Fixed wrong vector sincos/sincosf ABI to have it compatible with

current vector function declaration "#pragma omp declare simd notinbranch",
according to which vector sincos should have vector of pointers for second and
third parameters. It is fixed with implementation as wrapper to version
having second and third parameters as pointers.

    [BZ #20024]
    * sysdeps/x86/fpu/test-math-vector-sincos.h: New.
    * sysdeps/x86_64/fpu/multiarch/svml_d_sincos2_core_sse4.S: Fixed ABI
    of this implementation of vector function.
    * sysdeps/x86_64/fpu/multiarch/svml_d_sincos4_core_avx2.S: Likewise.
    * sysdeps/x86_64/fpu/multiarch/svml_d_sincos8_core_avx512.S: Likewise.
    * sysdeps/x86_64/fpu/multiarch/svml_s_sincosf16_core_avx512.S:
    Likewise.
    * sysdeps/x86_64/fpu/multiarch/svml_s_sincosf4_core_sse4.S: Likewise.
    * sysdeps/x86_64/fpu/multiarch/svml_s_sincosf8_core_avx2.S: Likewise.
    * sysdeps/x86_64/fpu/svml_d_sincos2_core.S: Likewise.
    * sysdeps/x86_64/fpu/svml_d_sincos4_core.S: Likewise.
    * sysdeps/x86_64/fpu/svml_d_sincos4_core_avx.S: Likewise.
    * sysdeps/x86_64/fpu/svml_d_sincos8_core.S: Likewise.
    * sysdeps/x86_64/fpu/svml_s_sincosf16_core.S: Likewise.
    * sysdeps/x86_64/fpu/svml_s_sincosf4_core.S: Likewise.
    * sysdeps/x86_64/fpu/svml_s_sincosf8_core.S: Likewise.
    * sysdeps/x86_64/fpu/svml_s_sincosf8_core_avx.S: Likewise.
    * sysdeps/x86_64/fpu/test-double-vlen2-wrappers.c: Use another wrapper
    for testing vector sincos with fixed ABI.
    * sysdeps/x86_64/fpu/test-double-vlen4-avx2-wrappers.c: Likewise.
    * sysdeps/x86_64/fpu/test-double-vlen4-wrappers.c: Likewise.
    * sysdeps/x86_64/fpu/test-double-vlen8-wrappers.c: Likewise.
    * sysdeps/x86_64/fpu/test-float-vlen16-wrappers.c: Likewise.
    * sysdeps/x86_64/fpu/test-float-vlen4-wrappers.c: Likewise.
    * sysdeps/x86_64/fpu/test-float-vlen8-avx2-wrappers.c: Likewise.
    * sysdeps/x86_64/fpu/test-float-vlen8-wrappers.c: Likewise.
    * sysdeps/x86_64/fpu/test-double-libmvec-sincos-avx.c: New test.
    * sysdeps/x86_64/fpu/test-double-libmvec-sincos-avx2.c: Likewise.
    * sysdeps/x86_64/fpu/test-double-libmvec-sincos-avx512.c: Likewise.
    * sysdeps/x86_64/fpu/test-double-libmvec-sincos.c: Likewise.
    * sysdeps/x86_64/fpu/test-float-libmvec-sincosf-avx.c: Likewise.
    * sysdeps/x86_64/fpu/test-float-libmvec-sincosf-avx2.c: Likewise.
    * sysdeps/x86_64/fpu/test-float-libmvec-sincosf-avx512.c: Likewise.
    * sysdeps/x86_64/fpu/test-float-libmvec-sincosf.c: Likewise.
    * sysdeps/x86_64/fpu/Makefile: Added new tests.

1 files changed, 79 insertions, 1 deletions

diff --git a/sysdeps/x86_64/fpu/multiarch/svml_s_sincosf4_core_sse4.S b/sysdeps/x86_64/fpu/multiarch/svml_s_sincosf4_core_sse4.S
index 562367b..5e8ea8b 100644
--- a/sysdeps/x86_64/fpu/multiarch/svml_s_sincosf4_core_sse4.S
+++ b/sysdeps/x86_64/fpu/multiarch/svml_s_sincosf4_core_sse4.S
@@ -20,7 +20,7 @@
 #include "svml_s_trig_data.h"
 
 	.text
-ENTRY (_ZGVbN4vvv_sincosf_sse4)
+ENTRY (_ZGVbN4vl4l4_sincosf_sse4)
 /*
    ALGORITHM DESCRIPTION:
 
@@ -265,4 +265,82 @@ ENTRY (_ZGVbN4vvv_sincosf_sse4)
         movss     %xmm0, 256(%rsp,%r15,8)
         jmp       .LBL_1_7
 
+END (_ZGVbN4vl4l4_sincosf_sse4)
+libmvec_hidden_def(_ZGVbN4vl4l4_sincosf_sse4)
+
+/* vvv version implemented with wrapper to vl4l4 variant.  */
+ENTRY (_ZGVbN4vvv_sincosf_sse4)
+#ifndef __ILP32__
+        subq      $104, %rsp
+        .cfi_def_cfa_offset 112
+        movdqu    %xmm1, 32(%rsp)
+        lea       (%rsp), %rdi
+        movdqu    %xmm2, 48(%rdi)
+        lea       16(%rsp), %rsi
+        movdqu    %xmm3, 48(%rsi)
+        movdqu    %xmm4, 64(%rsi)
+        call      HIDDEN_JUMPTARGET(_ZGVbN4vl4l4_sincosf_sse4)
+        movq      32(%rsp), %rdx
+        movq      40(%rsp), %rsi
+        movq      48(%rsp), %r8
+        movq      56(%rsp), %r10
+        movl      (%rsp), %eax
+        movl      4(%rsp), %ecx
+        movl      8(%rsp), %edi
+        movl      12(%rsp), %r9d
+        movl      %eax, (%rdx)
+        movl      %ecx, (%rsi)
+        movq      64(%rsp), %rax
+        movq      72(%rsp), %rcx
+        movl      %edi, (%r8)
+        movl      %r9d, (%r10)
+        movq      80(%rsp), %rdi
+        movq      88(%rsp), %r9
+        movl      16(%rsp), %r11d
+        movl      20(%rsp), %edx
+        movl      24(%rsp), %esi
+        movl      28(%rsp), %r8d
+        movl      %r11d, (%rax)
+        movl      %edx, (%rcx)
+        movl      %esi, (%rdi)
+        movl      %r8d, (%r9)
+        addq      $104, %rsp
+        .cfi_def_cfa_offset 8
+        ret
+#else
+        subl    $72, %esp
+        .cfi_def_cfa_offset 80
+        leal    48(%rsp), %esi
+        movaps  %xmm1, 16(%esp)
+        leal    32(%rsp), %edi
+        movaps  %xmm2, (%esp)
+        call    HIDDEN_JUMPTARGET(_ZGVbN4vl4l4_sincosf_sse4)
+        movl    16(%esp), %eax
+        movss   32(%esp), %xmm0
+        movss   %xmm0, (%eax)
+        movl    20(%esp), %eax
+        movss   36(%esp), %xmm0
+        movss   %xmm0, (%eax)
+        movl    24(%esp), %eax
+        movss   40(%esp), %xmm0
+        movss   %xmm0, (%eax)
+        movl    28(%esp), %eax
+        movss   44(%esp), %xmm0
+        movss   %xmm0, (%eax)
+        movl    (%esp), %eax
+        movss   48(%esp), %xmm0
+        movss   %xmm0, (%eax)
+        movl    4(%esp), %eax
+        movss   52(%esp), %xmm0
+        movss   %xmm0, (%eax)
+        movl    8(%esp), %eax
+        movss   56(%esp), %xmm0
+        movss   %xmm0, (%eax)
+        movl    12(%esp), %eax
+        movss   60(%esp), %xmm0
+        movss   %xmm0, (%eax)
+        addl    $72, %esp
+        .cfi_def_cfa_offset 8
+        ret
+#endif
 END (_ZGVbN4vvv_sincosf_sse4)