps/x86_64/fpu/multiarch/svml_s_sinf8_core.S
@@ -0,0 +1,38 @@
+/* Multiple versions of vectorized sinf, vector length is 8.
+   Copyright (C) 2014-2015 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 <init-arch.h>
+
+	.text
+ENTRY (_ZGVdN8v_sinf)
+        .type   _ZGVdN8v_sinf, @gnu_indirect_function
+        cmpl    $0, KIND_OFFSET+__cpu_features(%rip)
+        jne     1f
+        call    __init_cpu_features
+1:      leaq    _ZGVdN8v_sinf_avx2(%rip), %rax
+        testl   $bit_AVX2_Usable, __cpu_features+FEATURE_OFFSET+index_AVX2_Usable(%rip)
+        jz      2f
+        ret
+2:      leaq    _ZGVdN8v_sinf_sse_wrapper(%rip), %rax
+        ret
+END (_ZGVdN8v_sinf)
+libmvec_hidden_def (_ZGVdN8v_sinf)
+
+#define _ZGVdN8v_sinf _ZGVdN8v_sinf_sse_wrapper
+#include "../svml_s_sinf8_core.S"
diff --git a/sysdeps/x86_64/fpu/multiarch/svml_s_sinf8_core_avx2.S b/sysdeps/x86_64/fpu/multiarch/svml_s_sinf8_core_avx2.S
new file mode 100644
index 0000000000..aea4cdd5c0
--- /dev/null
+++ b/sysdeps/x86_64/fpu/multiarch/svml_s_sinf8_core_avx2.S
@@ -0,0 +1,219 @@
+/* Function sinf vectorized with AVX2.
+   Copyright (C) 2014-2015 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_s_sinf_data.h"
+
+	.text
+ENTRY(_ZGVdN8v_sinf_avx2)
+/*
+   ALGORITHM DESCRIPTION:
+
+   1) Range reduction to [-Pi/2; +Pi/2] interval
+      a) Grab sign from source argument and save it.
+      b) Remove sign using AND operation
+      c) Getting octant Y by 1/Pi multiplication
+      d) Add "Right Shifter" value
+      e) Treat obtained value as integer for destination sign setting.
+         Shift first bit of this value to the last (sign) position
+      f) Change destination sign if source sign is negative
+         using XOR operation.
+      g) Subtract "Right Shifter" value
+      h) Subtract Y*PI from X argument, where PI divided to 4 parts:
+         X = X - Y*PI1 - Y*PI2 - Y*PI3 - Y*PI4;
+   2) Polynomial (minimax for sin within [-Pi/2; +Pi/2] interval)
+      a) Calculate X^2 = X * X
+      b) Calculate polynomial:
+         R = X + X * X^2 * (A3 + x^2 * (A5 + ......
+   3) Destination sign setting
+      a) Set shifted destination sign using XOR operation:
+         R = XOR( R, S );
+ */
+        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_ssin_data@GOTPCREL(%rip), %rax
+        vmovdqa   %ymm0, %ymm5
+        vmovups __sAbsMask(%rax), %ymm3
+        vmovups __sInvPI(%rax), %ymm7
+        vmovups __sRShifter(%rax), %ymm0
+        vmovups __sPI1_FMA(%rax), %ymm1
+
+/* b) Remove sign using AND operation */
+        vandps    %ymm3, %ymm5, %ymm4
+
+/*
+  c) Getting octant Y by 1/Pi multiplication
+  d) Add "Right Shifter" value
+ */
+        vfmadd213ps %ymm0, %ymm4, %ymm7
+
+/* g) Subtract "Right Shifter" value */
+        vsubps    %ymm0, %ymm7, %ymm2
+
+/*
+  e) Treat obtained value as integer for destination sign setting.
+  Shift first bit of this value to the last (sign) position
+ */
+        vpslld    $31, %ymm7, %ymm6
+
+/*
+  h) Subtract Y*PI from X argument, where PI divided to 4 parts:
+  X = X - Y*PI1 - Y*PI2 - Y*PI3;
+ */
+        vmovdqa   %ymm4, %ymm0
+        vfnmadd231ps %ymm2, %ymm1, %ymm0
+
+/* Check for large and special values */
+        vcmpnle_uqps __sRangeReductionVal(%rax), %ymm4, %ymm4
+        vfnmadd231ps __sPI2_FMA(%rax), %ymm2, %ymm0
+        vfnmadd132ps __sPI3_FMA(%rax), %ymm0, %ymm2
+
+/*
+  2) Polynomial (minimax for sin within [-Pi/2; +Pi/2] interval)
+  a) Calculate X^2 = X * X
+  b) Calculate polynomial:
+  R = X + X * X^2 * (A3 + x^2 * (A5 + ......
+ */
+        vmulps    %ymm2, %ymm2, %ymm1
+
+/*
+  f) Change destination sign if source sign is negative
+  using XOR operation.
+ */
+        vandnps   %ymm5, %ymm3, %ymm0
+        vxorps    %ymm6, %ymm2, %ymm3
+        vmovups __sA9(%rax), %ymm2
+        vfmadd213ps __sA7(%rax), %ymm1, %ymm2
+        vfmadd213ps __sA5(%rax), %ymm1, %ymm2
+        vfmadd213ps __sA3(%rax), %ymm1, %ymm2
+        vmulps    %ymm1, %ymm2, %ymm6
+        vfmadd213ps %ymm3, %ymm3, %ymm6
+        vmovmskps %ymm4, %ecx
+
+/*
+  3) Destination sign setting
+  a) Set shifted destination sign using XOR operation:
+  R = XOR( R, S );
+ */
+        vxorps    %ymm0, %ymm6, %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
+        vmovups   %ymm5, 320(%rsp)
+        vmovups   %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
+        vmovups   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
+        vmovss    324(%rsp,%r15,8), %xmm0
+        vzeroupper
+
+        call      sinf@PLT
+
+        vmovss    %xmm0, 388(%rsp,%r15,8)
+        jmp       .LBL_1_8
+
+.LBL_1_12:
+        movzbl    %r12b, %r15d
+        vmovss    320(%rsp,%r15,8), %xmm0
+        vzeroupper
+
+        call      sinf@PLT
+
+        vmovss    %xmm0, 384(%rsp,%r15,8)
+        jmp       .LBL_1_7
+
+END(_ZGVdN8v_sinf_avx2)