| 123456789101112131415161718192021222324252627282930313233343536373839404142434445464748495051525354555657585960616263646566676869707172737475767778798081828384858687888990919293949596979899100101102103104105106107108109110111112113114115116117118119120121122123124125126127128129130131132133134135136137138139140141142143144145146147148149150151152153154155156157158159160161162163164165166167168169170171172173174175176177178179180181182183184185186187188189190191192193194195196197198199200201202203204205206207208209210211212213214215216217218219220221222223224225226227228229230231232233234235236237238239240241242243244245246247248249250251252253254255256257258259260261262263264265266267268269270271272273274275276277278279280281282283284285286287288289290291292293294295296297298299300301302303304305306307308309310311312313314315316317318319320321322323324325326327328329330331332333334335336337338339340341342343344345346347348349350351352353354355356357358359360361362363364365366367368369370371372373374375376377378379380381382383384385386387388389390391392393394395396397398399400401402403404405406407408409410411412413414415416417418419420421422423424425426427428429430431432433434435436437438439440441442443444445446447448449450451452453454455456457458459460461462463464465466467468469470471472473474475476477478479480481482483484485486487488489490491492493494495496497498499500501502503504505506507508509510511512513514515516517 | 
							- /*
 
- * 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 "exp2_gen.c"
 
- 	.text
 
- ..TXTST0:
 
- # -- Begin  exp2
 
- 	.text
 
-        .align    16,0x90
 
- 	.globl exp2
 
- exp2:
 
- # parameter 1: %xmm0
 
- ..B1.1:
 
- 	.cfi_startproc
 
- ..___tag_value_exp2.1:
 
- ..L2:
 
-         subq      $56, %rsp
 
- 	.cfi_def_cfa_offset 64
 
-         xorb      %sil, %sil
 
-         movsd     %xmm0, 40(%rsp)
 
- ..B1.2:
 
-         fnstcw    34(%rsp)
 
- ..B1.3:
 
-         movl      44(%rsp), %edx
 
-         movl      %edx, %eax
 
-         andl      $2147483647, %eax
 
-         lea       -1072693248(%rax), %ecx
 
-         cmpl      $10483712, %ecx
 
-         ja        ..B1.9
 
- ..B1.4:
 
-         movl      %eax, %ecx
 
-         movl      $1048575, %edi
 
-         shrl      $20, %ecx
 
-         incl      %ecx
 
-         shrl      %cl, %edi
 
-         andl      %eax, %edi
 
-         orl       40(%rsp), %edi
 
-         jne       ..B1.9
 
- ..B1.5:
 
-         lea       _TWO_52H(%rip), %rcx
 
-         movsd     40(%rsp), %xmm0
 
-         addsd     (%rcx), %xmm0
 
-         movsd     %xmm0, 16(%rsp)
 
-         movl      16(%rsp), %ecx
 
-         cmpl      $-1074, %ecx
 
-         jl        ..B1.9
 
- ..B1.6:
 
-         lea       1023(%rcx), %eax
 
-         testl     %eax, %eax
 
-         jle       ..B1.37
 
- ..B1.7:
 
-         movslq    %eax, %rax
 
-         shlq      $52, %rax
 
-         movq      %rax, 8(%rsp)
 
- ..B1.8:
 
-         movsd     8(%rsp), %xmm0
 
-         addq      $56, %rsp
 
- 	.cfi_def_cfa_offset 8
 
-         ret       
 
- 	.cfi_def_cfa_offset 64
 
- ..B1.9:
 
-         cmpl      $1079984128, %eax
 
-         jae       ..B1.14
 
- ..B1.10:
 
-         cmpl      $1012924416, %eax
 
-         jae       ..B1.12
 
- ..B1.11:
 
-         movsd     .L_2il0floatpacket.11(%rip), %xmm0
 
-         addsd     40(%rsp), %xmm0
 
-         addq      $56, %rsp
 
- 	.cfi_def_cfa_offset 8
 
-         ret       
 
- 	.cfi_def_cfa_offset 64
 
- ..B1.12:
 
-         movsd     40(%rsp), %xmm0
 
-         pxor      %xmm13, %xmm13
 
-         lea       _TWO_52H(%rip), %rax
 
-         lea       _two_32p1(%rip), %rdx
 
-         movsd     .L_2il0floatpacket.4(%rip), %xmm9
 
-         lea       _two_32(%rip), %rcx
 
-         movsd     .L_2il0floatpacket.7(%rip), %xmm10
 
-         movsd     .L_2il0floatpacket.2(%rip), %xmm4
 
-         movsd     (%rax), %xmm1
 
-         mulsd     .L_2il0floatpacket.0(%rip), %xmm0
 
-         movsd     (%rdx), %xmm2
 
-         addsd     %xmm1, %xmm0
 
-         movsd     %xmm0, 16(%rsp)
 
-         movsd     16(%rsp), %xmm8
 
-         movl      16(%rsp), %esi
 
-         movl      %esi, %edi
 
-         movsd     .L_2il0floatpacket.3(%rip), %xmm3
 
-         subsd     %xmm1, %xmm8
 
-         mulsd     .L_2il0floatpacket.1(%rip), %xmm8
 
-         shll      $25, %edi
 
-         addsd     40(%rsp), %xmm8
 
-         movaps    %xmm8, %xmm7
 
-         movaps    %xmm8, %xmm5
 
-         mulsd     %xmm8, %xmm7
 
-         mulsd     %xmm7, %xmm9
 
-         mulsd     %xmm7, %xmm10
 
-         addsd     .L_2il0floatpacket.5(%rip), %xmm9
 
-         addsd     .L_2il0floatpacket.8(%rip), %xmm10
 
-         mulsd     %xmm7, %xmm9
 
-         mulsd     %xmm7, %xmm10
 
-         addsd     .L_2il0floatpacket.6(%rip), %xmm9
 
-         addsd     .L_2il0floatpacket.9(%rip), %xmm10
 
-         mulsd     %xmm7, %xmm9
 
-         mulsd     %xmm7, %xmm10
 
-         movsd     %xmm8, (%rsp)
 
-         movl      $0, (%rsp)
 
-         movsd     (%rsp), %xmm6
 
-         sarl      $25, %edi
 
-         subsd     %xmm6, %xmm5
 
-         mulsd     %xmm4, %xmm6
 
-         addsd     .L_2il0floatpacket.10(%rip), %xmm10
 
-         mulsd     %xmm4, %xmm5
 
-         addsd     %xmm6, %xmm2
 
-         mulsd     %xmm8, %xmm10
 
-         addsd     %xmm5, %xmm9
 
-         movsd     %xmm2, 16(%rsp)
 
-         subl      %edi, %esi
 
-         movsd     16(%rsp), %xmm11
 
-         movslq    %edi, %rdi
 
-         subsd     (%rcx), %xmm11
 
-         shlq      $4, %rdi
 
-         addsd     %xmm11, %xmm3
 
-         movq      __libm_exp_table_128@GOTPCREL(%rip), %r8
 
-         subsd     %xmm3, %xmm6
 
-         movsd     1032(%r8,%rdi), %xmm12
 
-         addsd     %xmm6, %xmm9
 
-         movaps    %xmm12, %xmm0
 
-         addsd     %xmm9, %xmm10
 
-         mulsd     %xmm11, %xmm12
 
-         mulsd     %xmm10, %xmm0
 
-         addsd     %xmm11, %xmm10
 
-         mulsd     1024(%r8,%rdi), %xmm10
 
-         shrl      $7, %esi
 
-         addsd     %xmm10, %xmm0
 
-         shll      $23, %esi
 
-         addsd     %xmm12, %xmm0
 
-         addl      $1065353216, %esi
 
-         movl      %esi, 24(%rsp)
 
-         cvtss2sd  24(%rsp), %xmm13
 
-         mulsd     %xmm13, %xmm0
 
-         movsd     %xmm11, (%rsp)
 
-         movsd     %xmm0, 8(%rsp)
 
- ..B1.13:
 
-         addq      $56, %rsp
 
- 	.cfi_def_cfa_offset 8
 
-         ret       
 
- 	.cfi_def_cfa_offset 64
 
- ..B1.14:
 
-         lea       _range(%rip), %r8
 
-         movl      %edx, %ecx
 
-         shrl      $31, %ecx
 
-         cmpl      4(%r8,%rcx,8), %eax
 
-         jb        ..B1.17
 
- ..B1.15:
 
-         jne       ..B1.28
 
- ..B1.16:
 
-         movl      40(%rsp), %edi
 
-         cmpl      (%r8,%rcx,8), %edi
 
-         ja        ..B1.28
 
- ..B1.17:
 
-         movsd     40(%rsp), %xmm0
 
-         lea       _TWO_52H(%rip), %rdi
 
-         mulsd     .L_2il0floatpacket.0(%rip), %xmm0
 
-         lea       _two_32p1(%rip), %r9
 
-         movsd     (%rdi), %xmm1
 
-         lea       _two_32(%rip), %r10
 
-         movsd     .L_2il0floatpacket.4(%rip), %xmm9
 
-         lea       SC2_BIAS(%rip), %r11
 
-         movsd     .L_2il0floatpacket.2(%rip), %xmm4
 
-         addsd     %xmm1, %xmm0
 
-         movsd     %xmm0, 16(%rsp)
 
-         movsd     16(%rsp), %xmm8
 
-         movsd     (%r9), %xmm2
 
-         subsd     %xmm1, %xmm8
 
-         mulsd     .L_2il0floatpacket.1(%rip), %xmm8
 
-         movsd     .L_2il0floatpacket.7(%rip), %xmm1
 
-         movl      16(%rsp), %edx
 
-         movl      %edx, %eax
 
-         movsd     .L_2il0floatpacket.3(%rip), %xmm3
 
-         movl      %edx, %r8d
 
-         shll      $25, %eax
 
-         addsd     40(%rsp), %xmm8
 
-         movaps    %xmm8, %xmm7
 
-         movaps    %xmm8, %xmm5
 
-         mulsd     %xmm8, %xmm7
 
-         mulsd     %xmm7, %xmm9
 
-         mulsd     %xmm7, %xmm1
 
-         addsd     .L_2il0floatpacket.5(%rip), %xmm9
 
-         addsd     .L_2il0floatpacket.8(%rip), %xmm1
 
-         mulsd     %xmm7, %xmm9
 
-         mulsd     %xmm7, %xmm1
 
-         addsd     .L_2il0floatpacket.6(%rip), %xmm9
 
-         addsd     .L_2il0floatpacket.9(%rip), %xmm1
 
-         mulsd     %xmm7, %xmm9
 
-         mulsd     %xmm7, %xmm1
 
-         movsd     %xmm8, (%rsp)
 
-         movl      $0, (%rsp)
 
-         movsd     (%rsp), %xmm6
 
-         sarl      $25, %eax
 
-         subsd     %xmm6, %xmm5
 
-         mulsd     %xmm4, %xmm6
 
-         addsd     .L_2il0floatpacket.10(%rip), %xmm1
 
-         mulsd     %xmm4, %xmm5
 
-         addsd     %xmm6, %xmm2
 
-         mulsd     %xmm8, %xmm1
 
-         addsd     %xmm5, %xmm9
 
-         movsd     %xmm2, 16(%rsp)
 
-         subl      %eax, %r8d
 
-         movsd     16(%rsp), %xmm11
 
-         movsd     %xmm6, (%rsp)
 
-         movslq    %eax, %rax
 
-         subsd     (%r10), %xmm11
 
-         shlq      $4, %rax
 
-         addsd     %xmm11, %xmm3
 
-         movq      __libm_exp_table_128@GOTPCREL(%rip), %r9
 
-         subsd     %xmm3, %xmm6
 
-         movsd     1032(%r9,%rax), %xmm2
 
-         addsd     %xmm6, %xmm9
 
-         shrl      $7, %r8d
 
-         addsd     %xmm9, %xmm1
 
-         movaps    %xmm1, %xmm10
 
-         mulsd     %xmm2, %xmm1
 
-         addsd     %xmm11, %xmm10
 
-         mulsd     %xmm11, %xmm2
 
-         mulsd     1024(%r9,%rax), %xmm10
 
-         movslq    (%r11,%rcx,4), %rdi
 
-         addsd     %xmm10, %xmm1
 
-         addq      %r8, %rdi
 
-         movaps    %xmm1, %xmm0
 
-         shlq      $52, %rdi
 
-         addsd     %xmm2, %xmm0
 
-         movq      %rdi, 24(%rsp)
 
-         cmpl      $-130815, %edx
 
-         jg        ..B1.26
 
- ..B1.18:
 
-         movsd     %xmm0, (%rsp)
 
-         andl      $-4096, (%rsp)
 
-         movsd     (%rsp), %xmm0
 
-         movzwl    34(%rsp), %edx
 
-         movl      %edx, %eax
 
-         andl      $768, %eax
 
-         subsd     %xmm0, %xmm2
 
-         cmpl      $768, %eax
 
-         addsd     %xmm1, %xmm2
 
-         je        ..B1.22
 
- ..B1.19:
 
-         orl       $-64768, %edx
 
-         movw      %dx, 32(%rsp)
 
- ..B1.20:
 
-         fldcw     32(%rsp)
 
- ..B1.21:
 
-         movsd     (%rsp), %xmm0
 
-         movb      $1, %sil
 
- ..B1.22:
 
-         fldl      24(%rsp)
 
-         lea       _SC2(%rip), %rax
 
-         movsd     %xmm0, (%rsp)
 
-         testb     %sil, %sil
 
-         fldl      (%rsp)
 
-         movsd     %xmm2, (%rsp)
 
-         fldl      (%rsp)
 
-         faddp     %st, %st(1)
 
-         fmulp     %st, %st(1)
 
-         fmull     (%rax,%rcx,8)
 
-         fstpl     8(%rsp)
 
-         je        ..B1.24
 
- ..B1.23:
 
-         fldcw     34(%rsp)
 
- ..B1.24:
 
-         cmpl      $1048576, 12(%rsp)
 
-         jl        ..B1.8
 
- ..B1.25:
 
-         movsd     8(%rsp), %xmm0
 
-         addq      $56, %rsp
 
- 	.cfi_def_cfa_offset 8
 
-         ret       
 
- 	.cfi_def_cfa_offset 64
 
- ..B1.26:
 
-         movsd     24(%rsp), %xmm1
 
-         lea       _SC2(%rip), %rax
 
-         mulsd     %xmm1, %xmm0
 
-         mulsd     (%rax,%rcx,8), %xmm0
 
-         movsd     %xmm0, 8(%rsp)
 
- ..B1.27:
 
-         addq      $56, %rsp
 
- 	.cfi_def_cfa_offset 8
 
-         ret       
 
- 	.cfi_def_cfa_offset 64
 
- ..B1.28:
 
-         cmpl      $2146435072, %eax
 
-         jae       ..B1.33
 
- ..B1.29:
 
-         testl     $-2147483648, %edx
 
-         je        ..B1.31
 
- ..B1.30:
 
-         lea       _small_value_64(%rip), %rax
 
-         movsd     (%rax), %xmm1
 
-         movaps    %xmm1, %xmm0
 
-         mulsd     %xmm1, %xmm0
 
-         movsd     %xmm0, 8(%rsp)
 
-         addq      $56, %rsp
 
- 	.cfi_def_cfa_offset 8
 
-         ret       
 
- 	.cfi_def_cfa_offset 64
 
- ..B1.31:
 
-         lea       _large_value_64(%rip), %rax
 
-         movsd     (%rax), %xmm1
 
-         movaps    %xmm1, %xmm0
 
-         mulsd     %xmm1, %xmm0
 
-         movsd     %xmm0, 8(%rsp)
 
- ..B1.32:
 
-         addq      $56, %rsp
 
- 	.cfi_def_cfa_offset 8
 
-         ret       
 
- 	.cfi_def_cfa_offset 64
 
- ..B1.33:
 
-         addl      $-2146435072, %eax
 
-         orl       40(%rsp), %eax
 
-         jne       ..B1.35
 
- ..B1.34:
 
-         lea       _inf_zero(%rip), %rax
 
-         movsd     (%rax,%rcx,8), %xmm0
 
-         addq      $56, %rsp
 
- 	.cfi_def_cfa_offset 8
 
-         ret       
 
- 	.cfi_def_cfa_offset 64
 
- ..B1.35:
 
-         movsd     40(%rsp), %xmm0
 
-         addsd     %xmm0, %xmm0
 
- ..B1.36:
 
-         addq      $56, %rsp
 
- 	.cfi_def_cfa_offset 8
 
-         ret       
 
- 	.cfi_def_cfa_offset 64
 
- ..B1.37:
 
-         addl      $1074, %ecx
 
-         movl      $1, %eax
 
-         shlq      %cl, %rax
 
-         movq      %rax, 8(%rsp)
 
-         jmp       ..B1.8
 
-         .align    16,0x90
 
- 	.cfi_endproc
 
- 	.type	exp2,@function
 
- 	.size	exp2,.-exp2
 
- 	.data
 
- # -- End  exp2
 
- 	.section .rodata, "a"
 
- 	.align 8
 
- 	.align 8
 
- .L_2il0floatpacket.0:
 
- 	.long	0x00000000,0x40600000
 
- 	.type	.L_2il0floatpacket.0,@object
 
- 	.size	.L_2il0floatpacket.0,8
 
- 	.align 8
 
- .L_2il0floatpacket.1:
 
- 	.long	0x00000000,0xbf800000
 
- 	.type	.L_2il0floatpacket.1,@object
 
- 	.size	.L_2il0floatpacket.1,8
 
- 	.align 8
 
- .L_2il0floatpacket.2:
 
- 	.long	0x00000000,0x3fe62e42
 
- 	.type	.L_2il0floatpacket.2,@object
 
- 	.size	.L_2il0floatpacket.2,8
 
- 	.align 8
 
- .L_2il0floatpacket.3:
 
- 	.long	0x00000000,0xbff00000
 
- 	.type	.L_2il0floatpacket.3,@object
 
- 	.size	.L_2il0floatpacket.3,8
 
- 	.align 8
 
- .L_2il0floatpacket.4:
 
- 	.long	0xac59a345,0x3f24308c
 
- 	.type	.L_2il0floatpacket.4,@object
 
- 	.size	.L_2il0floatpacket.4,8
 
- 	.align 8
 
- .L_2il0floatpacket.5:
 
- 	.long	0x6fba31d1,0x3f83b2ab
 
- 	.type	.L_2il0floatpacket.5,@object
 
- 	.size	.L_2il0floatpacket.5,8
 
- 	.align 8
 
- .L_2il0floatpacket.6:
 
- 	.long	0xff82c58f,0x3fcebfbd
 
- 	.type	.L_2il0floatpacket.6,@object
 
- 	.size	.L_2il0floatpacket.6,8
 
- 	.align 8
 
- .L_2il0floatpacket.7:
 
- 	.long	0x00cb0678,0x3ef0097a
 
- 	.type	.L_2il0floatpacket.7,@object
 
- 	.size	.L_2il0floatpacket.7,8
 
- 	.align 8
 
- .L_2il0floatpacket.8:
 
- 	.long	0xe87ed439,0x3f55d87f
 
- 	.type	.L_2il0floatpacket.8,@object
 
- 	.size	.L_2il0floatpacket.8,8
 
- 	.align 8
 
- .L_2il0floatpacket.9:
 
- 	.long	0xd704a0c3,0x3fac6b08
 
- 	.type	.L_2il0floatpacket.9,@object
 
- 	.size	.L_2il0floatpacket.9,8
 
- 	.align 8
 
- .L_2il0floatpacket.10:
 
- 	.long	0x3de6af28,0x3e9fdf47
 
- 	.type	.L_2il0floatpacket.10,@object
 
- 	.size	.L_2il0floatpacket.10,8
 
- 	.align 8
 
- .L_2il0floatpacket.11:
 
- 	.long	0x00000000,0x3ff00000
 
- 	.type	.L_2il0floatpacket.11,@object
 
- 	.size	.L_2il0floatpacket.11,8
 
- 	.align 4
 
- _TWO_52H:
 
- 	.long	0
 
- 	.long	1127743488
 
- 	.type	_TWO_52H,@object
 
- 	.size	_TWO_52H,8
 
- 	.align 4
 
- _two_32p1:
 
- 	.long	1048576
 
- 	.long	1106247680
 
- 	.type	_two_32p1,@object
 
- 	.size	_two_32p1,8
 
- 	.align 4
 
- _two_32:
 
- 	.long	0
 
- 	.long	1106247680
 
- 	.type	_two_32,@object
 
- 	.size	_two_32,8
 
- 	.align 4
 
- _range:
 
- 	.long	4294967295
 
- 	.long	1083179007
 
- 	.long	4294967295
 
- 	.long	1083232255
 
- 	.type	_range,@object
 
- 	.size	_range,16
 
- 	.align 4
 
- SC2_BIAS:
 
- 	.long	511
 
- 	.long	1535
 
- 	.type	SC2_BIAS,@object
 
- 	.size	SC2_BIAS,8
 
- 	.align 4
 
- _SC2:
 
- 	.long	0
 
- 	.long	1609564160
 
- 	.long	0
 
- 	.long	535822336
 
- 	.type	_SC2,@object
 
- 	.size	_SC2,16
 
- 	.align 4
 
- _small_value_64:
 
- 	.long	0
 
- 	.long	24117248
 
- 	.long	0
 
- 	.long	2171600896
 
- 	.type	_small_value_64,@object
 
- 	.size	_small_value_64,16
 
- 	.align 4
 
- _large_value_64:
 
- 	.long	0
 
- 	.long	2121269248
 
- 	.long	0
 
- 	.long	4268752896
 
- 	.type	_large_value_64,@object
 
- 	.size	_large_value_64,16
 
- 	.align 4
 
- _inf_zero:
 
- 	.long	0
 
- 	.long	2146435072
 
- 	.long	0
 
- 	.long	0
 
- 	.type	_inf_zero,@object
 
- 	.size	_inf_zero,16
 
- 	.data
 
- 	.section .note.GNU-stack, ""
 
- // -- Begin DWARF2 SEGMENT .eh_frame
 
- 	.section .eh_frame,"a",@progbits
 
- .eh_frame_seg:
 
- 	.align 1
 
- # End
 
 
  |