-rw-r--r-- 20027 lib25519-20240321/crypto_multiscalar/ed25519/amd64-mxaa-p3/ge25519_add.S raw
#include "crypto_asm_hidden.h"
#define mask63 CRYPTO_SHARED_NAMESPACE(mask63)
#define EC2D0 CRYPTO_SHARED_NAMESPACE(EC2D0)
#define EC2D1 CRYPTO_SHARED_NAMESPACE(EC2D1)
#define EC2D2 CRYPTO_SHARED_NAMESPACE(EC2D2)
#define EC2D3 CRYPTO_SHARED_NAMESPACE(EC2D3)
// ge25519_add
.p2align 5
ASM_HIDDEN _CRYPTO_NAMESPACE(ge25519_add)
.globl _CRYPTO_NAMESPACE(ge25519_add)
ASM_HIDDEN CRYPTO_NAMESPACE(ge25519_add)
.globl CRYPTO_NAMESPACE(ge25519_add)
_CRYPTO_NAMESPACE(ge25519_add):
CRYPTO_NAMESPACE(ge25519_add):
movq %rsp,%r11
andq $-32,%rsp
subq $352,%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)
movq 64(%rsi),%r8
movq 72(%rsi),%r9
movq 80(%rsi),%r10
movq 88(%rsi),%r11
movq %r8,216(%rsp)
movq %r9,224(%rsp)
movq %r10,232(%rsp)
movq %r11,240(%rsp)
movq 96(%rsi),%r8
movq 104(%rsi),%r9
movq 112(%rsi),%r10
movq 120(%rsi),%r11
movq %r8,256(%rsp)
movq %r9,264(%rsp)
movq %r10,272(%rsp)
movq %r11,280(%rsp)
movq 64(%rdx),%r8
movq 72(%rdx),%r9
movq 80(%rdx),%r10
movq 88(%rdx),%r11
movq %r8,288(%rsp)
movq %r9,296(%rsp)
movq %r10,304(%rsp)
movq %r11,312(%rsp)
movq 96(%rdx),%r8
movq 104(%rdx),%r9
movq 112(%rdx),%r10
movq 120(%rdx),%r11
movq %r8,320(%rsp)
movq %r9,328(%rsp)
movq %r10,336(%rsp)
movq %r11,344(%rsp)
movq %rdx,%rcx
/* add p1p1 */
// load
movq 32(%rsi),%rdx
movq 40(%rsi),%r8
movq 48(%rsi),%r9
movq 56(%rsi),%rax
// copy
movq %rdx,%r10
movq %r8,%r11
movq %r9,%r12
movq %rax,%r13
// sub
subq 0(%rsi),%rdx
sbbq 8(%rsi),%r8
sbbq 16(%rsi),%r9
sbbq 24(%rsi),%rax
movq $0,%r14
movq $38,%r15
cmovae %r14,%r15
subq %r15,%rdx
sbbq %r14,%r8
sbbq %r14,%r9
sbbq %r14,%rax
cmovc %r15,%r14
subq %r14,%rdx
// add
addq 0(%rsi),%r10
adcq 8(%rsi),%r11
adcq 16(%rsi),%r12
adcq 24(%rsi),%r13
movq $0,%r14
movq $38,%r15
cmovae %r14,%r15
addq %r15,%r10
adcq %r14,%r11
adcq %r14,%r12
adcq %r14,%r13
cmovc %r15,%r14
addq %r14,%r10
// store
movq %rdx,56(%rsp)
movq %r8,64(%rsp)
movq %r9,72(%rsp)
movq %rax,80(%rsp)
// store
movq %r10,88(%rsp)
movq %r11,96(%rsp)
movq %r12,104(%rsp)
movq %r13,112(%rsp)
// load
movq 32(%rcx),%rdx
movq 40(%rcx),%r8
movq 48(%rcx),%r9
movq 56(%rcx),%rax
// copy
movq %rdx,%r10
movq %r8,%r11
movq %r9,%r12
movq %rax,%r13
// sub
subq 0(%rcx),%rdx
sbbq 8(%rcx),%r8
sbbq 16(%rcx),%r9
sbbq 24(%rcx),%rax
movq $0,%r14
movq $38,%r15
cmovae %r14,%r15
subq %r15,%rdx
sbbq %r14,%r8
sbbq %r14,%r9
sbbq %r14,%rax
cmovc %r15,%r14
subq %r14,%rdx
// add
addq 0(%rcx),%r10
adcq 8(%rcx),%r11
adcq 16(%rcx),%r12
adcq 24(%rcx),%r13
movq $0,%r14
movq $38,%r15
cmovae %r14,%r15
addq %r15,%r10
adcq %r14,%r11
adcq %r14,%r12
adcq %r14,%r13
cmovc %r15,%r14
addq %r14,%r10
// store
movq %rdx,120(%rsp)
movq %r8,128(%rsp)
movq %r9,136(%rsp)
movq %rax,144(%rsp)
// store
movq %r10,152(%rsp)
movq %r11,160(%rsp)
movq %r12,168(%rsp)
movq %r13,176(%rsp)
// mul
movq 56(%rsp),%rdx
mulx 120(%rsp),%r8,%r9
mulx 128(%rsp),%rcx,%r10
addq %rcx,%r9
mulx 136(%rsp),%rcx,%r11
adcq %rcx,%r10
mulx 144(%rsp),%rcx,%r12
adcq %rcx,%r11
adcq $0,%r12
movq 64(%rsp),%rdx
mulx 120(%rsp),%rax,%rbx
mulx 128(%rsp),%rcx,%rbp
addq %rcx,%rbx
mulx 136(%rsp),%rcx,%rsi
adcq %rcx,%rbp
mulx 144(%rsp),%rcx,%r13
adcq %rcx,%rsi
adcq $0,%r13
addq %rax,%r9
adcq %rbx,%r10
adcq %rbp,%r11
adcq %rsi,%r12
adcq $0,%r13
movq 72(%rsp),%rdx
mulx 120(%rsp),%rax,%rbx
mulx 128(%rsp),%rcx,%rbp
addq %rcx,%rbx
mulx 136(%rsp),%rcx,%rsi
adcq %rcx,%rbp
mulx 144(%rsp),%rcx,%r14
adcq %rcx,%rsi
adcq $0,%r14
addq %rax,%r10
adcq %rbx,%r11
adcq %rbp,%r12
adcq %rsi,%r13
adcq $0,%r14
movq 80(%rsp),%rdx
mulx 120(%rsp),%rax,%rbx
mulx 128(%rsp),%rcx,%rbp
addq %rcx,%rbx
mulx 136(%rsp),%rcx,%rsi
adcq %rcx,%rbp
mulx 144(%rsp),%rcx,%r15
adcq %rcx,%rsi
adcq $0,%r15
addq %rax,%r11
adcq %rbx,%r12
adcq %rbp,%r13
adcq %rsi,%r14
adcq $0,%r15
movq $38,%rdx
mulx %r12,%r12,%rbx
mulx %r13,%r13,%rcx
addq %rbx,%r13
mulx %r14,%r14,%rbx
adcq %rcx,%r14
mulx %r15,%r15,%rcx
adcq %rbx,%r15
adcq $0,%rcx
addq %r12,%r8
adcq %r13,%r9
adcq %r14,%r10
adcq %r15,%r11
adcq $0,%rcx
shld $1,%r11,%rcx
andq mask63(%rip),%r11
imul $19,%rcx,%rcx
addq %rcx,%r8
adcq $0,%r9
adcq $0,%r10
adcq $0,%r11
// store
movq %r8,56(%rsp)
movq %r9,64(%rsp)
movq %r10,72(%rsp)
movq %r11,80(%rsp)
// mul
movq 88(%rsp),%rdx
mulx 152(%rsp),%r8,%r9
mulx 160(%rsp),%rcx,%r10
addq %rcx,%r9
mulx 168(%rsp),%rcx,%r11
adcq %rcx,%r10
mulx 176(%rsp),%rcx,%r12
adcq %rcx,%r11
adcq $0,%r12
movq 96(%rsp),%rdx
mulx 152(%rsp),%rax,%rbx
mulx 160(%rsp),%rcx,%rbp
addq %rcx,%rbx
mulx 168(%rsp),%rcx,%rsi
adcq %rcx,%rbp
mulx 176(%rsp),%rcx,%r13
adcq %rcx,%rsi
adcq $0,%r13
addq %rax,%r9
adcq %rbx,%r10
adcq %rbp,%r11
adcq %rsi,%r12
adcq $0,%r13
movq 104(%rsp),%rdx
mulx 152(%rsp),%rax,%rbx
mulx 160(%rsp),%rcx,%rbp
addq %rcx,%rbx
mulx 168(%rsp),%rcx,%rsi
adcq %rcx,%rbp
mulx 176(%rsp),%rcx,%r14
adcq %rcx,%rsi
adcq $0,%r14
addq %rax,%r10
adcq %rbx,%r11
adcq %rbp,%r12
adcq %rsi,%r13
adcq $0,%r14
movq 112(%rsp),%rdx
mulx 152(%rsp),%rax,%rbx
mulx 160(%rsp),%rcx,%rbp
addq %rcx,%rbx
mulx 168(%rsp),%rcx,%rsi
adcq %rcx,%rbp
mulx 176(%rsp),%rcx,%r15
adcq %rcx,%rsi
adcq $0,%r15
addq %rax,%r11
adcq %rbx,%r12
adcq %rbp,%r13
adcq %rsi,%r14
adcq $0,%r15
movq $38,%rdx
mulx %r12,%r12,%rbx
mulx %r13,%r13,%rcx
addq %rbx,%r13
mulx %r14,%r14,%rbx
adcq %rcx,%r14
mulx %r15,%r15,%rcx
adcq %rbx,%r15
adcq $0,%rcx
addq %r12,%r8
adcq %r13,%r9
adcq %r14,%r10
adcq %r15,%r11
adcq $0,%rcx
shld $1,%r11,%rcx
andq mask63(%rip),%r11
imul $19,%rcx,%rcx
addq %rcx,%r8
adcq $0,%r9
adcq $0,%r10
adcq $0,%r11
// copy
movq %r8,%r12
movq %r9,%r13
movq %r10,%r14
movq %r11,%r15
// add
addq 56(%rsp),%r12
adcq 64(%rsp),%r13
adcq 72(%rsp),%r14
adcq 80(%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
// sub
subq 56(%rsp),%r8
sbbq 64(%rsp),%r9
sbbq 72(%rsp),%r10
sbbq 80(%rsp),%r11
movq $0,%rdx
mov $38,%rax
cmovae %rdx,%rax
subq %rax,%r8
sbbq %rdx,%r9
sbbq %rdx,%r10
sbbq %rdx,%r11
cmovc %rax,%rdx
subq %rdx,%r8
// store
movq %r8,64(%rsp)
movq %r9,72(%rsp)
movq %r10,80(%rsp)
movq %r11,88(%rsp)
// store
movq %r12,128(%rsp)
movq %r13,136(%rsp)
movq %r14,144(%rsp)
movq %r15,152(%rsp)
// mul
movq 256(%rsp),%rdx
mulx 320(%rsp),%r8,%r9
mulx 328(%rsp),%rcx,%r10
addq %rcx,%r9
mulx 336(%rsp),%rcx,%r11
adcq %rcx,%r10
mulx 344(%rsp),%rcx,%r12
adcq %rcx,%r11
adcq $0,%r12
movq 264(%rsp),%rdx
mulx 320(%rsp),%rax,%rbx
mulx 328(%rsp),%rcx,%rbp
addq %rcx,%rbx
mulx 336(%rsp),%rcx,%rsi
adcq %rcx,%rbp
mulx 344(%rsp),%rcx,%r13
adcq %rcx,%rsi
adcq $0,%r13
addq %rax,%r9
adcq %rbx,%r10
adcq %rbp,%r11
adcq %rsi,%r12
adcq $0,%r13
movq 272(%rsp),%rdx
mulx 320(%rsp),%rax,%rbx
mulx 328(%rsp),%rcx,%rbp
addq %rcx,%rbx
mulx 336(%rsp),%rcx,%rsi
adcq %rcx,%rbp
mulx 344(%rsp),%rcx,%r14
adcq %rcx,%rsi
adcq $0,%r14
addq %rax,%r10
adcq %rbx,%r11
adcq %rbp,%r12
adcq %rsi,%r13
adcq $0,%r14
movq 280(%rsp),%rdx
mulx 320(%rsp),%rax,%rbx
mulx 328(%rsp),%rcx,%rbp
addq %rcx,%rbx
mulx 336(%rsp),%rcx,%rsi
adcq %rcx,%rbp
mulx 344(%rsp),%rcx,%r15
adcq %rcx,%rsi
adcq $0,%r15
addq %rax,%r11
adcq %rbx,%r12
adcq %rbp,%r13
adcq %rsi,%r14
adcq $0,%r15
movq $38,%rdx
mulx %r12,%r12,%rbx
mulx %r13,%r13,%rcx
addq %rbx,%r13
mulx %r14,%r14,%rbx
adcq %rcx,%r14
mulx %r15,%r15,%rcx
adcq %rbx,%r15
adcq $0,%rcx
addq %r12,%r8
adcq %r13,%r9
adcq %r14,%r10
adcq %r15,%r11
adcq $0,%rcx
shld $1,%r11,%rcx
andq mask63(%rip),%r11
imul $19,%rcx,%rcx
addq %rcx,%r8
adcq $0,%r9
adcq $0,%r10
adcq $0,%r11
// store
movq %r8,184(%rsp)
movq %r9,192(%rsp)
movq %r10,200(%rsp)
movq %r11,208(%rsp)
// mul
movq EC2D0(%rip),%rdx
mulx 184(%rsp),%r8,%r9
mulx 192(%rsp),%rcx,%r10
addq %rcx,%r9
mulx 200(%rsp),%rcx,%r11
adcq %rcx,%r10
mulx 208(%rsp),%rcx,%r12
adcq %rcx,%r11
adcq $0,%r12
movq EC2D1(%rip),%rdx
mulx 184(%rsp),%rax,%rbx
mulx 192(%rsp),%rcx,%rbp
addq %rcx,%rbx
mulx 200(%rsp),%rcx,%rsi
adcq %rcx,%rbp
mulx 208(%rsp),%rcx,%r13
adcq %rcx,%rsi
adcq $0,%r13
addq %rax,%r9
adcq %rbx,%r10
adcq %rbp,%r11
adcq %rsi,%r12
adcq $0,%r13
movq EC2D2(%rip),%rdx
mulx 184(%rsp),%rax,%rbx
mulx 192(%rsp),%rcx,%rbp
addq %rcx,%rbx
mulx 200(%rsp),%rcx,%rsi
adcq %rcx,%rbp
mulx 208(%rsp),%rcx,%r14
adcq %rcx,%rsi
adcq $0,%r14
addq %rax,%r10
adcq %rbx,%r11
adcq %rbp,%r12
adcq %rsi,%r13
adcq $0,%r14
movq EC2D3(%rip),%rdx
mulx 184(%rsp),%rax,%rbx
mulx 192(%rsp),%rcx,%rbp
addq %rcx,%rbx
mulx 200(%rsp),%rcx,%rsi
adcq %rcx,%rbp
mulx 208(%rsp),%rcx,%r15
adcq %rcx,%rsi
adcq $0,%r15
addq %rax,%r11
adcq %rbx,%r12
adcq %rbp,%r13
adcq %rsi,%r14
adcq $0,%r15
movq $38,%rdx
mulx %r12,%r12,%rbx
mulx %r13,%r13,%rcx
addq %rbx,%r13
mulx %r14,%r14,%rbx
adcq %rcx,%r14
mulx %r15,%r15,%rcx
adcq %rbx,%r15
adcq $0,%rcx
addq %r12,%r8
adcq %r13,%r9
adcq %r14,%r10
adcq %r15,%r11
adcq $0,%rcx
shld $1,%r11,%rcx
andq mask63(%rip),%r11
imul $19,%rcx,%rcx
addq %rcx,%r8
adcq $0,%r9
adcq $0,%r10
adcq $0,%r11
// store
movq %r8,184(%rsp)
movq %r9,192(%rsp)
movq %r10,200(%rsp)
movq %r11,208(%rsp)
// mul
movq 216(%rsp),%rdx
mulx 288(%rsp),%r8,%r9
mulx 296(%rsp),%rcx,%r10
addq %rcx,%r9
mulx 304(%rsp),%rcx,%r11
adcq %rcx,%r10
mulx 312(%rsp),%rcx,%r12
adcq %rcx,%r11
adcq $0,%r12
movq 224(%rsp),%rdx
mulx 288(%rsp),%rax,%rbx
mulx 296(%rsp),%rcx,%rbp
addq %rcx,%rbx
mulx 304(%rsp),%rcx,%rsi
adcq %rcx,%rbp
mulx 312(%rsp),%rcx,%r13
adcq %rcx,%rsi
adcq $0,%r13
addq %rax,%r9
adcq %rbx,%r10
adcq %rbp,%r11
adcq %rsi,%r12
adcq $0,%r13
movq 232(%rsp),%rdx
mulx 288(%rsp),%rax,%rbx
mulx 296(%rsp),%rcx,%rbp
addq %rcx,%rbx
mulx 304(%rsp),%rcx,%rsi
adcq %rcx,%rbp
mulx 312(%rsp),%rcx,%r14
adcq %rcx,%rsi
adcq $0,%r14
addq %rax,%r10
adcq %rbx,%r11
adcq %rbp,%r12
adcq %rsi,%r13
adcq $0,%r14
movq 240(%rsp),%rdx
mulx 288(%rsp),%rax,%rbx
mulx 296(%rsp),%rcx,%rbp
addq %rcx,%rbx
mulx 304(%rsp),%rcx,%rsi
adcq %rcx,%rbp
mulx 312(%rsp),%rcx,%r15
adcq %rcx,%rsi
adcq $0,%r15
addq %rax,%r11
adcq %rbx,%r12
adcq %rbp,%r13
adcq %rsi,%r14
adcq $0,%r15
movq $38,%rdx
mulx %r12,%r12,%rbx
mulx %r13,%r13,%rcx
addq %rbx,%r13
mulx %r14,%r14,%rbx
adcq %rcx,%r14
mulx %r15,%r15,%rcx
adcq %rbx,%r15
adcq $0,%rcx
addq %r12,%r8
adcq %r13,%r9
adcq %r14,%r10
adcq %r15,%r11
adcq $0,%rcx
shld $1,%r11,%rcx
andq mask63(%rip),%r11
imul $19,%rcx,%rcx
addq %rcx,%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
// copy
movq %r8,%r12
movq %r9,%r13
movq %r10,%r14
movq %r11,%r15
// add
addq 184(%rsp),%r12
adcq 192(%rsp),%r13
adcq 200(%rsp),%r14
adcq 208(%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
// sub
subq 184(%rsp),%r8
sbbq 192(%rsp),%r9
sbbq 200(%rsp),%r10
sbbq 208(%rsp),%r11
movq $0,%rdx
mov $38,%rax
cmovae %rdx,%rax
subq %rax,%r8
sbbq %rdx,%r9
sbbq %rdx,%r10
sbbq %rdx,%r11
cmovc %rax,%rdx
subq %rdx,%r8
// store
movq %r12,96(%rsp)
movq %r13,104(%rsp)
movq %r14,112(%rsp)
movq %r15,120(%rsp)
// store
movq %r8,160(%rsp)
movq %r9,168(%rsp)
movq %r10,176(%rsp)
movq %r11,184(%rsp)
/* p1p1 to p3 */
// mul
movq 64(%rsp),%rdx
mulx 160(%rsp),%r8,%r9
mulx 168(%rsp),%rcx,%r10
addq %rcx,%r9
mulx 176(%rsp),%rcx,%r11
adcq %rcx,%r10
mulx 184(%rsp),%rcx,%r12
adcq %rcx,%r11
adcq $0,%r12
movq 72(%rsp),%rdx
mulx 160(%rsp),%rax,%rbx
mulx 168(%rsp),%rcx,%rbp
addq %rcx,%rbx
mulx 176(%rsp),%rcx,%rsi
adcq %rcx,%rbp
mulx 184(%rsp),%rcx,%r13
adcq %rcx,%rsi
adcq $0,%r13
addq %rax,%r9
adcq %rbx,%r10
adcq %rbp,%r11
adcq %rsi,%r12
adcq $0,%r13
movq 80(%rsp),%rdx
mulx 160(%rsp),%rax,%rbx
mulx 168(%rsp),%rcx,%rbp
addq %rcx,%rbx
mulx 176(%rsp),%rcx,%rsi
adcq %rcx,%rbp
mulx 184(%rsp),%rcx,%r14
adcq %rcx,%rsi
adcq $0,%r14
addq %rax,%r10
adcq %rbx,%r11
adcq %rbp,%r12
adcq %rsi,%r13
adcq $0,%r14
movq 88(%rsp),%rdx
mulx 160(%rsp),%rax,%rbx
mulx 168(%rsp),%rcx,%rbp
addq %rcx,%rbx
mulx 176(%rsp),%rcx,%rsi
adcq %rcx,%rbp
mulx 184(%rsp),%rcx,%r15
adcq %rcx,%rsi
adcq $0,%r15
addq %rax,%r11
adcq %rbx,%r12
adcq %rbp,%r13
adcq %rsi,%r14
adcq $0,%r15
movq $38,%rdx
mulx %r12,%r12,%rbx
mulx %r13,%r13,%rcx
addq %rbx,%r13
mulx %r14,%r14,%rbx
adcq %rcx,%r14
mulx %r15,%r15,%rcx
adcq %rbx,%r15
adcq $0,%rcx
addq %r12,%r8
adcq %r13,%r9
adcq %r14,%r10
adcq %r15,%r11
adcq $0,%rcx
shld $1,%r11,%rcx
andq mask63(%rip),%r11
imul $19,%rcx,%rcx
addq %rcx,%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
movq 96(%rsp),%rdx
mulx 128(%rsp),%r8,%r9
mulx 136(%rsp),%rcx,%r10
addq %rcx,%r9
mulx 144(%rsp),%rcx,%r11
adcq %rcx,%r10
mulx 152(%rsp),%rcx,%r12
adcq %rcx,%r11
adcq $0,%r12
movq 104(%rsp),%rdx
mulx 128(%rsp),%rax,%rbx
mulx 136(%rsp),%rcx,%rbp
addq %rcx,%rbx
mulx 144(%rsp),%rcx,%rsi
adcq %rcx,%rbp
mulx 152(%rsp),%rcx,%r13
adcq %rcx,%rsi
adcq $0,%r13
addq %rax,%r9
adcq %rbx,%r10
adcq %rbp,%r11
adcq %rsi,%r12
adcq $0,%r13
movq 112(%rsp),%rdx
mulx 128(%rsp),%rax,%rbx
mulx 136(%rsp),%rcx,%rbp
addq %rcx,%rbx
mulx 144(%rsp),%rcx,%rsi
adcq %rcx,%rbp
mulx 152(%rsp),%rcx,%r14
adcq %rcx,%rsi
adcq $0,%r14
addq %rax,%r10
adcq %rbx,%r11
adcq %rbp,%r12
adcq %rsi,%r13
adcq $0,%r14
movq 120(%rsp),%rdx
mulx 128(%rsp),%rax,%rbx
mulx 136(%rsp),%rcx,%rbp
addq %rcx,%rbx
mulx 144(%rsp),%rcx,%rsi
adcq %rcx,%rbp
mulx 152(%rsp),%rcx,%r15
adcq %rcx,%rsi
adcq $0,%r15
addq %rax,%r11
adcq %rbx,%r12
adcq %rbp,%r13
adcq %rsi,%r14
adcq $0,%r15
movq $38,%rdx
mulx %r12,%r12,%rbx
mulx %r13,%r13,%rcx
addq %rbx,%r13
mulx %r14,%r14,%rbx
adcq %rcx,%r14
mulx %r15,%r15,%rcx
adcq %rbx,%r15
adcq $0,%rcx
addq %r12,%r8
adcq %r13,%r9
adcq %r14,%r10
adcq %r15,%r11
adcq $0,%rcx
shld $1,%r11,%rcx
andq mask63(%rip),%r11
imul $19,%rcx,%rcx
addq %rcx,%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
movq 96(%rsp),%rdx
mulx 160(%rsp),%r8,%r9
mulx 168(%rsp),%rcx,%r10
addq %rcx,%r9
mulx 176(%rsp),%rcx,%r11
adcq %rcx,%r10
mulx 184(%rsp),%rcx,%r12
adcq %rcx,%r11
adcq $0,%r12
movq 104(%rsp),%rdx
mulx 160(%rsp),%rax,%rbx
mulx 168(%rsp),%rcx,%rbp
addq %rcx,%rbx
mulx 176(%rsp),%rcx,%rsi
adcq %rcx,%rbp
mulx 184(%rsp),%rcx,%r13
adcq %rcx,%rsi
adcq $0,%r13
addq %rax,%r9
adcq %rbx,%r10
adcq %rbp,%r11
adcq %rsi,%r12
adcq $0,%r13
movq 112(%rsp),%rdx
mulx 160(%rsp),%rax,%rbx
mulx 168(%rsp),%rcx,%rbp
addq %rcx,%rbx
mulx 176(%rsp),%rcx,%rsi
adcq %rcx,%rbp
mulx 184(%rsp),%rcx,%r14
adcq %rcx,%rsi
adcq $0,%r14
addq %rax,%r10
adcq %rbx,%r11
adcq %rbp,%r12
adcq %rsi,%r13
adcq $0,%r14
movq 120(%rsp),%rdx
mulx 160(%rsp),%rax,%rbx
mulx 168(%rsp),%rcx,%rbp
addq %rcx,%rbx
mulx 176(%rsp),%rcx,%rsi
adcq %rcx,%rbp
mulx 184(%rsp),%rcx,%r15
adcq %rcx,%rsi
adcq $0,%r15
addq %rax,%r11
adcq %rbx,%r12
adcq %rbp,%r13
adcq %rsi,%r14
adcq $0,%r15
movq $38,%rdx
mulx %r12,%r12,%rbx
mulx %r13,%r13,%rcx
addq %rbx,%r13
mulx %r14,%r14,%rbx
adcq %rcx,%r14
mulx %r15,%r15,%rcx
adcq %rbx,%r15
adcq $0,%rcx
addq %r12,%r8
adcq %r13,%r9
adcq %r14,%r10
adcq %r15,%r11
adcq $0,%rcx
shld $1,%r11,%rcx
andq mask63(%rip),%r11
imul $19,%rcx,%rcx
addq %rcx,%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)
// mul
movq 64(%rsp),%rdx
mulx 128(%rsp),%r8,%r9
mulx 136(%rsp),%rcx,%r10
addq %rcx,%r9
mulx 144(%rsp),%rcx,%r11
adcq %rcx,%r10
mulx 152(%rsp),%rcx,%r12
adcq %rcx,%r11
adcq $0,%r12
movq 72(%rsp),%rdx
mulx 128(%rsp),%rax,%rbx
mulx 136(%rsp),%rcx,%rbp
addq %rcx,%rbx
mulx 144(%rsp),%rcx,%rsi
adcq %rcx,%rbp
mulx 152(%rsp),%rcx,%r13
adcq %rcx,%rsi
adcq $0,%r13
addq %rax,%r9
adcq %rbx,%r10
adcq %rbp,%r11
adcq %rsi,%r12
adcq $0,%r13
movq 80(%rsp),%rdx
mulx 128(%rsp),%rax,%rbx
mulx 136(%rsp),%rcx,%rbp
addq %rcx,%rbx
mulx 144(%rsp),%rcx,%rsi
adcq %rcx,%rbp
mulx 152(%rsp),%rcx,%r14
adcq %rcx,%rsi
adcq $0,%r14
addq %rax,%r10
adcq %rbx,%r11
adcq %rbp,%r12
adcq %rsi,%r13
adcq $0,%r14
movq 88(%rsp),%rdx
mulx 128(%rsp),%rax,%rbx
mulx 136(%rsp),%rcx,%rbp
addq %rcx,%rbx
mulx 144(%rsp),%rcx,%rsi
adcq %rcx,%rbp
mulx 152(%rsp),%rcx,%r15
adcq %rcx,%rsi
adcq $0,%r15
addq %rax,%r11
adcq %rbx,%r12
adcq %rbp,%r13
adcq %rsi,%r14
adcq $0,%r15
movq $38,%rdx
mulx %r12,%r12,%rbx
mulx %r13,%r13,%rcx
addq %rbx,%r13
mulx %r14,%r14,%rbx
adcq %rcx,%r14
mulx %r15,%r15,%rcx
adcq %rbx,%r15
adcq $0,%rcx
addq %r12,%r8
adcq %r13,%r9
adcq %r14,%r10
adcq %r15,%r11
adcq $0,%rcx
shld $1,%r11,%rcx
andq mask63(%rip),%r11
imul $19,%rcx,%rcx
addq %rcx,%r8
adcq $0,%r9
adcq $0,%r10
adcq $0,%r11
movq %r8,96(%rdi)
movq %r9,104(%rdi)
movq %r10,112(%rdi)
movq %r11,120(%rdi)
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