/* * 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 "libm_exp_k64.c" .text ..TXTST0: # -- Begin __libm_exp_k64 .text .align 16,0x90 .globl __libm_exp_k64 __libm_exp_k64: # parameter 1: %xmm0 # parameter 2: %rdi # parameter 3: %rsi ..B1.1: .cfi_startproc ..___tag_value___libm_exp_k64.1: ..L2: movsd %xmm0, -8(%rsp) movzwl -2(%rsp), %eax andl $32752, %eax movb -1(%rsp), %dl andb $-128, %dl shrl $4, %eax shrb $7, %dl cmpl $2047, %eax je ..B1.10 ..B1.2: cmpl $966, %eax jge ..B1.6 ..B1.3: movl $0, (%rdi) cmpl $917, %eax jge ..B1.5 ..B1.4: movq $0x3ff0000000000000, %rax movq %rax, (%rsi) movq $0, 8(%rsi) ret ..B1.5: movsd .L_2il0floatpacket.9(%rip), %xmm0 movsd -8(%rsp), %xmm2 movaps %xmm0, %xmm1 addsd %xmm2, %xmm1 movsd %xmm1, (%rsi) subsd %xmm0, %xmm1 movsd %xmm1, -24(%rsp) subsd %xmm1, %xmm2 movsd %xmm2, 8(%rsi) ret ..B1.6: cmpl $1035, %eax jge ..B1.8 ..B1.7: movsd -8(%rsp), %xmm0 lea _TWO_52H(%rip), %rax movsd .L_2il0floatpacket.0(%rip), %xmm4 movsd .L_2il0floatpacket.1(%rip), %xmm2 movsd .L_2il0floatpacket.2(%rip), %xmm3 mulsd %xmm0, %xmm4 movsd (%rax), %xmm1 movsd .L_2il0floatpacket.4(%rip), %xmm12 addsd %xmm1, %xmm4 movsd %xmm4, -24(%rsp) subsd %xmm1, %xmm4 mulsd %xmm4, %xmm2 mulsd %xmm3, %xmm4 subsd %xmm2, %xmm0 movaps %xmm0, %xmm7 movsd %xmm0, -8(%rsp) subsd %xmm4, %xmm7 movaps %xmm7, %xmm8 subsd %xmm7, %xmm0 movsd .L_2il0floatpacket.6(%rip), %xmm9 subsd %xmm4, %xmm0 movsd .L_2il0floatpacket.9(%rip), %xmm5 addsd %xmm0, %xmm8 addsd %xmm7, %xmm5 movaps %xmm8, %xmm10 mulsd %xmm8, %xmm10 mulsd %xmm10, %xmm12 mulsd %xmm10, %xmm9 addsd .L_2il0floatpacket.5(%rip), %xmm12 addsd .L_2il0floatpacket.7(%rip), %xmm9 mulsd %xmm10, %xmm12 mulsd %xmm8, %xmm9 movsd %xmm5, -16(%rsp) addsd %xmm9, %xmm12 movl $0, -16(%rsp) movsd -16(%rsp), %xmm14 movsd .L_2il0floatpacket.3(%rip), %xmm6 movsd .L_2il0floatpacket.8(%rip), %xmm11 addsd %xmm14, %xmm6 mulsd %xmm10, %xmm12 mulsd %xmm10, %xmm11 subsd %xmm6, %xmm7 addsd %xmm11, %xmm12 addsd %xmm7, %xmm0 movl -24(%rsp), %r8d movl %r8d, %edx shll $25, %edx addsd %xmm12, %xmm0 sarl $25, %edx subl %edx, %r8d movslq %edx, %rdx shlq $4, %rdx movq __libm_exp_table_128@GOTPCREL(%rip), %rcx sarl $7, %r8d movsd 1032(%rcx,%rdx), %xmm1 movaps %xmm1, %xmm13 mulsd %xmm0, %xmm1 addsd %xmm14, %xmm0 mulsd %xmm14, %xmm13 movsd 1024(%rcx,%rdx), %xmm15 mulsd %xmm0, %xmm15 movl %r8d, (%rdi) addsd %xmm15, %xmm1 movsd %xmm13, (%rsi) movsd %xmm1, 8(%rsi) ret ..B1.8: movzbl %dl, %edx lea _inf_zeros(%rip), %rax movl $0, (%rdi) movq $0, 8(%rsi) movq (%rax,%rdx,8), %rcx movq %rcx, (%rsi) ..B1.9: ret ..B1.10: testl $1048575, -4(%rsp) jne ..B1.13 ..B1.11: cmpl $0, -8(%rsp) jne ..B1.13 ..B1.12: movzbl %dl, %edx lea _inf_zeros(%rip), %rax movsd (%rax,%rdx,8), %xmm0 jmp ..B1.14 ..B1.13: movsd -8(%rsp), %xmm0 ..B1.14: movl $0, (%rdi) movsd %xmm0, (%rsi) movq $0, 8(%rsi) ret .align 16,0x90 .cfi_endproc .type __libm_exp_k64,@function .size __libm_exp_k64,.-__libm_exp_k64 .data # -- End __libm_exp_k64 .section .rodata, "a" .align 8 .align 8 .L_2il0floatpacket.0: .long 0x652b82fe,0x40671547 .type .L_2il0floatpacket.0,@object .size .L_2il0floatpacket.0,8 .align 8 .L_2il0floatpacket.1: .long 0x00000000,0x3f762e42 .type .L_2il0floatpacket.1,@object .size .L_2il0floatpacket.1,8 .align 8 .L_2il0floatpacket.2: .long 0x3de6af28,0x3e2fdf47 .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 0x87372663,0x3f56c16c .type .L_2il0floatpacket.4,@object .size .L_2il0floatpacket.4,8 .align 8 .L_2il0floatpacket.5: .long 0x5555541d,0x3fa55555 .type .L_2il0floatpacket.5,@object .size .L_2il0floatpacket.5,8 .align 8 .L_2il0floatpacket.6: .long 0x6887cd7c,0x3f811111 .type .L_2il0floatpacket.6,@object .size .L_2il0floatpacket.6,8 .align 8 .L_2il0floatpacket.7: .long 0x55555405,0x3fc55555 .type .L_2il0floatpacket.7,@object .size .L_2il0floatpacket.7,8 .align 8 .L_2il0floatpacket.8: .long 0x00000000,0x3fe00000 .type .L_2il0floatpacket.8,@object .size .L_2il0floatpacket.8,8 .align 8 .L_2il0floatpacket.9: .long 0x00000000,0x3ff00000 .type .L_2il0floatpacket.9,@object .size .L_2il0floatpacket.9,8 .align 4 _TWO_52H: .long 0 .long 1127743488 .type _TWO_52H,@object .size _TWO_52H,8 .align 4 _inf_zeros: .long 0 .long 2146435072 .long 0 .long 0 .type _inf_zeros,@object .size _inf_zeros,16 .data .section .note.GNU-stack, "" // -- Begin DWARF2 SEGMENT .eh_frame .section .eh_frame,"a",@progbits .eh_frame_seg: .align 1 # End