123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210211212213214215216217218219220221222223224225226227228229230231232233234235236237238239240241242243244245246247248249250251252253254255256257258259260261262263264265266267268269270271272273274275276277278279280281282283284285286287288289290291292293294295296297298299300301302303304305306307308309310311312313314315316317318319320321322323324325326327328329330331332333334335336337338339340341342343344345346347348349350351352353354355356357358359360361362363364365366367368369370371372373374375376377378379380381382383384 |
- /*
- * 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 "acosh_gen.c"
- .text
- ..TXTST0:
- # -- Begin acosh
- .text
- .align 16,0x90
- .globl acosh
- acosh:
- # parameter 1: %xmm0
- ..B1.1:
- .cfi_startproc
- ..___tag_value_acosh.1:
- ..L2:
- movsd %xmm0, -8(%rsp)
- movl -4(%rsp), %eax
- lea -1072693248(%rax), %edx
- cmpl $1073741824, %edx
- jae ..B1.14
- ..B1.2:
- cmpl $6144, %edx
- jae ..B1.6
- ..B1.3:
- movl -8(%rsp), %eax
- orl %eax, %edx
- jne ..B1.5
- ..B1.4:
- lea _zeros(%rip), %rax
- movsd (%rax), %xmm0
- ret
- ..B1.5:
- lea 8+_ones(%rip), %rax
- pxor %xmm3, %xmm3
- movsd -8(%rsp), %xmm5
- xorl %r9d, %r9d
- movsd .L_2il0floatpacket.0(%rip), %xmm4
- lea 32+_PA(%rip), %rdx
- lea 16+_PA(%rip), %rcx
- lea 24+_PA(%rip), %rdi
- lea _PA(%rip), %rsi
- addsd (%rax), %xmm5
- mulsd %xmm5, %xmm4
- movaps %xmm5, %xmm6
- mulsd %xmm5, %xmm6
- sqrtsd %xmm4, %xmm3
- movsd %xmm3, -16(%rsp)
- movaps %xmm3, %xmm0
- movl %r9d, -16(%rsp)
- lea 8+_PA(%rip), %r8
- movsd -16(%rsp), %xmm11
- movaps %xmm11, %xmm1
- movaps %xmm11, %xmm2
- movsd (%rdx), %xmm8
- subsd %xmm11, %xmm0
- mulsd %xmm11, %xmm1
- mulsd %xmm6, %xmm8
- mulsd %xmm0, %xmm2
- subsd %xmm1, %xmm4
- addsd (%rcx), %xmm8
- subsd %xmm2, %xmm4
- mulsd %xmm6, %xmm8
- divsd %xmm3, %xmm4
- movsd (%rdi), %xmm7
- addsd %xmm4, %xmm0
- mulsd %xmm6, %xmm7
- addsd (%rsi), %xmm8
- mulsd .L_2il0floatpacket.1(%rip), %xmm0
- addsd (%r8), %xmm7
- mulsd %xmm5, %xmm8
- mulsd %xmm6, %xmm7
- addsd %xmm7, %xmm8
- movsd %xmm8, -24(%rsp)
- movaps %xmm8, %xmm9
- movl %r9d, -24(%rsp)
- movsd -24(%rsp), %xmm10
- mulsd %xmm0, %xmm8
- subsd %xmm10, %xmm9
- mulsd %xmm11, %xmm10
- mulsd %xmm11, %xmm9
- movsd %xmm10, -24(%rsp)
- addsd %xmm8, %xmm9
- addsd %xmm9, %xmm0
- addsd %xmm10, %xmm0
- addsd %xmm11, %xmm0
- ret
- ..B1.6:
- cmpl $29360128, %edx
- jae ..B1.11
- ..B1.7:
- movsd -8(%rsp), %xmm7
- cmpl $2293760, %edx
- jae ..B1.9
- ..B1.8:
- xorl %edx, %edx
- movaps %xmm7, %xmm1
- movl %edx, -8(%rsp)
- lea 8+_ones(%rip), %rax
- movsd -8(%rsp), %xmm8
- movaps %xmm8, %xmm4
- subsd %xmm8, %xmm1
- mulsd %xmm8, %xmm4
- addsd %xmm8, %xmm7
- mulsd %xmm1, %xmm7
- addsd (%rax), %xmm4
- movaps %xmm4, %xmm0
- addsd %xmm7, %xmm0
- sqrtsd %xmm0, %xmm0
- movsd %xmm0, -16(%rsp)
- movl %edx, -16(%rsp)
- movsd -16(%rsp), %xmm6
- movaps %xmm6, %xmm2
- movaps %xmm6, %xmm3
- mulsd %xmm6, %xmm2
- subsd %xmm6, %xmm0
- addsd %xmm6, %xmm8
- mulsd %xmm0, %xmm3
- subsd %xmm2, %xmm4
- movaps %xmm6, %xmm5
- subsd %xmm3, %xmm4
- addsd %xmm0, %xmm5
- addsd %xmm4, %xmm7
- divsd %xmm5, %xmm7
- addsd %xmm7, %xmm0
- mulsd .L_2il0floatpacket.1(%rip), %xmm0
- addsd %xmm0, %xmm1
- jmp ..B1.10
- ..B1.9:
- movaps %xmm7, %xmm0
- lea 8+_ones(%rip), %rax
- movsd .L_2il0floatpacket.0(%rip), %xmm2
- mulsd %xmm7, %xmm0
- movsd (%rax), %xmm1
- addsd %xmm1, %xmm0
- sqrtsd %xmm0, %xmm0
- addsd %xmm7, %xmm0
- mulsd %xmm2, %xmm7
- divsd %xmm0, %xmm1
- movsd %xmm7, -8(%rsp)
- movl $0, -8(%rsp)
- movsd -8(%rsp), %xmm8
- subsd %xmm8, %xmm7
- addsd %xmm7, %xmm1
- ..B1.10:
- movaps %xmm1, %xmm0
- movq $0x3ff0000000000000, %rax
- addsd %xmm8, %xmm0
- movsd %xmm0, -8(%rsp)
- movl $0, -8(%rsp)
- movsd -8(%rsp), %xmm7
- movzwl -2(%rsp), %ecx
- subsd %xmm7, %xmm8
- andl $32752, %ecx
- addsd %xmm8, %xmm1
- shrl $4, %ecx
- addl $-1023, %ecx
- movslq %ecx, %rdx
- negq %rdx
- shlq $52, %rdx
- addq %rax, %rdx
- movq %rdx, -24(%rsp)
- movsd -24(%rsp), %xmm2
- mulsd %xmm2, %xmm1
- mulsd %xmm2, %xmm7
- movaps %xmm1, %xmm3
- addsd %xmm7, %xmm3
- movsd %xmm3, -16(%rsp)
- movl -12(%rsp), %esi
- shrl $12, %esi
- movzbl %sil, %edx
- jmp ..B1.12
- ..B1.11:
- movzwl -2(%rsp), %eax
- movl %eax, %ecx
- andl $-32753, %eax
- andl $32752, %ecx
- orl $-49168, %eax
- movw %ax, -2(%rsp)
- movsd -8(%rsp), %xmm1
- movl $0, -8(%rsp)
- movl -4(%rsp), %edx
- movsd -8(%rsp), %xmm7
- shrl $4, %ecx
- subsd %xmm7, %xmm1
- shrl $12, %edx
- addl $-1022, %ecx
- movzbl %dl, %edx
- ..B1.12:
- movq __libm_rcp_table_256@GOTPCREL(%rip), %rsi
- pxor %xmm0, %xmm0
- lea _ones(%rip), %rdi
- lea 32+_PL(%rip), %r8
- lea 24+_PL(%rip), %r11
- lea 16+_PL(%rip), %r9
- lea _PL(%rip), %r10
- pxor %xmm6, %xmm6
- movq __libm_log_table_256@GOTPCREL(%rip), %rax
- movsd (%r8), %xmm5
- movsd (%r11), %xmm4
- cvtss2sd (%rsi,%rdx,4), %xmm0
- cvtsi2sd %ecx, %xmm6
- mulsd %xmm0, %xmm7
- mulsd %xmm0, %xmm1
- subsd (%rdi), %xmm7
- movaps %xmm7, %xmm3
- lea _LN2(%rip), %rcx
- lea 8+_PL(%rip), %rsi
- addsd %xmm1, %xmm3
- movaps %xmm3, %xmm2
- mulsd %xmm3, %xmm2
- mulsd %xmm2, %xmm5
- mulsd %xmm2, %xmm4
- addsd (%r9), %xmm5
- addsd (%rsi), %xmm4
- mulsd %xmm2, %xmm5
- mulsd %xmm2, %xmm4
- addsd (%r10), %xmm5
- mulsd %xmm3, %xmm4
- mulsd %xmm2, %xmm5
- movsd (%rcx), %xmm0
- addsd %xmm4, %xmm5
- mulsd %xmm6, %xmm0
- addsd %xmm5, %xmm1
- shlq $4, %rdx
- lea 8+_LN2(%rip), %rcx
- movsd %xmm3, -16(%rsp)
- addsd (%rax,%rdx), %xmm0
- addsd %xmm1, %xmm0
- movsd (%rcx), %xmm1
- mulsd %xmm1, %xmm6
- addsd 8(%rax,%rdx), %xmm6
- movsd %xmm6, -24(%rsp)
- addsd %xmm6, %xmm7
- movsd %xmm7, -8(%rsp)
- addsd %xmm7, %xmm0
- ..B1.13:
- ret
- ..B1.14:
- movl %eax, %edx
- andl $2147483647, %edx
- cmpl $2146435072, %edx
- jbe ..B1.16
- ..B1.15:
- movsd -8(%rsp), %xmm0
- addsd %xmm0, %xmm0
- ret
- ..B1.16:
- cmpl $2146435072, %eax
- jne ..B1.18
- ..B1.17:
- cmpl $0, -8(%rsp)
- je ..B1.15
- ..B1.18:
- cmpl $2146435072, %edx
- jne ..B1.20
- ..B1.19:
- cmpl $0, -8(%rsp)
- jne ..B1.15
- ..B1.20:
- lea _infs(%rip), %rax
- lea _zeros(%rip), %rdx
- movsd (%rax), %xmm0
- mulsd (%rdx), %xmm0
- ret
- .align 16,0x90
- .cfi_endproc
- .type acosh,@function
- .size acosh,.-acosh
- .data
- # -- End acosh
- .section .rodata, "a"
- .align 8
- .align 8
- .L_2il0floatpacket.0:
- .long 0x00000000,0x40000000
- .type .L_2il0floatpacket.0,@object
- .size .L_2il0floatpacket.0,8
- .align 8
- .L_2il0floatpacket.1:
- .long 0x00000000,0x3fe00000
- .type .L_2il0floatpacket.1,@object
- .size .L_2il0floatpacket.1,8
- .align 4
- _zeros:
- .long 0
- .long 0
- .long 0
- .long 2147483648
- .type _zeros,@object
- .size _zeros,16
- .align 4
- _ones:
- .long 0
- .long 1072693248
- .long 0
- .long 3220176896
- .type _ones,@object
- .size _ones,16
- .align 4
- _PA:
- .long 1431655760
- .long 3216332117
- .long 858954823
- .long 1066611507
- .long 2956777430
- .long 3212237677
- .long 4158004615
- .long 1063197775
- .long 2173429939
- .long 3209085130
- .type _PA,@object
- .size _PA,40
- .align 4
- _PL:
- .long 0
- .long 3219128320
- .long 1431621855
- .long 1070945621
- .long 4294842013
- .long 3218079743
- .long 1289448124
- .long 1070176674
- .long 2077359316
- .long 3217380703
- .type _PL,@object
- .size _PL,40
- .align 4
- _LN2:
- .long 897137782
- .long 1038760431
- .long 4276092928
- .long 1072049730
- .type _LN2,@object
- .size _LN2,16
- .align 4
- _infs:
- .long 0
- .long 2146435072
- .long 0
- .long 4293918720
- .type _infs,@object
- .size _infs,16
- .data
- .section .note.GNU-stack, ""
- // -- Begin DWARF2 SEGMENT .eh_frame
- .section .eh_frame,"a",@progbits
- .eh_frame_seg:
- .align 1
- # End
|