stdlib/mul_1.s

   1  .text
   2 .globl __mpn_mul_1
   3 .type __mpn_mul_1,@function
   4 .align 1<<4
   5 __mpn_mul_1:
   6  push %rbx
   7  xor %r10, %r10
   8  mov (%rsi), %rax
   9  mov %rdx, %rbx
  10  mul %rcx
  11  mov %rbx, %r11
  12  add %r10, %rax
  13  adc $0, %rdx
  14  and $3, %ebx
  15  jz .Lb0
  16  cmp $2, %ebx
  17  jz .Lb2
  18  jg .Lb3
  19 .Lb1: dec %r11
  20  jne .Lgt1
  21  mov %rax, (%rdi)
  22  jmp .Lret
  23 .Lgt1: lea 8(%rsi,%r11,8), %rsi
  24  lea -8(%rdi,%r11,8), %rdi
  25  neg %r11
  26  xor %r10, %r10
  27  xor %ebx, %ebx
  28  mov %rax, %r9
  29  mov (%rsi,%r11,8), %rax
  30  mov %rdx, %r8
  31  jmp .LL1
  32 .Lb0: lea (%rsi,%r11,8), %rsi
  33  lea -16(%rdi,%r11,8), %rdi
  34  neg %r11
  35  xor %r10, %r10
  36  mov %rax, %r8
  37  mov %rdx, %rbx
  38  jmp .LL0
  39 .Lb3: lea -8(%rsi,%r11,8), %rsi
  40  lea -24(%rdi,%r11,8), %rdi
  41  neg %r11
  42  mov %rax, %rbx
  43  mov %rdx, %r10
  44  jmp .LL3
  45 .Lb2: lea -16(%rsi,%r11,8), %rsi
  46  lea -32(%rdi,%r11,8), %rdi
  47  neg %r11
  48  xor %r8, %r8
  49  xor %ebx, %ebx
  50  mov %rax, %r10
  51  mov 24(%rsi,%r11,8), %rax
  52  mov %rdx, %r9
  53  jmp .LL2
  54  .p2align 4
  55 .Ltop: mov %r10, (%rdi,%r11,8)
  56  add %rax, %r9
  57  mov (%rsi,%r11,8), %rax
  58  adc %rdx, %r8
  59  mov $0, %r10d
  60 .LL1: mul %rcx
  61  mov %r9, 8(%rdi,%r11,8)
  62  add %rax, %r8
  63  adc %rdx, %rbx
  64 .LL0: mov 8(%rsi,%r11,8), %rax
  65  mul %rcx
  66  mov %r8, 16(%rdi,%r11,8)
  67  add %rax, %rbx
  68  adc %rdx, %r10
  69 .LL3: mov 16(%rsi,%r11,8), %rax
  70  mul %rcx
  71  mov %rbx, 24(%rdi,%r11,8)
  72  mov $0, %r8d # zero
  73  mov %r8, %rbx # zero
  74  add %rax, %r10
  75  mov 24(%rsi,%r11,8), %rax
  76  mov %r8, %r9 # zero
  77  adc %rdx, %r9
  78 .LL2: mul %rcx
  79  add $4, %r11
  80  js .Ltop
  81  mov %r10, (%rdi,%r11,8)
  82  add %rax, %r9
  83  adc %r8, %rdx
  84  mov %r9, 8(%rdi,%r11,8)
  85  add %r8, %rdx
  86 .Lret: mov %rdx, %rax
  87  pop %rbx
  88  ret
  89 .size __mpn_mul_1,.-__mpn_mul_1