-rw-r--r-- 41457 lib25519-20240321/crypto_mGnP/ed25519/amd64-maax/ge25519_double_scalarmult_precompute.S raw
#include "crypto_asm_hidden.h"
// linker define ge25519_double_scalarmult_precompute
// linker use EC2D0 EC2D1 EC2D2 EC2D3 mask63
// linker use twoexp8_p0
// linker use twoexp8_p123
// linker use twoexp8_p4
/* Assembly for the precomputaion phase used in 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)
#define EC2D0 CRYPTO_SHARED_NAMESPACE(EC2D0)
#define EC2D1 CRYPTO_SHARED_NAMESPACE(EC2D1)
#define EC2D2 CRYPTO_SHARED_NAMESPACE(EC2D2)
#define EC2D3 CRYPTO_SHARED_NAMESPACE(EC2D3)
#define mask63 CRYPTO_SHARED_NAMESPACE(mask63)
#define twoexp8_p0 CRYPTO_SHARED_NAMESPACE(twoexp8_p0)
#define twoexp8_p123 CRYPTO_SHARED_NAMESPACE(twoexp8_p123)
#define twoexp8_p4 CRYPTO_SHARED_NAMESPACE(twoexp8_p4)
.p2align 5
ASM_HIDDEN _CRYPTO_SHARED_NAMESPACE(ge25519_double_scalarmult_precompute)
.globl _CRYPTO_SHARED_NAMESPACE(ge25519_double_scalarmult_precompute)
ASM_HIDDEN CRYPTO_SHARED_NAMESPACE(ge25519_double_scalarmult_precompute)
.globl CRYPTO_SHARED_NAMESPACE(ge25519_double_scalarmult_precompute)
_CRYPTO_SHARED_NAMESPACE(ge25519_double_scalarmult_precompute):
CRYPTO_SHARED_NAMESPACE(ge25519_double_scalarmult_precompute):
movq %rsp,%r11
andq $-32,%rsp
subq $472,%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)
decq %rdx
movq %rdx,56(%rsp)
movq 0(%rsi),%r8
movq 8(%rsi),%r9
movq 16(%rsi),%r10
movq 24(%rsi),%r11
movq %r8,0(%rdi)
movq %r9,8(%rdi)
movq %r10,16(%rdi)
movq %r11,24(%rdi)
movq 32(%rsi),%r8
movq 40(%rsi),%r9
movq 48(%rsi),%r10
movq 56(%rsi),%r11
movq %r8,32(%rdi)
movq %r9,40(%rdi)
movq %r10,48(%rdi)
movq %r11,56(%rdi)
movq 64(%rsi),%r8
movq 72(%rsi),%r9
movq 80(%rsi),%r10
movq 88(%rsi),%r11
movq %r8,64(%rdi)
movq %r9,72(%rdi)
movq %r10,80(%rdi)
movq %r11,88(%rdi)
movq 96(%rsi),%r8
movq 104(%rsi),%r9
movq 112(%rsi),%r10
movq 120(%rsi),%r11
movq %r8,96(%rdi)
movq %r9,104(%rdi)
movq %r10,112(%rdi)
movq %r11,120(%rdi)
/* 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
movq %r8,64(%rsp)
movq %r9,72(%rsp)
movq %r10,80(%rsp)
movq %r11,88(%rsp)
movq %r15,96(%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
movq %r8,104(%rsp)
movq %r9,112(%rsp)
movq %r10,120(%rsp)
movq %r11,128(%rsp)
movq %r15,136(%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
// double
addq %r8,%r8
adcq %r9,%r9
adcq %r10,%r10
adcq %r11,%r11
adcq %r15,%r15
movq %r8,144(%rsp)
movq %r9,152(%rsp)
movq %r10,160(%rsp)
movq %r11,168(%rsp)
movq %r15,176(%rsp)
// sub
movq twoexp8_p0(%rip),%r8
movq twoexp8_p123(%rip),%r9
movq twoexp8_p123(%rip),%r10
movq twoexp8_p123(%rip),%r11
movq twoexp8_p4(%rip),%rax
subq 64(%rsp),%r8
sbbq 72(%rsp),%r9
sbbq 80(%rsp),%r10
sbbq 88(%rsp),%r11
sbbq 96(%rsp),%rax
movq %r8,64(%rsp)
movq %r9,72(%rsp)
movq %r10,80(%rsp)
movq %r11,88(%rsp)
movq %rax,96(%rsp)
// sub
movq twoexp8_p0(%rip),%r12
movq twoexp8_p123(%rip),%r13
movq twoexp8_p123(%rip),%r14
movq twoexp8_p123(%rip),%r15
movq twoexp8_p4(%rip),%rbx
subq 104(%rsp),%r12
sbbq 112(%rsp),%r13
sbbq 120(%rsp),%r14
sbbq 128(%rsp),%r15
sbbq 136(%rsp),%rbx
movq %r12,184(%rsp)
movq %r13,192(%rsp)
movq %r14,200(%rsp)
movq %r15,208(%rsp)
movq %rbx,216(%rsp)
// add
movq %r8,%r12
movq %r9,%r13
movq %r10,%r14
movq %r11,%r15
movq %rax,%rbx
addq 104(%rsp),%r12
adcq 112(%rsp),%r13
adcq 120(%rsp),%r14
adcq 128(%rsp),%r15
adcq 136(%rsp),%rbx
movq %r12,224(%rsp)
movq %r13,232(%rsp)
movq %r14,240(%rsp)
movq %r15,248(%rsp)
movq %rbx,256(%rsp)
// sub
subq 104(%rsp),%r8
sbbq 112(%rsp),%r9
sbbq 120(%rsp),%r10
sbbq 128(%rsp),%r11
sbbq 136(%rsp),%rax
shld $1,%r11,%rax
andq mask63(%rip),%r11
imul $19,%rax,%rax
addq %rax,%r8
adcq $0,%r9
adcq $0,%r10
adcq $0,%r11
movq %r8,328(%rsp)
movq %r9,336(%rsp)
movq %r10,344(%rsp)
movq %r11,352(%rsp)
// sub
subq 144(%rsp),%r12
sbbq 152(%rsp),%r13
sbbq 160(%rsp),%r14
sbbq 168(%rsp),%r15
sbbq 176(%rsp),%rbx
shld $1,%r15,%rbx
andq mask63(%rip),%r15
imul $19,%rbx,%rbx
addq %rbx,%r12
adcq $0,%r13
adcq $0,%r14
adcq $0,%r15
movq %r12,360(%rsp)
movq %r13,368(%rsp)
movq %r14,376(%rsp)
movq %r15,384(%rsp)
movq 224(%rsp),%r12
movq 232(%rsp),%r13
movq 240(%rsp),%r14
movq 248(%rsp),%r15
movq 256(%rsp),%rbx
shld $1,%r15,%rbx
andq mask63(%rip),%r15
imul $19,%rbx,%rbx
addq %rbx,%r12
adcq $0,%r13
adcq $0,%r14
adcq $0,%r15
movq %r12,296(%rsp)
movq %r13,304(%rsp)
movq %r14,312(%rsp)
movq %r15,320(%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 %r8,104(%rsp)
movq %r9,112(%rsp)
movq %r10,120(%rsp)
movq %r11,128(%rsp)
// square
xorq %r13,%r13
movq 104(%rsp),%rdx
mulx 112(%rsp),%r9,%r10
mulx 120(%rsp),%rcx,%r11
adcx %rcx,%r10
mulx 128(%rsp),%rcx,%r12
adcx %rcx,%r11
adcx %r13,%r12
movq 112(%rsp),%rdx
xorq %r14,%r14
mulx 120(%rsp),%rcx,%rdx
adcx %rcx,%r11
adox %rdx,%r12
movq 112(%rsp),%rdx
mulx 128(%rsp),%rcx,%rdx
adcx %rcx,%r12
adox %rdx,%r13
adcx %r14,%r13
xorq %r15,%r15
movq 120(%rsp),%rdx
mulx 128(%rsp),%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 104(%rsp),%rdx
mulx %rdx,%r8,%rdx
adcx %rdx,%r9
movq 112(%rsp),%rdx
mulx %rdx,%rcx,%rdx
adcx %rcx,%r10
adcx %rdx,%r11
movq 120(%rsp),%rdx
mulx %rdx,%rcx,%rdx
adcx %rcx,%r12
adcx %rdx,%r13
movq 128(%rsp),%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
// add
addq 64(%rsp),%r8
adcq 72(%rsp),%r9
adcq 80(%rsp),%r10
adcq 88(%rsp),%r11
adcq 96(%rsp),%r15
addq 184(%rsp),%r8
adcq 192(%rsp),%r9
adcq 200(%rsp),%r10
adcq 208(%rsp),%r11
adcq 216(%rsp),%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 %r8,264(%rsp)
movq %r9,272(%rsp)
movq %r10,280(%rsp)
movq %r11,288(%rsp)
/* p1p1 to p3 */
// mul
xorq %r13,%r13
movq 264(%rsp),%rdx
mulx 360(%rsp),%r8,%r9
mulx 368(%rsp),%rcx,%r10
adcx %rcx,%r9
mulx 376(%rsp),%rcx,%r11
adcx %rcx,%r10
mulx 384(%rsp),%rcx,%r12
adcx %rcx,%r11
adcx %r13,%r12
xorq %r14,%r14
movq 272(%rsp),%rdx
mulx 360(%rsp),%rcx,%rbp
adcx %rcx,%r9
adox %rbp,%r10
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
adcx %r14,%r13
xorq %r15,%r15
movq 280(%rsp),%rdx
mulx 360(%rsp),%rcx,%rbp
adcx %rcx,%r10
adox %rbp,%r11
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
adcx %r15,%r14
xorq %rax,%rax
movq 288(%rsp),%rdx
mulx 360(%rsp),%rcx,%rbp
adcx %rcx,%r11
adox %rbp,%r12
mulx 368(%rsp),%rcx,%rbp
adcx %rcx,%r12
adox %rbp,%r13
mulx 376(%rsp),%rcx,%rbp
adcx %rcx,%r13
adox %rbp,%r14
mulx 384(%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
movq %r8,64(%rsp)
movq %r9,72(%rsp)
movq %r10,80(%rsp)
movq %r11,88(%rsp)
movq %r15,96(%rsp)
// mul
xorq %r13,%r13
movq 296(%rsp),%rdx
mulx 328(%rsp),%r8,%r9
mulx 336(%rsp),%rcx,%r10
adcx %rcx,%r9
mulx 344(%rsp),%rcx,%r11
adcx %rcx,%r10
mulx 352(%rsp),%rcx,%r12
adcx %rcx,%r11
adcx %r13,%r12
xorq %r14,%r14
movq 304(%rsp),%rdx
mulx 328(%rsp),%rcx,%rbp
adcx %rcx,%r9
adox %rbp,%r10
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
adcx %r14,%r13
xorq %r15,%r15
movq 312(%rsp),%rdx
mulx 328(%rsp),%rcx,%rbp
adcx %rcx,%r10
adox %rbp,%r11
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
adcx %r15,%r14
xorq %rax,%rax
movq 320(%rsp),%rdx
mulx 328(%rsp),%rcx,%rbp
adcx %rcx,%r11
adox %rbp,%r12
mulx 336(%rsp),%rcx,%rbp
adcx %rcx,%r12
adox %rbp,%r13
mulx 344(%rsp),%rcx,%rbp
adcx %rcx,%r13
adox %rbp,%r14
mulx 352(%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
movq %r8,104(%rsp)
movq %r9,112(%rsp)
movq %r10,120(%rsp)
movq %r11,128(%rsp)
movq %r15,136(%rsp)
// mul
xorq %r13,%r13
movq 296(%rsp),%rdx
mulx 360(%rsp),%r8,%r9
mulx 368(%rsp),%rcx,%r10
adcx %rcx,%r9
mulx 376(%rsp),%rcx,%r11
adcx %rcx,%r10
mulx 384(%rsp),%rcx,%r12
adcx %rcx,%r11
adcx %r13,%r12
xorq %r14,%r14
movq 304(%rsp),%rdx
mulx 360(%rsp),%rcx,%rbp
adcx %rcx,%r9
adox %rbp,%r10
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
adcx %r14,%r13
xorq %r15,%r15
movq 312(%rsp),%rdx
mulx 360(%rsp),%rcx,%rbp
adcx %rcx,%r10
adox %rbp,%r11
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
adcx %r15,%r14
xorq %rax,%rax
movq 320(%rsp),%rdx
mulx 360(%rsp),%rcx,%rbp
adcx %rcx,%r11
adox %rbp,%r12
mulx 368(%rsp),%rcx,%rbp
adcx %rcx,%r12
adox %rbp,%r13
mulx 376(%rsp),%rcx,%rbp
adcx %rcx,%r13
adox %rbp,%r14
mulx 384(%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 264(%rsp),%rdx
mulx 328(%rsp),%r8,%r9
mulx 336(%rsp),%rcx,%r10
adcx %rcx,%r9
mulx 344(%rsp),%rcx,%r11
adcx %rcx,%r10
mulx 352(%rsp),%rcx,%r12
adcx %rcx,%r11
adcx %r13,%r12
xorq %r14,%r14
movq 272(%rsp),%rdx
mulx 328(%rsp),%rcx,%rbp
adcx %rcx,%r9
adox %rbp,%r10
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
adcx %r14,%r13
xorq %r15,%r15
movq 280(%rsp),%rdx
mulx 328(%rsp),%rcx,%rbp
adcx %rcx,%r10
adox %rbp,%r11
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
adcx %r15,%r14
xorq %rax,%rax
movq 288(%rsp),%rdx
mulx 328(%rsp),%rcx,%rbp
adcx %rcx,%r11
adox %rbp,%r12
mulx 336(%rsp),%rcx,%rbp
adcx %rcx,%r12
adox %rbp,%r13
mulx 344(%rsp),%rcx,%rbp
adcx %rcx,%r13
adox %rbp,%r14
mulx 352(%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 %r8,184(%rsp)
movq %r9,192(%rsp)
movq %r10,200(%rsp)
movq %r11,208(%rsp)
// Convert pre[0] to projective Niels representation
movq 0(%rdi),%rbx
movq 8(%rdi),%rcx
movq 16(%rdi),%rbp
movq 24(%rdi),%rsi
movq 32(%rdi),%r8
movq 40(%rdi),%r9
movq 48(%rdi),%r10
movq 56(%rdi),%r11
movq %r8,%r12
movq %r9,%r13
movq %r10,%r14
movq %r11,%r15
subq %rbx,%r8
sbbq %rcx,%r9
sbbq %rbp,%r10
sbbq %rsi,%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 %r8,0(%rdi)
movq %r9,8(%rdi)
movq %r10,16(%rdi)
movq %r11,24(%rdi)
addq %rbx,%r12
adcq %rcx,%r13
adcq %rbp,%r14
adcq %rsi,%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 %r12,32(%rdi)
movq %r13,40(%rdi)
movq %r14,48(%rdi)
movq %r15,56(%rdi)
// mul
xorq %r13,%r13
movq EC2D0(%rip),%rdx
mulx 96(%rdi),%r8,%r9
mulx 104(%rdi),%rcx,%r10
adcx %rcx,%r9
mulx 112(%rdi),%rcx,%r11
adcx %rcx,%r10
mulx 120(%rdi),%rcx,%r12
adcx %rcx,%r11
adcx %r13,%r12
xorq %r14,%r14
movq EC2D1(%rip),%rdx
mulx 96(%rdi),%rcx,%rbp
adcx %rcx,%r9
adox %rbp,%r10
mulx 104(%rdi),%rcx,%rbp
adcx %rcx,%r10
adox %rbp,%r11
mulx 112(%rdi),%rcx,%rbp
adcx %rcx,%r11
adox %rbp,%r12
mulx 120(%rdi),%rcx,%rbp
adcx %rcx,%r12
adox %rbp,%r13
adcx %r14,%r13
xorq %r15,%r15
movq EC2D2(%rip),%rdx
mulx 96(%rdi),%rcx,%rbp
adcx %rcx,%r10
adox %rbp,%r11
mulx 104(%rdi),%rcx,%rbp
adcx %rcx,%r11
adox %rbp,%r12
mulx 112(%rdi),%rcx,%rbp
adcx %rcx,%r12
adox %rbp,%r13
mulx 120(%rdi),%rcx,%rbp
adcx %rcx,%r13
adox %rbp,%r14
adcx %r15,%r14
xorq %rax,%rax
movq EC2D3(%rip),%rdx
mulx 96(%rdi),%rcx,%rbp
adcx %rcx,%r11
adox %rbp,%r12
mulx 104(%rdi),%rcx,%rbp
adcx %rcx,%r12
adox %rbp,%r13
mulx 112(%rdi),%rcx,%rbp
adcx %rcx,%r13
adox %rbp,%r14
mulx 120(%rdi),%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 %r8,96(%rdi)
movq %r9,104(%rdi)
movq %r10,112(%rdi)
movq %r11,120(%rdi)
movq $0,464(%rsp)
.L:
// pnielsadd_p1p1
movq 104(%rsp),%r8
movq 112(%rsp),%r9
movq 120(%rsp),%r10
movq 128(%rsp),%r11
movq 136(%rsp),%rax
movq %r8,%r12
movq %r9,%r13
movq %r10,%r14
movq %r11,%r15
movq %rax,%rbx
addq twoexp8_p0(%rip),%r8
adcq twoexp8_p123(%rip),%r9
adcq twoexp8_p123(%rip),%r10
adcq twoexp8_p123(%rip),%r11
adcq twoexp8_p4(%rip),%rax
subq 64(%rsp),%r8
sbbq 72(%rsp),%r9
sbbq 80(%rsp),%r10
sbbq 88(%rsp),%r11
sbbq 96(%rsp),%rax
shld $1,%r11,%rax
andq mask63(%rip),%r11
imul $19,%rax,%rax
addq %rax,%r8
adcq $0,%r9
adcq $0,%r10
adcq $0,%r11
movq %r8,392(%rsp)
movq %r9,400(%rsp)
movq %r10,408(%rsp)
movq %r11,416(%rsp)
addq 64(%rsp),%r12
adcq 72(%rsp),%r13
adcq 80(%rsp),%r14
adcq 88(%rsp),%r15
adcq 96(%rsp),%rbx
shld $1,%r15,%rbx
andq mask63(%rip),%r15
imul $19,%rbx,%rbx
addq %rbx,%r12
adcq $0,%r13
adcq $0,%r14
adcq $0,%r15
movq %r12,432(%rsp)
movq %r13,440(%rsp)
movq %r14,448(%rsp)
movq %r15,456(%rsp)
// mul
xorq %r13,%r13
movq 392(%rsp),%rdx
mulx 0(%rdi),%r8,%r9
mulx 8(%rdi),%rcx,%r10
adcx %rcx,%r9
mulx 16(%rdi),%rcx,%r11
adcx %rcx,%r10
mulx 24(%rdi),%rcx,%r12
adcx %rcx,%r11
adcx %r13,%r12
xorq %r14,%r14
movq 400(%rsp),%rdx
mulx 0(%rdi),%rcx,%rbp
adcx %rcx,%r9
adox %rbp,%r10
mulx 8(%rdi),%rcx,%rbp
adcx %rcx,%r10
adox %rbp,%r11
mulx 16(%rdi),%rcx,%rbp
adcx %rcx,%r11
adox %rbp,%r12
mulx 24(%rdi),%rcx,%rbp
adcx %rcx,%r12
adox %rbp,%r13
adcx %r14,%r13
xorq %r15,%r15
movq 408(%rsp),%rdx
mulx 0(%rdi),%rcx,%rbp
adcx %rcx,%r10
adox %rbp,%r11
mulx 8(%rdi),%rcx,%rbp
adcx %rcx,%r11
adox %rbp,%r12
mulx 16(%rdi),%rcx,%rbp
adcx %rcx,%r12
adox %rbp,%r13
mulx 24(%rdi),%rcx,%rbp
adcx %rcx,%r13
adox %rbp,%r14
adcx %r15,%r14
xorq %rax,%rax
movq 416(%rsp),%rdx
mulx 0(%rdi),%rcx,%rbp
adcx %rcx,%r11
adox %rbp,%r12
mulx 8(%rdi),%rcx,%rbp
adcx %rcx,%r12
adox %rbp,%r13
mulx 16(%rdi),%rcx,%rbp
adcx %rcx,%r13
adox %rbp,%r14
mulx 24(%rdi),%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
movq %r8,392(%rsp)
movq %r9,400(%rsp)
movq %r10,408(%rsp)
movq %r11,416(%rsp)
movq %r15,424(%rsp)
// mul
xorq %r13,%r13
movq 432(%rsp),%rdx
mulx 32(%rdi),%r8,%r9
mulx 40(%rdi),%rcx,%r10
adcx %rcx,%r9
mulx 48(%rdi),%rcx,%r11
adcx %rcx,%r10
mulx 56(%rdi),%rcx,%r12
adcx %rcx,%r11
adcx %r13,%r12
xorq %r14,%r14
movq 440(%rsp),%rdx
mulx 32(%rdi),%rcx,%rbp
adcx %rcx,%r9
adox %rbp,%r10
mulx 40(%rdi),%rcx,%rbp
adcx %rcx,%r10
adox %rbp,%r11
mulx 48(%rdi),%rcx,%rbp
adcx %rcx,%r11
adox %rbp,%r12
mulx 56(%rdi),%rcx,%rbp
adcx %rcx,%r12
adox %rbp,%r13
adcx %r14,%r13
xorq %r15,%r15
movq 448(%rsp),%rdx
mulx 32(%rdi),%rcx,%rbp
adcx %rcx,%r10
adox %rbp,%r11
mulx 40(%rdi),%rcx,%rbp
adcx %rcx,%r11
adox %rbp,%r12
mulx 48(%rdi),%rcx,%rbp
adcx %rcx,%r12
adox %rbp,%r13
mulx 56(%rdi),%rcx,%rbp
adcx %rcx,%r13
adox %rbp,%r14
adcx %r15,%r14
xorq %rax,%rax
movq 456(%rsp),%rdx
mulx 32(%rdi),%rcx,%rbp
adcx %rcx,%r11
adox %rbp,%r12
mulx 40(%rdi),%rcx,%rbp
adcx %rcx,%r12
adox %rbp,%r13
mulx 48(%rdi),%rcx,%rbp
adcx %rcx,%r13
adox %rbp,%r14
mulx 56(%rdi),%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
// add
movq %r8,%r12
movq %r9,%r13
movq %r10,%r14
movq %r11,%rax
movq %r15,%rbx
addq 392(%rsp),%r8
adcq 400(%rsp),%r9
adcq 408(%rsp),%r10
adcq 416(%rsp),%r11
adcq 424(%rsp),%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 %r8,328(%rsp)
movq %r9,336(%rsp)
movq %r10,344(%rsp)
movq %r11,352(%rsp)
// sub
addq twoexp8_p0(%rip),%r12
adcq twoexp8_p123(%rip),%r13
adcq twoexp8_p123(%rip),%r14
adcq twoexp8_p123(%rip),%rax
adcq twoexp8_p4(%rip),%rbx
subq 392(%rsp),%r12
sbbq 400(%rsp),%r13
sbbq 408(%rsp),%r14
sbbq 416(%rsp),%rax
sbbq 424(%rsp),%rbx
shld $1,%rax,%rbx
andq mask63(%rip),%rax
imul $19,%rbx,%rbx
addq %rbx,%r12
adcq $0,%r13
adcq $0,%r14
adcq $0,%rax
movq %r12,264(%rsp)
movq %r13,272(%rsp)
movq %r14,280(%rsp)
movq %rax,288(%rsp)
// mul
xorq %r13,%r13
movq 184(%rsp),%rdx
mulx 96(%rdi),%r8,%r9
mulx 104(%rdi),%rcx,%r10
adcx %rcx,%r9
mulx 112(%rdi),%rcx,%r11
adcx %rcx,%r10
mulx 120(%rdi),%rcx,%r12
adcx %rcx,%r11
adcx %r13,%r12
xorq %r14,%r14
movq 192(%rsp),%rdx
mulx 96(%rdi),%rcx,%rbp
adcx %rcx,%r9
adox %rbp,%r10
mulx 104(%rdi),%rcx,%rbp
adcx %rcx,%r10
adox %rbp,%r11
mulx 112(%rdi),%rcx,%rbp
adcx %rcx,%r11
adox %rbp,%r12
mulx 120(%rdi),%rcx,%rbp
adcx %rcx,%r12
adox %rbp,%r13
adcx %r14,%r13
xorq %r15,%r15
movq 200(%rsp),%rdx
mulx 96(%rdi),%rcx,%rbp
adcx %rcx,%r10
adox %rbp,%r11
mulx 104(%rdi),%rcx,%rbp
adcx %rcx,%r11
adox %rbp,%r12
mulx 112(%rdi),%rcx,%rbp
adcx %rcx,%r12
adox %rbp,%r13
mulx 120(%rdi),%rcx,%rbp
adcx %rcx,%r13
adox %rbp,%r14
adcx %r15,%r14
xorq %rax,%rax
movq 208(%rsp),%rdx
mulx 96(%rdi),%rcx,%rbp
adcx %rcx,%r11
adox %rbp,%r12
mulx 104(%rdi),%rcx,%rbp
adcx %rcx,%r12
adox %rbp,%r13
mulx 112(%rdi),%rcx,%rbp
adcx %rcx,%r13
adox %rbp,%r14
mulx 120(%rdi),%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
movq %r8,392(%rsp)
movq %r9,400(%rsp)
movq %r10,408(%rsp)
movq %r11,416(%rsp)
movq %r15,424(%rsp)
// mul
xorq %r13,%r13
movq 144(%rsp),%rdx
mulx 64(%rdi),%r8,%r9
mulx 72(%rdi),%rcx,%r10
adcx %rcx,%r9
mulx 80(%rdi),%rcx,%r11
adcx %rcx,%r10
mulx 88(%rdi),%rcx,%r12
adcx %rcx,%r11
adcx %r13,%r12
xorq %r14,%r14
movq 152(%rsp),%rdx
mulx 64(%rdi),%rcx,%rbp
adcx %rcx,%r9
adox %rbp,%r10
mulx 72(%rdi),%rcx,%rbp
adcx %rcx,%r10
adox %rbp,%r11
mulx 80(%rdi),%rcx,%rbp
adcx %rcx,%r11
adox %rbp,%r12
mulx 88(%rdi),%rcx,%rbp
adcx %rcx,%r12
adox %rbp,%r13
adcx %r14,%r13
xorq %r15,%r15
movq 160(%rsp),%rdx
mulx 64(%rdi),%rcx,%rbp
adcx %rcx,%r10
adox %rbp,%r11
mulx 72(%rdi),%rcx,%rbp
adcx %rcx,%r11
adox %rbp,%r12
mulx 80(%rdi),%rcx,%rbp
adcx %rcx,%r12
adox %rbp,%r13
mulx 88(%rdi),%rcx,%rbp
adcx %rcx,%r13
adox %rbp,%r14
adcx %r15,%r14
xorq %rax,%rax
movq 168(%rsp),%rdx
mulx 64(%rdi),%rcx,%rbp
adcx %rcx,%r11
adox %rbp,%r12
mulx 72(%rdi),%rcx,%rbp
adcx %rcx,%r12
adox %rbp,%r13
mulx 80(%rdi),%rcx,%rbp
adcx %rcx,%r13
adox %rbp,%r14
mulx 88(%rdi),%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
// double
addq %r8,%r8
adcq %r9,%r9
adcq %r10,%r10
adcq %r11,%r11
adcq %r15,%r15
// add
movq %r8,%r12
movq %r9,%r13
movq %r10,%r14
movq %r11,%rax
movq %r15,%rbx
addq 392(%rsp),%r8
adcq 400(%rsp),%r9
adcq 408(%rsp),%r10
adcq 416(%rsp),%r11
adcq 424(%rsp),%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 %r8,296(%rsp)
movq %r9,304(%rsp)
movq %r10,312(%rsp)
movq %r11,320(%rsp)
// sub
addq twoexp8_p0(%rip),%r12
adcq twoexp8_p123(%rip),%r13
adcq twoexp8_p123(%rip),%r14
adcq twoexp8_p123(%rip),%rax
adcq twoexp8_p4(%rip),%rbx
subq 392(%rsp),%r12
sbbq 400(%rsp),%r13
sbbq 408(%rsp),%r14
sbbq 416(%rsp),%rax
sbbq 424(%rsp),%rbx
shld $1,%rax,%rbx
andq mask63(%rip),%rax
imul $19,%rbx,%rbx
addq %rbx,%r12
adcq $0,%r13
adcq $0,%r14
adcq $0,%rax
movq %r12,360(%rsp)
movq %r13,368(%rsp)
movq %r14,376(%rsp)
movq %rax,384(%rsp)
/* p1p1 to p3 */
// mul
xorq %r13,%r13
movq 296(%rsp),%rdx
mulx 360(%rsp),%r8,%r9
mulx 368(%rsp),%rcx,%r10
adcx %rcx,%r9
mulx 376(%rsp),%rcx,%r11
adcx %rcx,%r10
mulx 384(%rsp),%rcx,%r12
adcx %rcx,%r11
adcx %r13,%r12
xorq %r14,%r14
movq 304(%rsp),%rdx
mulx 360(%rsp),%rcx,%rbp
adcx %rcx,%r9
adox %rbp,%r10
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
adcx %r14,%r13
xorq %r15,%r15
movq 312(%rsp),%rdx
mulx 360(%rsp),%rcx,%rbp
adcx %rcx,%r10
adox %rbp,%r11
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
adcx %r15,%r14
xorq %rax,%rax
movq 320(%rsp),%rdx
mulx 360(%rsp),%rcx,%rbp
adcx %rcx,%r11
adox %rbp,%r12
mulx 368(%rsp),%rcx,%rbp
adcx %rcx,%r12
adox %rbp,%r13
mulx 376(%rsp),%rcx,%rbp
adcx %rcx,%r13
adox %rbp,%r14
mulx 384(%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 %r8,192(%rdi)
movq %r9,200(%rdi)
movq %r10,208(%rdi)
movq %r11,216(%rdi)
// mul
xorq %r13,%r13
movq 264(%rsp),%rdx
mulx 328(%rsp),%r8,%r9
mulx 336(%rsp),%rcx,%r10
adcx %rcx,%r9
mulx 344(%rsp),%rcx,%r11
adcx %rcx,%r10
mulx 352(%rsp),%rcx,%r12
adcx %rcx,%r11
adcx %r13,%r12
xorq %r14,%r14
movq 272(%rsp),%rdx
mulx 328(%rsp),%rcx,%rbp
adcx %rcx,%r9
adox %rbp,%r10
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
adcx %r14,%r13
xorq %r15,%r15
movq 280(%rsp),%rdx
mulx 328(%rsp),%rcx,%rbp
adcx %rcx,%r10
adox %rbp,%r11
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
adcx %r15,%r14
xorq %rax,%rax
movq 288(%rsp),%rdx
mulx 328(%rsp),%rcx,%rbp
adcx %rcx,%r11
adox %rbp,%r12
mulx 336(%rsp),%rcx,%rbp
adcx %rcx,%r12
adox %rbp,%r13
mulx 344(%rsp),%rcx,%rbp
adcx %rcx,%r13
adox %rbp,%r14
mulx 352(%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 %r8,224(%rdi)
movq %r9,232(%rdi)
movq %r10,240(%rdi)
movq %r11,248(%rdi)
// mul
xorq %r13,%r13
movq 296(%rsp),%rdx
mulx 328(%rsp),%r8,%r9
mulx 336(%rsp),%rcx,%r10
adcx %rcx,%r9
mulx 344(%rsp),%rcx,%r11
adcx %rcx,%r10
mulx 352(%rsp),%rcx,%r12
adcx %rcx,%r11
adcx %r13,%r12
xorq %r14,%r14
movq 304(%rsp),%rdx
mulx 328(%rsp),%rcx,%rbp
adcx %rcx,%r9
adox %rbp,%r10
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
adcx %r14,%r13
xorq %r15,%r15
movq 312(%rsp),%rdx
mulx 328(%rsp),%rcx,%rbp
adcx %rcx,%r10
adox %rbp,%r11
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
adcx %r15,%r14
xorq %rax,%rax
movq 320(%rsp),%rdx
mulx 328(%rsp),%rcx,%rbp
adcx %rcx,%r11
adox %rbp,%r12
mulx 336(%rsp),%rcx,%rbp
adcx %rcx,%r12
adox %rbp,%r13
mulx 344(%rsp),%rcx,%rbp
adcx %rcx,%r13
adox %rbp,%r14
mulx 352(%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
movq %r8,224(%rsp)
movq %r9,232(%rsp)
movq %r10,240(%rsp)
movq %r11,248(%rsp)
movq %r15,256(%rsp)
// mul
xorq %r13,%r13
movq 264(%rsp),%rdx
mulx 360(%rsp),%r8,%r9
mulx 368(%rsp),%rcx,%r10
adcx %rcx,%r9
mulx 376(%rsp),%rcx,%r11
adcx %rcx,%r10
mulx 384(%rsp),%rcx,%r12
adcx %rcx,%r11
adcx %r13,%r12
xorq %r14,%r14
movq 272(%rsp),%rdx
mulx 360(%rsp),%rcx,%rbp
adcx %rcx,%r9
adox %rbp,%r10
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
adcx %r14,%r13
xorq %r15,%r15
movq 280(%rsp),%rdx
mulx 360(%rsp),%rcx,%rbp
adcx %rcx,%r10
adox %rbp,%r11
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
adcx %r15,%r14
xorq %rax,%rax
movq 288(%rsp),%rdx
mulx 360(%rsp),%rcx,%rbp
adcx %rcx,%r11
adox %rbp,%r12
mulx 368(%rsp),%rcx,%rbp
adcx %rcx,%r12
adox %rbp,%r13
mulx 376(%rsp),%rcx,%rbp
adcx %rcx,%r13
adox %rbp,%r14
mulx 384(%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
// Convert pre[i1] to projective Niels representation
movq 224(%rsp),%r12
movq 232(%rsp),%r13
movq 240(%rsp),%r14
movq 248(%rsp),%rax
movq 256(%rsp),%rbx
movq %r12,%rbp
movq %r13,%rcx
movq %r14,%rdx
movq %rax,%rsi
movq %rbx,224(%rsp)
addq twoexp8_p0(%rip),%r12
adcq twoexp8_p123(%rip),%r13
adcq twoexp8_p123(%rip),%r14
adcq twoexp8_p123(%rip),%rax
adcq twoexp8_p4(%rip),%rbx
subq %r8,%r12
sbbq %r9,%r13
sbbq %r10,%r14
sbbq %r11,%rax
sbbq %r15,%rbx
shld $1,%rax,%rbx
andq mask63(%rip),%rax
imul $19,%rbx,%rbx
addq %rbx,%r12
adcq $0,%r13
adcq $0,%r14
adcq $0,%rax
movq %r12,128(%rdi)
movq %r13,136(%rdi)
movq %r14,144(%rdi)
movq %rax,152(%rdi)
addq %r8,%rbp
adcq %r9,%rcx
adcq %r10,%rdx
adcq %r11,%rsi
adcq 224(%rsp),%r15
shld $1,%rsi,%r15
andq mask63(%rip),%rsi
imul $19,%r15,%r15
addq %r15,%rbp
adcq $0,%rcx
adcq $0,%rdx
adcq $0,%rsi
movq %rbp,160(%rdi)
movq %rcx,168(%rdi)
movq %rdx,176(%rdi)
movq %rsi,184(%rdi)
// mul
xorq %r13,%r13
movq EC2D0(%rip),%rdx
mulx 224(%rdi),%r8,%r9
mulx 232(%rdi),%rcx,%r10
adcx %rcx,%r9
mulx 240(%rdi),%rcx,%r11
adcx %rcx,%r10
mulx 248(%rdi),%rcx,%r12
adcx %rcx,%r11
adcx %r13,%r12
xorq %r14,%r14
movq EC2D1(%rip),%rdx
mulx 224(%rdi),%rcx,%rbp
adcx %rcx,%r9
adox %rbp,%r10
mulx 232(%rdi),%rcx,%rbp
adcx %rcx,%r10
adox %rbp,%r11
mulx 240(%rdi),%rcx,%rbp
adcx %rcx,%r11
adox %rbp,%r12
mulx 248(%rdi),%rcx,%rbp
adcx %rcx,%r12
adox %rbp,%r13
adcx %r14,%r13
xorq %r15,%r15
movq EC2D2(%rip),%rdx
mulx 224(%rdi),%rcx,%rbp
adcx %rcx,%r10
adox %rbp,%r11
mulx 232(%rdi),%rcx,%rbp
adcx %rcx,%r11
adox %rbp,%r12
mulx 240(%rdi),%rcx,%rbp
adcx %rcx,%r12
adox %rbp,%r13
mulx 248(%rdi),%rcx,%rbp
adcx %rcx,%r13
adox %rbp,%r14
adcx %r15,%r14
xorq %rax,%rax
movq EC2D3(%rip),%rdx
mulx 224(%rdi),%rcx,%rbp
adcx %rcx,%r11
adox %rbp,%r12
mulx 232(%rdi),%rcx,%rbp
adcx %rcx,%r12
adox %rbp,%r13
mulx 240(%rdi),%rcx,%rbp
adcx %rcx,%r13
adox %rbp,%r14
mulx 248(%rdi),%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 %r8,224(%rdi)
movq %r9,232(%rdi)
movq %r10,240(%rdi)
movq %r11,248(%rdi)
addq $128,%rdi
movq 464(%rsp),%r8
incq %r8
movq %r8,464(%rsp)
cmpq 56(%rsp),%r8
jl .L
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