-rw-r--r-- 3113 lib25519-20241004/crypto_multiscalar/ed25519/amd64-maa4-opt/fe25519_square.S raw
#include "crypto_asm_hidden.h"
// linker define fe25519_square
// linker use mask63
/* Assembly for field squaring. */
#define mask63 CRYPTO_SHARED_NAMESPACE(mask63)
.p2align 5
ASM_HIDDEN _CRYPTO_SHARED_NAMESPACE(fe25519_square)
.globl _CRYPTO_SHARED_NAMESPACE(fe25519_square)
ASM_HIDDEN CRYPTO_SHARED_NAMESPACE(fe25519_square)
.globl CRYPTO_SHARED_NAMESPACE(fe25519_square)
_CRYPTO_SHARED_NAMESPACE(fe25519_square):
CRYPTO_SHARED_NAMESPACE(fe25519_square):
movq %rsp,%r11
andq $-32,%rsp
subq $56,%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 24(%rsi),%rax
mulq 24(%rsi)
movq %rax,%r12
movq $0,%r13
movq $38,%rax
mulq %rdx
movq %rax,%r14
movq %rdx,%r15
movq 8(%rsi),%rax
mulq 24(%rsi)
movq %rax,%r8
movq $0,%r9
movq %rdx,%r10
movq $0,%r11
addq %rax,%r8
adcq $0,%r9
addq %rdx,%r10
adcq $0,%r11
movq 16(%rsi),%rax
mulq 16(%rsi)
addq %rax,%r8
adcq $0,%r9
addq %rdx,%r10
adcq $0,%r11
movq 16(%rsi),%rax
mulq 24(%rsi)
addq %rax,%r10
adcq $0,%r11
addq %rdx,%r12
adcq $0,%r13
addq %rax,%r10
adcq $0,%r11
addq %rdx,%r12
adcq $0,%r13
movq $38,%rax
mulq %r10
imul $38,%r11,%r11
movq %rax,%r10
addq %rdx,%r11
movq $38,%rax
mulq %r12
imul $38,%r13,%r13
movq %rax,%r12
addq %rdx,%r13
movq 0(%rsi),%rax
mulq 24(%rsi)
addq %rax,%r14
adcq $0,%r15
addq %rdx,%r8
adcq $0,%r9
addq %rax,%r14
adcq $0,%r15
addq %rdx,%r8
adcq $0,%r9
movq 8(%rsi),%rax
mulq 16(%rsi)
addq %rax,%r14
adcq $0,%r15
addq %rdx,%r8
adcq $0,%r9
addq %rax,%r14
adcq $0,%r15
addq %rdx,%r8
adcq $0,%r9
movq $38,%rax
mulq %r8
imul $38,%r9,%r9
movq %rax,%r8
addq %rdx,%r9
movq 0(%rsi),%rax
mulq 0(%rsi)
addq %rax,%r8
adcq $0,%r9
addq %rdx,%r10
adcq $0,%r11
movq 0(%rsi),%rax
mulq 8(%rsi)
addq %rax,%r10
adcq $0,%r11
addq %rdx,%r12
adcq $0,%r13
addq %rax,%r10
adcq $0,%r11
addq %rdx,%r12
adcq $0,%r13
movq 0(%rsi),%rax
mulq 16(%rsi)
addq %rax,%r12
adcq $0,%r13
addq %rdx,%r14
adcq $0,%r15
addq %rax,%r12
adcq $0,%r13
addq %rdx,%r14
adcq $0,%r15
movq 8(%rsi),%rax
mulq 8(%rsi)
addq %rax,%r12
adcq $0,%r13
addq %rdx,%r14
adcq $0,%r15
addq %r9,%r10
adcq $0,%r11
addq %r11,%r12
adcq $0,%r13
addq %r13,%r14
adcq $0,%r15
shld $1,%r14,%r15
andq mask63(%rip),%r14
imul $19,%r15,%r15
addq %r15,%r8
adcq $0,%r10
adcq $0,%r12
adcq $0,%r14
movq %r8,0(%rdi)
movq %r10,8(%rdi)
movq %r12,16(%rdi)
movq %r14,24(%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
.section .note.GNU-stack,"",@progbits