-rw-r--r-- 16174 lib25519-20240321/crypto_multiscalar/ed25519/amd64-mxaa-p3/ge25519_double.S raw
#include "crypto_asm_hidden.h"
#define mask63 CRYPTO_SHARED_NAMESPACE(mask63)
// ge25519_double
.p2align 5
ASM_HIDDEN _CRYPTO_NAMESPACE(ge25519_double)
.globl _CRYPTO_NAMESPACE(ge25519_double)
ASM_HIDDEN CRYPTO_NAMESPACE(ge25519_double)
.globl CRYPTO_NAMESPACE(ge25519_double)
_CRYPTO_NAMESPACE(ge25519_double):
CRYPTO_NAMESPACE(ge25519_double):
movq %rsp,%r11
andq $-32,%rsp
subq $288,%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 %rdi,56(%rsp)
movq %rsi,%rdi
/* dbl p1p1 */
// square
movq 0(%rdi),%rdx
mulx 8(%rdi),%r9,%r10
mulx 16(%rdi),%rcx,%r11
addq %rcx,%r10
mulx 24(%rdi),%rcx,%r12
adcq %rcx,%r11
adcq $0,%r12
movq 8(%rdi),%rdx
mulx 16(%rdi),%rax,%rbx
mulx 24(%rdi),%rcx,%r13
addq %rcx,%rbx
adcq $0,%r13
addq %rax,%r11
adcq %rbx,%r12
adcq $0,%r13
movq 16(%rdi),%rdx
mulx 24(%rdi),%rax,%r14
addq %rax,%r13
adcq $0,%r14
movq $0,%r15
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
movq 0(%rdi),%rdx
mulx %rdx,%r8,%rax
addq %rax,%r9
movq 8(%rdi),%rdx
mulx %rdx,%rax,%rbx
adcq %rax,%r10
adcq %rbx,%r11
movq 16(%rdi),%rdx
mulx %rdx,%rax,%rbx
adcq %rax,%r12
adcq %rbx,%r13
movq 24(%rdi),%rdx
mulx %rdx,%rax,%rbx
adcq %rax,%r14
adcq %rbx,%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(%rsp)
movq %r9,72(%rsp)
movq %r10,80(%rsp)
movq %r11,88(%rsp)
// square
movq 32(%rdi),%rdx
mulx 40(%rdi),%r9,%r10
mulx 48(%rdi),%rcx,%r11
addq %rcx,%r10
mulx 56(%rdi),%rcx,%r12
adcq %rcx,%r11
adcq $0,%r12
movq 40(%rdi),%rdx
mulx 48(%rdi),%rax,%rbx
mulx 56(%rdi),%rcx,%r13
addq %rcx,%rbx
adcq $0,%r13
addq %rax,%r11
adcq %rbx,%r12
adcq $0,%r13
movq 48(%rdi),%rdx
mulx 56(%rdi),%rax,%r14
addq %rax,%r13
adcq $0,%r14
movq $0,%r15
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
movq 32(%rdi),%rdx
mulx %rdx,%r8,%rax
addq %rax,%r9
movq 40(%rdi),%rdx
mulx %rdx,%rax,%rbx
adcq %rax,%r10
adcq %rbx,%r11
movq 48(%rdi),%rdx
mulx %rdx,%rax,%rbx
adcq %rax,%r12
adcq %rbx,%r13
movq 56(%rdi),%rdx
mulx %rdx,%rax,%rbx
adcq %rax,%r14
adcq %rbx,%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(%rsp)
movq %r9,104(%rsp)
movq %r10,112(%rsp)
movq %r11,120(%rsp)
// square
movq 64(%rdi),%rdx
mulx 72(%rdi),%r9,%r10
mulx 80(%rdi),%rcx,%r11
addq %rcx,%r10
mulx 88(%rdi),%rcx,%r12
adcq %rcx,%r11
adcq $0,%r12
movq 72(%rdi),%rdx
mulx 80(%rdi),%rax,%rbx
mulx 88(%rdi),%rcx,%r13
addq %rcx,%rbx
adcq $0,%r13
addq %rax,%r11
adcq %rbx,%r12
adcq $0,%r13
movq 80(%rdi),%rdx
mulx 88(%rdi),%rax,%r14
addq %rax,%r13
adcq $0,%r14
movq $0,%r15
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
movq 64(%rdi),%rdx
mulx %rdx,%r8,%rax
addq %rax,%r9
movq 72(%rdi),%rdx
mulx %rdx,%rax,%rbx
adcq %rax,%r10
adcq %rbx,%r11
movq 80(%rdi),%rdx
mulx %rdx,%rax,%rbx
adcq %rax,%r12
adcq %rbx,%r13
movq 88(%rdi),%rdx
mulx %rdx,%rax,%rbx
adcq %rax,%r14
adcq %rbx,%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
movq %r8,128(%rsp)
movq %r9,136(%rsp)
movq %r10,144(%rsp)
movq %r11,152(%rsp)
// neg
movq $0,%r8
movq $0,%r9
movq $0,%r10
movq $0,%r11
subq 64(%rsp),%r8
sbbq 72(%rsp),%r9
sbbq 80(%rsp),%r10
sbbq 88(%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 %r8,64(%rsp)
movq %r9,72(%rsp)
movq %r10,80(%rsp)
movq %r11,88(%rsp)
// copy
movq %r8,%r12
movq %r9,%r13
movq %r10,%r14
movq %r11,%r15
// sub
subq 96(%rsp),%r8
sbbq 104(%rsp),%r9
sbbq 112(%rsp),%r10
sbbq 120(%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 %r8,224(%rsp)
movq %r9,232(%rsp)
movq %r10,240(%rsp)
movq %r11,248(%rsp)
// add
addq 96(%rsp),%r12
adcq 104(%rsp),%r13
adcq 112(%rsp),%r14
adcq 120(%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 %r12,192(%rsp)
movq %r13,200(%rsp)
movq %r14,208(%rsp)
movq %r15,216(%rsp)
// sub
subq 128(%rsp),%r12
sbbq 136(%rsp),%r13
sbbq 144(%rsp),%r14
sbbq 152(%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 %r12,256(%rsp)
movq %r13,264(%rsp)
movq %r14,272(%rsp)
movq %r15,280(%rsp)
// add
movq 0(%rdi),%r8
movq 8(%rdi),%r9
movq 16(%rdi),%r10
movq 24(%rdi),%r11
addq 32(%rdi),%r8
adcq 40(%rdi),%r9
adcq 48(%rdi),%r10
adcq 56(%rdi),%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
movq %r8,160(%rsp)
movq %r9,168(%rsp)
movq %r10,176(%rsp)
movq %r11,184(%rsp)
// square
movq 160(%rsp),%rdx
mulx 168(%rsp),%r9,%r10
mulx 176(%rsp),%rcx,%r11
addq %rcx,%r10
mulx 184(%rsp),%rcx,%r12
adcq %rcx,%r11
adcq $0,%r12
movq 168(%rsp),%rdx
mulx 176(%rsp),%rax,%rbx
mulx 184(%rsp),%rcx,%r13
addq %rcx,%rbx
adcq $0,%r13
addq %rax,%r11
adcq %rbx,%r12
adcq $0,%r13
movq 176(%rsp),%rdx
mulx 184(%rsp),%rax,%r14
addq %rax,%r13
adcq $0,%r14
movq $0,%r15
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
movq 160(%rsp),%rdx
mulx %rdx,%r8,%rax
addq %rax,%r9
movq 168(%rsp),%rdx
mulx %rdx,%rax,%rbx
adcq %rax,%r10
adcq %rbx,%r11
movq 176(%rsp),%rdx
mulx %rdx,%rax,%rbx
adcq %rax,%r12
adcq %rbx,%r13
movq 184(%rsp),%rdx
mulx %rdx,%rax,%rbx
adcq %rax,%r14
adcq %rbx,%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
// add
addq 64(%rsp),%r8
adcq 72(%rsp),%r9
adcq 80(%rsp),%r10
adcq 88(%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 96(%rsp),%r8
sbbq 104(%rsp),%r9
sbbq 112(%rsp),%r10
sbbq 120(%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 %r8,160(%rsp)
movq %r9,168(%rsp)
movq %r10,176(%rsp)
movq %r11,184(%rsp)
/* p1p1 to p3 */
movq 56(%rsp),%rdi
// mul
movq 160(%rsp),%rdx
mulx 256(%rsp),%r8,%r9
mulx 264(%rsp),%rcx,%r10
addq %rcx,%r9
mulx 272(%rsp),%rcx,%r11
adcq %rcx,%r10
mulx 280(%rsp),%rcx,%r12
adcq %rcx,%r11
adcq $0,%r12
movq 168(%rsp),%rdx
mulx 256(%rsp),%rax,%rbx
mulx 264(%rsp),%rcx,%rbp
addq %rcx,%rbx
mulx 272(%rsp),%rcx,%rsi
adcq %rcx,%rbp
mulx 280(%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 176(%rsp),%rdx
mulx 256(%rsp),%rax,%rbx
mulx 264(%rsp),%rcx,%rbp
addq %rcx,%rbx
mulx 272(%rsp),%rcx,%rsi
adcq %rcx,%rbp
mulx 280(%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 184(%rsp),%rdx
mulx 256(%rsp),%rax,%rbx
mulx 264(%rsp),%rcx,%rbp
addq %rcx,%rbx
mulx 272(%rsp),%rcx,%rsi
adcq %rcx,%rbp
mulx 280(%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 192(%rsp),%rdx
mulx 224(%rsp),%r8,%r9
mulx 232(%rsp),%rcx,%r10
addq %rcx,%r9
mulx 240(%rsp),%rcx,%r11
adcq %rcx,%r10
mulx 248(%rsp),%rcx,%r12
adcq %rcx,%r11
adcq $0,%r12
movq 200(%rsp),%rdx
mulx 224(%rsp),%rax,%rbx
mulx 232(%rsp),%rcx,%rbp
addq %rcx,%rbx
mulx 240(%rsp),%rcx,%rsi
adcq %rcx,%rbp
mulx 248(%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 208(%rsp),%rdx
mulx 224(%rsp),%rax,%rbx
mulx 232(%rsp),%rcx,%rbp
addq %rcx,%rbx
mulx 240(%rsp),%rcx,%rsi
adcq %rcx,%rbp
mulx 248(%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 216(%rsp),%rdx
mulx 224(%rsp),%rax,%rbx
mulx 232(%rsp),%rcx,%rbp
addq %rcx,%rbx
mulx 240(%rsp),%rcx,%rsi
adcq %rcx,%rbp
mulx 248(%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 192(%rsp),%rdx
mulx 256(%rsp),%r8,%r9
mulx 264(%rsp),%rcx,%r10
addq %rcx,%r9
mulx 272(%rsp),%rcx,%r11
adcq %rcx,%r10
mulx 280(%rsp),%rcx,%r12
adcq %rcx,%r11
adcq $0,%r12
movq 200(%rsp),%rdx
mulx 256(%rsp),%rax,%rbx
mulx 264(%rsp),%rcx,%rbp
addq %rcx,%rbx
mulx 272(%rsp),%rcx,%rsi
adcq %rcx,%rbp
mulx 280(%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 208(%rsp),%rdx
mulx 256(%rsp),%rax,%rbx
mulx 264(%rsp),%rcx,%rbp
addq %rcx,%rbx
mulx 272(%rsp),%rcx,%rsi
adcq %rcx,%rbp
mulx 280(%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 216(%rsp),%rdx
mulx 256(%rsp),%rax,%rbx
mulx 264(%rsp),%rcx,%rbp
addq %rcx,%rbx
mulx 272(%rsp),%rcx,%rsi
adcq %rcx,%rbp
mulx 280(%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 160(%rsp),%rdx
mulx 224(%rsp),%r8,%r9
mulx 232(%rsp),%rcx,%r10
addq %rcx,%r9
mulx 240(%rsp),%rcx,%r11
adcq %rcx,%r10
mulx 248(%rsp),%rcx,%r12
adcq %rcx,%r11
adcq $0,%r12
movq 168(%rsp),%rdx
mulx 224(%rsp),%rax,%rbx
mulx 232(%rsp),%rcx,%rbp
addq %rcx,%rbx
mulx 240(%rsp),%rcx,%rsi
adcq %rcx,%rbp
mulx 248(%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 176(%rsp),%rdx
mulx 224(%rsp),%rax,%rbx
mulx 232(%rsp),%rcx,%rbp
addq %rcx,%rbx
mulx 240(%rsp),%rcx,%rsi
adcq %rcx,%rbp
mulx 248(%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 184(%rsp),%rdx
mulx 224(%rsp),%rax,%rbx
mulx 232(%rsp),%rcx,%rbp
addq %rcx,%rbx
mulx 240(%rsp),%rcx,%rsi
adcq %rcx,%rbp
mulx 248(%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