// linker define ge25519_double_scalarmult_process // linker use mask63 /* Assembly for double base scalar multiplication. * * This assembly has been developed after studying the * amd64-64-24k implementation of the work "High speed * high security signatures" by Bernstein et al. */ #define mask63 CRYPTO_SHARED_NAMESPACE(mask63) .p2align 5 .globl _CRYPTO_SHARED_NAMESPACE(ge25519_double_scalarmult_process) .globl CRYPTO_SHARED_NAMESPACE(ge25519_double_scalarmult_process) _CRYPTO_SHARED_NAMESPACE(ge25519_double_scalarmult_process): CRYPTO_SHARED_NAMESPACE(ge25519_double_scalarmult_process): movq %rsp,%r11 andq $-32,%rsp subq $464,%rsp movq %r11,0(%rsp) movq %r12,8(%rsp) movq %r13,16(%rsp) movq %r14,24(%rsp) movq %r15,32(%rsp) movq %rbx,40(%rsp) movq %rbp,48(%rsp) // setint movq $0,%rax movq $1,%rbx movq %rax,0(%rdi) movq %rax,8(%rdi) movq %rax,16(%rdi) movq %rax,24(%rdi) movq %rbx,32(%rdi) movq %rax,40(%rdi) movq %rax,48(%rdi) movq %rax,56(%rdi) movq %rbx,64(%rdi) movq %rax,72(%rdi) movq %rax,80(%rdi) movq %rax,88(%rdi) movq %rax,96(%rdi) movq %rax,104(%rdi) movq %rax,112(%rdi) movq %rax,120(%rdi) movq $255,%rax addq $255,%rsi addq $255,%rdx movq %rdi,56(%rsp) movq %rcx,64(%rsp) movq %r8,72(%rsp) .L1: movb 0(%rsi),%r14b movb 0(%rdx),%r15b cmpb $0,%r14b jg .L2 cmpb $0,%r15b jg .L2 decq %rsi decq %rdx decq %rax cmpq $0,%rax jge .L1 cmpq $0,%rax jl .L10 .L2: movq %rsi,80(%rsp) movq %rdx,88(%rsp) movq %rax,96(%rsp) .L3: /* dbl p1p1 */ // square xorq %r13,%r13 movq 0(%rdi),%rdx mulx 8(%rdi),%r9,%r10 mulx 16(%rdi),%rcx,%r11 adcx %rcx,%r10 mulx 24(%rdi),%rcx,%r12 adcx %rcx,%r11 adcx %r13,%r12 movq 8(%rdi),%rdx xorq %r14,%r14 mulx 16(%rdi),%rcx,%rdx adcx %rcx,%r11 adox %rdx,%r12 movq 8(%rdi),%rdx mulx 24(%rdi),%rcx,%rdx adcx %rcx,%r12 adox %rdx,%r13 adcx %r14,%r13 xorq %r15,%r15 movq 16(%rdi),%rdx mulx 24(%rdi),%rcx,%r14 adcx %rcx,%r13 adcx %r15,%r14 shld $1,%r14,%r15 shld $1,%r13,%r14 shld $1,%r12,%r13 shld $1,%r11,%r12 shld $1,%r10,%r11 shld $1,%r9,%r10 shlq $1,%r9 xorq %rdx,%rdx movq 0(%rdi),%rdx mulx %rdx,%r8,%rdx adcx %rdx,%r9 movq 8(%rdi),%rdx mulx %rdx,%rcx,%rdx adcx %rcx,%r10 adcx %rdx,%r11 movq 16(%rdi),%rdx mulx %rdx,%rcx,%rdx adcx %rcx,%r12 adcx %rdx,%r13 movq 24(%rdi),%rdx mulx %rdx,%rcx,%rdx adcx %rcx,%r14 adcx %rdx,%r15 xorq %rbp,%rbp movq $38,%rdx mulx %r12,%rax,%r12 adcx %rax,%r8 adox %r12,%r9 mulx %r13,%rcx,%r13 adcx %rcx,%r9 adox %r13,%r10 mulx %r14,%rcx,%r14 adcx %rcx,%r10 adox %r14,%r11 mulx %r15,%rcx,%r15 adcx %rcx,%r11 adox %rbp,%r15 adcx %rbp,%r15 shld $1,%r11,%r15 andq mask63(%rip),%r11 imul $19,%r15,%r15 addq %r15,%r8 adcq $0,%r9 adcq $0,%r10 adcq $0,%r11 movq %r8,112(%rsp) movq %r9,120(%rsp) movq %r10,128(%rsp) movq %r11,136(%rsp) // square xorq %r13,%r13 movq 32(%rdi),%rdx mulx 40(%rdi),%r9,%r10 mulx 48(%rdi),%rcx,%r11 adcx %rcx,%r10 mulx 56(%rdi),%rcx,%r12 adcx %rcx,%r11 adcx %r13,%r12 movq 40(%rdi),%rdx xorq %r14,%r14 mulx 48(%rdi),%rcx,%rdx adcx %rcx,%r11 adox %rdx,%r12 movq 40(%rdi),%rdx mulx 56(%rdi),%rcx,%rdx adcx %rcx,%r12 adox %rdx,%r13 adcx %r14,%r13 xorq %r15,%r15 movq 48(%rdi),%rdx mulx 56(%rdi),%rcx,%r14 adcx %rcx,%r13 adcx %r15,%r14 shld $1,%r14,%r15 shld $1,%r13,%r14 shld $1,%r12,%r13 shld $1,%r11,%r12 shld $1,%r10,%r11 shld $1,%r9,%r10 shlq $1,%r9 xorq %rdx,%rdx movq 32(%rdi),%rdx mulx %rdx,%r8,%rdx adcx %rdx,%r9 movq 40(%rdi),%rdx mulx %rdx,%rcx,%rdx adcx %rcx,%r10 adcx %rdx,%r11 movq 48(%rdi),%rdx mulx %rdx,%rcx,%rdx adcx %rcx,%r12 adcx %rdx,%r13 movq 56(%rdi),%rdx mulx %rdx,%rcx,%rdx adcx %rcx,%r14 adcx %rdx,%r15 xorq %rbp,%rbp movq $38,%rdx mulx %r12,%rax,%r12 adcx %rax,%r8 adox %r12,%r9 mulx %r13,%rcx,%r13 adcx %rcx,%r9 adox %r13,%r10 mulx %r14,%rcx,%r14 adcx %rcx,%r10 adox %r14,%r11 mulx %r15,%rcx,%r15 adcx %rcx,%r11 adox %rbp,%r15 adcx %rbp,%r15 shld $1,%r11,%r15 andq mask63(%rip),%r11 imul $19,%r15,%r15 addq %r15,%r8 adcq $0,%r9 adcq $0,%r10 adcq $0,%r11 movq %r8,144(%rsp) movq %r9,152(%rsp) movq %r10,160(%rsp) movq %r11,168(%rsp) // square xorq %r13,%r13 movq 64(%rdi),%rdx mulx 72(%rdi),%r9,%r10 mulx 80(%rdi),%rcx,%r11 adcx %rcx,%r10 mulx 88(%rdi),%rcx,%r12 adcx %rcx,%r11 adcx %r13,%r12 movq 72(%rdi),%rdx xorq %r14,%r14 mulx 80(%rdi),%rcx,%rdx adcx %rcx,%r11 adox %rdx,%r12 movq 72(%rdi),%rdx mulx 88(%rdi),%rcx,%rdx adcx %rcx,%r12 adox %rdx,%r13 adcx %r14,%r13 xorq %r15,%r15 movq 80(%rdi),%rdx mulx 88(%rdi),%rcx,%r14 adcx %rcx,%r13 adcx %r15,%r14 shld $1,%r14,%r15 shld $1,%r13,%r14 shld $1,%r12,%r13 shld $1,%r11,%r12 shld $1,%r10,%r11 shld $1,%r9,%r10 shlq $1,%r9 xorq %rdx,%rdx movq 64(%rdi),%rdx mulx %rdx,%r8,%rdx adcx %rdx,%r9 movq 72(%rdi),%rdx mulx %rdx,%rcx,%rdx adcx %rcx,%r10 adcx %rdx,%r11 movq 80(%rdi),%rdx mulx %rdx,%rcx,%rdx adcx %rcx,%r12 adcx %rdx,%r13 movq 88(%rdi),%rdx mulx %rdx,%rcx,%rdx adcx %rcx,%r14 adcx %rdx,%r15 xorq %rbp,%rbp movq $38,%rdx mulx %r12,%rax,%r12 adcx %rax,%r8 adox %r12,%r9 mulx %r13,%rcx,%r13 adcx %rcx,%r9 adox %r13,%r10 mulx %r14,%rcx,%r14 adcx %rcx,%r10 adox %r14,%r11 mulx %r15,%rcx,%r15 adcx %rcx,%r11 adox %rbp,%r15 adcx %rbp,%r15 shld $1,%r11,%r15 andq mask63(%rip),%r11 imul $19,%r15,%r15 addq %r15,%r8 adcq $0,%r9 adcq $0,%r10 adcq $0,%r11 // double addq %r8,%r8 adcq %r9,%r9 adcq %r10,%r10 adcq %r11,%r11 movq $0,%rdx movq $38,%rcx cmovae %rdx,%rcx addq %rcx,%r8 adcq %rdx,%r9 adcq %rdx,%r10 adcq %rdx,%r11 cmovc %rcx,%rdx addq %rdx,%r8 movq %r8,176(%rsp) movq %r9,184(%rsp) movq %r10,192(%rsp) movq %r11,200(%rsp) // neg movq $0,%r8 movq $0,%r9 movq $0,%r10 movq $0,%r11 subq 112(%rsp),%r8 sbbq 120(%rsp),%r9 sbbq 128(%rsp),%r10 sbbq 136(%rsp),%r11 movq $0,%rdx movq $38,%rax cmovae %rdx,%rax subq %rax,%r8 sbbq %rdx,%r9 sbbq %rdx,%r10 sbbq %rdx,%r11 cmovc %rax,%rdx subq %rdx,%r8 movq %r8,112(%rsp) movq %r9,120(%rsp) movq %r10,128(%rsp) movq %r11,136(%rsp) // copy movq %r8,%r12 movq %r9,%r13 movq %r10,%r14 movq %r11,%r15 // sub subq 144(%rsp),%r8 sbbq 152(%rsp),%r9 sbbq 160(%rsp),%r10 sbbq 168(%rsp),%r11 movq $0,%rdx movq $38,%rax cmovae %rdx,%rax subq %rax,%r8 sbbq %rdx,%r9 sbbq %rdx,%r10 sbbq %rdx,%r11 cmovc %rax,%rdx subq %rdx,%r8 movq %r8,304(%rsp) movq %r9,312(%rsp) movq %r10,320(%rsp) movq %r11,328(%rsp) // add addq 144(%rsp),%r12 adcq 152(%rsp),%r13 adcq 160(%rsp),%r14 adcq 168(%rsp),%r15 movq $0,%rdx movq $38,%rax cmovae %rdx,%rax addq %rax,%r12 adcq %rdx,%r13 adcq %rdx,%r14 adcq %rdx,%r15 cmovc %rax,%rdx subq %rdx,%r12 movq %r12,272(%rsp) movq %r13,280(%rsp) movq %r14,288(%rsp) movq %r15,296(%rsp) // sub subq 176(%rsp),%r12 sbbq 184(%rsp),%r13 sbbq 192(%rsp),%r14 sbbq 200(%rsp),%r15 movq $0,%rdx movq $38,%rax cmovae %rdx,%rax subq %rax,%r12 sbbq %rdx,%r13 sbbq %rdx,%r14 sbbq %rdx,%r15 cmovc %rax,%rdx subq %rdx,%r12 movq %r12,336(%rsp) movq %r13,344(%rsp) movq %r14,352(%rsp) movq %r15,360(%rsp) // add movq 0(%rdi),%rbx movq 8(%rdi),%rbp movq 16(%rdi),%rcx movq 24(%rdi),%rsi addq 32(%rdi),%rbx adcq 40(%rdi),%rbp adcq 48(%rdi),%rcx adcq 56(%rdi),%rsi movq $0,%rdx movq $38,%rax cmovae %rdx,%rax addq %rax,%rbx adcq %rdx,%rbp adcq %rdx,%rcx adcq %rdx,%rsi cmovc %rax,%rdx addq %rdx,%rbx // square xorq %r13,%r13 movq %rbx,%rdx mulx %rbp,%r9,%r10 mulx %rcx,%r8,%r11 adcx %r8,%r10 mulx %rsi,%r8,%r12 adcx %r8,%r11 adcx %r13,%r12 movq %rbp,%rdx xorq %r14,%r14 mulx %rcx,%r8,%rdx adcx %r8,%r11 adox %rdx,%r12 movq %rbp,%rdx mulx %rsi,%r8,%rdx adcx %r8,%r12 adox %rdx,%r13 adcx %r14,%r13 xorq %r15,%r15 movq %rcx,%rdx mulx %rsi,%r8,%r14 adcx %r8,%r13 adcx %r15,%r14 shld $1,%r14,%r15 shld $1,%r13,%r14 shld $1,%r12,%r13 shld $1,%r11,%r12 shld $1,%r10,%r11 shld $1,%r9,%r10 shlq $1,%r9 xorq %rdx,%rdx movq %rbx,%rdx mulx %rdx,%r8,%rdx adcx %rdx,%r9 movq %rbp,%rdx mulx %rdx,%rax,%rdx adcx %rax,%r10 adcx %rdx,%r11 movq %rcx,%rdx mulx %rdx,%rax,%rdx adcx %rax,%r12 adcx %rdx,%r13 movq %rsi,%rdx mulx %rdx,%rax,%rdx adcx %rax,%r14 adcx %rdx,%r15 xorq %rbp,%rbp movq $38,%rdx mulx %r12,%rax,%r12 adcx %rax,%r8 adox %r12,%r9 mulx %r13,%rcx,%r13 adcx %rcx,%r9 adox %r13,%r10 mulx %r14,%rcx,%r14 adcx %rcx,%r10 adox %r14,%r11 mulx %r15,%rcx,%r15 adcx %rcx,%r11 adox %rbp,%r15 adcx %rbp,%r15 shld $1,%r11,%r15 andq mask63(%rip),%r11 imul $19,%r15,%r15 addq %r15,%r8 adcq $0,%r9 adcq $0,%r10 adcq $0,%r11 // add addq 112(%rsp),%r8 adcq 120(%rsp),%r9 adcq 128(%rsp),%r10 adcq 136(%rsp),%r11 movq $0,%rdx movq $38,%rax cmovae %rdx,%rax addq %rax,%r8 adcq %rdx,%r9 adcq %rdx,%r10 adcq %rdx,%r11 cmovc %rax,%rdx addq %rdx,%r8 // sub subq 144(%rsp),%r8 sbbq 152(%rsp),%r9 sbbq 160(%rsp),%r10 sbbq 168(%rsp),%r11 movq $0,%rdx movq $38,%rax cmovae %rdx,%rax subq %rax,%r8 sbbq %rdx,%r9 sbbq %rdx,%r10 sbbq %rdx,%r11 cmovc %rax,%rdx subq %rdx,%r8 movq %r8,240(%rsp) movq %r9,248(%rsp) movq %r10,256(%rsp) movq %r11,264(%rsp) movq 80(%rsp),%rsi movb 0(%rsi),%r14b movb %r14b,104(%rsp) decq %rsi movq %rsi,80(%rsp) movq 64(%rsp),%rdi cmpb $0,%r14b jg .L4 jl .L5 je .L6 .L4: /* p1p1 to p3 */ // mul xorq %r13,%r13 movq 240(%rsp),%rdx mulx 336(%rsp),%r8,%r9 mulx 344(%rsp),%rcx,%r10 adcx %rcx,%r9 mulx 352(%rsp),%rcx,%r11 adcx %rcx,%r10 mulx 360(%rsp),%rcx,%r12 adcx %rcx,%r11 adcx %r13,%r12 xorq %r14,%r14 movq 248(%rsp),%rdx mulx 336(%rsp),%rcx,%rbp adcx %rcx,%r9 adox %rbp,%r10 mulx 344(%rsp),%rcx,%rbp adcx %rcx,%r10 adox %rbp,%r11 mulx 352(%rsp),%rcx,%rbp adcx %rcx,%r11 adox %rbp,%r12 mulx 360(%rsp),%rcx,%rbp adcx %rcx,%r12 adox %rbp,%r13 adcx %r14,%r13 xorq %r15,%r15 movq 256(%rsp),%rdx mulx 336(%rsp),%rcx,%rbp adcx %rcx,%r10 adox %rbp,%r11 mulx 344(%rsp),%rcx,%rbp adcx %rcx,%r11 adox %rbp,%r12 mulx 352(%rsp),%rcx,%rbp adcx %rcx,%r12 adox %rbp,%r13 mulx 360(%rsp),%rcx,%rbp adcx %rcx,%r13 adox %rbp,%r14 adcx %r15,%r14 xorq %rax,%rax movq 264(%rsp),%rdx mulx 336(%rsp),%rcx,%rbp adcx %rcx,%r11 adox %rbp,%r12 mulx 344(%rsp),%rcx,%rbp adcx %rcx,%r12 adox %rbp,%r13 mulx 352(%rsp),%rcx,%rbp adcx %rcx,%r13 adox %rbp,%r14 mulx 360(%rsp),%rcx,%rbp adcx %rcx,%r14 adox %rbp,%r15 adcx %rax,%r15 xorq %rbp,%rbp movq $38,%rdx mulx %r12,%rax,%r12 adcx %rax,%r8 adox %r12,%r9 mulx %r13,%rcx,%r13 adcx %rcx,%r9 adox %r13,%r10 mulx %r14,%rcx,%r14 adcx %rcx,%r10 adox %r14,%r11 mulx %r15,%rcx,%r15 adcx %rcx,%r11 adox %rbp,%r15 adcx %rbp,%r15 shld $1,%r11,%r15 andq mask63(%rip),%r11 imul $19,%r15,%r15 addq %r15,%r8 adcq $0,%r9 adcq $0,%r10 adcq $0,%r11 movq %r8,112(%rsp) movq %r9,120(%rsp) movq %r10,128(%rsp) movq %r11,136(%rsp) // mul xorq %r13,%r13 movq 272(%rsp),%rdx mulx 304(%rsp),%r8,%r9 mulx 312(%rsp),%rcx,%r10 adcx %rcx,%r9 mulx 320(%rsp),%rcx,%r11 adcx %rcx,%r10 mulx 328(%rsp),%rcx,%r12 adcx %rcx,%r11 adcx %r13,%r12 xorq %r14,%r14 movq 280(%rsp),%rdx mulx 304(%rsp),%rcx,%rbp adcx %rcx,%r9 adox %rbp,%r10 mulx 312(%rsp),%rcx,%rbp adcx %rcx,%r10 adox %rbp,%r11 mulx 320(%rsp),%rcx,%rbp adcx %rcx,%r11 adox %rbp,%r12 mulx 328(%rsp),%rcx,%rbp adcx %rcx,%r12 adox %rbp,%r13 adcx %r14,%r13 xorq %r15,%r15 movq 288(%rsp),%rdx mulx 304(%rsp),%rcx,%rbp adcx %rcx,%r10 adox %rbp,%r11 mulx 312(%rsp),%rcx,%rbp adcx %rcx,%r11 adox %rbp,%r12 mulx 320(%rsp),%rcx,%rbp adcx %rcx,%r12 adox %rbp,%r13 mulx 328(%rsp),%rcx,%rbp adcx %rcx,%r13 adox %rbp,%r14 adcx %r15,%r14 xorq %rax,%rax movq 296(%rsp),%rdx mulx 304(%rsp),%rcx,%rbp adcx %rcx,%r11 adox %rbp,%r12 mulx 312(%rsp),%rcx,%rbp adcx %rcx,%r12 adox %rbp,%r13 mulx 320(%rsp),%rcx,%rbp adcx %rcx,%r13 adox %rbp,%r14 mulx 328(%rsp),%rcx,%rbp adcx %rcx,%r14 adox %rbp,%r15 adcx %rax,%r15 xorq %rbp,%rbp movq $38,%rdx mulx %r12,%rax,%r12 adcx %rax,%r8 adox %r12,%r9 mulx %r13,%rcx,%r13 adcx %rcx,%r9 adox %r13,%r10 mulx %r14,%rcx,%r14 adcx %rcx,%r10 adox %r14,%r11 mulx %r15,%rcx,%r15 adcx %rcx,%r11 adox %rbp,%r15 adcx %rbp,%r15 shld $1,%r11,%r15 andq mask63(%rip),%r11 imul $19,%r15,%r15 addq %r15,%r8 adcq $0,%r9 adcq $0,%r10 adcq $0,%r11 movq %r8,144(%rsp) movq %r9,152(%rsp) movq %r10,160(%rsp) movq %r11,168(%rsp) // mul xorq %r13,%r13 movq 272(%rsp),%rdx mulx 336(%rsp),%r8,%r9 mulx 344(%rsp),%rcx,%r10 adcx %rcx,%r9 mulx 352(%rsp),%rcx,%r11 adcx %rcx,%r10 mulx 360(%rsp),%rcx,%r12 adcx %rcx,%r11 adcx %r13,%r12 xorq %r14,%r14 movq 280(%rsp),%rdx mulx 336(%rsp),%rcx,%rbp adcx %rcx,%r9 adox %rbp,%r10 mulx 344(%rsp),%rcx,%rbp adcx %rcx,%r10 adox %rbp,%r11 mulx 352(%rsp),%rcx,%rbp adcx %rcx,%r11 adox %rbp,%r12 mulx 360(%rsp),%rcx,%rbp adcx %rcx,%r12 adox %rbp,%r13 adcx %r14,%r13 xorq %r15,%r15 movq 288(%rsp),%rdx mulx 336(%rsp),%rcx,%rbp adcx %rcx,%r10 adox %rbp,%r11 mulx 344(%rsp),%rcx,%rbp adcx %rcx,%r11 adox %rbp,%r12 mulx 352(%rsp),%rcx,%rbp adcx %rcx,%r12 adox %rbp,%r13 mulx 360(%rsp),%rcx,%rbp adcx %rcx,%r13 adox %rbp,%r14 adcx %r15,%r14 xorq %rax,%rax movq 296(%rsp),%rdx mulx 336(%rsp),%rcx,%rbp adcx %rcx,%r11 adox %rbp,%r12 mulx 344(%rsp),%rcx,%rbp adcx %rcx,%r12 adox %rbp,%r13 mulx 352(%rsp),%rcx,%rbp adcx %rcx,%r13 adox %rbp,%r14 mulx 360(%rsp),%rcx,%rbp adcx %rcx,%r14 adox %rbp,%r15 adcx %rax,%r15 xorq %rbp,%rbp movq $38,%rdx mulx %r12,%rax,%r12 adcx %rax,%r8 adox %r12,%r9 mulx %r13,%rcx,%r13 adcx %rcx,%r9 adox %r13,%r10 mulx %r14,%rcx,%r14 adcx %rcx,%r10 adox %r14,%r11 mulx %r15,%rcx,%r15 adcx %rcx,%r11 adox %rbp,%r15 adcx %rbp,%r15 shld $1,%r11,%r15 andq mask63(%rip),%r11 imul $19,%r15,%r15 addq %r15,%r8 adcq $0,%r9 adcq $0,%r10 adcq $0,%r11 movq %r8,176(%rsp) movq %r9,184(%rsp) movq %r10,192(%rsp) movq %r11,200(%rsp) // mul xorq %r13,%r13 movq 240(%rsp),%rdx mulx 304(%rsp),%r8,%r9 mulx 312(%rsp),%rcx,%r10 adcx %rcx,%r9 mulx 320(%rsp),%rcx,%r11 adcx %rcx,%r10 mulx 328(%rsp),%rcx,%r12 adcx %rcx,%r11 adcx %r13,%r12 xorq %r14,%r14 movq 248(%rsp),%rdx mulx 304(%rsp),%rcx,%rbp adcx %rcx,%r9 adox %rbp,%r10 mulx 312(%rsp),%rcx,%rbp adcx %rcx,%r10 adox %rbp,%r11 mulx 320(%rsp),%rcx,%rbp adcx %rcx,%r11 adox %rbp,%r12 mulx 328(%rsp),%rcx,%rbp adcx %rcx,%r12 adox %rbp,%r13 adcx %r14,%r13 xorq %r15,%r15 movq 256(%rsp),%rdx mulx 304(%rsp),%rcx,%rbp adcx %rcx,%r10 adox %rbp,%r11 mulx 312(%rsp),%rcx,%rbp adcx %rcx,%r11 adox %rbp,%r12 mulx 320(%rsp),%rcx,%rbp adcx %rcx,%r12 adox %rbp,%r13 mulx 328(%rsp),%rcx,%rbp adcx %rcx,%r13 adox %rbp,%r14 adcx %r15,%r14 xorq %rax,%rax movq 264(%rsp),%rdx mulx 304(%rsp),%rcx,%rbp adcx %rcx,%r11 adox %rbp,%r12 mulx 312(%rsp),%rcx,%rbp adcx %rcx,%r12 adox %rbp,%r13 mulx 320(%rsp),%rcx,%rbp adcx %rcx,%r13 adox %rbp,%r14 mulx 328(%rsp),%rcx,%rbp adcx %rcx,%r14 adox %rbp,%r15 adcx %rax,%r15 xorq %rbp,%rbp movq $38,%rdx mulx %r12,%rax,%r12 adcx %rax,%r8 adox %r12,%r9 mulx %r13,%rcx,%r13 adcx %rcx,%r9 adox %r13,%r10 mulx %r14,%rcx,%r14 adcx %rcx,%r10 adox %r14,%r11 mulx %r15,%rcx,%r15 adcx %rcx,%r11 adox %rbp,%r15 adcx %rbp,%r15 shld $1,%r11,%r15 andq mask63(%rip),%r11 imul $19,%r15,%r15 addq %r15,%r8 adcq $0,%r9 adcq $0,%r10 adcq $0,%r11 movq %r8,208(%rsp) movq %r9,216(%rsp) movq %r10,224(%rsp) movq %r11,232(%rsp) movb 104(%rsp),%r14b shrb $1,%r14b movzbq %r14b,%r14 imul $128,%r14,%r14 addq %r14,%rdi /* pnielsadd p1p1 */ movq 144(%rsp),%r8 movq 152(%rsp),%r9 movq 160(%rsp),%r10 movq 168(%rsp),%r11 // copy movq %r8,%r12 movq %r9,%r13 movq %r10,%r14 movq %r11,%r15 // sub subq 112(%rsp),%r8 sbbq 120(%rsp),%r9 sbbq 128(%rsp),%r10 sbbq 136(%rsp),%r11 movq $0,%rdx movq $38,%rax cmovae %rdx,%rax subq %rax,%r8 sbbq %rdx,%r9 sbbq %rdx,%r10 sbbq %rdx,%r11 cmovc %rax,%rdx subq %rdx,%r8 movq %r8,368(%rsp) movq %r9,376(%rsp) movq %r10,384(%rsp) movq %r11,392(%rsp) // add addq 112(%rsp),%r12 adcq 120(%rsp),%r13 adcq 128(%rsp),%r14 adcq 136(%rsp),%r15 movq $0,%rdx movq $38,%rax cmovae %rdx,%rax addq %rax,%r12 adcq %rdx,%r13 adcq %rdx,%r14 adcq %rdx,%r15 cmovc %rax,%rdx addq %rdx,%r12 movq %r12,400(%rsp) movq %r13,408(%rsp) movq %r14,416(%rsp) movq %r15,424(%rsp) // mul xorq %r13,%r13 movq 0(%rdi),%rdx mulx 368(%rsp),%r8,%r9 mulx 376(%rsp),%rcx,%r10 adcx %rcx,%r9 mulx 384(%rsp),%rcx,%r11 adcx %rcx,%r10 mulx 392(%rsp),%rcx,%r12 adcx %rcx,%r11 adcx %r13,%r12 xorq %r14,%r14 movq 8(%rdi),%rdx mulx 368(%rsp),%rcx,%rbp adcx %rcx,%r9 adox %rbp,%r10 mulx 376(%rsp),%rcx,%rbp adcx %rcx,%r10 adox %rbp,%r11 mulx 384(%rsp),%rcx,%rbp adcx %rcx,%r11 adox %rbp,%r12 mulx 392(%rsp),%rcx,%rbp adcx %rcx,%r12 adox %rbp,%r13 adcx %r14,%r13 xorq %r15,%r15 movq 16(%rdi),%rdx mulx 368(%rsp),%rcx,%rbp adcx %rcx,%r10 adox %rbp,%r11 mulx 376(%rsp),%rcx,%rbp adcx %rcx,%r11 adox %rbp,%r12 mulx 384(%rsp),%rcx,%rbp adcx %rcx,%r12 adox %rbp,%r13 mulx 392(%rsp),%rcx,%rbp adcx %rcx,%r13 adox %rbp,%r14 adcx %r15,%r14 xorq %rax,%rax movq 24(%rdi),%rdx mulx 368(%rsp),%rcx,%rbp adcx %rcx,%r11 adox %rbp,%r12 mulx 376(%rsp),%rcx,%rbp adcx %rcx,%r12 adox %rbp,%r13 mulx 384(%rsp),%rcx,%rbp adcx %rcx,%r13 adox %rbp,%r14 mulx 392(%rsp),%rcx,%rbp adcx %rcx,%r14 adox %rbp,%r15 adcx %rax,%r15 xorq %rbp,%rbp movq $38,%rdx mulx %r12,%rax,%r12 adcx %rax,%r8 adox %r12,%r9 mulx %r13,%rcx,%r13 adcx %rcx,%r9 adox %r13,%r10 mulx %r14,%rcx,%r14 adcx %rcx,%r10 adox %r14,%r11 mulx %r15,%rcx,%r15 adcx %rcx,%r11 adox %rbp,%r15 adcx %rbp,%r15 shld $1,%r11,%r15 andq mask63(%rip),%r11 imul $19,%r15,%r15 addq %r15,%r8 adcq $0,%r9 adcq $0,%r10 adcq $0,%r11 movq %r8,368(%rsp) movq %r9,376(%rsp) movq %r10,384(%rsp) movq %r11,392(%rsp) // mul xorq %r13,%r13 movq 32(%rdi),%rdx mulx 400(%rsp),%r8,%r9 mulx 408(%rsp),%rcx,%r10 adcx %rcx,%r9 mulx 416(%rsp),%rcx,%r11 adcx %rcx,%r10 mulx 424(%rsp),%rcx,%r12 adcx %rcx,%r11 adcx %r13,%r12 xorq %r14,%r14 movq 40(%rdi),%rdx mulx 400(%rsp),%rcx,%rbp adcx %rcx,%r9 adox %rbp,%r10 mulx 408(%rsp),%rcx,%rbp adcx %rcx,%r10 adox %rbp,%r11 mulx 416(%rsp),%rcx,%rbp adcx %rcx,%r11 adox %rbp,%r12 mulx 424(%rsp),%rcx,%rbp adcx %rcx,%r12 adox %rbp,%r13 adcx %r14,%r13 xorq %r15,%r15 movq 48(%rdi),%rdx mulx 400(%rsp),%rcx,%rbp adcx %rcx,%r10 adox %rbp,%r11 mulx 408(%rsp),%rcx,%rbp adcx %rcx,%r11 adox %rbp,%r12 mulx 416(%rsp),%rcx,%rbp adcx %rcx,%r12 adox %rbp,%r13 mulx 424(%rsp),%rcx,%rbp adcx %rcx,%r13 adox %rbp,%r14 adcx %r15,%r14 xorq %rax,%rax movq 56(%rdi),%rdx mulx 400(%rsp),%rcx,%rbp adcx %rcx,%r11 adox %rbp,%r12 mulx 408(%rsp),%rcx,%rbp adcx %rcx,%r12 adox %rbp,%r13 mulx 416(%rsp),%rcx,%rbp adcx %rcx,%r13 adox %rbp,%r14 mulx 424(%rsp),%rcx,%rbp adcx %rcx,%r14 adox %rbp,%r15 adcx %rax,%r15 xorq %rbp,%rbp movq $38,%rdx mulx %r12,%rax,%r12 adcx %rax,%r8 adox %r12,%r9 mulx %r13,%rcx,%r13 adcx %rcx,%r9 adox %r13,%r10 mulx %r14,%rcx,%r14 adcx %rcx,%r10 adox %r14,%r11 mulx %r15,%rcx,%r15 adcx %rcx,%r11 adox %rbp,%r15 adcx %rbp,%r15 shld $1,%r11,%r15 andq mask63(%rip),%r11 imul $19,%r15,%r15 addq %r15,%r8 adcq $0,%r9 adcq $0,%r10 adcq $0,%r11 // add movq %r8,%r12 movq %r9,%r13 movq %r10,%r14 movq %r11,%r15 addq 368(%rsp),%r8 adcq 376(%rsp),%r9 adcq 384(%rsp),%r10 adcq 392(%rsp),%r11 movq $0,%rdx mov $38,%rax cmovae %rdx,%rax addq %rax,%r8 adcq %rdx,%r9 adcq %rdx,%r10 adcq %rdx,%r11 cmovc %rax,%rdx addq %rdx,%r8 movq %r8,304(%rsp) movq %r9,312(%rsp) movq %r10,320(%rsp) movq %r11,328(%rsp) // sub subq 368(%rsp),%r12 sbbq 376(%rsp),%r13 sbbq 384(%rsp),%r14 sbbq 392(%rsp),%r15 movq $0,%rdx mov $38,%rax cmovae %rdx,%rax subq %rax,%r12 sbbq %rdx,%r13 sbbq %rdx,%r14 sbbq %rdx,%r15 cmovc %rax,%rdx subq %rdx,%r12 movq %r12,240(%rsp) movq %r13,248(%rsp) movq %r14,256(%rsp) movq %r15,264(%rsp) // mul xorq %r13,%r13 movq 96(%rdi),%rdx mulx 208(%rsp),%r8,%r9 mulx 216(%rsp),%rcx,%r10 adcx %rcx,%r9 mulx 224(%rsp),%rcx,%r11 adcx %rcx,%r10 mulx 232(%rsp),%rcx,%r12 adcx %rcx,%r11 adcx %r13,%r12 xorq %r14,%r14 movq 104(%rdi),%rdx mulx 208(%rsp),%rcx,%rbp adcx %rcx,%r9 adox %rbp,%r10 mulx 216(%rsp),%rcx,%rbp adcx %rcx,%r10 adox %rbp,%r11 mulx 224(%rsp),%rcx,%rbp adcx %rcx,%r11 adox %rbp,%r12 mulx 232(%rsp),%rcx,%rbp adcx %rcx,%r12 adox %rbp,%r13 adcx %r14,%r13 xorq %r15,%r15 movq 112(%rdi),%rdx mulx 208(%rsp),%rcx,%rbp adcx %rcx,%r10 adox %rbp,%r11 mulx 216(%rsp),%rcx,%rbp adcx %rcx,%r11 adox %rbp,%r12 mulx 224(%rsp),%rcx,%rbp adcx %rcx,%r12 adox %rbp,%r13 mulx 232(%rsp),%rcx,%rbp adcx %rcx,%r13 adox %rbp,%r14 adcx %r15,%r14 xorq %rax,%rax movq 120(%rdi),%rdx mulx 208(%rsp),%rcx,%rbp adcx %rcx,%r11 adox %rbp,%r12 mulx 216(%rsp),%rcx,%rbp adcx %rcx,%r12 adox %rbp,%r13 mulx 224(%rsp),%rcx,%rbp adcx %rcx,%r13 adox %rbp,%r14 mulx 232(%rsp),%rcx,%rbp adcx %rcx,%r14 adox %rbp,%r15 adcx %rax,%r15 xorq %rbp,%rbp movq $38,%rdx mulx %r12,%rax,%r12 adcx %rax,%r8 adox %r12,%r9 mulx %r13,%rcx,%r13 adcx %rcx,%r9 adox %r13,%r10 mulx %r14,%rcx,%r14 adcx %rcx,%r10 adox %r14,%r11 mulx %r15,%rcx,%r15 adcx %rcx,%r11 adox %rbp,%r15 adcx %rbp,%r15 shld $1,%r11,%r15 andq mask63(%rip),%r11 imul $19,%r15,%r15 addq %r15,%r8 adcq $0,%r9 adcq $0,%r10 adcq $0,%r11 movq %r8,368(%rsp) movq %r9,376(%rsp) movq %r10,384(%rsp) movq %r11,392(%rsp) // mul xorq %r13,%r13 movq 64(%rdi),%rdx mulx 176(%rsp),%r8,%r9 mulx 184(%rsp),%rcx,%r10 adcx %rcx,%r9 mulx 192(%rsp),%rcx,%r11 adcx %rcx,%r10 mulx 200(%rsp),%rcx,%r12 adcx %rcx,%r11 adcx %r13,%r12 xorq %r14,%r14 movq 72(%rdi),%rdx mulx 176(%rsp),%rcx,%rbp adcx %rcx,%r9 adox %rbp,%r10 mulx 184(%rsp),%rcx,%rbp adcx %rcx,%r10 adox %rbp,%r11 mulx 192(%rsp),%rcx,%rbp adcx %rcx,%r11 adox %rbp,%r12 mulx 200(%rsp),%rcx,%rbp adcx %rcx,%r12 adox %rbp,%r13 adcx %r14,%r13 xorq %r15,%r15 movq 80(%rdi),%rdx mulx 176(%rsp),%rcx,%rbp adcx %rcx,%r10 adox %rbp,%r11 mulx 184(%rsp),%rcx,%rbp adcx %rcx,%r11 adox %rbp,%r12 mulx 192(%rsp),%rcx,%rbp adcx %rcx,%r12 adox %rbp,%r13 mulx 200(%rsp),%rcx,%rbp adcx %rcx,%r13 adox %rbp,%r14 adcx %r15,%r14 xorq %rax,%rax movq 88(%rdi),%rdx mulx 176(%rsp),%rcx,%rbp adcx %rcx,%r11 adox %rbp,%r12 mulx 184(%rsp),%rcx,%rbp adcx %rcx,%r12 adox %rbp,%r13 mulx 192(%rsp),%rcx,%rbp adcx %rcx,%r13 adox %rbp,%r14 mulx 200(%rsp),%rcx,%rbp adcx %rcx,%r14 adox %rbp,%r15 adcx %rax,%r15 xorq %rbp,%rbp movq $38,%rdx mulx %r12,%rax,%r12 adcx %rax,%r8 adox %r12,%r9 mulx %r13,%rcx,%r13 adcx %rcx,%r9 adox %r13,%r10 mulx %r14,%rcx,%r14 adcx %rcx,%r10 adox %r14,%r11 mulx %r15,%rcx,%r15 adcx %rcx,%r11 adox %rbp,%r15 adcx %rbp,%r15 shld $1,%r11,%r15 andq mask63(%rip),%r11 imul $19,%r15,%r15 addq %r15,%r8 adcq $0,%r9 adcq $0,%r10 adcq $0,%r11 // double addq %r8,%r8 adcq %r9,%r9 adcq %r10,%r10 adcq %r11,%r11 movq $0,%rdx mov $38,%rax cmovae %rdx,%rax addq %rax,%r8 adcq %rdx,%r9 adcq %rdx,%r10 adcq %rdx,%r11 cmovc %rax,%rdx addq %rdx,%r8 // add movq %r8,%r12 movq %r9,%r13 movq %r10,%r14 movq %r11,%r15 addq 368(%rsp),%r8 adcq 376(%rsp),%r9 adcq 384(%rsp),%r10 adcq 392(%rsp),%r11 movq $0,%rdx mov $38,%rax cmovae %rdx,%rax addq %rax,%r8 adcq %rdx,%r9 adcq %rdx,%r10 adcq %rdx,%r11 cmovc %rax,%rdx addq %rdx,%r8 movq %r8,272(%rsp) movq %r9,280(%rsp) movq %r10,288(%rsp) movq %r11,296(%rsp) // sub subq 368(%rsp),%r12 sbbq 376(%rsp),%r13 sbbq 384(%rsp),%r14 sbbq 392(%rsp),%r15 movq $0,%rdx mov $38,%rax cmovae %rdx,%rax subq %rax,%r12 sbbq %rdx,%r13 sbbq %rdx,%r14 sbbq %rdx,%r15 cmovc %rax,%rdx subq %rdx,%r12 movq %r12,336(%rsp) movq %r13,344(%rsp) movq %r14,352(%rsp) movq %r15,360(%rsp) jmp .L6 .L5: /* p1p1 to p3 */ // mul xorq %r13,%r13 movq 240(%rsp),%rdx mulx 336(%rsp),%r8,%r9 mulx 344(%rsp),%rcx,%r10 adcx %rcx,%r9 mulx 352(%rsp),%rcx,%r11 adcx %rcx,%r10 mulx 360(%rsp),%rcx,%r12 adcx %rcx,%r11 adcx %r13,%r12 xorq %r14,%r14 movq 248(%rsp),%rdx mulx 336(%rsp),%rcx,%rbp adcx %rcx,%r9 adox %rbp,%r10 mulx 344(%rsp),%rcx,%rbp adcx %rcx,%r10 adox %rbp,%r11 mulx 352(%rsp),%rcx,%rbp adcx %rcx,%r11 adox %rbp,%r12 mulx 360(%rsp),%rcx,%rbp adcx %rcx,%r12 adox %rbp,%r13 adcx %r14,%r13 xorq %r15,%r15 movq 256(%rsp),%rdx mulx 336(%rsp),%rcx,%rbp adcx %rcx,%r10 adox %rbp,%r11 mulx 344(%rsp),%rcx,%rbp adcx %rcx,%r11 adox %rbp,%r12 mulx 352(%rsp),%rcx,%rbp adcx %rcx,%r12 adox %rbp,%r13 mulx 360(%rsp),%rcx,%rbp adcx %rcx,%r13 adox %rbp,%r14 adcx %r15,%r14 xorq %rax,%rax movq 264(%rsp),%rdx mulx 336(%rsp),%rcx,%rbp adcx %rcx,%r11 adox %rbp,%r12 mulx 344(%rsp),%rcx,%rbp adcx %rcx,%r12 adox %rbp,%r13 mulx 352(%rsp),%rcx,%rbp adcx %rcx,%r13 adox %rbp,%r14 mulx 360(%rsp),%rcx,%rbp adcx %rcx,%r14 adox %rbp,%r15 adcx %rax,%r15 xorq %rbp,%rbp movq $38,%rdx mulx %r12,%rax,%r12 adcx %rax,%r8 adox %r12,%r9 mulx %r13,%rcx,%r13 adcx %rcx,%r9 adox %r13,%r10 mulx %r14,%rcx,%r14 adcx %rcx,%r10 adox %r14,%r11 mulx %r15,%rcx,%r15 adcx %rcx,%r11 adox %rbp,%r15 adcx %rbp,%r15 shld $1,%r11,%r15 andq mask63(%rip),%r11 imul $19,%r15,%r15 addq %r15,%r8 adcq $0,%r9 adcq $0,%r10 adcq $0,%r11 movq %r8,112(%rsp) movq %r9,120(%rsp) movq %r10,128(%rsp) movq %r11,136(%rsp) // mul xorq %r13,%r13 movq 272(%rsp),%rdx mulx 304(%rsp),%r8,%r9 mulx 312(%rsp),%rcx,%r10 adcx %rcx,%r9 mulx 320(%rsp),%rcx,%r11 adcx %rcx,%r10 mulx 328(%rsp),%rcx,%r12 adcx %rcx,%r11 adcx %r13,%r12 xorq %r14,%r14 movq 280(%rsp),%rdx mulx 304(%rsp),%rcx,%rbp adcx %rcx,%r9 adox %rbp,%r10 mulx 312(%rsp),%rcx,%rbp adcx %rcx,%r10 adox %rbp,%r11 mulx 320(%rsp),%rcx,%rbp adcx %rcx,%r11 adox %rbp,%r12 mulx 328(%rsp),%rcx,%rbp adcx %rcx,%r12 adox %rbp,%r13 adcx %r14,%r13 xorq %r15,%r15 movq 288(%rsp),%rdx mulx 304(%rsp),%rcx,%rbp adcx %rcx,%r10 adox %rbp,%r11 mulx 312(%rsp),%rcx,%rbp adcx %rcx,%r11 adox %rbp,%r12 mulx 320(%rsp),%rcx,%rbp adcx %rcx,%r12 adox %rbp,%r13 mulx 328(%rsp),%rcx,%rbp adcx %rcx,%r13 adox %rbp,%r14 adcx %r15,%r14 xorq %rax,%rax movq 296(%rsp),%rdx mulx 304(%rsp),%rcx,%rbp adcx %rcx,%r11 adox %rbp,%r12 mulx 312(%rsp),%rcx,%rbp adcx %rcx,%r12 adox %rbp,%r13 mulx 320(%rsp),%rcx,%rbp adcx %rcx,%r13 adox %rbp,%r14 mulx 328(%rsp),%rcx,%rbp adcx %rcx,%r14 adox %rbp,%r15 adcx %rax,%r15 xorq %rbp,%rbp movq $38,%rdx mulx %r12,%rax,%r12 adcx %rax,%r8 adox %r12,%r9 mulx %r13,%rcx,%r13 adcx %rcx,%r9 adox %r13,%r10 mulx %r14,%rcx,%r14 adcx %rcx,%r10 adox %r14,%r11 mulx %r15,%rcx,%r15 adcx %rcx,%r11 adox %rbp,%r15 adcx %rbp,%r15 shld $1,%r11,%r15 andq mask63(%rip),%r11 imul $19,%r15,%r15 addq %r15,%r8 adcq $0,%r9 adcq $0,%r10 adcq $0,%r11 movq %r8,144(%rsp) movq %r9,152(%rsp) movq %r10,160(%rsp) movq %r11,168(%rsp) // mul xorq %r13,%r13 movq 272(%rsp),%rdx mulx 336(%rsp),%r8,%r9 mulx 344(%rsp),%rcx,%r10 adcx %rcx,%r9 mulx 352(%rsp),%rcx,%r11 adcx %rcx,%r10 mulx 360(%rsp),%rcx,%r12 adcx %rcx,%r11 adcx %r13,%r12 xorq %r14,%r14 movq 280(%rsp),%rdx mulx 336(%rsp),%rcx,%rbp adcx %rcx,%r9 adox %rbp,%r10 mulx 344(%rsp),%rcx,%rbp adcx %rcx,%r10 adox %rbp,%r11 mulx 352(%rsp),%rcx,%rbp adcx %rcx,%r11 adox %rbp,%r12 mulx 360(%rsp),%rcx,%rbp adcx %rcx,%r12 adox %rbp,%r13 adcx %r14,%r13 xorq %r15,%r15 movq 288(%rsp),%rdx mulx 336(%rsp),%rcx,%rbp adcx %rcx,%r10 adox %rbp,%r11 mulx 344(%rsp),%rcx,%rbp adcx %rcx,%r11 adox %rbp,%r12 mulx 352(%rsp),%rcx,%rbp adcx %rcx,%r12 adox %rbp,%r13 mulx 360(%rsp),%rcx,%rbp adcx %rcx,%r13 adox %rbp,%r14 adcx %r15,%r14 xorq %rax,%rax movq 296(%rsp),%rdx mulx 336(%rsp),%rcx,%rbp adcx %rcx,%r11 adox %rbp,%r12 mulx 344(%rsp),%rcx,%rbp adcx %rcx,%r12 adox %rbp,%r13 mulx 352(%rsp),%rcx,%rbp adcx %rcx,%r13 adox %rbp,%r14 mulx 360(%rsp),%rcx,%rbp adcx %rcx,%r14 adox %rbp,%r15 adcx %rax,%r15 xorq %rbp,%rbp movq $38,%rdx mulx %r12,%rax,%r12 adcx %rax,%r8 adox %r12,%r9 mulx %r13,%rcx,%r13 adcx %rcx,%r9 adox %r13,%r10 mulx %r14,%rcx,%r14 adcx %rcx,%r10 adox %r14,%r11 mulx %r15,%rcx,%r15 adcx %rcx,%r11 adox %rbp,%r15 adcx %rbp,%r15 shld $1,%r11,%r15 andq mask63(%rip),%r11 imul $19,%r15,%r15 addq %r15,%r8 adcq $0,%r9 adcq $0,%r10 adcq $0,%r11 movq %r8,176(%rsp) movq %r9,184(%rsp) movq %r10,192(%rsp) movq %r11,200(%rsp) // mul xorq %r13,%r13 movq 240(%rsp),%rdx mulx 304(%rsp),%r8,%r9 mulx 312(%rsp),%rcx,%r10 adcx %rcx,%r9 mulx 320(%rsp),%rcx,%r11 adcx %rcx,%r10 mulx 328(%rsp),%rcx,%r12 adcx %rcx,%r11 adcx %r13,%r12 xorq %r14,%r14 movq 248(%rsp),%rdx mulx 304(%rsp),%rcx,%rbp adcx %rcx,%r9 adox %rbp,%r10 mulx 312(%rsp),%rcx,%rbp adcx %rcx,%r10 adox %rbp,%r11 mulx 320(%rsp),%rcx,%rbp adcx %rcx,%r11 adox %rbp,%r12 mulx 328(%rsp),%rcx,%rbp adcx %rcx,%r12 adox %rbp,%r13 adcx %r14,%r13 xorq %r15,%r15 movq 256(%rsp),%rdx mulx 304(%rsp),%rcx,%rbp adcx %rcx,%r10 adox %rbp,%r11 mulx 312(%rsp),%rcx,%rbp adcx %rcx,%r11 adox %rbp,%r12 mulx 320(%rsp),%rcx,%rbp adcx %rcx,%r12 adox %rbp,%r13 mulx 328(%rsp),%rcx,%rbp adcx %rcx,%r13 adox %rbp,%r14 adcx %r15,%r14 xorq %rax,%rax movq 264(%rsp),%rdx mulx 304(%rsp),%rcx,%rbp adcx %rcx,%r11 adox %rbp,%r12 mulx 312(%rsp),%rcx,%rbp adcx %rcx,%r12 adox %rbp,%r13 mulx 320(%rsp),%rcx,%rbp adcx %rcx,%r13 adox %rbp,%r14 mulx 328(%rsp),%rcx,%rbp adcx %rcx,%r14 adox %rbp,%r15 adcx %rax,%r15 xorq %rbp,%rbp movq $38,%rdx mulx %r12,%rax,%r12 adcx %rax,%r8 adox %r12,%r9 mulx %r13,%rcx,%r13 adcx %rcx,%r9 adox %r13,%r10 mulx %r14,%rcx,%r14 adcx %rcx,%r10 adox %r14,%r11 mulx %r15,%rcx,%r15 adcx %rcx,%r11 adox %rbp,%r15 adcx %rbp,%r15 shld $1,%r11,%r15 andq mask63(%rip),%r11 imul $19,%r15,%r15 addq %r15,%r8 adcq $0,%r9 adcq $0,%r10 adcq $0,%r11 movq %r8,208(%rsp) movq %r9,216(%rsp) movq %r10,224(%rsp) movq %r11,232(%rsp) movb 104(%rsp),%r14b movb $0,%r15b subb %r14b,%r15b shrb $1,%r15b movzbq %r15b,%r15 imul $128,%r15,%r15 addq %r15,%rdi // neg movq $0,%r8 movq $0,%r9 movq $0,%r10 movq $0,%r11 subq 96(%rdi),%r8 sbbq 104(%rdi),%r9 sbbq 112(%rdi),%r10 sbbq 120(%rdi),%r11 movq $0,%rdx movq $38,%rax cmovae %rdx,%rax subq %rax,%r8 sbbq %rdx,%r9 sbbq %rdx,%r10 sbbq %rdx,%r11 cmovc %rax,%rdx subq %rdx,%r8 movq %r8,432(%rsp) movq %r9,440(%rsp) movq %r10,448(%rsp) movq %r11,456(%rsp) /* pnielsadd p1p1 */ movq 144(%rsp),%r8 movq 152(%rsp),%r9 movq 160(%rsp),%r10 movq 168(%rsp),%r11 // copy movq %r8,%r12 movq %r9,%r13 movq %r10,%r14 movq %r11,%r15 // sub subq 112(%rsp),%r8 sbbq 120(%rsp),%r9 sbbq 128(%rsp),%r10 sbbq 136(%rsp),%r11 movq $0,%rdx movq $38,%rax cmovae %rdx,%rax subq %rax,%r8 sbbq %rdx,%r9 sbbq %rdx,%r10 sbbq %rdx,%r11 cmovc %rax,%rdx subq %rdx,%r8 movq %r8,368(%rsp) movq %r9,376(%rsp) movq %r10,384(%rsp) movq %r11,392(%rsp) // add addq 112(%rsp),%r12 adcq 120(%rsp),%r13 adcq 128(%rsp),%r14 adcq 136(%rsp),%r15 movq $0,%rdx movq $38,%rax cmovae %rdx,%rax addq %rax,%r12 adcq %rdx,%r13 adcq %rdx,%r14 adcq %rdx,%r15 cmovc %rax,%rdx addq %rdx,%r12 movq %r12,400(%rsp) movq %r13,408(%rsp) movq %r14,416(%rsp) movq %r15,424(%rsp) // mul xorq %r13,%r13 movq 32(%rdi),%rdx mulx 368(%rsp),%r8,%r9 mulx 376(%rsp),%rcx,%r10 adcx %rcx,%r9 mulx 384(%rsp),%rcx,%r11 adcx %rcx,%r10 mulx 392(%rsp),%rcx,%r12 adcx %rcx,%r11 adcx %r13,%r12 xorq %r14,%r14 movq 40(%rdi),%rdx mulx 368(%rsp),%rcx,%rbp adcx %rcx,%r9 adox %rbp,%r10 mulx 376(%rsp),%rcx,%rbp adcx %rcx,%r10 adox %rbp,%r11 mulx 384(%rsp),%rcx,%rbp adcx %rcx,%r11 adox %rbp,%r12 mulx 392(%rsp),%rcx,%rbp adcx %rcx,%r12 adox %rbp,%r13 adcx %r14,%r13 xorq %r15,%r15 movq 48(%rdi),%rdx mulx 368(%rsp),%rcx,%rbp adcx %rcx,%r10 adox %rbp,%r11 mulx 376(%rsp),%rcx,%rbp adcx %rcx,%r11 adox %rbp,%r12 mulx 384(%rsp),%rcx,%rbp adcx %rcx,%r12 adox %rbp,%r13 mulx 392(%rsp),%rcx,%rbp adcx %rcx,%r13 adox %rbp,%r14 adcx %r15,%r14 xorq %rax,%rax movq 56(%rdi),%rdx mulx 368(%rsp),%rcx,%rbp adcx %rcx,%r11 adox %rbp,%r12 mulx 376(%rsp),%rcx,%rbp adcx %rcx,%r12 adox %rbp,%r13 mulx 384(%rsp),%rcx,%rbp adcx %rcx,%r13 adox %rbp,%r14 mulx 392(%rsp),%rcx,%rbp adcx %rcx,%r14 adox %rbp,%r15 adcx %rax,%r15 xorq %rbp,%rbp movq $38,%rdx mulx %r12,%rax,%r12 adcx %rax,%r8 adox %r12,%r9 mulx %r13,%rcx,%r13 adcx %rcx,%r9 adox %r13,%r10 mulx %r14,%rcx,%r14 adcx %rcx,%r10 adox %r14,%r11 mulx %r15,%rcx,%r15 adcx %rcx,%r11 adox %rbp,%r15 adcx %rbp,%r15 shld $1,%r11,%r15 andq mask63(%rip),%r11 imul $19,%r15,%r15 addq %r15,%r8 adcq $0,%r9 adcq $0,%r10 adcq $0,%r11 movq %r8,368(%rsp) movq %r9,376(%rsp) movq %r10,384(%rsp) movq %r11,392(%rsp) // mul xorq %r13,%r13 movq 0(%rdi),%rdx mulx 400(%rsp),%r8,%r9 mulx 408(%rsp),%rcx,%r10 adcx %rcx,%r9 mulx 416(%rsp),%rcx,%r11 adcx %rcx,%r10 mulx 424(%rsp),%rcx,%r12 adcx %rcx,%r11 adcx %r13,%r12 xorq %r14,%r14 movq 8(%rdi),%rdx mulx 400(%rsp),%rcx,%rbp adcx %rcx,%r9 adox %rbp,%r10 mulx 408(%rsp),%rcx,%rbp adcx %rcx,%r10 adox %rbp,%r11 mulx 416(%rsp),%rcx,%rbp adcx %rcx,%r11 adox %rbp,%r12 mulx 424(%rsp),%rcx,%rbp adcx %rcx,%r12 adox %rbp,%r13 adcx %r14,%r13 xorq %r15,%r15 movq 16(%rdi),%rdx mulx 400(%rsp),%rcx,%rbp adcx %rcx,%r10 adox %rbp,%r11 mulx 408(%rsp),%rcx,%rbp adcx %rcx,%r11 adox %rbp,%r12 mulx 416(%rsp),%rcx,%rbp adcx %rcx,%r12 adox %rbp,%r13 mulx 424(%rsp),%rcx,%rbp adcx %rcx,%r13 adox %rbp,%r14 adcx %r15,%r14 xorq %rax,%rax movq 24(%rdi),%rdx mulx 400(%rsp),%rcx,%rbp adcx %rcx,%r11 adox %rbp,%r12 mulx 408(%rsp),%rcx,%rbp adcx %rcx,%r12 adox %rbp,%r13 mulx 416(%rsp),%rcx,%rbp adcx %rcx,%r13 adox %rbp,%r14 mulx 424(%rsp),%rcx,%rbp adcx %rcx,%r14 adox %rbp,%r15 adcx %rax,%r15 xorq %rbp,%rbp movq $38,%rdx mulx %r12,%rax,%r12 adcx %rax,%r8 adox %r12,%r9 mulx %r13,%rcx,%r13 adcx %rcx,%r9 adox %r13,%r10 mulx %r14,%rcx,%r14 adcx %rcx,%r10 adox %r14,%r11 mulx %r15,%rcx,%r15 adcx %rcx,%r11 adox %rbp,%r15 adcx %rbp,%r15 shld $1,%r11,%r15 andq mask63(%rip),%r11 imul $19,%r15,%r15 addq %r15,%r8 adcq $0,%r9 adcq $0,%r10 adcq $0,%r11 // add movq %r8,%r12 movq %r9,%r13 movq %r10,%r14 movq %r11,%r15 addq 368(%rsp),%r8 adcq 376(%rsp),%r9 adcq 384(%rsp),%r10 adcq 392(%rsp),%r11 movq $0,%rdx mov $38,%rax cmovae %rdx,%rax addq %rax,%r8 adcq %rdx,%r9 adcq %rdx,%r10 adcq %rdx,%r11 cmovc %rax,%rdx addq %rdx,%r8 movq %r8,304(%rsp) movq %r9,312(%rsp) movq %r10,320(%rsp) movq %r11,328(%rsp) // sub subq 368(%rsp),%r12 sbbq 376(%rsp),%r13 sbbq 384(%rsp),%r14 sbbq 392(%rsp),%r15 movq $0,%rdx mov $38,%rax cmovae %rdx,%rax subq %rax,%r12 sbbq %rdx,%r13 sbbq %rdx,%r14 sbbq %rdx,%r15 cmovc %rax,%rdx subq %rdx,%r12 movq %r12,240(%rsp) movq %r13,248(%rsp) movq %r14,256(%rsp) movq %r15,264(%rsp) // mul xorq %r13,%r13 movq 208(%rsp),%rdx mulx 432(%rsp),%r8,%r9 mulx 440(%rsp),%rcx,%r10 adcx %rcx,%r9 mulx 448(%rsp),%rcx,%r11 adcx %rcx,%r10 mulx 456(%rsp),%rcx,%r12 adcx %rcx,%r11 adcx %r13,%r12 xorq %r14,%r14 movq 216(%rsp),%rdx mulx 432(%rsp),%rcx,%rbp adcx %rcx,%r9 adox %rbp,%r10 mulx 440(%rsp),%rcx,%rbp adcx %rcx,%r10 adox %rbp,%r11 mulx 448(%rsp),%rcx,%rbp adcx %rcx,%r11 adox %rbp,%r12 mulx 456(%rsp),%rcx,%rbp adcx %rcx,%r12 adox %rbp,%r13 adcx %r14,%r13 xorq %r15,%r15 movq 224(%rsp),%rdx mulx 432(%rsp),%rcx,%rbp adcx %rcx,%r10 adox %rbp,%r11 mulx 440(%rsp),%rcx,%rbp adcx %rcx,%r11 adox %rbp,%r12 mulx 448(%rsp),%rcx,%rbp adcx %rcx,%r12 adox %rbp,%r13 mulx 456(%rsp),%rcx,%rbp adcx %rcx,%r13 adox %rbp,%r14 adcx %r15,%r14 xorq %rax,%rax movq 232(%rsp),%rdx mulx 432(%rsp),%rcx,%rbp adcx %rcx,%r11 adox %rbp,%r12 mulx 440(%rsp),%rcx,%rbp adcx %rcx,%r12 adox %rbp,%r13 mulx 448(%rsp),%rcx,%rbp adcx %rcx,%r13 adox %rbp,%r14 mulx 456(%rsp),%rcx,%rbp adcx %rcx,%r14 adox %rbp,%r15 adcx %rax,%r15 xorq %rbp,%rbp movq $38,%rdx mulx %r12,%rax,%r12 adcx %rax,%r8 adox %r12,%r9 mulx %r13,%rcx,%r13 adcx %rcx,%r9 adox %r13,%r10 mulx %r14,%rcx,%r14 adcx %rcx,%r10 adox %r14,%r11 mulx %r15,%rcx,%r15 adcx %rcx,%r11 adox %rbp,%r15 adcx %rbp,%r15 shld $1,%r11,%r15 andq mask63(%rip),%r11 imul $19,%r15,%r15 addq %r15,%r8 adcq $0,%r9 adcq $0,%r10 adcq $0,%r11 movq %r8,368(%rsp) movq %r9,376(%rsp) movq %r10,384(%rsp) movq %r11,392(%rsp) // mul xorq %r13,%r13 movq 64(%rdi),%rdx mulx 176(%rsp),%r8,%r9 mulx 184(%rsp),%rcx,%r10 adcx %rcx,%r9 mulx 192(%rsp),%rcx,%r11 adcx %rcx,%r10 mulx 200(%rsp),%rcx,%r12 adcx %rcx,%r11 adcx %r13,%r12 xorq %r14,%r14 movq 72(%rdi),%rdx mulx 176(%rsp),%rcx,%rbp adcx %rcx,%r9 adox %rbp,%r10 mulx 184(%rsp),%rcx,%rbp adcx %rcx,%r10 adox %rbp,%r11 mulx 192(%rsp),%rcx,%rbp adcx %rcx,%r11 adox %rbp,%r12 mulx 200(%rsp),%rcx,%rbp adcx %rcx,%r12 adox %rbp,%r13 adcx %r14,%r13 xorq %r15,%r15 movq 80(%rdi),%rdx mulx 176(%rsp),%rcx,%rbp adcx %rcx,%r10 adox %rbp,%r11 mulx 184(%rsp),%rcx,%rbp adcx %rcx,%r11 adox %rbp,%r12 mulx 192(%rsp),%rcx,%rbp adcx %rcx,%r12 adox %rbp,%r13 mulx 200(%rsp),%rcx,%rbp adcx %rcx,%r13 adox %rbp,%r14 adcx %r15,%r14 xorq %rax,%rax movq 88(%rdi),%rdx mulx 176(%rsp),%rcx,%rbp adcx %rcx,%r11 adox %rbp,%r12 mulx 184(%rsp),%rcx,%rbp adcx %rcx,%r12 adox %rbp,%r13 mulx 192(%rsp),%rcx,%rbp adcx %rcx,%r13 adox %rbp,%r14 mulx 200(%rsp),%rcx,%rbp adcx %rcx,%r14 adox %rbp,%r15 adcx %rax,%r15 xorq %rbp,%rbp movq $38,%rdx mulx %r12,%rax,%r12 adcx %rax,%r8 adox %r12,%r9 mulx %r13,%rcx,%r13 adcx %rcx,%r9 adox %r13,%r10 mulx %r14,%rcx,%r14 adcx %rcx,%r10 adox %r14,%r11 mulx %r15,%rcx,%r15 adcx %rcx,%r11 adox %rbp,%r15 adcx %rbp,%r15 shld $1,%r11,%r15 andq mask63(%rip),%r11 imul $19,%r15,%r15 addq %r15,%r8 adcq $0,%r9 adcq $0,%r10 adcq $0,%r11 // double addq %r8,%r8 adcq %r9,%r9 adcq %r10,%r10 adcq %r11,%r11 movq $0,%rdx mov $38,%rax cmovae %rdx,%rax addq %rax,%r8 adcq %rdx,%r9 adcq %rdx,%r10 adcq %rdx,%r11 cmovc %rax,%rdx addq %rdx,%r8 // add movq %r8,%r12 movq %r9,%r13 movq %r10,%r14 movq %r11,%r15 addq 368(%rsp),%r8 adcq 376(%rsp),%r9 adcq 384(%rsp),%r10 adcq 392(%rsp),%r11 movq $0,%rdx mov $38,%rax cmovae %rdx,%rax addq %rax,%r8 adcq %rdx,%r9 adcq %rdx,%r10 adcq %rdx,%r11 cmovc %rax,%rdx addq %rdx,%r8 movq %r8,272(%rsp) movq %r9,280(%rsp) movq %r10,288(%rsp) movq %r11,296(%rsp) // sub subq 368(%rsp),%r12 sbbq 376(%rsp),%r13 sbbq 384(%rsp),%r14 sbbq 392(%rsp),%r15 movq $0,%rdx mov $38,%rax cmovae %rdx,%rax subq %rax,%r12 sbbq %rdx,%r13 sbbq %rdx,%r14 sbbq %rdx,%r15 cmovc %rax,%rdx subq %rdx,%r12 movq %r12,336(%rsp) movq %r13,344(%rsp) movq %r14,352(%rsp) movq %r15,360(%rsp) .L6: movq 88(%rsp),%rsi movb 0(%rsi),%r14b movb %r14b,104(%rsp) decq %rsi movq %rsi,88(%rsp) movq 72(%rsp),%rdi cmpb $0,%r14b jg .L7 jl .L8 je .L9 .L7: /* p1p1 to p3 */ // mul xorq %r13,%r13 movq 240(%rsp),%rdx mulx 336(%rsp),%r8,%r9 mulx 344(%rsp),%rcx,%r10 adcx %rcx,%r9 mulx 352(%rsp),%rcx,%r11 adcx %rcx,%r10 mulx 360(%rsp),%rcx,%r12 adcx %rcx,%r11 adcx %r13,%r12 xorq %r14,%r14 movq 248(%rsp),%rdx mulx 336(%rsp),%rcx,%rbp adcx %rcx,%r9 adox %rbp,%r10 mulx 344(%rsp),%rcx,%rbp adcx %rcx,%r10 adox %rbp,%r11 mulx 352(%rsp),%rcx,%rbp adcx %rcx,%r11 adox %rbp,%r12 mulx 360(%rsp),%rcx,%rbp adcx %rcx,%r12 adox %rbp,%r13 adcx %r14,%r13 xorq %r15,%r15 movq 256(%rsp),%rdx mulx 336(%rsp),%rcx,%rbp adcx %rcx,%r10 adox %rbp,%r11 mulx 344(%rsp),%rcx,%rbp adcx %rcx,%r11 adox %rbp,%r12 mulx 352(%rsp),%rcx,%rbp adcx %rcx,%r12 adox %rbp,%r13 mulx 360(%rsp),%rcx,%rbp adcx %rcx,%r13 adox %rbp,%r14 adcx %r15,%r14 xorq %rax,%rax movq 264(%rsp),%rdx mulx 336(%rsp),%rcx,%rbp adcx %rcx,%r11 adox %rbp,%r12 mulx 344(%rsp),%rcx,%rbp adcx %rcx,%r12 adox %rbp,%r13 mulx 352(%rsp),%rcx,%rbp adcx %rcx,%r13 adox %rbp,%r14 mulx 360(%rsp),%rcx,%rbp adcx %rcx,%r14 adox %rbp,%r15 adcx %rax,%r15 xorq %rbp,%rbp movq $38,%rdx mulx %r12,%rax,%r12 adcx %rax,%r8 adox %r12,%r9 mulx %r13,%rcx,%r13 adcx %rcx,%r9 adox %r13,%r10 mulx %r14,%rcx,%r14 adcx %rcx,%r10 adox %r14,%r11 mulx %r15,%rcx,%r15 adcx %rcx,%r11 adox %rbp,%r15 adcx %rbp,%r15 shld $1,%r11,%r15 andq mask63(%rip),%r11 imul $19,%r15,%r15 addq %r15,%r8 adcq $0,%r9 adcq $0,%r10 adcq $0,%r11 movq %r8,112(%rsp) movq %r9,120(%rsp) movq %r10,128(%rsp) movq %r11,136(%rsp) // mul xorq %r13,%r13 movq 272(%rsp),%rdx mulx 304(%rsp),%r8,%r9 mulx 312(%rsp),%rcx,%r10 adcx %rcx,%r9 mulx 320(%rsp),%rcx,%r11 adcx %rcx,%r10 mulx 328(%rsp),%rcx,%r12 adcx %rcx,%r11 adcx %r13,%r12 xorq %r14,%r14 movq 280(%rsp),%rdx mulx 304(%rsp),%rcx,%rbp adcx %rcx,%r9 adox %rbp,%r10 mulx 312(%rsp),%rcx,%rbp adcx %rcx,%r10 adox %rbp,%r11 mulx 320(%rsp),%rcx,%rbp adcx %rcx,%r11 adox %rbp,%r12 mulx 328(%rsp),%rcx,%rbp adcx %rcx,%r12 adox %rbp,%r13 adcx %r14,%r13 xorq %r15,%r15 movq 288(%rsp),%rdx mulx 304(%rsp),%rcx,%rbp adcx %rcx,%r10 adox %rbp,%r11 mulx 312(%rsp),%rcx,%rbp adcx %rcx,%r11 adox %rbp,%r12 mulx 320(%rsp),%rcx,%rbp adcx %rcx,%r12 adox %rbp,%r13 mulx 328(%rsp),%rcx,%rbp adcx %rcx,%r13 adox %rbp,%r14 adcx %r15,%r14 xorq %rax,%rax movq 296(%rsp),%rdx mulx 304(%rsp),%rcx,%rbp adcx %rcx,%r11 adox %rbp,%r12 mulx 312(%rsp),%rcx,%rbp adcx %rcx,%r12 adox %rbp,%r13 mulx 320(%rsp),%rcx,%rbp adcx %rcx,%r13 adox %rbp,%r14 mulx 328(%rsp),%rcx,%rbp adcx %rcx,%r14 adox %rbp,%r15 adcx %rax,%r15 xorq %rbp,%rbp movq $38,%rdx mulx %r12,%rax,%r12 adcx %rax,%r8 adox %r12,%r9 mulx %r13,%rcx,%r13 adcx %rcx,%r9 adox %r13,%r10 mulx %r14,%rcx,%r14 adcx %rcx,%r10 adox %r14,%r11 mulx %r15,%rcx,%r15 adcx %rcx,%r11 adox %rbp,%r15 adcx %rbp,%r15 shld $1,%r11,%r15 andq mask63(%rip),%r11 imul $19,%r15,%r15 addq %r15,%r8 adcq $0,%r9 adcq $0,%r10 adcq $0,%r11 movq %r8,144(%rsp) movq %r9,152(%rsp) movq %r10,160(%rsp) movq %r11,168(%rsp) // mul xorq %r13,%r13 movq 272(%rsp),%rdx mulx 336(%rsp),%r8,%r9 mulx 344(%rsp),%rcx,%r10 adcx %rcx,%r9 mulx 352(%rsp),%rcx,%r11 adcx %rcx,%r10 mulx 360(%rsp),%rcx,%r12 adcx %rcx,%r11 adcx %r13,%r12 xorq %r14,%r14 movq 280(%rsp),%rdx mulx 336(%rsp),%rcx,%rbp adcx %rcx,%r9 adox %rbp,%r10 mulx 344(%rsp),%rcx,%rbp adcx %rcx,%r10 adox %rbp,%r11 mulx 352(%rsp),%rcx,%rbp adcx %rcx,%r11 adox %rbp,%r12 mulx 360(%rsp),%rcx,%rbp adcx %rcx,%r12 adox %rbp,%r13 adcx %r14,%r13 xorq %r15,%r15 movq 288(%rsp),%rdx mulx 336(%rsp),%rcx,%rbp adcx %rcx,%r10 adox %rbp,%r11 mulx 344(%rsp),%rcx,%rbp adcx %rcx,%r11 adox %rbp,%r12 mulx 352(%rsp),%rcx,%rbp adcx %rcx,%r12 adox %rbp,%r13 mulx 360(%rsp),%rcx,%rbp adcx %rcx,%r13 adox %rbp,%r14 adcx %r15,%r14 xorq %rax,%rax movq 296(%rsp),%rdx mulx 336(%rsp),%rcx,%rbp adcx %rcx,%r11 adox %rbp,%r12 mulx 344(%rsp),%rcx,%rbp adcx %rcx,%r12 adox %rbp,%r13 mulx 352(%rsp),%rcx,%rbp adcx %rcx,%r13 adox %rbp,%r14 mulx 360(%rsp),%rcx,%rbp adcx %rcx,%r14 adox %rbp,%r15 adcx %rax,%r15 xorq %rbp,%rbp movq $38,%rdx mulx %r12,%rax,%r12 adcx %rax,%r8 adox %r12,%r9 mulx %r13,%rcx,%r13 adcx %rcx,%r9 adox %r13,%r10 mulx %r14,%rcx,%r14 adcx %rcx,%r10 adox %r14,%r11 mulx %r15,%rcx,%r15 adcx %rcx,%r11 adox %rbp,%r15 adcx %rbp,%r15 shld $1,%r11,%r15 andq mask63(%rip),%r11 imul $19,%r15,%r15 addq %r15,%r8 adcq $0,%r9 adcq $0,%r10 adcq $0,%r11 movq %r8,176(%rsp) movq %r9,184(%rsp) movq %r10,192(%rsp) movq %r11,200(%rsp) // mul xorq %r13,%r13 movq 240(%rsp),%rdx mulx 304(%rsp),%r8,%r9 mulx 312(%rsp),%rcx,%r10 adcx %rcx,%r9 mulx 320(%rsp),%rcx,%r11 adcx %rcx,%r10 mulx 328(%rsp),%rcx,%r12 adcx %rcx,%r11 adcx %r13,%r12 xorq %r14,%r14 movq 248(%rsp),%rdx mulx 304(%rsp),%rcx,%rbp adcx %rcx,%r9 adox %rbp,%r10 mulx 312(%rsp),%rcx,%rbp adcx %rcx,%r10 adox %rbp,%r11 mulx 320(%rsp),%rcx,%rbp adcx %rcx,%r11 adox %rbp,%r12 mulx 328(%rsp),%rcx,%rbp adcx %rcx,%r12 adox %rbp,%r13 adcx %r14,%r13 xorq %r15,%r15 movq 256(%rsp),%rdx mulx 304(%rsp),%rcx,%rbp adcx %rcx,%r10 adox %rbp,%r11 mulx 312(%rsp),%rcx,%rbp adcx %rcx,%r11 adox %rbp,%r12 mulx 320(%rsp),%rcx,%rbp adcx %rcx,%r12 adox %rbp,%r13 mulx 328(%rsp),%rcx,%rbp adcx %rcx,%r13 adox %rbp,%r14 adcx %r15,%r14 xorq %rax,%rax movq 264(%rsp),%rdx mulx 304(%rsp),%rcx,%rbp adcx %rcx,%r11 adox %rbp,%r12 mulx 312(%rsp),%rcx,%rbp adcx %rcx,%r12 adox %rbp,%r13 mulx 320(%rsp),%rcx,%rbp adcx %rcx,%r13 adox %rbp,%r14 mulx 328(%rsp),%rcx,%rbp adcx %rcx,%r14 adox %rbp,%r15 adcx %rax,%r15 xorq %rbp,%rbp movq $38,%rdx mulx %r12,%rax,%r12 adcx %rax,%r8 adox %r12,%r9 mulx %r13,%rcx,%r13 adcx %rcx,%r9 adox %r13,%r10 mulx %r14,%rcx,%r14 adcx %rcx,%r10 adox %r14,%r11 mulx %r15,%rcx,%r15 adcx %rcx,%r11 adox %rbp,%r15 adcx %rbp,%r15 shld $1,%r11,%r15 andq mask63(%rip),%r11 imul $19,%r15,%r15 addq %r15,%r8 adcq $0,%r9 adcq $0,%r10 adcq $0,%r11 movq %r8,208(%rsp) movq %r9,216(%rsp) movq %r10,224(%rsp) movq %r11,232(%rsp) movb 104(%rsp),%r14b shrb $1,%r14b movzbq %r14b,%r14 imul $96,%r14,%r14 addq %r14,%rdi /* nielsadd p1p1 */ movq 144(%rsp),%r8 movq 152(%rsp),%r9 movq 160(%rsp),%r10 movq 168(%rsp),%r11 // copy movq %r8,%r12 movq %r9,%r13 movq %r10,%r14 movq %r11,%r15 // sub subq 112(%rsp),%r8 sbbq 120(%rsp),%r9 sbbq 128(%rsp),%r10 sbbq 136(%rsp),%r11 movq $0,%rdx movq $38,%rax cmovae %rdx,%rax subq %rax,%r8 sbbq %rdx,%r9 sbbq %rdx,%r10 sbbq %rdx,%r11 cmovc %rax,%rdx subq %rdx,%r8 movq %r8,368(%rsp) movq %r9,376(%rsp) movq %r10,384(%rsp) movq %r11,392(%rsp) // add addq 112(%rsp),%r12 adcq 120(%rsp),%r13 adcq 128(%rsp),%r14 adcq 136(%rsp),%r15 movq $0,%rdx movq $38,%rax cmovae %rdx,%rax addq %rax,%r12 adcq %rdx,%r13 adcq %rdx,%r14 adcq %rdx,%r15 cmovc %rax,%rdx addq %rdx,%r12 movq %r12,400(%rsp) movq %r13,408(%rsp) movq %r14,416(%rsp) movq %r15,424(%rsp) // mul xorq %r13,%r13 movq 0(%rdi),%rdx mulx 368(%rsp),%r8,%r9 mulx 376(%rsp),%rcx,%r10 adcx %rcx,%r9 mulx 384(%rsp),%rcx,%r11 adcx %rcx,%r10 mulx 392(%rsp),%rcx,%r12 adcx %rcx,%r11 adcx %r13,%r12 xorq %r14,%r14 movq 8(%rdi),%rdx mulx 368(%rsp),%rcx,%rbp adcx %rcx,%r9 adox %rbp,%r10 mulx 376(%rsp),%rcx,%rbp adcx %rcx,%r10 adox %rbp,%r11 mulx 384(%rsp),%rcx,%rbp adcx %rcx,%r11 adox %rbp,%r12 mulx 392(%rsp),%rcx,%rbp adcx %rcx,%r12 adox %rbp,%r13 adcx %r14,%r13 xorq %r15,%r15 movq 16(%rdi),%rdx mulx 368(%rsp),%rcx,%rbp adcx %rcx,%r10 adox %rbp,%r11 mulx 376(%rsp),%rcx,%rbp adcx %rcx,%r11 adox %rbp,%r12 mulx 384(%rsp),%rcx,%rbp adcx %rcx,%r12 adox %rbp,%r13 mulx 392(%rsp),%rcx,%rbp adcx %rcx,%r13 adox %rbp,%r14 adcx %r15,%r14 xorq %rax,%rax movq 24(%rdi),%rdx mulx 368(%rsp),%rcx,%rbp adcx %rcx,%r11 adox %rbp,%r12 mulx 376(%rsp),%rcx,%rbp adcx %rcx,%r12 adox %rbp,%r13 mulx 384(%rsp),%rcx,%rbp adcx %rcx,%r13 adox %rbp,%r14 mulx 392(%rsp),%rcx,%rbp adcx %rcx,%r14 adox %rbp,%r15 adcx %rax,%r15 xorq %rbp,%rbp movq $38,%rdx mulx %r12,%rax,%r12 adcx %rax,%r8 adox %r12,%r9 mulx %r13,%rcx,%r13 adcx %rcx,%r9 adox %r13,%r10 mulx %r14,%rcx,%r14 adcx %rcx,%r10 adox %r14,%r11 mulx %r15,%rcx,%r15 adcx %rcx,%r11 adox %rbp,%r15 adcx %rbp,%r15 shld $1,%r11,%r15 andq mask63(%rip),%r11 imul $19,%r15,%r15 addq %r15,%r8 adcq $0,%r9 adcq $0,%r10 adcq $0,%r11 movq %r8,368(%rsp) movq %r9,376(%rsp) movq %r10,384(%rsp) movq %r11,392(%rsp) // mul xorq %r13,%r13 movq 32(%rdi),%rdx mulx 400(%rsp),%r8,%r9 mulx 408(%rsp),%rcx,%r10 adcx %rcx,%r9 mulx 416(%rsp),%rcx,%r11 adcx %rcx,%r10 mulx 424(%rsp),%rcx,%r12 adcx %rcx,%r11 adcx %r13,%r12 xorq %r14,%r14 movq 40(%rdi),%rdx mulx 400(%rsp),%rcx,%rbp adcx %rcx,%r9 adox %rbp,%r10 mulx 408(%rsp),%rcx,%rbp adcx %rcx,%r10 adox %rbp,%r11 mulx 416(%rsp),%rcx,%rbp adcx %rcx,%r11 adox %rbp,%r12 mulx 424(%rsp),%rcx,%rbp adcx %rcx,%r12 adox %rbp,%r13 adcx %r14,%r13 xorq %r15,%r15 movq 48(%rdi),%rdx mulx 400(%rsp),%rcx,%rbp adcx %rcx,%r10 adox %rbp,%r11 mulx 408(%rsp),%rcx,%rbp adcx %rcx,%r11 adox %rbp,%r12 mulx 416(%rsp),%rcx,%rbp adcx %rcx,%r12 adox %rbp,%r13 mulx 424(%rsp),%rcx,%rbp adcx %rcx,%r13 adox %rbp,%r14 adcx %r15,%r14 xorq %rax,%rax movq 56(%rdi),%rdx mulx 400(%rsp),%rcx,%rbp adcx %rcx,%r11 adox %rbp,%r12 mulx 408(%rsp),%rcx,%rbp adcx %rcx,%r12 adox %rbp,%r13 mulx 416(%rsp),%rcx,%rbp adcx %rcx,%r13 adox %rbp,%r14 mulx 424(%rsp),%rcx,%rbp adcx %rcx,%r14 adox %rbp,%r15 adcx %rax,%r15 xorq %rbp,%rbp movq $38,%rdx mulx %r12,%rax,%r12 adcx %rax,%r8 adox %r12,%r9 mulx %r13,%rcx,%r13 adcx %rcx,%r9 adox %r13,%r10 mulx %r14,%rcx,%r14 adcx %rcx,%r10 adox %r14,%r11 mulx %r15,%rcx,%r15 adcx %rcx,%r11 adox %rbp,%r15 adcx %rbp,%r15 shld $1,%r11,%r15 andq mask63(%rip),%r11 imul $19,%r15,%r15 addq %r15,%r8 adcq $0,%r9 adcq $0,%r10 adcq $0,%r11 // add movq %r8,%r12 movq %r9,%r13 movq %r10,%r14 movq %r11,%r15 addq 368(%rsp),%r8 adcq 376(%rsp),%r9 adcq 384(%rsp),%r10 adcq 392(%rsp),%r11 movq $0,%rdx mov $38,%rax cmovae %rdx,%rax addq %rax,%r8 adcq %rdx,%r9 adcq %rdx,%r10 adcq %rdx,%r11 cmovc %rax,%rdx addq %rdx,%r8 movq %r8,304(%rsp) movq %r9,312(%rsp) movq %r10,320(%rsp) movq %r11,328(%rsp) // sub subq 368(%rsp),%r12 sbbq 376(%rsp),%r13 sbbq 384(%rsp),%r14 sbbq 392(%rsp),%r15 movq $0,%rdx mov $38,%rax cmovae %rdx,%rax subq %rax,%r12 sbbq %rdx,%r13 sbbq %rdx,%r14 sbbq %rdx,%r15 cmovc %rax,%rdx subq %rdx,%r12 movq %r12,240(%rsp) movq %r13,248(%rsp) movq %r14,256(%rsp) movq %r15,264(%rsp) // mul xorq %r13,%r13 movq 64(%rdi),%rdx mulx 208(%rsp),%r8,%r9 mulx 216(%rsp),%rcx,%r10 adcx %rcx,%r9 mulx 224(%rsp),%rcx,%r11 adcx %rcx,%r10 mulx 232(%rsp),%rcx,%r12 adcx %rcx,%r11 adcx %r13,%r12 xorq %r14,%r14 movq 72(%rdi),%rdx mulx 208(%rsp),%rcx,%rbp adcx %rcx,%r9 adox %rbp,%r10 mulx 216(%rsp),%rcx,%rbp adcx %rcx,%r10 adox %rbp,%r11 mulx 224(%rsp),%rcx,%rbp adcx %rcx,%r11 adox %rbp,%r12 mulx 232(%rsp),%rcx,%rbp adcx %rcx,%r12 adox %rbp,%r13 adcx %r14,%r13 xorq %r15,%r15 movq 80(%rdi),%rdx mulx 208(%rsp),%rcx,%rbp adcx %rcx,%r10 adox %rbp,%r11 mulx 216(%rsp),%rcx,%rbp adcx %rcx,%r11 adox %rbp,%r12 mulx 224(%rsp),%rcx,%rbp adcx %rcx,%r12 adox %rbp,%r13 mulx 232(%rsp),%rcx,%rbp adcx %rcx,%r13 adox %rbp,%r14 adcx %r15,%r14 xorq %rax,%rax movq 88(%rdi),%rdx mulx 208(%rsp),%rcx,%rbp adcx %rcx,%r11 adox %rbp,%r12 mulx 216(%rsp),%rcx,%rbp adcx %rcx,%r12 adox %rbp,%r13 mulx 224(%rsp),%rcx,%rbp adcx %rcx,%r13 adox %rbp,%r14 mulx 232(%rsp),%rcx,%rbp adcx %rcx,%r14 adox %rbp,%r15 adcx %rax,%r15 xorq %rbp,%rbp movq $38,%rdx mulx %r12,%rax,%r12 adcx %rax,%r8 adox %r12,%r9 mulx %r13,%rcx,%r13 adcx %rcx,%r9 adox %r13,%r10 mulx %r14,%rcx,%r14 adcx %rcx,%r10 adox %r14,%r11 mulx %r15,%rcx,%r15 adcx %rcx,%r11 adox %rbp,%r15 adcx %rbp,%r15 shld $1,%r11,%r15 andq mask63(%rip),%r11 imul $19,%r15,%r15 addq %r15,%r8 adcq $0,%r9 adcq $0,%r10 adcq $0,%r11 // double movq 176(%rsp),%r12 movq 184(%rsp),%r13 movq 192(%rsp),%r14 movq 200(%rsp),%r15 addq %r12,%r12 adcq %r13,%r13 adcq %r14,%r14 adcq %r15,%r15 movq $0,%rdx mov $38,%rax cmovae %rdx,%rax addq %rax,%r12 adcq %rdx,%r13 adcq %rdx,%r14 adcq %rdx,%r15 cmovc %rax,%rdx addq %rdx,%r12 // sub movq %r12,%rbx movq %r13,%rcx movq %r14,%rbp movq %r15,%rsi subq %r8,%r12 sbbq %r9,%r13 sbbq %r10,%r14 sbbq %r11,%r15 movq $0,%rdx mov $38,%rax cmovae %rdx,%rax subq %rax,%r12 sbbq %rdx,%r13 sbbq %rdx,%r14 sbbq %rdx,%r15 cmovc %rax,%rdx sbbq %rdx,%r12 movq %r12,336(%rsp) movq %r13,344(%rsp) movq %r14,352(%rsp) movq %r15,360(%rsp) // add addq %rbx,%r8 adcq %rcx,%r9 adcq %rbp,%r10 adcq %rsi,%r11 movq $0,%rdx mov $38,%rax cmovae %rdx,%rax addq %rax,%r8 adcq %rdx,%r9 adcq %rdx,%r10 adcq %rdx,%r11 cmovc %rax,%rdx adcq %rdx,%r8 movq %r8,272(%rsp) movq %r9,280(%rsp) movq %r10,288(%rsp) movq %r11,296(%rsp) jmp .L9 .L8: /* p1p1 to p3 */ // mul xorq %r13,%r13 movq 240(%rsp),%rdx mulx 336(%rsp),%r8,%r9 mulx 344(%rsp),%rcx,%r10 adcx %rcx,%r9 mulx 352(%rsp),%rcx,%r11 adcx %rcx,%r10 mulx 360(%rsp),%rcx,%r12 adcx %rcx,%r11 adcx %r13,%r12 xorq %r14,%r14 movq 248(%rsp),%rdx mulx 336(%rsp),%rcx,%rbp adcx %rcx,%r9 adox %rbp,%r10 mulx 344(%rsp),%rcx,%rbp adcx %rcx,%r10 adox %rbp,%r11 mulx 352(%rsp),%rcx,%rbp adcx %rcx,%r11 adox %rbp,%r12 mulx 360(%rsp),%rcx,%rbp adcx %rcx,%r12 adox %rbp,%r13 adcx %r14,%r13 xorq %r15,%r15 movq 256(%rsp),%rdx mulx 336(%rsp),%rcx,%rbp adcx %rcx,%r10 adox %rbp,%r11 mulx 344(%rsp),%rcx,%rbp adcx %rcx,%r11 adox %rbp,%r12 mulx 352(%rsp),%rcx,%rbp adcx %rcx,%r12 adox %rbp,%r13 mulx 360(%rsp),%rcx,%rbp adcx %rcx,%r13 adox %rbp,%r14 adcx %r15,%r14 xorq %rax,%rax movq 264(%rsp),%rdx mulx 336(%rsp),%rcx,%rbp adcx %rcx,%r11 adox %rbp,%r12 mulx 344(%rsp),%rcx,%rbp adcx %rcx,%r12 adox %rbp,%r13 mulx 352(%rsp),%rcx,%rbp adcx %rcx,%r13 adox %rbp,%r14 mulx 360(%rsp),%rcx,%rbp adcx %rcx,%r14 adox %rbp,%r15 adcx %rax,%r15 xorq %rbp,%rbp movq $38,%rdx mulx %r12,%rax,%r12 adcx %rax,%r8 adox %r12,%r9 mulx %r13,%rcx,%r13 adcx %rcx,%r9 adox %r13,%r10 mulx %r14,%rcx,%r14 adcx %rcx,%r10 adox %r14,%r11 mulx %r15,%rcx,%r15 adcx %rcx,%r11 adox %rbp,%r15 adcx %rbp,%r15 shld $1,%r11,%r15 andq mask63(%rip),%r11 imul $19,%r15,%r15 addq %r15,%r8 adcq $0,%r9 adcq $0,%r10 adcq $0,%r11 movq %r8,112(%rsp) movq %r9,120(%rsp) movq %r10,128(%rsp) movq %r11,136(%rsp) // mul xorq %r13,%r13 movq 272(%rsp),%rdx mulx 304(%rsp),%r8,%r9 mulx 312(%rsp),%rcx,%r10 adcx %rcx,%r9 mulx 320(%rsp),%rcx,%r11 adcx %rcx,%r10 mulx 328(%rsp),%rcx,%r12 adcx %rcx,%r11 adcx %r13,%r12 xorq %r14,%r14 movq 280(%rsp),%rdx mulx 304(%rsp),%rcx,%rbp adcx %rcx,%r9 adox %rbp,%r10 mulx 312(%rsp),%rcx,%rbp adcx %rcx,%r10 adox %rbp,%r11 mulx 320(%rsp),%rcx,%rbp adcx %rcx,%r11 adox %rbp,%r12 mulx 328(%rsp),%rcx,%rbp adcx %rcx,%r12 adox %rbp,%r13 adcx %r14,%r13 xorq %r15,%r15 movq 288(%rsp),%rdx mulx 304(%rsp),%rcx,%rbp adcx %rcx,%r10 adox %rbp,%r11 mulx 312(%rsp),%rcx,%rbp adcx %rcx,%r11 adox %rbp,%r12 mulx 320(%rsp),%rcx,%rbp adcx %rcx,%r12 adox %rbp,%r13 mulx 328(%rsp),%rcx,%rbp adcx %rcx,%r13 adox %rbp,%r14 adcx %r15,%r14 xorq %rax,%rax movq 296(%rsp),%rdx mulx 304(%rsp),%rcx,%rbp adcx %rcx,%r11 adox %rbp,%r12 mulx 312(%rsp),%rcx,%rbp adcx %rcx,%r12 adox %rbp,%r13 mulx 320(%rsp),%rcx,%rbp adcx %rcx,%r13 adox %rbp,%r14 mulx 328(%rsp),%rcx,%rbp adcx %rcx,%r14 adox %rbp,%r15 adcx %rax,%r15 xorq %rbp,%rbp movq $38,%rdx mulx %r12,%rax,%r12 adcx %rax,%r8 adox %r12,%r9 mulx %r13,%rcx,%r13 adcx %rcx,%r9 adox %r13,%r10 mulx %r14,%rcx,%r14 adcx %rcx,%r10 adox %r14,%r11 mulx %r15,%rcx,%r15 adcx %rcx,%r11 adox %rbp,%r15 adcx %rbp,%r15 shld $1,%r11,%r15 andq mask63(%rip),%r11 imul $19,%r15,%r15 addq %r15,%r8 adcq $0,%r9 adcq $0,%r10 adcq $0,%r11 movq %r8,144(%rsp) movq %r9,152(%rsp) movq %r10,160(%rsp) movq %r11,168(%rsp) // mul xorq %r13,%r13 movq 272(%rsp),%rdx mulx 336(%rsp),%r8,%r9 mulx 344(%rsp),%rcx,%r10 adcx %rcx,%r9 mulx 352(%rsp),%rcx,%r11 adcx %rcx,%r10 mulx 360(%rsp),%rcx,%r12 adcx %rcx,%r11 adcx %r13,%r12 xorq %r14,%r14 movq 280(%rsp),%rdx mulx 336(%rsp),%rcx,%rbp adcx %rcx,%r9 adox %rbp,%r10 mulx 344(%rsp),%rcx,%rbp adcx %rcx,%r10 adox %rbp,%r11 mulx 352(%rsp),%rcx,%rbp adcx %rcx,%r11 adox %rbp,%r12 mulx 360(%rsp),%rcx,%rbp adcx %rcx,%r12 adox %rbp,%r13 adcx %r14,%r13 xorq %r15,%r15 movq 288(%rsp),%rdx mulx 336(%rsp),%rcx,%rbp adcx %rcx,%r10 adox %rbp,%r11 mulx 344(%rsp),%rcx,%rbp adcx %rcx,%r11 adox %rbp,%r12 mulx 352(%rsp),%rcx,%rbp adcx %rcx,%r12 adox %rbp,%r13 mulx 360(%rsp),%rcx,%rbp adcx %rcx,%r13 adox %rbp,%r14 adcx %r15,%r14 xorq %rax,%rax movq 296(%rsp),%rdx mulx 336(%rsp),%rcx,%rbp adcx %rcx,%r11 adox %rbp,%r12 mulx 344(%rsp),%rcx,%rbp adcx %rcx,%r12 adox %rbp,%r13 mulx 352(%rsp),%rcx,%rbp adcx %rcx,%r13 adox %rbp,%r14 mulx 360(%rsp),%rcx,%rbp adcx %rcx,%r14 adox %rbp,%r15 adcx %rax,%r15 xorq %rbp,%rbp movq $38,%rdx mulx %r12,%rax,%r12 adcx %rax,%r8 adox %r12,%r9 mulx %r13,%rcx,%r13 adcx %rcx,%r9 adox %r13,%r10 mulx %r14,%rcx,%r14 adcx %rcx,%r10 adox %r14,%r11 mulx %r15,%rcx,%r15 adcx %rcx,%r11 adox %rbp,%r15 adcx %rbp,%r15 shld $1,%r11,%r15 andq mask63(%rip),%r11 imul $19,%r15,%r15 addq %r15,%r8 adcq $0,%r9 adcq $0,%r10 adcq $0,%r11 movq %r8,176(%rsp) movq %r9,184(%rsp) movq %r10,192(%rsp) movq %r11,200(%rsp) // mul xorq %r13,%r13 movq 240(%rsp),%rdx mulx 304(%rsp),%r8,%r9 mulx 312(%rsp),%rcx,%r10 adcx %rcx,%r9 mulx 320(%rsp),%rcx,%r11 adcx %rcx,%r10 mulx 328(%rsp),%rcx,%r12 adcx %rcx,%r11 adcx %r13,%r12 xorq %r14,%r14 movq 248(%rsp),%rdx mulx 304(%rsp),%rcx,%rbp adcx %rcx,%r9 adox %rbp,%r10 mulx 312(%rsp),%rcx,%rbp adcx %rcx,%r10 adox %rbp,%r11 mulx 320(%rsp),%rcx,%rbp adcx %rcx,%r11 adox %rbp,%r12 mulx 328(%rsp),%rcx,%rbp adcx %rcx,%r12 adox %rbp,%r13 adcx %r14,%r13 xorq %r15,%r15 movq 256(%rsp),%rdx mulx 304(%rsp),%rcx,%rbp adcx %rcx,%r10 adox %rbp,%r11 mulx 312(%rsp),%rcx,%rbp adcx %rcx,%r11 adox %rbp,%r12 mulx 320(%rsp),%rcx,%rbp adcx %rcx,%r12 adox %rbp,%r13 mulx 328(%rsp),%rcx,%rbp adcx %rcx,%r13 adox %rbp,%r14 adcx %r15,%r14 xorq %rax,%rax movq 264(%rsp),%rdx mulx 304(%rsp),%rcx,%rbp adcx %rcx,%r11 adox %rbp,%r12 mulx 312(%rsp),%rcx,%rbp adcx %rcx,%r12 adox %rbp,%r13 mulx 320(%rsp),%rcx,%rbp adcx %rcx,%r13 adox %rbp,%r14 mulx 328(%rsp),%rcx,%rbp adcx %rcx,%r14 adox %rbp,%r15 adcx %rax,%r15 xorq %rbp,%rbp movq $38,%rdx mulx %r12,%rax,%r12 adcx %rax,%r8 adox %r12,%r9 mulx %r13,%rcx,%r13 adcx %rcx,%r9 adox %r13,%r10 mulx %r14,%rcx,%r14 adcx %rcx,%r10 adox %r14,%r11 mulx %r15,%rcx,%r15 adcx %rcx,%r11 adox %rbp,%r15 adcx %rbp,%r15 shld $1,%r11,%r15 andq mask63(%rip),%r11 imul $19,%r15,%r15 addq %r15,%r8 adcq $0,%r9 adcq $0,%r10 adcq $0,%r11 movq %r8,208(%rsp) movq %r9,216(%rsp) movq %r10,224(%rsp) movq %r11,232(%rsp) movb 104(%rsp),%r14b movb $0,%r15b subb %r14b,%r15b shrb $1,%r15b movzbq %r15b,%r15 imul $96,%r15,%r15 addq %r15,%rdi // neg movq $0,%r8 movq $0,%r9 movq $0,%r10 movq $0,%r11 subq 64(%rdi),%r8 sbbq 72(%rdi),%r9 sbbq 80(%rdi),%r10 sbbq 88(%rdi),%r11 movq $0,%rdx movq $38,%rax cmovae %rdx,%rax subq %rax,%r8 sbbq %rdx,%r9 sbbq %rdx,%r10 sbbq %rdx,%r11 cmovc %rax,%rdx subq %rdx,%r8 movq %r8,432(%rsp) movq %r9,440(%rsp) movq %r10,448(%rsp) movq %r11,456(%rsp) /* nielsadd p1p1 */ movq 144(%rsp),%r8 movq 152(%rsp),%r9 movq 160(%rsp),%r10 movq 168(%rsp),%r11 // copy movq %r8,%r12 movq %r9,%r13 movq %r10,%r14 movq %r11,%r15 // sub subq 112(%rsp),%r8 sbbq 120(%rsp),%r9 sbbq 128(%rsp),%r10 sbbq 136(%rsp),%r11 movq $0,%rdx movq $38,%rax cmovae %rdx,%rax subq %rax,%r8 sbbq %rdx,%r9 sbbq %rdx,%r10 sbbq %rdx,%r11 cmovc %rax,%rdx subq %rdx,%r8 movq %r8,368(%rsp) movq %r9,376(%rsp) movq %r10,384(%rsp) movq %r11,392(%rsp) // add addq 112(%rsp),%r12 adcq 120(%rsp),%r13 adcq 128(%rsp),%r14 adcq 136(%rsp),%r15 movq $0,%rdx movq $38,%rax cmovae %rdx,%rax addq %rax,%r12 adcq %rdx,%r13 adcq %rdx,%r14 adcq %rdx,%r15 cmovc %rax,%rdx addq %rdx,%r12 movq %r12,400(%rsp) movq %r13,408(%rsp) movq %r14,416(%rsp) movq %r15,424(%rsp) // mul xorq %r13,%r13 movq 32(%rdi),%rdx mulx 368(%rsp),%r8,%r9 mulx 376(%rsp),%rcx,%r10 adcx %rcx,%r9 mulx 384(%rsp),%rcx,%r11 adcx %rcx,%r10 mulx 392(%rsp),%rcx,%r12 adcx %rcx,%r11 adcx %r13,%r12 xorq %r14,%r14 movq 40(%rdi),%rdx mulx 368(%rsp),%rcx,%rbp adcx %rcx,%r9 adox %rbp,%r10 mulx 376(%rsp),%rcx,%rbp adcx %rcx,%r10 adox %rbp,%r11 mulx 384(%rsp),%rcx,%rbp adcx %rcx,%r11 adox %rbp,%r12 mulx 392(%rsp),%rcx,%rbp adcx %rcx,%r12 adox %rbp,%r13 adcx %r14,%r13 xorq %r15,%r15 movq 48(%rdi),%rdx mulx 368(%rsp),%rcx,%rbp adcx %rcx,%r10 adox %rbp,%r11 mulx 376(%rsp),%rcx,%rbp adcx %rcx,%r11 adox %rbp,%r12 mulx 384(%rsp),%rcx,%rbp adcx %rcx,%r12 adox %rbp,%r13 mulx 392(%rsp),%rcx,%rbp adcx %rcx,%r13 adox %rbp,%r14 adcx %r15,%r14 xorq %rax,%rax movq 56(%rdi),%rdx mulx 368(%rsp),%rcx,%rbp adcx %rcx,%r11 adox %rbp,%r12 mulx 376(%rsp),%rcx,%rbp adcx %rcx,%r12 adox %rbp,%r13 mulx 384(%rsp),%rcx,%rbp adcx %rcx,%r13 adox %rbp,%r14 mulx 392(%rsp),%rcx,%rbp adcx %rcx,%r14 adox %rbp,%r15 adcx %rax,%r15 xorq %rbp,%rbp movq $38,%rdx mulx %r12,%rax,%r12 adcx %rax,%r8 adox %r12,%r9 mulx %r13,%rcx,%r13 adcx %rcx,%r9 adox %r13,%r10 mulx %r14,%rcx,%r14 adcx %rcx,%r10 adox %r14,%r11 mulx %r15,%rcx,%r15 adcx %rcx,%r11 adox %rbp,%r15 adcx %rbp,%r15 shld $1,%r11,%r15 andq mask63(%rip),%r11 imul $19,%r15,%r15 addq %r15,%r8 adcq $0,%r9 adcq $0,%r10 adcq $0,%r11 movq %r8,368(%rsp) movq %r9,376(%rsp) movq %r10,384(%rsp) movq %r11,392(%rsp) // mul xorq %r13,%r13 movq 0(%rdi),%rdx mulx 400(%rsp),%r8,%r9 mulx 408(%rsp),%rcx,%r10 adcx %rcx,%r9 mulx 416(%rsp),%rcx,%r11 adcx %rcx,%r10 mulx 424(%rsp),%rcx,%r12 adcx %rcx,%r11 adcx %r13,%r12 xorq %r14,%r14 movq 8(%rdi),%rdx mulx 400(%rsp),%rcx,%rbp adcx %rcx,%r9 adox %rbp,%r10 mulx 408(%rsp),%rcx,%rbp adcx %rcx,%r10 adox %rbp,%r11 mulx 416(%rsp),%rcx,%rbp adcx %rcx,%r11 adox %rbp,%r12 mulx 424(%rsp),%rcx,%rbp adcx %rcx,%r12 adox %rbp,%r13 adcx %r14,%r13 xorq %r15,%r15 movq 16(%rdi),%rdx mulx 400(%rsp),%rcx,%rbp adcx %rcx,%r10 adox %rbp,%r11 mulx 408(%rsp),%rcx,%rbp adcx %rcx,%r11 adox %rbp,%r12 mulx 416(%rsp),%rcx,%rbp adcx %rcx,%r12 adox %rbp,%r13 mulx 424(%rsp),%rcx,%rbp adcx %rcx,%r13 adox %rbp,%r14 adcx %r15,%r14 xorq %rax,%rax movq 24(%rdi),%rdx mulx 400(%rsp),%rcx,%rbp adcx %rcx,%r11 adox %rbp,%r12 mulx 408(%rsp),%rcx,%rbp adcx %rcx,%r12 adox %rbp,%r13 mulx 416(%rsp),%rcx,%rbp adcx %rcx,%r13 adox %rbp,%r14 mulx 424(%rsp),%rcx,%rbp adcx %rcx,%r14 adox %rbp,%r15 adcx %rax,%r15 xorq %rbp,%rbp movq $38,%rdx mulx %r12,%rax,%r12 adcx %rax,%r8 adox %r12,%r9 mulx %r13,%rcx,%r13 adcx %rcx,%r9 adox %r13,%r10 mulx %r14,%rcx,%r14 adcx %rcx,%r10 adox %r14,%r11 mulx %r15,%rcx,%r15 adcx %rcx,%r11 adox %rbp,%r15 adcx %rbp,%r15 shld $1,%r11,%r15 andq mask63(%rip),%r11 imul $19,%r15,%r15 addq %r15,%r8 adcq $0,%r9 adcq $0,%r10 adcq $0,%r11 // add movq %r8,%r12 movq %r9,%r13 movq %r10,%r14 movq %r11,%r15 addq 368(%rsp),%r8 adcq 376(%rsp),%r9 adcq 384(%rsp),%r10 adcq 392(%rsp),%r11 movq $0,%rdx mov $38,%rax cmovae %rdx,%rax addq %rax,%r8 adcq %rdx,%r9 adcq %rdx,%r10 adcq %rdx,%r11 cmovc %rax,%rdx addq %rdx,%r8 movq %r8,304(%rsp) movq %r9,312(%rsp) movq %r10,320(%rsp) movq %r11,328(%rsp) // sub subq 368(%rsp),%r12 sbbq 376(%rsp),%r13 sbbq 384(%rsp),%r14 sbbq 392(%rsp),%r15 movq $0,%rdx mov $38,%rax cmovae %rdx,%rax subq %rax,%r12 sbbq %rdx,%r13 sbbq %rdx,%r14 sbbq %rdx,%r15 cmovc %rax,%rdx subq %rdx,%r12 movq %r12,240(%rsp) movq %r13,248(%rsp) movq %r14,256(%rsp) movq %r15,264(%rsp) // mul xorq %r13,%r13 movq 432(%rsp),%rdx mulx 208(%rsp),%r8,%r9 mulx 216(%rsp),%rcx,%r10 adcx %rcx,%r9 mulx 224(%rsp),%rcx,%r11 adcx %rcx,%r10 mulx 232(%rsp),%rcx,%r12 adcx %rcx,%r11 adcx %r13,%r12 xorq %r14,%r14 movq 440(%rsp),%rdx mulx 208(%rsp),%rcx,%rbp adcx %rcx,%r9 adox %rbp,%r10 mulx 216(%rsp),%rcx,%rbp adcx %rcx,%r10 adox %rbp,%r11 mulx 224(%rsp),%rcx,%rbp adcx %rcx,%r11 adox %rbp,%r12 mulx 232(%rsp),%rcx,%rbp adcx %rcx,%r12 adox %rbp,%r13 adcx %r14,%r13 xorq %r15,%r15 movq 448(%rsp),%rdx mulx 208(%rsp),%rcx,%rbp adcx %rcx,%r10 adox %rbp,%r11 mulx 216(%rsp),%rcx,%rbp adcx %rcx,%r11 adox %rbp,%r12 mulx 224(%rsp),%rcx,%rbp adcx %rcx,%r12 adox %rbp,%r13 mulx 232(%rsp),%rcx,%rbp adcx %rcx,%r13 adox %rbp,%r14 adcx %r15,%r14 xorq %rax,%rax movq 456(%rsp),%rdx mulx 208(%rsp),%rcx,%rbp adcx %rcx,%r11 adox %rbp,%r12 mulx 216(%rsp),%rcx,%rbp adcx %rcx,%r12 adox %rbp,%r13 mulx 224(%rsp),%rcx,%rbp adcx %rcx,%r13 adox %rbp,%r14 mulx 232(%rsp),%rcx,%rbp adcx %rcx,%r14 adox %rbp,%r15 adcx %rax,%r15 xorq %rbp,%rbp movq $38,%rdx mulx %r12,%rax,%r12 adcx %rax,%r8 adox %r12,%r9 mulx %r13,%rcx,%r13 adcx %rcx,%r9 adox %r13,%r10 mulx %r14,%rcx,%r14 adcx %rcx,%r10 adox %r14,%r11 mulx %r15,%rcx,%r15 adcx %rcx,%r11 adox %rbp,%r15 adcx %rbp,%r15 shld $1,%r11,%r15 andq mask63(%rip),%r11 imul $19,%r15,%r15 addq %r15,%r8 adcq $0,%r9 adcq $0,%r10 adcq $0,%r11 // double movq 176(%rsp),%r12 movq 184(%rsp),%r13 movq 192(%rsp),%r14 movq 200(%rsp),%r15 addq %r12,%r12 adcq %r13,%r13 adcq %r14,%r14 adcq %r15,%r15 movq $0,%rdx mov $38,%rax cmovae %rdx,%rax addq %rax,%r12 adcq %rdx,%r13 adcq %rdx,%r14 adcq %rdx,%r15 cmovc %rax,%rdx addq %rdx,%r12 // sub movq %r12,%rbx movq %r13,%rcx movq %r14,%rbp movq %r15,%rsi subq %r8,%r12 sbbq %r9,%r13 sbbq %r10,%r14 sbbq %r11,%r15 movq $0,%rdx mov $38,%rax cmovae %rdx,%rax subq %rax,%r12 sbbq %rdx,%r13 sbbq %rdx,%r14 sbbq %rdx,%r15 cmovc %rax,%rdx sbbq %rdx,%r12 movq %r12,336(%rsp) movq %r13,344(%rsp) movq %r14,352(%rsp) movq %r15,360(%rsp) // add addq %rbx,%r8 adcq %rcx,%r9 adcq %rbp,%r10 adcq %rsi,%r11 movq $0,%rdx mov $38,%rax cmovae %rdx,%rax addq %rax,%r8 adcq %rdx,%r9 adcq %rdx,%r10 adcq %rdx,%r11 cmovc %rax,%rdx adcq %rdx,%r8 movq %r8,272(%rsp) movq %r9,280(%rsp) movq %r10,288(%rsp) movq %r11,296(%rsp) .L9: movq 56(%rsp),%rdi /* p1p1 to p2 */ // mul xorq %r13,%r13 movq 240(%rsp),%rdx mulx 336(%rsp),%r8,%r9 mulx 344(%rsp),%rcx,%r10 adcx %rcx,%r9 mulx 352(%rsp),%rcx,%r11 adcx %rcx,%r10 mulx 360(%rsp),%rcx,%r12 adcx %rcx,%r11 adcx %r13,%r12 xorq %r14,%r14 movq 248(%rsp),%rdx mulx 336(%rsp),%rcx,%rbp adcx %rcx,%r9 adox %rbp,%r10 mulx 344(%rsp),%rcx,%rbp adcx %rcx,%r10 adox %rbp,%r11 mulx 352(%rsp),%rcx,%rbp adcx %rcx,%r11 adox %rbp,%r12 mulx 360(%rsp),%rcx,%rbp adcx %rcx,%r12 adox %rbp,%r13 adcx %r14,%r13 xorq %r15,%r15 movq 256(%rsp),%rdx mulx 336(%rsp),%rcx,%rbp adcx %rcx,%r10 adox %rbp,%r11 mulx 344(%rsp),%rcx,%rbp adcx %rcx,%r11 adox %rbp,%r12 mulx 352(%rsp),%rcx,%rbp adcx %rcx,%r12 adox %rbp,%r13 mulx 360(%rsp),%rcx,%rbp adcx %rcx,%r13 adox %rbp,%r14 adcx %r15,%r14 xorq %rax,%rax movq 264(%rsp),%rdx mulx 336(%rsp),%rcx,%rbp adcx %rcx,%r11 adox %rbp,%r12 mulx 344(%rsp),%rcx,%rbp adcx %rcx,%r12 adox %rbp,%r13 mulx 352(%rsp),%rcx,%rbp adcx %rcx,%r13 adox %rbp,%r14 mulx 360(%rsp),%rcx,%rbp adcx %rcx,%r14 adox %rbp,%r15 adcx %rax,%r15 xorq %rbp,%rbp movq $38,%rdx mulx %r12,%rax,%r12 adcx %rax,%r8 adox %r12,%r9 mulx %r13,%rcx,%r13 adcx %rcx,%r9 adox %r13,%r10 mulx %r14,%rcx,%r14 adcx %rcx,%r10 adox %r14,%r11 mulx %r15,%rcx,%r15 adcx %rcx,%r11 adox %rbp,%r15 adcx %rbp,%r15 shld $1,%r11,%r15 andq mask63(%rip),%r11 imul $19,%r15,%r15 addq %r15,%r8 adcq $0,%r9 adcq $0,%r10 adcq $0,%r11 movq %r8,0(%rdi) movq %r9,8(%rdi) movq %r10,16(%rdi) movq %r11,24(%rdi) // mul xorq %r13,%r13 movq 272(%rsp),%rdx mulx 304(%rsp),%r8,%r9 mulx 312(%rsp),%rcx,%r10 adcx %rcx,%r9 mulx 320(%rsp),%rcx,%r11 adcx %rcx,%r10 mulx 328(%rsp),%rcx,%r12 adcx %rcx,%r11 adcx %r13,%r12 xorq %r14,%r14 movq 280(%rsp),%rdx mulx 304(%rsp),%rcx,%rbp adcx %rcx,%r9 adox %rbp,%r10 mulx 312(%rsp),%rcx,%rbp adcx %rcx,%r10 adox %rbp,%r11 mulx 320(%rsp),%rcx,%rbp adcx %rcx,%r11 adox %rbp,%r12 mulx 328(%rsp),%rcx,%rbp adcx %rcx,%r12 adox %rbp,%r13 adcx %r14,%r13 xorq %r15,%r15 movq 288(%rsp),%rdx mulx 304(%rsp),%rcx,%rbp adcx %rcx,%r10 adox %rbp,%r11 mulx 312(%rsp),%rcx,%rbp adcx %rcx,%r11 adox %rbp,%r12 mulx 320(%rsp),%rcx,%rbp adcx %rcx,%r12 adox %rbp,%r13 mulx 328(%rsp),%rcx,%rbp adcx %rcx,%r13 adox %rbp,%r14 adcx %r15,%r14 xorq %rax,%rax movq 296(%rsp),%rdx mulx 304(%rsp),%rcx,%rbp adcx %rcx,%r11 adox %rbp,%r12 mulx 312(%rsp),%rcx,%rbp adcx %rcx,%r12 adox %rbp,%r13 mulx 320(%rsp),%rcx,%rbp adcx %rcx,%r13 adox %rbp,%r14 mulx 328(%rsp),%rcx,%rbp adcx %rcx,%r14 adox %rbp,%r15 adcx %rax,%r15 xorq %rbp,%rbp movq $38,%rdx mulx %r12,%rax,%r12 adcx %rax,%r8 adox %r12,%r9 mulx %r13,%rcx,%r13 adcx %rcx,%r9 adox %r13,%r10 mulx %r14,%rcx,%r14 adcx %rcx,%r10 adox %r14,%r11 mulx %r15,%rcx,%r15 adcx %rcx,%r11 adox %rbp,%r15 adcx %rbp,%r15 shld $1,%r11,%r15 andq mask63(%rip),%r11 imul $19,%r15,%r15 addq %r15,%r8 adcq $0,%r9 adcq $0,%r10 adcq $0,%r11 movq %r8,32(%rdi) movq %r9,40(%rdi) movq %r10,48(%rdi) movq %r11,56(%rdi) // mul xorq %r13,%r13 movq 272(%rsp),%rdx mulx 336(%rsp),%r8,%r9 mulx 344(%rsp),%rcx,%r10 adcx %rcx,%r9 mulx 352(%rsp),%rcx,%r11 adcx %rcx,%r10 mulx 360(%rsp),%rcx,%r12 adcx %rcx,%r11 adcx %r13,%r12 xorq %r14,%r14 movq 280(%rsp),%rdx mulx 336(%rsp),%rcx,%rbp adcx %rcx,%r9 adox %rbp,%r10 mulx 344(%rsp),%rcx,%rbp adcx %rcx,%r10 adox %rbp,%r11 mulx 352(%rsp),%rcx,%rbp adcx %rcx,%r11 adox %rbp,%r12 mulx 360(%rsp),%rcx,%rbp adcx %rcx,%r12 adox %rbp,%r13 adcx %r14,%r13 xorq %r15,%r15 movq 288(%rsp),%rdx mulx 336(%rsp),%rcx,%rbp adcx %rcx,%r10 adox %rbp,%r11 mulx 344(%rsp),%rcx,%rbp adcx %rcx,%r11 adox %rbp,%r12 mulx 352(%rsp),%rcx,%rbp adcx %rcx,%r12 adox %rbp,%r13 mulx 360(%rsp),%rcx,%rbp adcx %rcx,%r13 adox %rbp,%r14 adcx %r15,%r14 xorq %rax,%rax movq 296(%rsp),%rdx mulx 336(%rsp),%rcx,%rbp adcx %rcx,%r11 adox %rbp,%r12 mulx 344(%rsp),%rcx,%rbp adcx %rcx,%r12 adox %rbp,%r13 mulx 352(%rsp),%rcx,%rbp adcx %rcx,%r13 adox %rbp,%r14 mulx 360(%rsp),%rcx,%rbp adcx %rcx,%r14 adox %rbp,%r15 adcx %rax,%r15 xorq %rbp,%rbp movq $38,%rdx mulx %r12,%rax,%r12 adcx %rax,%r8 adox %r12,%r9 mulx %r13,%rcx,%r13 adcx %rcx,%r9 adox %r13,%r10 mulx %r14,%rcx,%r14 adcx %rcx,%r10 adox %r14,%r11 mulx %r15,%rcx,%r15 adcx %rcx,%r11 adox %rbp,%r15 adcx %rbp,%r15 shld $1,%r11,%r15 andq mask63(%rip),%r11 imul $19,%r15,%r15 addq %r15,%r8 adcq $0,%r9 adcq $0,%r10 adcq $0,%r11 movq %r8,64(%rdi) movq %r9,72(%rdi) movq %r10,80(%rdi) movq %r11,88(%rdi) movq 96(%rsp),%rax decq %rax movq %rax,96(%rsp) cmpq $0,%rax jge .L3 .L10: movq 0(%rsp),%r11 movq 8(%rsp),%r12 movq 16(%rsp),%r13 movq 24(%rsp),%r14 movq 32(%rsp),%r15 movq 40(%rsp),%rbx movq 48(%rsp),%rbp movq %r11,%rsp ret