-rw-r--r-- 27960 lib25519-20230630/crypto_nG/merged25519/amd64-mxaa/ge25519_base.S raw
#include "crypto_asm_hidden.h"
// linker define base
// linker use mask63
/* Assembly for fixed 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
ASM_HIDDEN _CRYPTO_SHARED_NAMESPACE(base)
.globl _CRYPTO_SHARED_NAMESPACE(base)
ASM_HIDDEN CRYPTO_SHARED_NAMESPACE(base)
.globl CRYPTO_SHARED_NAMESPACE(base)
_CRYPTO_SHARED_NAMESPACE(base):
CRYPTO_SHARED_NAMESPACE(base):
movq %rsp,%r11
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)
movq %rdi,56(%rsp)
movq %rsi,64(%rsp)
movq %rdx,72(%rsp)
/* choose t and initialize r */
movq %rdx,%rcx
movzbl 0(%rsi),%eax
movsbq %al,%rdx
movq $0,%rsi
imulq $768,%rsi,%rdi
movq %rdx,%rsi
sarq $7,%rsi
movq %rdx,%r8
addq %rsi,%r8
xorq %rsi,%r8
movq $1,%rsi
movq $0,%r9
movq $0,%rax
movq $0,%r10
movq $1,%r11
movq $0,%r12
movq $0,%r13
movq $0,%r14
cmpq $1,%r8
movq 0(%rcx,%rdi),%r15
cmove %r15,%rsi
movq 8(%rcx,%rdi),%r15
cmove %r15,%r9
movq 16(%rcx,%rdi),%r15
cmove %r15,%rax
movq 24(%rcx,%rdi),%r15
cmove %r15,%r10
movq 32(%rcx,%rdi),%r15
cmove %r15,%r11
movq 40(%rcx,%rdi),%r15
cmove %r15,%r12
movq 48(%rcx,%rdi),%r15
cmove %r15,%r13
movq 56(%rcx,%rdi),%r15
cmove %r15,%r14
cmpq $2,%r8
movq 96(%rcx,%rdi),%r15
cmove %r15,%rsi
movq 104(%rcx,%rdi),%r15
cmove %r15,%r9
movq 112(%rcx,%rdi),%r15
cmove %r15,%rax
movq 120(%rcx,%rdi),%r15
cmove %r15,%r10
movq 128(%rcx,%rdi),%r15
cmove %r15,%r11
movq 136(%rcx,%rdi),%r15
cmove %r15,%r12
movq 144(%rcx,%rdi),%r15
cmove %r15,%r13
movq 152(%rcx,%rdi),%r15
cmove %r15,%r14
cmpq $3,%r8
movq 192(%rcx,%rdi),%r15
cmove %r15,%rsi
movq 200(%rcx,%rdi),%r15
cmove %r15,%r9
movq 208(%rcx,%rdi),%r15
cmove %r15,%rax
movq 216(%rcx,%rdi),%r15
cmove %r15,%r10
movq 224(%rcx,%rdi),%r15
cmove %r15,%r11
movq 232(%rcx,%rdi),%r15
cmove %r15,%r12
movq 240(%rcx,%rdi),%r15
cmove %r15,%r13
movq 248(%rcx,%rdi),%r15
cmove %r15,%r14
cmpq $4,%r8
movq 288(%rcx,%rdi),%r15
cmove %r15,%rsi
movq 296(%rcx,%rdi),%r15
cmove %r15,%r9
movq 304(%rcx,%rdi),%r15
cmove %r15,%rax
movq 312(%rcx,%rdi),%r15
cmove %r15,%r10
movq 320(%rcx,%rdi),%r15
cmove %r15,%r11
movq 328(%rcx,%rdi),%r15
cmove %r15,%r12
movq 336(%rcx,%rdi),%r15
cmove %r15,%r13
movq 344(%rcx,%rdi),%r15
cmove %r15,%r14
cmpq $5,%r8
movq 384(%rcx,%rdi),%r15
cmove %r15,%rsi
movq 392(%rcx,%rdi),%r15
cmove %r15,%r9
movq 400(%rcx,%rdi),%r15
cmove %r15,%rax
movq 408(%rcx,%rdi),%r15
cmove %r15,%r10
movq 416(%rcx,%rdi),%r15
cmove %r15,%r11
movq 424(%rcx,%rdi),%r15
cmove %r15,%r12
movq 432(%rcx,%rdi),%r15
cmove %r15,%r13
movq 440(%rcx,%rdi),%r15
cmove %r15,%r14
cmpq $6,%r8
movq 480(%rcx,%rdi),%r15
cmove %r15,%rsi
movq 488(%rcx,%rdi),%r15
cmove %r15,%r9
movq 496(%rcx,%rdi),%r15
cmove %r15,%rax
movq 504(%rcx,%rdi),%r15
cmove %r15,%r10
movq 512(%rcx,%rdi),%r15
cmove %r15,%r11
movq 520(%rcx,%rdi),%r15
cmove %r15,%r12
movq 528(%rcx,%rdi),%r15
cmove %r15,%r13
movq 536(%rcx,%rdi),%r15
cmove %r15,%r14
cmpq $7,%r8
movq 576(%rcx,%rdi),%r15
cmove %r15,%rsi
movq 584(%rcx,%rdi),%r15
cmove %r15,%r9
movq 592(%rcx,%rdi),%r15
cmove %r15,%rax
movq 600(%rcx,%rdi),%r15
cmove %r15,%r10
movq 608(%rcx,%rdi),%r15
cmove %r15,%r11
movq 616(%rcx,%rdi),%r15
cmove %r15,%r12
movq 624(%rcx,%rdi),%r15
cmove %r15,%r13
movq 632(%rcx,%rdi),%r15
cmove %r15,%r14
cmpq $8,%r8
movq 672(%rcx,%rdi),%r15
cmove %r15,%rsi
movq 680(%rcx,%rdi),%r15
cmove %r15,%r9
movq 688(%rcx,%rdi),%r15
cmove %r15,%rax
movq 696(%rcx,%rdi),%r15
cmove %r15,%r10
movq 704(%rcx,%rdi),%r15
cmove %r15,%r11
movq 712(%rcx,%rdi),%r15
cmove %r15,%r12
movq 720(%rcx,%rdi),%r15
cmove %r15,%r13
movq 728(%rcx,%rdi),%r15
cmove %r15,%r14
cmpq $0,%rdx
movq %rsi,%r15
cmovl %r11,%rsi
cmovl %r15,%r11
movq %r9,%r15
cmovl %r12,%r9
cmovl %r15,%r12
movq %rax,%r15
cmovl %r13,%rax
cmovl %r15,%r13
movq %r10,%r15
cmovl %r14,%r10
cmovl %r15,%r14
movq %r11,%r15
movq %r12,80(%rsp)
movq %r13,88(%rsp)
movq %r14,96(%rsp)
// sub
subq %rsi,%r11
sbbq %r9,%r12
sbbq %rax,%r13
sbbq %r10,%r14
movq $0,%rbx
movq $38,%rbp
cmovae %rbx,%rbp
subq %rbp,%r11
sbbq %rbx,%r12
sbbq %rbx,%r13
sbbq %rbx,%r14
cmovc %rbp,%rbx
subq %rbx,%r11
movq %r11,104(%rsp)
movq %r12,112(%rsp)
movq %r13,120(%rsp)
movq %r14,128(%rsp)
// add
addq %r15,%rsi
adcq 80(%rsp),%r9
adcq 88(%rsp),%rax
adcq 96(%rsp),%r10
movq $0,%rbx
movq $38,%rbp
cmovae %rbx,%rbp
addq %rbp,%rsi
adcq %rbx,%r9
adcq %rbx,%rax
adcq %rbx,%r10
cmovc %rbp,%rbx
addq %rbx,%rsi
movq %rsi,136(%rsp)
movq %r9,144(%rsp)
movq %rax,152(%rsp)
movq %r10,160(%rsp)
movq $0,%rsi
movq $0,%r9
movq $0,%rax
movq $0,%r10
cmpq $1,%r8
movq 64(%rcx,%rdi),%r11
cmove %r11,%rsi
movq 72(%rcx,%rdi),%r11
cmove %r11,%r9
movq 80(%rcx,%rdi),%r11
cmove %r11,%rax
movq 88(%rcx,%rdi),%r11
cmove %r11,%r10
cmpq $2,%r8
movq 160(%rcx,%rdi),%r11
cmove %r11,%rsi
movq 168(%rcx,%rdi),%r11
cmove %r11,%r9
movq 176(%rcx,%rdi),%r11
cmove %r11,%rax
movq 184(%rcx,%rdi),%r11
cmove %r11,%r10
cmpq $3,%r8
movq 256(%rcx,%rdi),%r11
cmove %r11,%rsi
movq 264(%rcx,%rdi),%r11
cmove %r11,%r9
movq 272(%rcx,%rdi),%r11
cmove %r11,%rax
movq 280(%rcx,%rdi),%r11
cmove %r11,%r10
cmpq $4,%r8
movq 352(%rcx,%rdi),%r11
cmove %r11,%rsi
movq 360(%rcx,%rdi),%r11
cmove %r11,%r9
movq 368(%rcx,%rdi),%r11
cmove %r11,%rax
movq 376(%rcx,%rdi),%r11
cmove %r11,%r10
cmpq $5,%r8
movq 448(%rcx,%rdi),%r11
cmove %r11,%rsi
movq 456(%rcx,%rdi),%r11
cmove %r11,%r9
movq 464(%rcx,%rdi),%r11
cmove %r11,%rax
movq 472(%rcx,%rdi),%r11
cmove %r11,%r10
cmpq $6,%r8
movq 544(%rcx,%rdi),%r11
cmove %r11,%rsi
movq 552(%rcx,%rdi),%r11
cmove %r11,%r9
movq 560(%rcx,%rdi),%r11
cmove %r11,%rax
movq 568(%rcx,%rdi),%r11
cmove %r11,%r10
cmpq $7,%r8
movq 640(%rcx,%rdi),%r11
cmove %r11,%rsi
movq 648(%rcx,%rdi),%r11
cmove %r11,%r9
movq 656(%rcx,%rdi),%r11
cmove %r11,%rax
movq 664(%rcx,%rdi),%r11
cmove %r11,%r10
cmpq $8,%r8
movq 736(%rcx,%rdi),%r8
cmove %r8,%rsi
movq 744(%rcx,%rdi),%r8
cmove %r8,%r9
movq 752(%rcx,%rdi),%r8
cmove %r8,%rax
movq 760(%rcx,%rdi),%rdi
cmove %rdi,%r10
movq $0,%rdi
movq $0,%rcx
movq $0,%r8
movq $0,%r11
subq %rsi,%rdi
sbbq %r9,%rcx
sbbq %rax,%r8
sbbq %r10,%r11
movq $0,%r12
movq $38,%r13
cmovae %r12,%r13
subq %r13,%rdi
sbbq %r12,%rcx
sbbq %r12,%r8
sbbq %r12,%r11
cmovc %r13,%r12
subq %r12,%rdi
cmpq $0,%rdx
cmovl %rdi,%rsi
cmovl %rcx,%r9
cmovl %r8,%rax
cmovl %r11,%r10
movq %rsi,200(%rsp)
movq %r9,208(%rsp)
movq %rax,216(%rsp)
movq %r10,224(%rsp)
movq $2,168(%rsp)
movq $0,176(%rsp)
movq $0,184(%rsp)
movq $0,192(%rsp)
/* loop: i=1,i<64,i=i+1 */
movq $1,232(%rsp)
.L:
/* choose t */
movq 72(%rsp),%rcx
movq 232(%rsp),%rsi
movq 64(%rsp),%rdx
movzbl 0(%rdx,%rsi),%eax
movsbq %al,%rdx
imulq $768,%rsi,%rdi
movq %rdx,%rsi
sarq $7,%rsi
movq %rdx,%r8
addq %rsi,%r8
xorq %rsi,%r8
movq $1,%rsi
movq $0,%r9
movq $0,%rax
movq $0,%r10
movq $1,%r11
movq $0,%r12
movq $0,%r13
movq $0,%r14
cmpq $1,%r8
movq 0(%rcx,%rdi),%r15
cmove %r15,%rsi
movq 8(%rcx,%rdi),%r15
cmove %r15,%r9
movq 16(%rcx,%rdi),%r15
cmove %r15,%rax
movq 24(%rcx,%rdi),%r15
cmove %r15,%r10
movq 32(%rcx,%rdi),%r15
cmove %r15,%r11
movq 40(%rcx,%rdi),%r15
cmove %r15,%r12
movq 48(%rcx,%rdi),%r15
cmove %r15,%r13
movq 56(%rcx,%rdi),%r15
cmove %r15,%r14
cmpq $2,%r8
movq 96(%rcx,%rdi),%r15
cmove %r15,%rsi
movq 104(%rcx,%rdi),%r15
cmove %r15,%r9
movq 112(%rcx,%rdi),%r15
cmove %r15,%rax
movq 120(%rcx,%rdi),%r15
cmove %r15,%r10
movq 128(%rcx,%rdi),%r15
cmove %r15,%r11
movq 136(%rcx,%rdi),%r15
cmove %r15,%r12
movq 144(%rcx,%rdi),%r15
cmove %r15,%r13
movq 152(%rcx,%rdi),%r15
cmove %r15,%r14
cmpq $3,%r8
movq 192(%rcx,%rdi),%r15
cmove %r15,%rsi
movq 200(%rcx,%rdi),%r15
cmove %r15,%r9
movq 208(%rcx,%rdi),%r15
cmove %r15,%rax
movq 216(%rcx,%rdi),%r15
cmove %r15,%r10
movq 224(%rcx,%rdi),%r15
cmove %r15,%r11
movq 232(%rcx,%rdi),%r15
cmove %r15,%r12
movq 240(%rcx,%rdi),%r15
cmove %r15,%r13
movq 248(%rcx,%rdi),%r15
cmove %r15,%r14
cmpq $4,%r8
movq 288(%rcx,%rdi),%r15
cmove %r15,%rsi
movq 296(%rcx,%rdi),%r15
cmove %r15,%r9
movq 304(%rcx,%rdi),%r15
cmove %r15,%rax
movq 312(%rcx,%rdi),%r15
cmove %r15,%r10
movq 320(%rcx,%rdi),%r15
cmove %r15,%r11
movq 328(%rcx,%rdi),%r15
cmove %r15,%r12
movq 336(%rcx,%rdi),%r15
cmove %r15,%r13
movq 344(%rcx,%rdi),%r15
cmove %r15,%r14
cmpq $5,%r8
movq 384(%rcx,%rdi),%r15
cmove %r15,%rsi
movq 392(%rcx,%rdi),%r15
cmove %r15,%r9
movq 400(%rcx,%rdi),%r15
cmove %r15,%rax
movq 408(%rcx,%rdi),%r15
cmove %r15,%r10
movq 416(%rcx,%rdi),%r15
cmove %r15,%r11
movq 424(%rcx,%rdi),%r15
cmove %r15,%r12
movq 432(%rcx,%rdi),%r15
cmove %r15,%r13
movq 440(%rcx,%rdi),%r15
cmove %r15,%r14
cmpq $6,%r8
movq 480(%rcx,%rdi),%r15
cmove %r15,%rsi
movq 488(%rcx,%rdi),%r15
cmove %r15,%r9
movq 496(%rcx,%rdi),%r15
cmove %r15,%rax
movq 504(%rcx,%rdi),%r15
cmove %r15,%r10
movq 512(%rcx,%rdi),%r15
cmove %r15,%r11
movq 520(%rcx,%rdi),%r15
cmove %r15,%r12
movq 528(%rcx,%rdi),%r15
cmove %r15,%r13
movq 536(%rcx,%rdi),%r15
cmove %r15,%r14
cmpq $7,%r8
movq 576(%rcx,%rdi),%r15
cmove %r15,%rsi
movq 584(%rcx,%rdi),%r15
cmove %r15,%r9
movq 592(%rcx,%rdi),%r15
cmove %r15,%rax
movq 600(%rcx,%rdi),%r15
cmove %r15,%r10
movq 608(%rcx,%rdi),%r15
cmove %r15,%r11
movq 616(%rcx,%rdi),%r15
cmove %r15,%r12
movq 624(%rcx,%rdi),%r15
cmove %r15,%r13
movq 632(%rcx,%rdi),%r15
cmove %r15,%r14
cmpq $8,%r8
movq 672(%rcx,%rdi),%r15
cmove %r15,%rsi
movq 680(%rcx,%rdi),%r15
cmove %r15,%r9
movq 688(%rcx,%rdi),%r15
cmove %r15,%rax
movq 696(%rcx,%rdi),%r15
cmove %r15,%r10
movq 704(%rcx,%rdi),%r15
cmove %r15,%r11
movq 712(%rcx,%rdi),%r15
cmove %r15,%r12
movq 720(%rcx,%rdi),%r15
cmove %r15,%r13
movq 728(%rcx,%rdi),%r15
cmove %r15,%r14
cmpq $0,%rdx
movq %rsi,%r15
cmovl %r11,%rsi
cmovl %r15,%r11
movq %r9,%r15
cmovl %r12,%r9
cmovl %r15,%r12
movq %rax,%r15
cmovl %r13,%rax
cmovl %r15,%r13
movq %r10,%r15
cmovl %r14,%r10
cmovl %r15,%r14
movq %rsi,240(%rsp)
movq %r9,248(%rsp)
movq %rax,256(%rsp)
movq %r10,264(%rsp)
movq %r11,272(%rsp)
movq %r12,280(%rsp)
movq %r13,288(%rsp)
movq %r14,296(%rsp)
movq $0,%rsi
movq $0,%r9
movq $0,%rax
movq $0,%r10
cmpq $1,%r8
movq 64(%rcx,%rdi),%r11
cmove %r11,%rsi
movq 72(%rcx,%rdi),%r11
cmove %r11,%r9
movq 80(%rcx,%rdi),%r11
cmove %r11,%rax
movq 88(%rcx,%rdi),%r11
cmove %r11,%r10
cmpq $2,%r8
movq 160(%rcx,%rdi),%r11
cmove %r11,%rsi
movq 168(%rcx,%rdi),%r11
cmove %r11,%r9
movq 176(%rcx,%rdi),%r11
cmove %r11,%rax
movq 184(%rcx,%rdi),%r11
cmove %r11,%r10
cmpq $3,%r8
movq 256(%rcx,%rdi),%r11
cmove %r11,%rsi
movq 264(%rcx,%rdi),%r11
cmove %r11,%r9
movq 272(%rcx,%rdi),%r11
cmove %r11,%rax
movq 280(%rcx,%rdi),%r11
cmove %r11,%r10
cmpq $4,%r8
movq 352(%rcx,%rdi),%r11
cmove %r11,%rsi
movq 360(%rcx,%rdi),%r11
cmove %r11,%r9
movq 368(%rcx,%rdi),%r11
cmove %r11,%rax
movq 376(%rcx,%rdi),%r11
cmove %r11,%r10
cmpq $5,%r8
movq 448(%rcx,%rdi),%r11
cmove %r11,%rsi
movq 456(%rcx,%rdi),%r11
cmove %r11,%r9
movq 464(%rcx,%rdi),%r11
cmove %r11,%rax
movq 472(%rcx,%rdi),%r11
cmove %r11,%r10
cmpq $6,%r8
movq 544(%rcx,%rdi),%r11
cmove %r11,%rsi
movq 552(%rcx,%rdi),%r11
cmove %r11,%r9
movq 560(%rcx,%rdi),%r11
cmove %r11,%rax
movq 568(%rcx,%rdi),%r11
cmove %r11,%r10
cmpq $7,%r8
movq 640(%rcx,%rdi),%r11
cmove %r11,%rsi
movq 648(%rcx,%rdi),%r11
cmove %r11,%r9
movq 656(%rcx,%rdi),%r11
cmove %r11,%rax
movq 664(%rcx,%rdi),%r11
cmove %r11,%r10
cmpq $8,%r8
movq 736(%rcx,%rdi),%r8
cmove %r8,%rsi
movq 744(%rcx,%rdi),%r8
cmove %r8,%r9
movq 752(%rcx,%rdi),%r8
cmove %r8,%rax
movq 760(%rcx,%rdi),%rdi
cmove %rdi,%r10
movq $0,%rdi
movq $0,%rcx
movq $0,%r8
movq $0,%r11
subq %rsi,%rdi
sbbq %r9,%rcx
sbbq %rax,%r8
sbbq %r10,%r11
movq $0,%r12
movq $38,%r13
cmovae %r12,%r13
subq %r13,%rdi
sbbq %r12,%rcx
sbbq %r12,%r8
sbbq %r12,%r11
cmovc %r13,%r12
subq %r12,%rdi
cmpq $0,%rdx
cmovl %rdi,%rsi
cmovl %rcx,%r9
cmovl %r8,%rax
cmovl %r11,%r10
movq %rsi,304(%rsp)
movq %r9,312(%rsp)
movq %rax,320(%rsp)
movq %r10,328(%rsp)
/* nielsadd2 */
// load
movq 136(%rsp),%rdx
movq 144(%rsp),%rcx
movq 152(%rsp),%r8
movq 160(%rsp),%r9
// copy
movq %rdx,%rax
movq %rcx,%r10
movq %r8,%r11
movq %r9,%r12
// sub
subq 104(%rsp),%rdx
sbbq 112(%rsp),%rcx
sbbq 120(%rsp),%r8
sbbq 128(%rsp),%r9
movq $0,%r13
movq $38,%r14
cmovae %r13,%r14
subq %r14,%rdx
sbbq %r13,%rcx
sbbq %r13,%r8
sbbq %r13,%r9
cmovc %r14,%r13
subq %r13,%rdx
movq %rdx,336(%rsp)
movq %rcx,344(%rsp)
movq %r8,352(%rsp)
movq %r9,360(%rsp)
// add
addq 104(%rsp),%rax
adcq 112(%rsp),%r10
adcq 120(%rsp),%r11
adcq 128(%rsp),%r12
movq $0,%r13
movq $38,%r14
cmovae %r13,%r14
addq %r14,%rax
adcq %r13,%r10
adcq %r13,%r11
adcq %r13,%r12
cmovc %r14,%r13
addq %r13,%rax
movq %rax,368(%rsp)
movq %r10,376(%rsp)
movq %r11,384(%rsp)
movq %r12,392(%rsp)
// mul
movq 240(%rsp),%rdx
mulx 336(%rsp),%r8,%r9
mulx 344(%rsp),%rcx,%r10
addq %rcx,%r9
mulx 352(%rsp),%rcx,%r11
adcq %rcx,%r10
mulx 360(%rsp),%rcx,%r12
adcq %rcx,%r11
adcq $0,%r12
movq 248(%rsp),%rdx
mulx 336(%rsp),%rax,%rbx
mulx 344(%rsp),%rcx,%rbp
addq %rcx,%rbx
mulx 352(%rsp),%rcx,%rsi
adcq %rcx,%rbp
mulx 360(%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 256(%rsp),%rdx
mulx 336(%rsp),%rax,%rbx
mulx 344(%rsp),%rcx,%rbp
addq %rcx,%rbx
mulx 352(%rsp),%rcx,%rsi
adcq %rcx,%rbp
mulx 360(%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 264(%rsp),%rdx
mulx 336(%rsp),%rax,%rbx
mulx 344(%rsp),%rcx,%rbp
addq %rcx,%rbx
mulx 352(%rsp),%rcx,%rsi
adcq %rcx,%rbp
mulx 360(%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 %r8,336(%rsp)
movq %r9,344(%rsp)
movq %r10,352(%rsp)
movq %r11,360(%rsp)
// mul
movq 272(%rsp),%rdx
mulx 368(%rsp),%r8,%r9
mulx 376(%rsp),%rcx,%r10
addq %rcx,%r9
mulx 384(%rsp),%rcx,%r11
adcq %rcx,%r10
mulx 392(%rsp),%rcx,%r12
adcq %rcx,%r11
adcq $0,%r12
movq 280(%rsp),%rdx
mulx 368(%rsp),%rax,%rbx
mulx 376(%rsp),%rcx,%rbp
addq %rcx,%rbx
mulx 384(%rsp),%rcx,%rsi
adcq %rcx,%rbp
mulx 392(%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 288(%rsp),%rdx
mulx 368(%rsp),%rax,%rbx
mulx 376(%rsp),%rcx,%rbp
addq %rcx,%rbx
mulx 384(%rsp),%rcx,%rsi
adcq %rcx,%rbp
mulx 392(%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 296(%rsp),%rdx
mulx 368(%rsp),%rax,%rbx
mulx 376(%rsp),%rcx,%rbp
addq %rcx,%rbx
mulx 384(%rsp),%rcx,%rsi
adcq %rcx,%rbp
mulx 392(%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
// sub
subq 336(%rsp),%r8
sbbq 344(%rsp),%r9
sbbq 352(%rsp),%r10
sbbq 360(%rsp),%r11
movq $0,%rax
movq $38,%rbx
cmovae %rax,%rbx
subq %rbx,%r8
sbbq %rax,%r9
sbbq %rax,%r10
sbbq %rax,%r11
cmovc %rbx,%rax
subq %rax,%r8
movq %r8,368(%rsp)
movq %r9,376(%rsp)
movq %r10,384(%rsp)
movq %r11,392(%rsp)
// add
addq 336(%rsp),%r12
adcq 344(%rsp),%r13
adcq 352(%rsp),%r14
adcq 360(%rsp),%r15
movq $0,%rax
movq $38,%rbx
cmovae %rax,%rbx
addq %rbx,%r12
adcq %rax,%r13
adcq %rax,%r14
adcq %rax,%r15
cmovc %rbx,%rax
addq %rax,%r12
movq %r12,336(%rsp)
movq %r13,344(%rsp)
movq %r14,352(%rsp)
movq %r15,360(%rsp)
// mul
movq 304(%rsp),%rdx
mulx 200(%rsp),%r8,%r9
mulx 208(%rsp),%rcx,%r10
addq %rcx,%r9
mulx 216(%rsp),%rcx,%r11
adcq %rcx,%r10
mulx 224(%rsp),%rcx,%r12
adcq %rcx,%r11
adcq $0,%r12
movq 312(%rsp),%rdx
mulx 200(%rsp),%rax,%rbx
mulx 208(%rsp),%rcx,%rbp
addq %rcx,%rbx
mulx 216(%rsp),%rcx,%rsi
adcq %rcx,%rbp
mulx 224(%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 320(%rsp),%rdx
mulx 200(%rsp),%rax,%rbx
mulx 208(%rsp),%rcx,%rbp
addq %rcx,%rbx
mulx 216(%rsp),%rcx,%rsi
adcq %rcx,%rbp
mulx 224(%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 328(%rsp),%rdx
mulx 200(%rsp),%rax,%rbx
mulx 208(%rsp),%rcx,%rbp
addq %rcx,%rbx
mulx 216(%rsp),%rcx,%rsi
adcq %rcx,%rbp
mulx 224(%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 168(%rsp),%r12
movq 176(%rsp),%r13
movq 184(%rsp),%r14
movq 192(%rsp),%r15
// double
addq %r12,%r12
adcq %r13,%r13
adcq %r14,%r14
adcq %r15,%r15
movq $0,%rbx
movq $38,%rax
cmovae %rbx,%rax
addq %rax,%r12
adcq %rbx,%r13
adcq %rbx,%r14
adcq %rbx,%r15
cmovc %rax,%rbx
addq %rbx,%r12
// copy
movq %r12,%rsi
movq %r13,%rax
movq %r14,%rcx
movq %r15,%rdx
// sub
subq %r8,%r12
sbbq %r9,%r13
sbbq %r10,%r14
sbbq %r11,%r15
movq $0,%rbx
movq $38,%rbp
cmovae %rbx,%rbp
subq %rbp,%r12
sbbq %rbx,%r13
sbbq %rbx,%r14
sbbq %rbx,%r15
cmovc %rbp,%rbx
subq %rbx,%r12
movq %r12,432(%rsp)
movq %r13,440(%rsp)
movq %r14,448(%rsp)
movq %r15,456(%rsp)
// add
addq %r8,%rsi
adcq %r9,%rax
adcq %r10,%rcx
adcq %r11,%rdx
movq $0,%rbx
movq $38,%rbp
cmovae %rbx,%rbp
addq %rbp,%rsi
adcq %rbx,%rax
adcq %rbx,%rcx
adcq %rbx,%rdx
cmovc %rbp,%rbx
addq %rbx,%rsi
movq %rsi,400(%rsp)
movq %rax,408(%rsp)
movq %rcx,416(%rsp)
movq %rdx,424(%rsp)
/* p1p1 to p3 */
// mul
movq 368(%rsp),%rdx
mulx 432(%rsp),%r8,%r9
mulx 440(%rsp),%rcx,%r10
addq %rcx,%r9
mulx 448(%rsp),%rcx,%r11
adcq %rcx,%r10
mulx 456(%rsp),%rcx,%r12
adcq %rcx,%r11
adcq $0,%r12
movq 376(%rsp),%rdx
mulx 432(%rsp),%rax,%rbx
mulx 440(%rsp),%rcx,%rbp
addq %rcx,%rbx
mulx 448(%rsp),%rcx,%rsi
adcq %rcx,%rbp
mulx 456(%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 384(%rsp),%rdx
mulx 432(%rsp),%rax,%rbx
mulx 440(%rsp),%rcx,%rbp
addq %rcx,%rbx
mulx 448(%rsp),%rcx,%rsi
adcq %rcx,%rbp
mulx 456(%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 392(%rsp),%rdx
mulx 432(%rsp),%rax,%rbx
mulx 440(%rsp),%rcx,%rbp
addq %rcx,%rbx
mulx 448(%rsp),%rcx,%rsi
adcq %rcx,%rbp
mulx 456(%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 %r8,104(%rsp)
movq %r9,112(%rsp)
movq %r10,120(%rsp)
movq %r11,128(%rsp)
// mul
movq 336(%rsp),%rdx
mulx 400(%rsp),%r8,%r9
mulx 408(%rsp),%rcx,%r10
addq %rcx,%r9
mulx 416(%rsp),%rcx,%r11
adcq %rcx,%r10
mulx 424(%rsp),%rcx,%r12
adcq %rcx,%r11
adcq $0,%r12
movq 344(%rsp),%rdx
mulx 400(%rsp),%rax,%rbx
mulx 408(%rsp),%rcx,%rbp
addq %rcx,%rbx
mulx 416(%rsp),%rcx,%rsi
adcq %rcx,%rbp
mulx 424(%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 352(%rsp),%rdx
mulx 400(%rsp),%rax,%rbx
mulx 408(%rsp),%rcx,%rbp
addq %rcx,%rbx
mulx 416(%rsp),%rcx,%rsi
adcq %rcx,%rbp
mulx 424(%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 360(%rsp),%rdx
mulx 400(%rsp),%rax,%rbx
mulx 408(%rsp),%rcx,%rbp
addq %rcx,%rbx
mulx 416(%rsp),%rcx,%rsi
adcq %rcx,%rbp
mulx 424(%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 %r8,136(%rsp)
movq %r9,144(%rsp)
movq %r10,152(%rsp)
movq %r11,160(%rsp)
// mul
movq 432(%rsp),%rdx
mulx 400(%rsp),%r8,%r9
mulx 408(%rsp),%rcx,%r10
addq %rcx,%r9
mulx 416(%rsp),%rcx,%r11
adcq %rcx,%r10
mulx 424(%rsp),%rcx,%r12
adcq %rcx,%r11
adcq $0,%r12
movq 440(%rsp),%rdx
mulx 400(%rsp),%rax,%rbx
mulx 408(%rsp),%rcx,%rbp
addq %rcx,%rbx
mulx 416(%rsp),%rcx,%rsi
adcq %rcx,%rbp
mulx 424(%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 448(%rsp),%rdx
mulx 400(%rsp),%rax,%rbx
mulx 408(%rsp),%rcx,%rbp
addq %rcx,%rbx
mulx 416(%rsp),%rcx,%rsi
adcq %rcx,%rbp
mulx 424(%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 456(%rsp),%rdx
mulx 400(%rsp),%rax,%rbx
mulx 408(%rsp),%rcx,%rbp
addq %rcx,%rbx
mulx 416(%rsp),%rcx,%rsi
adcq %rcx,%rbp
mulx 424(%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 %r8,168(%rsp)
movq %r9,176(%rsp)
movq %r10,184(%rsp)
movq %r11,192(%rsp)
// mul
movq 336(%rsp),%rdx
mulx 368(%rsp),%r8,%r9
mulx 376(%rsp),%rcx,%r10
addq %rcx,%r9
mulx 384(%rsp),%rcx,%r11
adcq %rcx,%r10
mulx 392(%rsp),%rcx,%r12
adcq %rcx,%r11
adcq $0,%r12
movq 344(%rsp),%rdx
mulx 368(%rsp),%rax,%rbx
mulx 376(%rsp),%rcx,%rbp
addq %rcx,%rbx
mulx 384(%rsp),%rcx,%rsi
adcq %rcx,%rbp
mulx 392(%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 352(%rsp),%rdx
mulx 368(%rsp),%rax,%rbx
mulx 376(%rsp),%rcx,%rbp
addq %rcx,%rbx
mulx 384(%rsp),%rcx,%rsi
adcq %rcx,%rbp
mulx 392(%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 360(%rsp),%rdx
mulx 368(%rsp),%rax,%rbx
mulx 376(%rsp),%rcx,%rbp
addq %rcx,%rbx
mulx 384(%rsp),%rcx,%rsi
adcq %rcx,%rbp
mulx 392(%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 %r8,200(%rsp)
movq %r9,208(%rsp)
movq %r10,216(%rsp)
movq %r11,224(%rsp)
movq 232(%rsp),%r15
addq $1,%r15
movq %r15,232(%rsp)
cmpq $63,%r15
jle .L
/* store final value of r */
movq 56(%rsp),%rdi
movq 104(%rsp),%r8
movq 112(%rsp),%r9
movq 120(%rsp),%r10
movq 128(%rsp),%r11
movq %r8,0(%rdi)
movq %r9,8(%rdi)
movq %r10,16(%rdi)
movq %r11,24(%rdi)
movq 136(%rsp),%r8
movq 144(%rsp),%r9
movq 152(%rsp),%r10
movq 160(%rsp),%r11
movq %r8,32(%rdi)
movq %r9,40(%rdi)
movq %r10,48(%rdi)
movq %r11,56(%rdi)
movq 168(%rsp),%r8
movq 176(%rsp),%r9
movq 184(%rsp),%r10
movq 192(%rsp),%r11
movq %r8,64(%rdi)
movq %r9,72(%rdi)
movq %r10,80(%rdi)
movq %r11,88(%rdi)
movq 200(%rsp),%r8
movq 208(%rsp),%r9
movq 216(%rsp),%r10
movq 224(%rsp),%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