diff options
Diffstat (limited to 'sysdeps/x86_64/fpu/svml_d_sincos2_core.S')
| -rw-r--r-- | sysdeps/x86_64/fpu/svml_d_sincos2_core.S | 85 |
1 files changed, 83 insertions, 2 deletions
diff --git a/sysdeps/x86_64/fpu/svml_d_sincos2_core.S b/sysdeps/x86_64/fpu/svml_d_sincos2_core.S index 74afa0a677..ebf9e25aca 100644 --- a/sysdeps/x86_64/fpu/svml_d_sincos2_core.S +++ b/sysdeps/x86_64/fpu/svml_d_sincos2_core.S @@ -1,5 +1,5 @@ /* Function sincos vectorized with SSE2. - Copyright (C) 2014-2016 Free Software Foundation, Inc. + 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 @@ -20,8 +20,89 @@ #include "svml_d_wrapper_impl.h" .text -ENTRY (_ZGVbN2vvv_sincos) +ENTRY (_ZGVbN2vl8l8_sincos) WRAPPER_IMPL_SSE2_fFF sincos +END (_ZGVbN2vl8l8_sincos) +libmvec_hidden_def (_ZGVbN2vl8l8_sincos) + +/* SSE2 ISA version as wrapper to scalar (for vector + function declared with #pragma omp declare simd notinbranch). */ +.macro WRAPPER_IMPL_SSE2_fFF_vvv callee +#ifndef __ILP32__ + subq $88, %rsp + cfi_adjust_cfa_offset(88) + movaps %xmm0, 64(%rsp) + lea (%rsp), %rdi + movdqa %xmm1, 32(%rdi) + lea 16(%rsp), %rsi + movdqa %xmm2, 32(%rsi) + call JUMPTARGET(\callee) + movsd 72(%rsp), %xmm0 + lea 8(%rsp), %rdi + lea 24(%rsp), %rsi + call JUMPTARGET(\callee) + 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 $88, %rsp + cfi_adjust_cfa_offset(-88) + ret +#else + pushq %rbp + .cfi_def_cfa_offset 16 + .cfi_offset 6, -16 + pushq %rbx + .cfi_def_cfa_offset 24 + .cfi_offset 3, -24 + subl $88, %esp + .cfi_def_cfa_offset 112 + leal 64(%rsp), %esi + movaps %xmm1, 32(%esp) + leal 48(%rsp), %edi + movaps %xmm2, 16(%esp) + movq %rsi, %rbp + movq %rdi, %rbx + movaps %xmm0, (%esp) + call JUMPTARGET(\callee) + movupd 8(%esp), %xmm0 + leal 8(%rbp), %esi + leal 8(%rbx), %edi + call JUMPTARGET(\callee) + movdqa 32(%esp), %xmm1 + movsd 48(%esp), %xmm0 + movq %xmm1, %rax + movdqa 16(%esp), %xmm2 + movsd %xmm0, (%eax) + movsd 56(%esp), %xmm0 + pextrd $1, %xmm1, %eax + movsd %xmm0, (%eax) + movsd 64(%esp), %xmm0 + movq %xmm2, %rax + movsd %xmm0, (%eax) + movsd 72(%esp), %xmm0 + pextrd $1, %xmm2, %eax + movsd %xmm0, (%eax) + addl $88, %esp + .cfi_def_cfa_offset 24 + popq %rbx + .cfi_def_cfa_offset 16 + popq %rbp + .cfi_def_cfa_offset 8 + ret +#endif +.endm + +ENTRY (_ZGVbN2vvv_sincos) +WRAPPER_IMPL_SSE2_fFF_vvv sincos END (_ZGVbN2vvv_sincos) #ifndef USE_MULTIARCH |