-rw-r--r-- 2502 lib25519-20240321/crypto_mGnP/ed25519/amd64-mxaa/fe25519_nsquare.S raw
#include "crypto_asm_hidden.h"
// linker define fe25519_nsquare
// linker use mask63

/* Assembly for feedback field squaring. */

#define mask63 CRYPTO_SHARED_NAMESPACE(mask63)

	.p2align 5
	ASM_HIDDEN _CRYPTO_SHARED_NAMESPACE(fe25519_nsquare)
	.globl _CRYPTO_SHARED_NAMESPACE(fe25519_nsquare)
	ASM_HIDDEN CRYPTO_SHARED_NAMESPACE(fe25519_nsquare)
	.globl CRYPTO_SHARED_NAMESPACE(fe25519_nsquare)

_CRYPTO_SHARED_NAMESPACE(fe25519_nsquare):
CRYPTO_SHARED_NAMESPACE(fe25519_nsquare):

	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 	%rbp,40(%rsp)
	movq 	%rbx,48(%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)

	mov  	%rdx,%rbp

.L:
	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

	movq    16(%rdi),%rdx

	mulx    24(%rdi),%rax,%r14

	adcq    %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    %r8,0(%rdi)
	movq    %r9,8(%rdi)
	movq    %r10,16(%rdi)
	movq    %r11,24(%rdi)

	subq  	$1,%rbp
	cmpq    $0,%rbp

	jne     .L

	movq 	 0(%rsp),%r11
	movq 	 8(%rsp),%r12
	movq 	16(%rsp),%r13
	movq 	24(%rsp),%r14
	movq 	32(%rsp),%r15
	movq 	40(%rsp),%rbp
	movq 	48(%rsp),%rbx

	movq 	%r11,%rsp

	ret