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, 55 insertions, 1 deletions

diff --git a/sysdeps/x86_64/fpu/multiarch/svml_d_sincos2_core_sse4.S b/sysdeps/x86_64/fpu/multiarch/svml_d_sincos2_core_sse4.S
index d37275d7ab..6dfc61ee93 100644
--- a/sysdeps/x86_64/fpu/multiarch/svml_d_sincos2_core_sse4.S
+++ b/sysdeps/x86_64/fpu/multiarch/svml_d_sincos2_core_sse4.S
@@ -20,7 +20,7 @@
 #include "svml_d_trig_data.h"
 
 	.text
-ENTRY (_ZGVbN2vvv_sincos_sse4)
+ENTRY (_ZGVbN2vl8l8_sincos_sse4)
 /*
    ALGORITHM DESCRIPTION:
 
@@ -311,4 +311,58 @@ ENTRY (_ZGVbN2vvv_sincos_sse4)
 
         movsd     %xmm0, 256(%rsp,%r15)
         jmp       .LBL_1_7
+END (_ZGVbN2vl8l8_sincos_sse4)
+libmvec_hidden_def(_ZGVbN2vl8l8_sincos_sse4)
+
+/* vvv version implemented with wrapper to vl8l8 variant.  */
+ENTRY (_ZGVbN2vvv_sincos_sse4)
+#ifndef __ILP32__
+        subq      $72, %rsp
+        .cfi_def_cfa_offset 80
+        movdqu    %xmm1, 32(%rsp)
+        lea       (%rsp), %rdi
+        movdqu    %xmm2, 48(%rdi)
+        lea       16(%rsp), %rsi
+        call      HIDDEN_JUMPTARGET(_ZGVbN2vl8l8_sincos_sse4)
+        movq      32(%rsp), %rdx
+        movq      48(%rsp), %rsi
+        movq      40(%rsp), %r8
+        movq      56(%rsp), %r10
+        movq      (%rsp), %rax
+        movq      16(%rsp), %rcx
+        movq      8(%rsp), %rdi
+        movq      24(%rsp), %r9
+        movq      %rax, (%rdx)
+        movq      %rcx, (%rsi)
+        movq      %rdi, (%r8)
+        movq      %r9, (%r10)
+        addq      $72, %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(_ZGVbN2vl8l8_sincos_sse4)
+        movdqa  16(%esp), %xmm1
+        movsd   32(%esp), %xmm0
+        movq    %xmm1, %rax
+        movdqa  (%esp), %xmm2
+        movsd   %xmm0, (%eax)
+        movsd   40(%esp), %xmm0
+        pextrd  $1, %xmm1, %eax
+        movsd   %xmm0, (%eax)
+        movsd   48(%esp), %xmm0
+        movq    %xmm2, %rax
+        movsd   %xmm0, (%eax)
+        movsd   56(%esp), %xmm0
+        pextrd  $1, %xmm2, %eax
+        movsd   %xmm0, (%eax)
+        addl    $72, %esp
+        .cfi_def_cfa_offset 8
+        ret
+#endif
 END (_ZGVbN2vvv_sincos_sse4)