/* * 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 "asinh_gen.c" .text ..TXTST0: # -- Begin asinh .text .align 16,0x90 .globl asinh asinh: # parameter 1: %xmm0 ..B1.1: .cfi_startproc ..___tag_value_asinh.1: ..L2: movsd %xmm0, -16(%rsp) movl -12(%rsp), %esi movl %esi, %edx andl $2147483647, %edx cmpl $2146435072, %edx jae ..B1.18 ..B1.2: cmpl $1102053376, %edx jae ..B1.16 ..B1.3: cmpl $1074987008, %edx jae ..B1.14 ..B1.4: cmpl $1068498944, %edx jae ..B1.13 ..B1.5: cmpl $1012924416, %edx jae ..B1.12 ..B1.6: shrl $31, %esi cmpl $1048576, %edx jb ..B1.8 ..B1.7: lea _SCALE(%rip), %rax lea _MINNORM(%rip), %rdx movl %esi, %esi lea 8+_SCALE(%rip), %rcx movsd (%rax), %xmm1 mulsd %xmm1, %xmm0 subsd (%rdx,%rsi,8), %xmm0 mulsd (%rcx), %xmm0 ret ..B1.8: movl -16(%rsp), %eax orl %eax, %edx je ..B1.10 ..B1.9: lea _small_value_64(%rip), %rax movsd -16(%rsp), %xmm0 movsd (%rax,%rsi,8), %xmm1 mulsd (%rax), %xmm1 movsd %xmm1, -40(%rsp) subsd %xmm1, %xmm0 ret ..B1.10: movsd -16(%rsp), %xmm0 ..B1.11: ret ..B1.12: movsd -16(%rsp), %xmm0 lea 32+_PA(%rip), %rax movaps %xmm0, %xmm4 lea 24+_PA(%rip), %rcx mulsd %xmm0, %xmm4 lea 16+_PA(%rip), %rdx movaps %xmm4, %xmm1 lea 8+_PA(%rip), %rsi mulsd %xmm4, %xmm1 lea _PA(%rip), %rdi movsd (%rax), %xmm3 movsd (%rcx), %xmm2 mulsd %xmm1, %xmm3 mulsd %xmm1, %xmm2 addsd (%rdx), %xmm3 addsd (%rsi), %xmm2 mulsd %xmm1, %xmm3 mulsd %xmm4, %xmm2 mulsd %xmm0, %xmm4 addsd %xmm2, %xmm3 addsd (%rdi), %xmm3 mulsd %xmm3, %xmm4 addsd %xmm4, %xmm0 ret ..B1.13: movsd -16(%rsp), %xmm5 xorl %eax, %eax andps .L_2il0floatpacket.2(%rip), %xmm5 movsd %xmm5, -16(%rsp) movaps %xmm5, %xmm1 movl %eax, -16(%rsp) movsd -16(%rsp), %xmm9 movaps %xmm9, %xmm7 subsd %xmm9, %xmm1 mulsd %xmm9, %xmm7 addsd %xmm9, %xmm5 movsd .L_2il0floatpacket.3(%rip), %xmm0 mulsd %xmm1, %xmm5 addsd %xmm0, %xmm7 movaps %xmm7, %xmm2 addsd %xmm5, %xmm2 sqrtsd %xmm2, %xmm2 movsd %xmm2, -24(%rsp) movl %eax, -24(%rsp) movsd -24(%rsp), %xmm8 movaps %xmm8, %xmm3 movaps %xmm8, %xmm4 mulsd %xmm8, %xmm3 subsd %xmm8, %xmm2 addsd %xmm8, %xmm9 mulsd %xmm2, %xmm4 subsd %xmm3, %xmm7 movaps %xmm8, %xmm6 subsd %xmm4, %xmm7 addsd %xmm2, %xmm6 addsd %xmm5, %xmm7 divsd %xmm6, %xmm7 addsd %xmm7, %xmm2 mulsd .L_2il0floatpacket.1(%rip), %xmm2 addsd %xmm2, %xmm1 jmp ..B1.15 ..B1.14: movsd -16(%rsp), %xmm1 andps .L_2il0floatpacket.2(%rip), %xmm1 movaps %xmm1, %xmm2 mulsd %xmm1, %xmm2 movsd .L_2il0floatpacket.3(%rip), %xmm0 movaps %xmm0, %xmm4 addsd %xmm0, %xmm2 sqrtsd %xmm2, %xmm2 movsd .L_2il0floatpacket.0(%rip), %xmm3 addsd %xmm1, %xmm2 mulsd %xmm3, %xmm1 divsd %xmm2, %xmm4 movsd %xmm1, -16(%rsp) movl $0, -16(%rsp) movsd -16(%rsp), %xmm9 subsd %xmm9, %xmm1 addsd %xmm4, %xmm1 ..B1.15: movaps %xmm1, %xmm2 movq $0x3ff0000000000000, %rax addsd %xmm9, %xmm2 movsd %xmm2, -16(%rsp) movl $0, -16(%rsp) movsd -16(%rsp), %xmm8 movzwl -10(%rsp), %ecx subsd %xmm8, %xmm9 andl $32752, %ecx addsd %xmm9, %xmm1 shrl $4, %ecx addl $-1023, %ecx movslq %ecx, %rdx negq %rdx shlq $52, %rdx addq %rax, %rdx movq %rdx, -32(%rsp) movsd -32(%rsp), %xmm3 mulsd %xmm3, %xmm1 mulsd %xmm3, %xmm8 movaps %xmm1, %xmm4 addsd %xmm8, %xmm4 movsd %xmm4, -24(%rsp) movl -20(%rsp), %edi shrl $12, %edi movzbl %dil, %edx jmp ..B1.17 ..B1.16: movsd -16(%rsp), %xmm0 andps .L_2il0floatpacket.2(%rip), %xmm0 movsd %xmm0, -16(%rsp) movzwl -10(%rsp), %eax movl %eax, %ecx andl $-32753, %eax andl $32752, %ecx orl $-49168, %eax movw %ax, -10(%rsp) movsd -16(%rsp), %xmm1 movl $0, -16(%rsp) movl -12(%rsp), %edx movsd -16(%rsp), %xmm8 shrl $4, %ecx subsd %xmm8, %xmm1 shrl $12, %edx addl $-1022, %ecx movzbl %dl, %edx movsd .L_2il0floatpacket.3(%rip), %xmm0 ..B1.17: movq __libm_rcp_table_256@GOTPCREL(%rip), %rdi pxor %xmm2, %xmm2 lea 32+_PL(%rip), %r8 lea 16+_PL(%rip), %r9 lea 24+_PL(%rip), %r11 lea _PL(%rip), %r10 cvtss2sd (%rdi,%rdx,4), %xmm2 mulsd %xmm2, %xmm8 lea 8+_PL(%rip), %rdi mulsd %xmm2, %xmm1 subsd %xmm0, %xmm8 movaps %xmm8, %xmm3 movsd (%r8), %xmm5 addsd %xmm1, %xmm3 movaps %xmm3, %xmm0 mulsd %xmm3, %xmm0 mulsd %xmm0, %xmm5 movsd (%r11), %xmm4 mulsd %xmm0, %xmm4 addsd (%r9), %xmm5 mulsd %xmm0, %xmm5 addsd (%rdi), %xmm4 mulsd %xmm0, %xmm4 addsd (%r10), %xmm5 mulsd %xmm0, %xmm5 pxor %xmm0, %xmm0 cvtsi2sd %ecx, %xmm0 mulsd %xmm3, %xmm4 lea _LN2(%rip), %rcx addsd %xmm4, %xmm5 movsd (%rcx), %xmm6 lea 8+_LN2(%rip), %rcx mulsd %xmm0, %xmm6 addsd %xmm5, %xmm1 movsd (%rcx), %xmm7 mulsd %xmm7, %xmm0 shlq $4, %rdx movq __libm_log_table_256@GOTPCREL(%rip), %rax shrl $31, %esi addsd (%rax,%rdx), %xmm6 addsd 8(%rax,%rdx), %xmm0 addsd %xmm6, %xmm1 addsd %xmm8, %xmm0 lea ones(%rip), %rdx movsd %xmm0, -16(%rsp) movsd (%rdx,%rsi,8), %xmm8 mulsd %xmm8, %xmm0 mulsd %xmm8, %xmm1 movsd %xmm8, -24(%rsp) addsd %xmm1, %xmm0 ret ..B1.18: movsd -16(%rsp), %xmm0 ret .align 16,0x90 .cfi_endproc .type asinh,@function .size asinh,.-asinh .data # -- End asinh .section .rodata, "a" .align 16 .align 16 .L_2il0floatpacket.2: .long 0xffffffff,0x7fffffff,0x00000000,0x00000000 .type .L_2il0floatpacket.2,@object .size .L_2il0floatpacket.2,16 .align 16 _SCALE: .long 0 .long 1177550848 .long 0 .long 967835648 .type _SCALE,@object .size _SCALE,16 .align 16 _MINNORM: .long 0 .long 1048576 .long 0 .long 2148532224 .type _MINNORM,@object .size _MINNORM,16 .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 8 .L_2il0floatpacket.3: .long 0x00000000,0x3ff00000 .type .L_2il0floatpacket.3,@object .size .L_2il0floatpacket.3,8 .align 8 ones: .long 0x00000000,0x3ff00000 .long 0x00000000,0xbff00000 .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 1431655746 .long 3217380693 .long 858875226 .long 1068708659 .long 2809361764 .long 3215383405 .long 1241898124 .long 1067392054 .long 966918340 .long 3214324669 .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 .data .section .note.GNU-stack, "" // -- Begin DWARF2 SEGMENT .eh_frame .section .eh_frame,"a",@progbits .eh_frame_seg: .align 1 # End