| 1 | /* Wrapper implementations of vector math functions. |
| 2 | Copyright (C) 2014-2023 Free Software Foundation, Inc. |
| 3 | This file is part of the GNU C Library. |
| 4 | |
| 5 | The GNU C Library is free software; you can redistribute it and/or |
| 6 | modify it under the terms of the GNU Lesser General Public |
| 7 | License as published by the Free Software Foundation; either |
| 8 | version 2.1 of the License, or (at your option) any later version. |
| 9 | |
| 10 | The GNU C Library is distributed in the hope that it will be useful, |
| 11 | but WITHOUT ANY WARRANTY; without even the implied warranty of |
| 12 | MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU |
| 13 | Lesser General Public License for more details. |
| 14 | |
| 15 | You should have received a copy of the GNU Lesser General Public |
| 16 | License along with the GNU C Library; if not, see |
| 17 | <https://www.gnu.org/licenses/>. */ |
| 18 | |
| 19 | /* SSE2 ISA version as wrapper to scalar. */ |
| 20 | .macro WRAPPER_IMPL_SSE2 callee |
| 21 | subq $24, %rsp |
| 22 | cfi_adjust_cfa_offset (24) |
| 23 | movaps %xmm0, (%rsp) |
| 24 | call JUMPTARGET(\callee) |
| 25 | movsd %xmm0, (%rsp) |
| 26 | movsd 8(%rsp), %xmm0 |
| 27 | call JUMPTARGET(\callee) |
| 28 | movsd (%rsp), %xmm1 |
| 29 | unpcklpd %xmm0, %xmm1 |
| 30 | movaps %xmm1, %xmm0 |
| 31 | addq $24, %rsp |
| 32 | cfi_adjust_cfa_offset (-24) |
| 33 | ret |
| 34 | .endm |
| 35 | |
| 36 | |
| 37 | /* 2 argument SSE2 ISA version as wrapper to scalar. */ |
| 38 | .macro WRAPPER_IMPL_SSE2_ff callee |
| 39 | subq $40, %rsp |
| 40 | cfi_adjust_cfa_offset (40) |
| 41 | movaps %xmm0, (%rsp) |
| 42 | movaps %xmm1, 16(%rsp) |
| 43 | call JUMPTARGET(\callee) |
| 44 | movsd %xmm0, (%rsp) |
| 45 | movsd 8(%rsp), %xmm0 |
| 46 | movsd 24(%rsp), %xmm1 |
| 47 | call JUMPTARGET(\callee) |
| 48 | movsd (%rsp), %xmm1 |
| 49 | unpcklpd %xmm0, %xmm1 |
| 50 | movaps %xmm1, %xmm0 |
| 51 | addq $40, %rsp |
| 52 | cfi_adjust_cfa_offset (-40) |
| 53 | ret |
| 54 | .endm |
| 55 | |
| 56 | /* 3 argument SSE2 ISA version as wrapper to scalar. */ |
| 57 | .macro WRAPPER_IMPL_SSE2_fFF callee |
| 58 | pushq %rbp |
| 59 | cfi_adjust_cfa_offset (8) |
| 60 | cfi_rel_offset (%rbp, 0) |
| 61 | pushq %rbx |
| 62 | cfi_adjust_cfa_offset (8) |
| 63 | cfi_rel_offset (%rbx, 0) |
| 64 | subq $24, %rsp |
| 65 | cfi_adjust_cfa_offset (24) |
| 66 | movaps %xmm0, (%rsp) |
| 67 | movq %rdi, %rbp |
| 68 | movq %rsi, %rbx |
| 69 | call JUMPTARGET(\callee) |
| 70 | movsd 8(%rsp), %xmm0 |
| 71 | leaq 8(%rbp), %rdi |
| 72 | leaq 8(%rbx), %rsi |
| 73 | call JUMPTARGET(\callee) |
| 74 | addq $24, %rsp |
| 75 | cfi_adjust_cfa_offset (-24) |
| 76 | popq %rbx |
| 77 | cfi_adjust_cfa_offset (-8) |
| 78 | cfi_restore (%rbx) |
| 79 | popq %rbp |
| 80 | cfi_adjust_cfa_offset (-8) |
| 81 | cfi_restore (%rbp) |
| 82 | ret |
| 83 | .endm |
| 84 | |
| 85 | #include "svml_sd_wrapper_impl.h" |
| 86 | |