/*
* Math library
*
* Copyright (C) 2016 Intel Corporation. All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions
* are met:
*
* * Redistributions of source code must retain the above copyright
* notice, this list of conditions and the following disclaimer.
* * Redistributions in binary form must reproduce the above copyright
* notice, this list of conditions and the following disclaimer in
* the documentation and/or other materials provided with the
* distribution.
* * Neither the name of Intel Corporation nor the names of its
* contributors may be used to endorse or promote products derived
* from this software without specific prior written permission.
*
* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
* "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
* LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
* A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
* OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
* SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
* LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
* DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
* THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
* (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
* OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
*
*
* Author Name <jingwei.zhang@intel.com>
* History:
* 03-14-2016 Initial version. numerics svn rev. 12864
*/
.file "libm_mul_k64.c"
.text
..TXTST0:
# -- Begin __libm_mul_k64
.text
.align 16,0x90
.globl __libm_mul_k64
__libm_mul_k64:
# parameter 1: %edi
# parameter 2: %rsi
# parameter 3: %rdx
# parameter 4: %rcx
..B1.1:
.cfi_startproc
..___tag_value___libm_mul_k64.1:
..L2:
movq %rdx, %rax
movzwl 6(%rsi), %edx
andl $32752, %edx
shrl $4, %edx
movsd (%rsi), %xmm3
cmpl $2047, %edx
movsd 8(%rsi), %xmm7
movsd (%rax), %xmm2
movsd 8(%rax), %xmm4
je ..B1.12
..B1.2:
testl %edx, %edx
jne ..B1.7
..B1.3:
testl $1048575, 4(%rsi)
jne ..B1.7
..B1.4:
cmpl $0, (%rsi)
je ..B1.12
..B1.7:
movsd %xmm2, -24(%rsp)
..B1.8:
movzwl -18(%rsp), %eax
andl $32752, %eax
shrl $4, %eax
cmpl $2047, %eax
je ..B1.12
..B1.9:
testl %eax, %eax
jne ..B1.13
..B1.10:
testl $1048575, -20(%rsp)
jne ..B1.13
..B1.11:
cmpl $0, -24(%rsp)
jne ..B1.13
..B1.12:
mulsd %xmm2, %xmm3
movsd %xmm3, (%rcx)
ret
..B1.13:
testl %edx, %edx
jne ..B1.15
..B1.14:
lea _CONSTANTS(%rip), %rdx
movaps %xmm3, %xmm1
addl $-1023, %edi
movsd (%rdx), %xmm0
mulsd %xmm0, %xmm1
mulsd %xmm0, %xmm7
jmp ..B1.16
..B1.15:
lea 32+_CONSTANTS(%rip), %rsi
movl %edx, %r9d
negl %r9d
movaps %xmm3, %xmm1
addl $-2, %r9d
lea -1023(%rdi,%rdx), %edi
andl $2047, %r9d
movq (%rsi), %r8
movq %r8, -24(%rsp)
shrq $48, %r8
shll $4, %r9d
andl $-32753, %r8d
orl %r9d, %r8d
movw %r8w, -18(%rsp)
movsd -24(%rsp), %xmm0
mulsd %xmm0, %xmm1
mulsd %xmm0, %xmm7
..B1.16:
testl %eax, %eax
jne ..B1.18
..B1.17:
lea _CONSTANTS(%rip), %rax
movaps %xmm2, %xmm8
addl $-1023, %edi
movsd (%rax), %xmm0
mulsd %xmm0, %xmm8
mulsd %xmm0, %xmm4
jmp ..B1.19
..B1.18:
lea 32+_CONSTANTS(%rip), %rdx
movl %eax, %r8d
negl %r8d
movaps %xmm2, %xmm8
addl $-2, %r8d
lea -1023(%rdi,%rax), %edi
andl $2047, %r8d
movq (%rdx), %rsi
movq %rsi, -24(%rsp)
shrq $48, %rsi
shll $4, %r8d
andl $-32753, %esi
orl %r8d, %esi
movw %si, -18(%rsp)
movsd -24(%rsp), %xmm0
mulsd %xmm0, %xmm8
mulsd %xmm0, %xmm4
..B1.19:
movaps %xmm7, %xmm0
lea 16+_CONSTANTS(%rip), %rax
movaps %xmm4, %xmm10
addsd %xmm1, %xmm0
addsd %xmm8, %xmm10
movaps %xmm0, %xmm5
movaps %xmm0, %xmm9
movaps %xmm10, %xmm11
subsd %xmm1, %xmm5
movsd (%rax), %xmm1
subsd %xmm5, %xmm7
mulsd %xmm1, %xmm9
mulsd %xmm1, %xmm11
movaps %xmm9, %xmm6
subsd %xmm0, %xmm6
subsd %xmm6, %xmm9
movaps %xmm9, %xmm5
subsd %xmm9, %xmm0
addsd %xmm7, %xmm0
movaps %xmm10, %xmm7
subsd %xmm8, %xmm7
movaps %xmm11, %xmm8
movaps %xmm0, %xmm6
subsd %xmm10, %xmm8
subsd %xmm7, %xmm4
subsd %xmm8, %xmm11
mulsd %xmm11, %xmm0
subsd %xmm11, %xmm10
mulsd %xmm11, %xmm5
addsd %xmm4, %xmm10
mulsd %xmm10, %xmm6
movaps %xmm5, %xmm4
mulsd %xmm9, %xmm10
addsd %xmm10, %xmm6
addsd %xmm0, %xmm6
addsd %xmm6, %xmm4
movsd %xmm4, -16(%rsp)
movzwl -10(%rsp), %edx
movl %edx, %esi
andl $32752, %esi
shrl $4, %esi
lea (%rdi,%rsi), %eax
cmpl $2047, %eax
jl ..B1.21
..B1.20:
lea _CONSTANTS(%rip), %rax
movsd (%rax), %xmm0
mulsd %xmm0, %xmm0
mulsd %xmm3, %xmm0
mulsd %xmm2, %xmm0
movsd %xmm0, (%rcx)
ret
..B1.21:
testl %eax, %eax
jle ..B1.23
..B1.22:
andl $2047, %eax
andl $-32753, %edx
shll $4, %eax
orl %eax, %edx
movw %dx, -10(%rsp)
movq -16(%rsp), %rax
movq %rax, (%rcx)
ret
..B1.23:
cmpl $-9, %eax
jl ..B1.25
..B1.24:
lea 8+_CONSTANTS(%rip), %rax
lea 32+_CONSTANTS(%rip), %rsi
lea 24+_CONSTANTS(%rip), %rdx
addl $1423, %edi
andl $2047, %edi
shll $4, %edi
movsd (%rax), %xmm0
mulsd %xmm0, %xmm0
movq (%rsi), %r8
addsd %xmm0, %xmm5
movaps %xmm5, %xmm4
movq %r8, -24(%rsp)
addsd %xmm6, %xmm4
mulsd %xmm4, %xmm1
movaps %xmm4, %xmm2
subsd %xmm5, %xmm2
movaps %xmm1, %xmm5
subsd %xmm2, %xmm6
subsd %xmm4, %xmm5
shrq $48, %r8
subsd %xmm5, %xmm1
andl $-32753, %r8d
subsd %xmm1, %xmm4
orl %edi, %r8d
addsd %xmm6, %xmm4
movsd (%rdx), %xmm6
mulsd %xmm6, %xmm1
mulsd %xmm6, %xmm4
movw %r8w, -18(%rsp)
movsd -24(%rsp), %xmm3
mulsd %xmm3, %xmm1
mulsd %xmm3, %xmm4
addsd %xmm4, %xmm1
movsd %xmm1, (%rcx)
ret
..B1.25:
cmpl $-62, %eax
jle ..B1.27
..B1.26:
lea 32+_CONSTANTS(%rip), %rax
lea 1022(%rdi,%rsi), %esi
lea 8+_CONSTANTS(%rip), %rdi
andl $-32753, %edx
orl $16, %edx
andl $2047, %esi
movw %dx, -10(%rsp)
movq (%rax), %rdx
movsd (%rdi), %xmm0
mulsd %xmm0, %xmm0
movq %rdx, -24(%rsp)
shrq $48, %rdx
shll $4, %esi
andl $-32753, %edx
orl %esi, %edx
movw %dx, -18(%rsp)
movsd -16(%rsp), %xmm1
addsd -24(%rsp), %xmm0
mulsd %xmm0, %xmm1
movsd %xmm0, -24(%rsp)
movsd %xmm1, -16(%rsp)
movsd %xmm1, (%rcx)
ret
..B1.27:
lea 8+_CONSTANTS(%rip), %rax
movsd (%rax), %xmm0
mulsd %xmm0, %xmm0
mulsd %xmm3, %xmm0
mulsd %xmm2, %xmm0
movsd %xmm0, (%rcx)
..B1.28:
ret
.align 16,0x90
.cfi_endproc
.type __libm_mul_k64,@function
.size __libm_mul_k64,.-__libm_mul_k64
.data
# -- End __libm_mul_k64
.section .rodata, "a"
.align 16
.align 16
_CONSTANTS:
.long 0
.long 2145386496
.long 0
.long 1048576
.long 33554432
.long 1101004800
.long 0
.long 653262848
.long 0
.long 1072693248
.type _CONSTANTS,@object
.size _CONSTANTS,40
.data
.section .note.GNU-stack, ""
// -- Begin DWARF2 SEGMENT .eh_frame
.section .eh_frame,"a",@progbits
.eh_frame_seg:
.align 1
# End