/* * 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 * History: * 03-14-2016 Initial version. numerics svn rev. 12864 */ .file "atanh_gen.c" .text ..TXTST0: # -- Begin atanh .text .align 16,0x90 .globl atanh atanh: # parameter 1: %xmm0 ..B1.1: .cfi_startproc ..___tag_value_atanh.1: ..L2: movsd %xmm0, -8(%rsp) movl -4(%rsp), %esi movl %esi, %edx andl $2147483647, %edx cmpl $1072693248, %edx jae ..B1.12 ..B1.2: cmpl $1068498944, %edx jae ..B1.11 ..B1.3: cmpl $1012924416, %edx jae ..B1.10 ..B1.4: shrl $31, %esi cmpl $1048576, %edx jb ..B1.6 ..B1.5: lea _ones(%rip), %rax movsd (%rax), %xmm1 addsd %xmm0, %xmm1 movsd %xmm1, -40(%rsp) movsd -40(%rsp), %xmm2 mulsd %xmm2, %xmm0 ret ..B1.6: movl -8(%rsp), %eax orl %eax, %edx je ..B1.8 ..B1.7: lea _small_value_64(%rip), %rax movsd -8(%rsp), %xmm0 movsd (%rax,%rsi,8), %xmm1 mulsd (%rax), %xmm1 movsd %xmm1, -40(%rsp) addsd %xmm1, %xmm0 ret ..B1.8: movsd -8(%rsp), %xmm0 ..B1.9: ret ..B1.10: movsd -8(%rsp), %xmm4 lea 40+_PA(%rip), %rax movaps %xmm4, %xmm3 lea 32+_PA(%rip), %rsi mulsd %xmm4, %xmm3 lea 24+_PA(%rip), %rdx movaps %xmm3, %xmm1 lea 16+_PA(%rip), %rdi mulsd %xmm3, %xmm1 lea 8+_PA(%rip), %rcx movsd (%rax), %xmm0 lea _PA(%rip), %r8 mulsd %xmm1, %xmm0 movsd (%rsi), %xmm2 mulsd %xmm1, %xmm2 addsd (%rdx), %xmm0 mulsd %xmm1, %xmm0 addsd (%rdi), %xmm2 mulsd %xmm1, %xmm2 addsd (%rcx), %xmm0 mulsd %xmm3, %xmm0 addsd (%r8), %xmm2 addsd %xmm2, %xmm0 mulsd %xmm4, %xmm0 mulsd %xmm3, %xmm0 addsd %xmm4, %xmm0 ret ..B1.11: movsd -8(%rsp), %xmm9 lea 8+_ones(%rip), %rdi andps .L_2il0floatpacket.0(%rip), %xmm9 lea _ones(%rip), %r8 movsd %xmm9, -8(%rsp) movq $0x3ff0000000000000, %r10 andl $-268435456, -8(%rsp) pxor %xmm15, %xmm15 movsd -8(%rsp), %xmm12 movsd (%rdi), %xmm0 movaps %xmm12, %xmm6 movaps %xmm0, %xmm8 lea 32+_PL(%rip), %rdi movsd (%r8), %xmm4 lea 16+_PL(%rip), %r8 movq __libm_rcp_table_256@GOTPCREL(%rip), %rax addsd %xmm0, %xmm6 subsd %xmm12, %xmm9 addsd %xmm4, %xmm12 movaps %xmm6, %xmm2 movaps %xmm6, %xmm5 movaps %xmm9, %xmm3 movaps %xmm12, %xmm1 shrl $31, %esi addsd %xmm9, %xmm2 divsd %xmm2, %xmm8 movsd %xmm8, -32(%rsp) pxor %xmm2, %xmm2 andl $-268435456, -32(%rsp) movsd -32(%rsp), %xmm10 movaps %xmm10, %xmm7 subsd %xmm10, %xmm8 mulsd %xmm10, %xmm6 mulsd %xmm10, %xmm12 mulsd %xmm8, %xmm5 addsd %xmm8, %xmm7 addsd %xmm4, %xmm6 mulsd %xmm7, %xmm3 addsd %xmm3, %xmm5 addsd %xmm5, %xmm6 mulsd %xmm6, %xmm7 addsd %xmm7, %xmm8 mulsd %xmm8, %xmm1 addsd %xmm10, %xmm8 mulsd %xmm8, %xmm9 addsd %xmm9, %xmm1 movaps %xmm1, %xmm11 addsd %xmm12, %xmm11 movsd %xmm11, -8(%rsp) movl $0, -8(%rsp) movsd -8(%rsp), %xmm3 movl -4(%rsp), %ecx subsd %xmm3, %xmm12 sarl $20, %ecx addsd %xmm12, %xmm1 addl $-1023, %ecx movslq %ecx, %r9 shlq $52, %r9 subq %r9, %r10 lea _PL(%rip), %r9 movq %r10, -24(%rsp) lea 24+_PL(%rip), %r10 movsd -24(%rsp), %xmm13 mulsd %xmm13, %xmm1 cvtsi2sd %ecx, %xmm2 mulsd %xmm13, %xmm3 movaps %xmm1, %xmm14 lea _LN2(%rip), %rcx movsd (%r10), %xmm13 addsd %xmm3, %xmm14 movsd %xmm14, -16(%rsp) movl -12(%rsp), %r11d shrl $12, %r11d movzbl %r11b, %edx lea 8+_PL(%rip), %r11 movsd (%rdi), %xmm14 cvtss2sd (%rax,%rdx,4), %xmm15 mulsd %xmm15, %xmm3 mulsd %xmm15, %xmm1 addsd %xmm0, %xmm3 movaps %xmm3, %xmm12 shlq $4, %rdx addsd %xmm1, %xmm12 movaps %xmm12, %xmm0 mulsd %xmm12, %xmm0 mulsd %xmm0, %xmm14 mulsd %xmm0, %xmm13 addsd (%r8), %xmm14 addsd (%r11), %xmm13 mulsd %xmm0, %xmm14 mulsd %xmm0, %xmm13 addsd (%r9), %xmm14 mulsd %xmm12, %xmm13 mulsd %xmm0, %xmm14 movsd (%rcx), %xmm0 lea halfs(%rip), %rcx mulsd %xmm2, %xmm0 addsd %xmm13, %xmm14 movq __libm_log_table_256@GOTPCREL(%rip), %rax addsd %xmm14, %xmm1 addsd (%rax,%rdx), %xmm0 movsd (%rcx,%rsi,8), %xmm4 lea 8+_LN2(%rip), %rcx movsd %xmm4, -16(%rsp) addsd %xmm1, %xmm0 movsd (%rcx), %xmm1 mulsd %xmm1, %xmm2 addsd 8(%rax,%rdx), %xmm2 movsd %xmm2, -32(%rsp) addsd %xmm2, %xmm3 movsd %xmm3, -8(%rsp) addsd %xmm3, %xmm0 mulsd %xmm4, %xmm0 ret ..B1.12: jne ..B1.15 ..B1.13: cmpl $0, -8(%rsp) je ..B1.19 ..B1.14: lea _infs(%rip), %rax lea _zeros(%rip), %rdx movsd (%rax), %xmm0 mulsd (%rdx), %xmm0 ret ..B1.15: cmpl $2146435072, %edx jb ..B1.14 ..B1.16: jne ..B1.18 ..B1.17: cmpl $0, -8(%rsp) je ..B1.14 ..B1.18: lea _ones(%rip), %rax movsd -8(%rsp), %xmm0 mulsd (%rax), %xmm0 ret ..B1.19: lea _ones(%rip), %rax lea _zeros(%rip), %rdx shrl $31, %esi movsd (%rax,%rsi,8), %xmm0 divsd (%rdx), %xmm0 ret .align 16,0x90 .cfi_endproc .type atanh,@function .size atanh,.-atanh .data # -- End atanh .section .rodata, "a" .align 16 .align 16 .L_2il0floatpacket.0: .long 0xffffffff,0x7fffffff,0x00000000,0x00000000 .type .L_2il0floatpacket.0,@object .size .L_2il0floatpacket.0,16 .align 8 halfs: .long 0x00000000,0x3fe00000 .long 0x00000000,0xbfe00000 .type halfs,@object .size halfs,16 .align 4 _ones: .long 0 .long 1072693248 .long 0 .long 3220176896 .type _ones,@object .size _ones,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 _PA: .long 1431655765 .long 1070945621 .long 2576980801 .long 1070176665 .long 2453616913 .long 1069697316 .long 1427436931 .long 1069314503 .long 2129349532 .long 1068975486 .long 1629438381 .long 1068756329 .type _PA,@object .size _PA,48 .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 .align 4 _zeros: .long 0 .long 0 .long 0 .long 2147483648 .type _zeros,@object .size _zeros,16 .data .section .note.GNU-stack, "" // -- Begin DWARF2 SEGMENT .eh_frame .section .eh_frame,"a",@progbits .eh_frame_seg: .align 1 # End