/* * 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 "nearbyintl.c" .text ..TXTST0: # -- Begin nearbyintl .text .align 16,0x90 .globl nearbyintl nearbyintl: # parameter 1: 48 + %rsp ..B1.1: .cfi_startproc ..___tag_value_nearbyintl.1: ..L2: subq $40, %rsp .cfi_def_cfa_offset 48 xorb %dil, %dil ..B1.2: fnstcw 26(%rsp) ..B1.3: movzwl 56(%rsp), %r8d andl $32767, %r8d movzwl 26(%rsp), %r9d cmpl $16446, %r8d jge ..B1.95 ..B1.4: movl %r9d, %eax andl $3072, %eax cmpl $1024, %eax je ..B1.77 ..B1.5: cmpl $2048, %eax jne ..B1.24 ..B1.6: cmpl $16383, %r8d jl ..B1.19 ..B1.7: cmpl $16415, %r8d jl ..B1.9 ..B1.8: negl %r8d movl $-1, %edx addl $30, %r8d movl %r8d, %ecx shll %cl, %edx movl 48(%rsp), %eax andl %eax, %edx movl %edx, 48(%rsp) xorl %eax, %edx jmp ..B1.10 ..B1.9: negl %r8d movl $-1, %edx addl $30, %r8d movl %r8d, %ecx shll %cl, %edx movl 52(%rsp), %eax andl %eax, %edx movl %edx, 52(%rsp) xorl %eax, %edx orl 48(%rsp), %edx movl $0, 48(%rsp) ..B1.10: testb $-128, 57(%rsp) jne ..B1.18 ..B1.11: testl %edx, %edx je ..B1.18 ..B1.12: movl %r9d, %eax andl $768, %eax cmpl $768, %eax je ..B1.101 ..B1.13: orl $-64768, %r9d movw %r9w, 24(%rsp) ..B1.14: fldcw 24(%rsp) ..B1.15: fldt 48(%rsp) lea _ones(%rip), %rax faddl (%rax) fstpt (%rsp) ..B1.16: fldcw 26(%rsp) ..B1.17: fldt (%rsp) addq $40, %rsp .cfi_def_cfa_offset 8 ret .cfi_def_cfa_offset 48 ..B1.18: fldt 48(%rsp) addq $40, %rsp .cfi_def_cfa_offset 8 ret .cfi_def_cfa_offset 48 ..B1.19: testl %r8d, %r8d jne ..B1.23 ..B1.20: cmpq $0, 48(%rsp) jne ..B1.22 ..B1.21: fldt 48(%rsp) addq $40, %rsp .cfi_def_cfa_offset 8 ret .cfi_def_cfa_offset 48 ..B1.22: lea _smallest_value_64(%rip), %rax movq (%rax), %rdx movq %rdx, 16(%rsp) ..B1.23: movb 57(%rsp), %al lea _pone_nzero(%rip), %rdx andb $-128, %al shrb $7, %al movzbl %al, %ecx fldl (%rdx,%rcx,8) addq $40, %rsp .cfi_def_cfa_offset 8 ret .cfi_def_cfa_offset 48 ..B1.24: cmpl $3072, %eax jne ..B1.35 ..B1.25: cmpl $16383, %r8d jl ..B1.30 ..B1.26: cmpl $16415, %r8d jl ..B1.28 ..B1.27: negl %r8d movl $-1, %eax addl $30, %r8d movl %r8d, %ecx shll %cl, %eax andl 48(%rsp), %eax jmp ..B1.29 ..B1.28: negl %r8d movl $-1, %eax addl $30, %r8d movl %r8d, %ecx shll %cl, %eax andl %eax, 52(%rsp) xorl %eax, %eax ..B1.29: movl %eax, 48(%rsp) fldt 48(%rsp) addq $40, %rsp .cfi_def_cfa_offset 8 ret .cfi_def_cfa_offset 48 ..B1.30: testl %r8d, %r8d jne ..B1.34 ..B1.31: cmpl $0, 52(%rsp) jne ..B1.33 ..B1.32: cmpl $0, 48(%rsp) je ..B1.34 ..B1.33: lea _smallest_value_64(%rip), %rax movq (%rax), %rdx movq %rdx, 16(%rsp) ..B1.34: movb 57(%rsp), %al lea _zeros(%rip), %rdx andb $-128, %al shrb $7, %al movzbl %al, %ecx fldl (%rdx,%rcx,8) addq $40, %rsp .cfi_def_cfa_offset 8 ret .cfi_def_cfa_offset 48 ..B1.35: cmpl $16383, %r8d jl ..B1.69 ..B1.36: movl 48(%rsp), %esi cmpl $16414, %r8d jl ..B1.38 ..B1.37: movl %esi, %edx lea 2(%r8), %ecx shll %cl, %edx xorl %eax, %eax jmp ..B1.39 ..B1.38: movl 52(%rsp), %edx lea 2(%r8), %ecx shll %cl, %edx movl %esi, %eax ..B1.39: cmpl $16415, %r8d jl ..B1.41 ..B1.40: movl %r8d, %ecx movl $-1, %r10d negl %ecx addl $30, %ecx shll %cl, %r10d andl %r10d, %esi movl %esi, 48(%rsp) jmp ..B1.42 ..B1.41: movl %r8d, %ecx movl $-1, %r10d negl %ecx xorl %esi, %esi addl $30, %ecx shll %cl, %r10d movl $0, 48(%rsp) andl %r10d, 52(%rsp) ..B1.42: testl %edx, %edx jge ..B1.68 ..B1.43: andl $2147483647, %edx orl %eax, %edx je ..B1.51 ..B1.44: movl %r9d, %eax andl $768, %eax cmpl $768, %eax je ..B1.48 ..B1.45: orl $-64768, %r9d movw %r9w, 24(%rsp) ..B1.46: fldcw 24(%rsp) ..B1.47: movb $1, %dil ..B1.48: fldt 48(%rsp) lea _ones(%rip), %rdx movb 57(%rsp), %al andb $-128, %al shrb $7, %al movzbl %al, %ecx testb %dil, %dil faddl (%rdx,%rcx,8) fstpt (%rsp) je ..B1.50 ..B1.49: fldcw 26(%rsp) ..B1.50: fldt (%rsp) addq $40, %rsp .cfi_def_cfa_offset 8 ret .cfi_def_cfa_offset 48 ..B1.51: cmpl $16415, %r8d jl ..B1.60 ..B1.52: negl %r8d movl $1, %eax addl $30, %r8d movl %r8d, %ecx shll %cl, %eax testl %eax, %esi je ..B1.68 ..B1.53: movl %r9d, %eax andl $768, %eax cmpl $768, %eax je ..B1.57 ..B1.54: orl $-64768, %r9d movw %r9w, 24(%rsp) ..B1.55: fldcw 24(%rsp) ..B1.56: movb $1, %dil ..B1.57: fldt 48(%rsp) lea _ones(%rip), %rdx movb 57(%rsp), %al andb $-128, %al shrb $7, %al movzbl %al, %ecx testb %dil, %dil faddl (%rdx,%rcx,8) fstpt (%rsp) je ..B1.59 ..B1.58: fldcw 26(%rsp) ..B1.59: fldt (%rsp) addq $40, %rsp .cfi_def_cfa_offset 8 ret .cfi_def_cfa_offset 48 ..B1.60: negl %r8d movl $1, %eax addl $30, %r8d movl %r8d, %ecx shll %cl, %eax testl %eax, 52(%rsp) je ..B1.68 ..B1.61: movl %r9d, %eax andl $768, %eax cmpl $768, %eax je ..B1.65 ..B1.62: orl $-64768, %r9d movw %r9w, 24(%rsp) ..B1.63: fldcw 24(%rsp) ..B1.64: movb $1, %dil ..B1.65: fldt 48(%rsp) lea _ones(%rip), %rdx movb 57(%rsp), %al andb $-128, %al shrb $7, %al movzbl %al, %ecx testb %dil, %dil faddl (%rdx,%rcx,8) fstpt (%rsp) je ..B1.67 ..B1.66: fldcw 26(%rsp) ..B1.67: fldt (%rsp) addq $40, %rsp .cfi_def_cfa_offset 8 ret .cfi_def_cfa_offset 48 ..B1.68: fldt 48(%rsp) addq $40, %rsp .cfi_def_cfa_offset 8 ret .cfi_def_cfa_offset 48 ..B1.69: cmpl $16382, %r8d jg ..B1.76 ..B1.70: je ..B1.102 ..B1.71: testl %r8d, %r8d jne ..B1.75 ..B1.72: cmpl $0, 52(%rsp) jne ..B1.74 ..B1.73: cmpl $0, 48(%rsp) je ..B1.75 ..B1.74: lea _smallest_value_64(%rip), %rax movq (%rax), %rdx movq %rdx, 16(%rsp) ..B1.75: movb 57(%rsp), %al lea _zeros(%rip), %rdx andb $-128, %al shrb $7, %al movzbl %al, %ecx fldl (%rdx,%rcx,8) addq $40, %rsp .cfi_def_cfa_offset 8 ret .cfi_def_cfa_offset 48 ..B1.76: movb 57(%rsp), %al lea _ones(%rip), %rdx andb $-128, %al shrb $7, %al movzbl %al, %ecx fldl (%rdx,%rcx,8) addq $40, %rsp .cfi_def_cfa_offset 8 ret .cfi_def_cfa_offset 48 ..B1.77: cmpl $16383, %r8d jl ..B1.90 ..B1.78: cmpl $16415, %r8d jl ..B1.80 ..B1.79: negl %r8d movl $-1, %eax addl $30, %r8d movl %r8d, %ecx shll %cl, %eax movl 48(%rsp), %edx andl %edx, %eax movl %eax, 48(%rsp) xorl %eax, %edx jmp ..B1.81 ..B1.80: negl %r8d movl $-1, %eax addl $30, %r8d movl %r8d, %ecx shll %cl, %eax movl 52(%rsp), %edx andl %edx, %eax xorl %eax, %edx orl 48(%rsp), %edx movl %eax, 52(%rsp) movl $0, 48(%rsp) ..B1.81: testb $-128, 57(%rsp) je ..B1.89 ..B1.82: testl %edx, %edx je ..B1.89 ..B1.83: movl %r9d, %eax andl $768, %eax cmpl $768, %eax je ..B1.105 ..B1.84: orl $-64768, %r9d movw %r9w, 24(%rsp) ..B1.85: fldcw 24(%rsp) ..B1.86: fldt 48(%rsp) lea 8+_ones(%rip), %rax faddl (%rax) fstpt (%rsp) ..B1.87: fldcw 26(%rsp) ..B1.88: fldt (%rsp) addq $40, %rsp .cfi_def_cfa_offset 8 ret .cfi_def_cfa_offset 48 ..B1.89: fldt 48(%rsp) addq $40, %rsp .cfi_def_cfa_offset 8 ret .cfi_def_cfa_offset 48 ..B1.90: testl %r8d, %r8d jne ..B1.94 ..B1.91: cmpq $0, 48(%rsp) jne ..B1.93 ..B1.92: fldt 48(%rsp) addq $40, %rsp .cfi_def_cfa_offset 8 ret .cfi_def_cfa_offset 48 ..B1.93: lea _smallest_value_64(%rip), %rax movq (%rax), %rdx movq %rdx, 16(%rsp) ..B1.94: movb 57(%rsp), %al lea _pzero_none(%rip), %rdx andb $-128, %al shrb $7, %al movzbl %al, %ecx fldl (%rdx,%rcx,8) addq $40, %rsp .cfi_def_cfa_offset 8 ret .cfi_def_cfa_offset 48 ..B1.95: movl %r9d, %eax andl $768, %eax cmpl $768, %eax je ..B1.106 ..B1.96: orl $-64768, %r9d movw %r9w, 24(%rsp) ..B1.97: fldcw 24(%rsp) ..B1.98: fldt 48(%rsp) lea _ones(%rip), %rax fmull (%rax) fstpt (%rsp) ..B1.99: fldcw 26(%rsp) ..B1.100: fldt (%rsp) addq $40, %rsp .cfi_def_cfa_offset 8 ret .cfi_def_cfa_offset 48 ..B1.101: fldt 48(%rsp) lea _ones(%rip), %rax faddl (%rax) fstpt (%rsp) jmp ..B1.17 ..B1.102: movl 52(%rsp), %eax cmpl $-2147483648, %eax ja ..B1.76 ..B1.103: jne ..B1.75 ..B1.104: cmpl $0, 48(%rsp) ja ..B1.76 jmp ..B1.75 ..B1.105: fldt 48(%rsp) lea 8+_ones(%rip), %rax faddl (%rax) fstpt (%rsp) jmp ..B1.88 ..B1.106: fldt 48(%rsp) lea _ones(%rip), %rax fmull (%rax) fstpt (%rsp) jmp ..B1.100 .align 16,0x90 .cfi_endproc .type nearbyintl,@function .size nearbyintl,.-nearbyintl .data # -- End nearbyintl .section .rodata, "a" .align 4 .align 4 _ones: .long 0 .long 1072693248 .long 0 .long 3220176896 .type _ones,@object .size _ones,16 .align 4 _smallest_value_64: .long 1 .long 0 .long 1 .long 2147483648 .type _smallest_value_64,@object .size _smallest_value_64,16 .align 4 _pone_nzero: .long 0 .long 1072693248 .long 0 .long 2147483648 .type _pone_nzero,@object .size _pone_nzero,16 .align 4 _zeros: .long 0 .long 0 .long 0 .long 2147483648 .type _zeros,@object .size _zeros,16 .align 4 _pzero_none: .long 0 .long 0 .long 0 .long 3220176896 .type _pzero_none,@object .size _pzero_none,16 .data .section .note.GNU-stack, "" // -- Begin DWARF2 SEGMENT .eh_frame .section .eh_frame,"a",@progbits .eh_frame_seg: .align 1 # End