hsblst-0.0.5: c-source/build/cheri/mul_mont_384-armv8.S
#if defined(__ARM_FEATURE_PAC_DEFAULT) && __ARM_FEATURE_PAC_DEFAULT==2
# define PACI_HINT 27
# define AUTI_HINT 31
#else
# define PACI_HINT 25
# define AUTI_HINT 29
#endif
.text
.globl add_mod_384x384
.hidden add_mod_384x384
.type add_mod_384x384,%function
.align 5
add_mod_384x384:
hint #PACI_HINT
stp c29,c30,[csp,#-8*__SIZEOF_POINTER__]!
add c29,csp,#0
stp c19,c20,[csp,#2*__SIZEOF_POINTER__]
stp c21,c22,[csp,#4*__SIZEOF_POINTER__]
stp c23,c24,[csp,#6*__SIZEOF_POINTER__]
ldp x5,x6,[c3]
ldp x7,x8,[c3,#16]
ldp x9,x10,[c3,#32]
bl __add_mod_384x384
ldr c30,[c29,#__SIZEOF_POINTER__]
ldp c19,c20,[c29,#2*__SIZEOF_POINTER__]
ldp c21,c22,[c29,#4*__SIZEOF_POINTER__]
ldp c23,c24,[c29,#6*__SIZEOF_POINTER__]
ldr c29,[csp],#8*__SIZEOF_POINTER__
hint #AUTI_HINT
ret
.size add_mod_384x384,.-add_mod_384x384
.type __add_mod_384x384,%function
.align 5
__add_mod_384x384:
ldp x11, x12, [c1]
ldp x19,x20,[c2]
ldp x13, x14, [c1,#16]
adds x11,x11,x19
ldp x21,x22,[c2,#16]
adcs x12,x12,x20
ldp x15, x16, [c1,#32]
adcs x13,x13,x21
ldp x23,x24,[c2,#32]
adcs x14,x14,x22
stp x11, x12, [c0]
adcs x15,x15,x23
ldp x11, x12, [c1,#48]
adcs x16,x16,x24
ldp x19,x20,[c2,#48]
stp x13, x14, [c0,#16]
ldp x13, x14, [c1,#64]
ldp x21,x22,[c2,#64]
adcs x11,x11,x19
stp x15, x16, [c0,#32]
adcs x12,x12,x20
ldp x15, x16, [c1,#80]
adcs x13,x13,x21
ldp x23,x24,[c2,#80]
adcs x14,x14,x22
adcs x15,x15,x23
adcs x16,x16,x24
adc x17,xzr,xzr
subs x19,x11,x5
sbcs x20,x12,x6
sbcs x21,x13,x7
sbcs x22,x14,x8
sbcs x23,x15,x9
sbcs x24,x16,x10
sbcs xzr,x17,xzr
csel x11,x11,x19,lo
csel x12,x12,x20,lo
csel x13,x13,x21,lo
csel x14,x14,x22,lo
stp x11,x12,[c0,#48]
csel x15,x15,x23,lo
stp x13,x14,[c0,#64]
csel x16,x16,x24,lo
stp x15,x16,[c0,#80]
ret
.size __add_mod_384x384,.-__add_mod_384x384
.globl sub_mod_384x384
.hidden sub_mod_384x384
.type sub_mod_384x384,%function
.align 5
sub_mod_384x384:
hint #PACI_HINT
stp c29,c30,[csp,#-8*__SIZEOF_POINTER__]!
add c29,csp,#0
stp c19,c20,[csp,#2*__SIZEOF_POINTER__]
stp c21,c22,[csp,#4*__SIZEOF_POINTER__]
stp c23,c24,[csp,#6*__SIZEOF_POINTER__]
ldp x5,x6,[c3]
ldp x7,x8,[c3,#16]
ldp x9,x10,[c3,#32]
bl __sub_mod_384x384
ldr c30,[c29,#__SIZEOF_POINTER__]
ldp c19,c20,[c29,#2*__SIZEOF_POINTER__]
ldp c21,c22,[c29,#4*__SIZEOF_POINTER__]
ldp c23,c24,[c29,#6*__SIZEOF_POINTER__]
ldr c29,[csp],#8*__SIZEOF_POINTER__
hint #AUTI_HINT
ret
.size sub_mod_384x384,.-sub_mod_384x384
.type __sub_mod_384x384,%function
.align 5
__sub_mod_384x384:
ldp x11, x12, [c1]
ldp x19,x20,[c2]
ldp x13, x14, [c1,#16]
subs x11,x11,x19
ldp x21,x22,[c2,#16]
sbcs x12,x12,x20
ldp x15, x16, [c1,#32]
sbcs x13,x13,x21
ldp x23,x24,[c2,#32]
sbcs x14,x14,x22
stp x11, x12, [c0]
sbcs x15,x15,x23
ldp x11, x12, [c1,#48]
sbcs x16,x16,x24
ldp x19,x20,[c2,#48]
stp x13, x14, [c0,#16]
ldp x13, x14, [c1,#64]
ldp x21,x22,[c2,#64]
sbcs x11,x11,x19
stp x15, x16, [c0,#32]
sbcs x12,x12,x20
ldp x15, x16, [c1,#80]
sbcs x13,x13,x21
ldp x23,x24,[c2,#80]
sbcs x14,x14,x22
sbcs x15,x15,x23
sbcs x16,x16,x24
sbc x17,xzr,xzr
and x19,x5,x17
and x20,x6,x17
adds x11,x11,x19
and x21,x7,x17
adcs x12,x12,x20
and x22,x8,x17
adcs x13,x13,x21
and x23,x9,x17
adcs x14,x14,x22
and x24,x10,x17
adcs x15,x15,x23
stp x11,x12,[c0,#48]
adc x16,x16,x24
stp x13,x14,[c0,#64]
stp x15,x16,[c0,#80]
ret
.size __sub_mod_384x384,.-__sub_mod_384x384
.type __add_mod_384,%function
.align 5
__add_mod_384:
ldp x11, x12, [c1]
ldp x19,x20,[c2]
ldp x13, x14, [c1,#16]
adds x11,x11,x19
ldp x21,x22,[c2,#16]
adcs x12,x12,x20
ldp x15, x16, [c1,#32]
adcs x13,x13,x21
ldp x23,x24,[c2,#32]
adcs x14,x14,x22
adcs x15,x15,x23
adcs x16,x16,x24
adc x17,xzr,xzr
subs x19,x11,x5
sbcs x20,x12,x6
sbcs x21,x13,x7
sbcs x22,x14,x8
sbcs x23,x15,x9
sbcs x24,x16,x10
sbcs xzr,x17,xzr
csel x11,x11,x19,lo
csel x12,x12,x20,lo
csel x13,x13,x21,lo
csel x14,x14,x22,lo
csel x15,x15,x23,lo
stp x11,x12,[c0]
csel x16,x16,x24,lo
stp x13,x14,[c0,#16]
stp x15,x16,[c0,#32]
ret
.size __add_mod_384,.-__add_mod_384
.type __sub_mod_384,%function
.align 5
__sub_mod_384:
ldp x11, x12, [c1]
ldp x19,x20,[c2]
ldp x13, x14, [c1,#16]
subs x11,x11,x19
ldp x21,x22,[c2,#16]
sbcs x12,x12,x20
ldp x15, x16, [c1,#32]
sbcs x13,x13,x21
ldp x23,x24,[c2,#32]
sbcs x14,x14,x22
sbcs x15,x15,x23
sbcs x16,x16,x24
sbc x17,xzr,xzr
and x19,x5,x17
and x20,x6,x17
adds x11,x11,x19
and x21,x7,x17
adcs x12,x12,x20
and x22,x8,x17
adcs x13,x13,x21
and x23,x9,x17
adcs x14,x14,x22
and x24,x10,x17
adcs x15,x15,x23
stp x11,x12,[c0]
adc x16,x16,x24
stp x13,x14,[c0,#16]
stp x15,x16,[c0,#32]
ret
.size __sub_mod_384,.-__sub_mod_384
.globl mul_mont_384x
.hidden mul_mont_384x
.type mul_mont_384x,%function
.align 5
mul_mont_384x:
hint #PACI_HINT
stp c29,c30,[csp,#-16*__SIZEOF_POINTER__]!
add c29,csp,#0
stp c19,c20,[csp,#2*__SIZEOF_POINTER__]
stp c21,c22,[csp,#4*__SIZEOF_POINTER__]
stp c23,c24,[csp,#6*__SIZEOF_POINTER__]
stp c25,c26,[csp,#8*__SIZEOF_POINTER__]
stp c27,c28,[csp,#10*__SIZEOF_POINTER__]
sub csp,csp,#288 // space for 3 768-bit vectors
mov c26,c0 // save r_ptr
mov c27,c1 // save b_ptr
mov c28,c2 // save b_ptr
add c0,csp,#0
bl __mul_384
add c1,c1,#48
add c2,c2,#48
add c0,csp,#96
bl __mul_384
ldp x5,x6,[c3]
ldp x7,x8,[c3,#16]
ldp x9,x10,[c3,#32]
sub c2,c1,#48
add c0,csp,#240
bl __add_mod_384
add c1,c28,#0
add c2,c28,#48
add c0,csp,#192
bl __add_mod_384
add c1,c0,#0
add c2,c0,#48
bl __mul_384 // mul_384(t2, a->re+a->im, b->re+b->im)
ldp x5,x6,[c3]
ldp x7,x8,[c3,#16]
ldp x9,x10,[c3,#32]
mov c1,c0
add c2,csp,#0
bl __sub_mod_384x384
add c2,csp,#96
bl __sub_mod_384x384 // t2 = t2-t0-t1
add c1,csp,#0
add c2,csp,#96
add c0,csp,#0
bl __sub_mod_384x384 // t0 = t0-t1
add c1,csp,#0
add c0,c26,#0
bl __mul_by_1_mont_384
bl __redc_tail_mont_384
add c1,csp,#192
add c0,c0,#48
bl __mul_by_1_mont_384
bl __redc_tail_mont_384
ldr c30,[c29,#__SIZEOF_POINTER__]
add csp,csp,#288
ldp c19,c20,[c29,#2*__SIZEOF_POINTER__]
ldp c21,c22,[c29,#4*__SIZEOF_POINTER__]
ldp c23,c24,[c29,#6*__SIZEOF_POINTER__]
ldp c25,c26,[c29,#8*__SIZEOF_POINTER__]
ldp c27,c28,[c29,#10*__SIZEOF_POINTER__]
ldr c29,[csp],#16*__SIZEOF_POINTER__
hint #AUTI_HINT
ret
.size mul_mont_384x,.-mul_mont_384x
.globl sqr_mont_384x
.hidden sqr_mont_384x
.type sqr_mont_384x,%function
.align 5
sqr_mont_384x:
hint #PACI_HINT
stp c29,c30,[csp,#-16*__SIZEOF_POINTER__]!
add c29,csp,#0
stp c19,c20,[csp,#2*__SIZEOF_POINTER__]
stp c21,c22,[csp,#4*__SIZEOF_POINTER__]
stp c23,c24,[csp,#6*__SIZEOF_POINTER__]
stp c25,c26,[csp,#8*__SIZEOF_POINTER__]
stp c27,c28,[csp,#10*__SIZEOF_POINTER__]
stp c3,c0,[csp,#12*__SIZEOF_POINTER__] // __mul_mont_384 wants them there
sub csp,csp,#96 // space for 2 384-bit vectors
mov x4,x3 // adjust for missing b_ptr
ldp x5,x6,[c2]
ldp x7,x8,[c2,#16]
ldp x9,x10,[c2,#32]
add c2,c1,#48
add c0,csp,#0
bl __add_mod_384 // t0 = a->re + a->im
add c0,csp,#48
bl __sub_mod_384 // t1 = a->re - a->im
ldp x11,x12,[c1]
ldr x17, [c2]
ldp x13,x14,[c1,#16]
ldp x15,x16,[c1,#32]
bl __mul_mont_384 // mul_mont_384(ret->im, a->re, a->im)
adds x11,x11,x11 // add with itself
adcs x12,x12,x12
adcs x13,x13,x13
adcs x14,x14,x14
adcs x15,x15,x15
adcs x16,x16,x16
adc x25,xzr,xzr
subs x19,x11,x5
sbcs x20,x12,x6
sbcs x21,x13,x7
sbcs x22,x14,x8
sbcs x23,x15,x9
sbcs x24,x16,x10
sbcs xzr,x25,xzr
csel x19,x11,x19,lo
csel x20,x12,x20,lo
csel x21,x13,x21,lo
ldp x11,x12,[csp]
csel x22,x14,x22,lo
ldr x17, [csp,#48]
csel x23,x15,x23,lo
ldp x13,x14,[csp,#16]
csel x24,x16,x24,lo
ldp x15,x16,[csp,#32]
stp x19,x20,[c2,#48]
stp x21,x22,[c2,#64]
stp x23,x24,[c2,#80]
add c2,csp,#48
bl __mul_mont_384 // mul_mont_384(ret->re, t0, t1)
ldr c30,[c29,#__SIZEOF_POINTER__]
stp x11,x12,[c2]
stp x13,x14,[c2,#16]
stp x15,x16,[c2,#32]
add csp,csp,#96
ldp c19,c20,[c29,#2*__SIZEOF_POINTER__]
ldp c21,c22,[c29,#4*__SIZEOF_POINTER__]
ldp c23,c24,[c29,#6*__SIZEOF_POINTER__]
ldp c25,c26,[c29,#8*__SIZEOF_POINTER__]
ldp c27,c28,[c29,#10*__SIZEOF_POINTER__]
ldr c29,[csp],#16*__SIZEOF_POINTER__
hint #AUTI_HINT
ret
.size sqr_mont_384x,.-sqr_mont_384x
.globl mul_mont_384
.hidden mul_mont_384
.type mul_mont_384,%function
.align 5
mul_mont_384:
hint #PACI_HINT
stp c29,c30,[csp,#-16*__SIZEOF_POINTER__]!
add c29,csp,#0
stp c19,c20,[csp,#2*__SIZEOF_POINTER__]
stp c21,c22,[csp,#4*__SIZEOF_POINTER__]
stp c23,c24,[csp,#6*__SIZEOF_POINTER__]
stp c25,c26,[csp,#8*__SIZEOF_POINTER__]
stp c27,c28,[csp,#10*__SIZEOF_POINTER__]
stp c4,c0,[csp,#12*__SIZEOF_POINTER__] // __mul_mont_384 wants them there
ldp x11,x12,[c1]
ldr x17, [c2]
ldp x13,x14,[c1,#16]
ldp x15,x16,[c1,#32]
ldp x5,x6,[c3]
ldp x7,x8,[c3,#16]
ldp x9,x10,[c3,#32]
bl __mul_mont_384
ldr c30,[c29,#__SIZEOF_POINTER__]
stp x11,x12,[c2]
stp x13,x14,[c2,#16]
stp x15,x16,[c2,#32]
ldp c19,c20,[c29,#2*__SIZEOF_POINTER__]
ldp c21,c22,[c29,#4*__SIZEOF_POINTER__]
ldp c23,c24,[c29,#6*__SIZEOF_POINTER__]
ldp c25,c26,[c29,#8*__SIZEOF_POINTER__]
ldp c27,c28,[c29,#10*__SIZEOF_POINTER__]
ldr c29,[csp],#16*__SIZEOF_POINTER__
hint #AUTI_HINT
ret
.size mul_mont_384,.-mul_mont_384
.type __mul_mont_384,%function
.align 5
__mul_mont_384:
mul x19,x11,x17
mul x20,x12,x17
mul x21,x13,x17
mul x22,x14,x17
mul x23,x15,x17
mul x24,x16,x17
mul x4,x4,x19
umulh x26,x11,x17
umulh x27,x12,x17
umulh x28,x13,x17
umulh x0,x14,x17
umulh x1,x15,x17
umulh x3,x16,x17
adds x20,x20,x26
// mul x26,x5,x4
adcs x21,x21,x27
mul x27,x6,x4
adcs x22,x22,x28
mul x28,x7,x4
adcs x23,x23,x0
mul x0,x8,x4
adcs x24,x24,x1
mul x1,x9,x4
adc x25,xzr, x3
mul x3,x10,x4
mov x17,xzr
subs xzr,x19,#1 // adds x19,x19,x26
umulh x26,x5,x4
adcs x20,x20,x27
umulh x27,x6,x4
adcs x21,x21,x28
umulh x28,x7,x4
adcs x22,x22,x0
umulh x0,x8,x4
adcs x23,x23,x1
umulh x1,x9,x4
adcs x24,x24,x3
umulh x3,x10,x4
adcs x25,x25,xzr
adc x4,x17,xzr
ldr x17,[c2,8*1]
adds x19,x20,x26
mul x26,x11,x17
adcs x20,x21,x27
mul x27,x12,x17
adcs x21,x22,x28
mul x28,x13,x17
adcs x22,x23,x0
mul x0,x14,x17
adcs x23,x24,x1
mul x1,x15,x17
adcs x24,x25,x3
mul x3,x16,x17
adc x25,x4,xzr
ldr x4,[c29,#12*__SIZEOF_POINTER__]
adds x19,x19,x26
umulh x26,x11,x17
adcs x20,x20,x27
umulh x27,x12,x17
adcs x21,x21,x28
mul x4,x4,x19
umulh x28,x13,x17
adcs x22,x22,x0
umulh x0,x14,x17
adcs x23,x23,x1
umulh x1,x15,x17
adcs x24,x24,x3
umulh x3,x16,x17
adcs x25,x25,xzr
adc x17,xzr,xzr
adds x20,x20,x26
// mul x26,x5,x4
adcs x21,x21,x27
mul x27,x6,x4
adcs x22,x22,x28
mul x28,x7,x4
adcs x23,x23,x0
mul x0,x8,x4
adcs x24,x24,x1
mul x1,x9,x4
adcs x25,x25,x3
mul x3,x10,x4
adc x17,x17,xzr
subs xzr,x19,#1 // adds x19,x19,x26
umulh x26,x5,x4
adcs x20,x20,x27
umulh x27,x6,x4
adcs x21,x21,x28
umulh x28,x7,x4
adcs x22,x22,x0
umulh x0,x8,x4
adcs x23,x23,x1
umulh x1,x9,x4
adcs x24,x24,x3
umulh x3,x10,x4
adcs x25,x25,xzr
adc x4,x17,xzr
ldr x17,[c2,8*2]
adds x19,x20,x26
mul x26,x11,x17
adcs x20,x21,x27
mul x27,x12,x17
adcs x21,x22,x28
mul x28,x13,x17
adcs x22,x23,x0
mul x0,x14,x17
adcs x23,x24,x1
mul x1,x15,x17
adcs x24,x25,x3
mul x3,x16,x17
adc x25,x4,xzr
ldr x4,[c29,#12*__SIZEOF_POINTER__]
adds x19,x19,x26
umulh x26,x11,x17
adcs x20,x20,x27
umulh x27,x12,x17
adcs x21,x21,x28
mul x4,x4,x19
umulh x28,x13,x17
adcs x22,x22,x0
umulh x0,x14,x17
adcs x23,x23,x1
umulh x1,x15,x17
adcs x24,x24,x3
umulh x3,x16,x17
adcs x25,x25,xzr
adc x17,xzr,xzr
adds x20,x20,x26
// mul x26,x5,x4
adcs x21,x21,x27
mul x27,x6,x4
adcs x22,x22,x28
mul x28,x7,x4
adcs x23,x23,x0
mul x0,x8,x4
adcs x24,x24,x1
mul x1,x9,x4
adcs x25,x25,x3
mul x3,x10,x4
adc x17,x17,xzr
subs xzr,x19,#1 // adds x19,x19,x26
umulh x26,x5,x4
adcs x20,x20,x27
umulh x27,x6,x4
adcs x21,x21,x28
umulh x28,x7,x4
adcs x22,x22,x0
umulh x0,x8,x4
adcs x23,x23,x1
umulh x1,x9,x4
adcs x24,x24,x3
umulh x3,x10,x4
adcs x25,x25,xzr
adc x4,x17,xzr
ldr x17,[c2,8*3]
adds x19,x20,x26
mul x26,x11,x17
adcs x20,x21,x27
mul x27,x12,x17
adcs x21,x22,x28
mul x28,x13,x17
adcs x22,x23,x0
mul x0,x14,x17
adcs x23,x24,x1
mul x1,x15,x17
adcs x24,x25,x3
mul x3,x16,x17
adc x25,x4,xzr
ldr x4,[c29,#12*__SIZEOF_POINTER__]
adds x19,x19,x26
umulh x26,x11,x17
adcs x20,x20,x27
umulh x27,x12,x17
adcs x21,x21,x28
mul x4,x4,x19
umulh x28,x13,x17
adcs x22,x22,x0
umulh x0,x14,x17
adcs x23,x23,x1
umulh x1,x15,x17
adcs x24,x24,x3
umulh x3,x16,x17
adcs x25,x25,xzr
adc x17,xzr,xzr
adds x20,x20,x26
// mul x26,x5,x4
adcs x21,x21,x27
mul x27,x6,x4
adcs x22,x22,x28
mul x28,x7,x4
adcs x23,x23,x0
mul x0,x8,x4
adcs x24,x24,x1
mul x1,x9,x4
adcs x25,x25,x3
mul x3,x10,x4
adc x17,x17,xzr
subs xzr,x19,#1 // adds x19,x19,x26
umulh x26,x5,x4
adcs x20,x20,x27
umulh x27,x6,x4
adcs x21,x21,x28
umulh x28,x7,x4
adcs x22,x22,x0
umulh x0,x8,x4
adcs x23,x23,x1
umulh x1,x9,x4
adcs x24,x24,x3
umulh x3,x10,x4
adcs x25,x25,xzr
adc x4,x17,xzr
ldr x17,[c2,8*4]
adds x19,x20,x26
mul x26,x11,x17
adcs x20,x21,x27
mul x27,x12,x17
adcs x21,x22,x28
mul x28,x13,x17
adcs x22,x23,x0
mul x0,x14,x17
adcs x23,x24,x1
mul x1,x15,x17
adcs x24,x25,x3
mul x3,x16,x17
adc x25,x4,xzr
ldr x4,[c29,#12*__SIZEOF_POINTER__]
adds x19,x19,x26
umulh x26,x11,x17
adcs x20,x20,x27
umulh x27,x12,x17
adcs x21,x21,x28
mul x4,x4,x19
umulh x28,x13,x17
adcs x22,x22,x0
umulh x0,x14,x17
adcs x23,x23,x1
umulh x1,x15,x17
adcs x24,x24,x3
umulh x3,x16,x17
adcs x25,x25,xzr
adc x17,xzr,xzr
adds x20,x20,x26
// mul x26,x5,x4
adcs x21,x21,x27
mul x27,x6,x4
adcs x22,x22,x28
mul x28,x7,x4
adcs x23,x23,x0
mul x0,x8,x4
adcs x24,x24,x1
mul x1,x9,x4
adcs x25,x25,x3
mul x3,x10,x4
adc x17,x17,xzr
subs xzr,x19,#1 // adds x19,x19,x26
umulh x26,x5,x4
adcs x20,x20,x27
umulh x27,x6,x4
adcs x21,x21,x28
umulh x28,x7,x4
adcs x22,x22,x0
umulh x0,x8,x4
adcs x23,x23,x1
umulh x1,x9,x4
adcs x24,x24,x3
umulh x3,x10,x4
adcs x25,x25,xzr
adc x4,x17,xzr
ldr x17,[c2,8*5]
adds x19,x20,x26
mul x26,x11,x17
adcs x20,x21,x27
mul x27,x12,x17
adcs x21,x22,x28
mul x28,x13,x17
adcs x22,x23,x0
mul x0,x14,x17
adcs x23,x24,x1
mul x1,x15,x17
adcs x24,x25,x3
mul x3,x16,x17
adc x25,x4,xzr
ldr x4,[c29,#12*__SIZEOF_POINTER__]
adds x19,x19,x26
umulh x26,x11,x17
adcs x20,x20,x27
umulh x27,x12,x17
adcs x21,x21,x28
mul x4,x4,x19
umulh x28,x13,x17
adcs x22,x22,x0
umulh x0,x14,x17
adcs x23,x23,x1
umulh x1,x15,x17
adcs x24,x24,x3
umulh x3,x16,x17
adcs x25,x25,xzr
adc x17,xzr,xzr
adds x20,x20,x26
// mul x26,x5,x4
adcs x21,x21,x27
mul x27,x6,x4
adcs x22,x22,x28
mul x28,x7,x4
adcs x23,x23,x0
mul x0,x8,x4
adcs x24,x24,x1
mul x1,x9,x4
adcs x25,x25,x3
mul x3,x10,x4
adc x17,x17,xzr
subs xzr,x19,#1 // adds x19,x19,x26
umulh x26,x5,x4
adcs x20,x20,x27
umulh x27,x6,x4
adcs x21,x21,x28
umulh x28,x7,x4
adcs x22,x22,x0
umulh x0,x8,x4
adcs x23,x23,x1
umulh x1,x9,x4
adcs x24,x24,x3
umulh x3,x10,x4
adcs x25,x25,xzr
ldp c4,c2,[c29,#12*__SIZEOF_POINTER__] // pull r_ptr
adc x17,x17,xzr
adds x19,x20,x26
adcs x20,x21,x27
adcs x21,x22,x28
adcs x22,x23,x0
adcs x23,x24,x1
adcs x24,x25,x3
adc x25,x17,xzr
subs x26,x19,x5
sbcs x27,x20,x6
sbcs x28,x21,x7
sbcs x0,x22,x8
sbcs x1,x23,x9
sbcs x3,x24,x10
sbcs xzr, x25,xzr
csel x11,x19,x26,lo
csel x12,x20,x27,lo
csel x13,x21,x28,lo
csel x14,x22,x0,lo
csel x15,x23,x1,lo
csel x16,x24,x3,lo
ret
.size __mul_mont_384,.-__mul_mont_384
.globl sqr_mont_384
.hidden sqr_mont_384
.type sqr_mont_384,%function
.align 5
sqr_mont_384:
hint #PACI_HINT
stp c29,c30,[csp,#-16*__SIZEOF_POINTER__]!
add c29,csp,#0
stp c19,c20,[csp,#2*__SIZEOF_POINTER__]
stp c21,c22,[csp,#4*__SIZEOF_POINTER__]
stp c23,c24,[csp,#6*__SIZEOF_POINTER__]
stp c25,c26,[csp,#8*__SIZEOF_POINTER__]
stp c27,c28,[csp,#10*__SIZEOF_POINTER__]
sub csp,csp,#96 // space for 768-bit vector
mov c4,c3 // adjust for missing b_ptr
mov c3,c0 // save r_ptr
mov c0,csp
ldp x11,x12,[c1]
ldp x13,x14,[c1,#16]
ldp x15,x16,[c1,#32]
bl __sqr_384
ldp x5,x6,[c2]
ldp x7,x8,[c2,#16]
ldp x9,x10,[c2,#32]
mov c1,csp
mov c0,c3 // restore r_ptr
bl __mul_by_1_mont_384
bl __redc_tail_mont_384
ldr c30,[c29,#__SIZEOF_POINTER__]
add csp,csp,#96
ldp c19,c20,[c29,#2*__SIZEOF_POINTER__]
ldp c21,c22,[c29,#4*__SIZEOF_POINTER__]
ldp c23,c24,[c29,#6*__SIZEOF_POINTER__]
ldp c25,c26,[c29,#8*__SIZEOF_POINTER__]
ldp c27,c28,[c29,#10*__SIZEOF_POINTER__]
ldr c29,[csp],#16*__SIZEOF_POINTER__
hint #AUTI_HINT
ret
.size sqr_mont_384,.-sqr_mont_384
.globl sqr_n_mul_mont_383
.hidden sqr_n_mul_mont_383
.type sqr_n_mul_mont_383,%function
.align 5
sqr_n_mul_mont_383:
hint #PACI_HINT
stp c29,c30,[csp,#-16*__SIZEOF_POINTER__]!
add c29,csp,#0
stp c19,c20,[csp,#2*__SIZEOF_POINTER__]
stp c21,c22,[csp,#4*__SIZEOF_POINTER__]
stp c23,c24,[csp,#6*__SIZEOF_POINTER__]
stp c25,c26,[csp,#8*__SIZEOF_POINTER__]
stp c27,c28,[csp,#10*__SIZEOF_POINTER__]
stp c4,c0,[csp,#12*__SIZEOF_POINTER__] // __mul_mont_384 wants them there
sub csp,csp,#96 // space for 768-bit vector
mov c17,c5 // save b_ptr
ldp x11,x12,[c1]
ldp x13,x14,[c1,#16]
ldp x15,x16,[c1,#32]
mov c0,csp
.Loop_sqr_383:
bl __sqr_384
sub x2,x2,#1 // counter
ldp x5,x6,[c3]
ldp x7,x8,[c3,#16]
ldp x9,x10,[c3,#32]
mov c1,csp
bl __mul_by_1_mont_384
ldp x19,x20,[c1,#48]
ldp x21,x22,[c1,#64]
ldp x23,x24,[c1,#80]
adds x11,x11,x19 // just accumulate upper half
adcs x12,x12,x20
adcs x13,x13,x21
adcs x14,x14,x22
adcs x15,x15,x23
adc x16,x16,x24
cbnz x2,.Loop_sqr_383
mov c2,c17
ldr x17,[c17]
bl __mul_mont_384
ldr c30,[c29,#__SIZEOF_POINTER__]
stp x11,x12,[c2]
stp x13,x14,[c2,#16]
stp x15,x16,[c2,#32]
add csp,csp,#96
ldp c19,c20,[c29,#2*__SIZEOF_POINTER__]
ldp c21,c22,[c29,#4*__SIZEOF_POINTER__]
ldp c23,c24,[c29,#6*__SIZEOF_POINTER__]
ldp c25,c26,[c29,#8*__SIZEOF_POINTER__]
ldp c27,c28,[c29,#10*__SIZEOF_POINTER__]
ldr c29,[csp],#16*__SIZEOF_POINTER__
hint #AUTI_HINT
ret
.size sqr_n_mul_mont_383,.-sqr_n_mul_mont_383
.type __sqr_384,%function
.align 5
__sqr_384:
mul x19,x12,x11
mul x20,x13,x11
mul x21,x14,x11
mul x22,x15,x11
mul x23,x16,x11
umulh x6,x12,x11
umulh x7,x13,x11
umulh x8,x14,x11
umulh x9,x15,x11
adds x20,x20,x6
umulh x10,x16,x11
adcs x21,x21,x7
mul x7,x13,x12
adcs x22,x22,x8
mul x8,x14,x12
adcs x23,x23,x9
mul x9,x15,x12
adc x24,xzr, x10
mul x10,x16,x12
adds x21,x21,x7
umulh x7,x13,x12
adcs x22,x22,x8
umulh x8,x14,x12
adcs x23,x23,x9
umulh x9,x15,x12
adcs x24,x24,x10
umulh x10,x16,x12
adc x25,xzr,xzr
mul x5,x11,x11
adds x22,x22,x7
umulh x11, x11,x11
adcs x23,x23,x8
mul x8,x14,x13
adcs x24,x24,x9
mul x9,x15,x13
adc x25,x25,x10
mul x10,x16,x13
adds x23,x23,x8
umulh x8,x14,x13
adcs x24,x24,x9
umulh x9,x15,x13
adcs x25,x25,x10
umulh x10,x16,x13
adc x26,xzr,xzr
mul x6,x12,x12
adds x24,x24,x8
umulh x12, x12,x12
adcs x25,x25,x9
mul x9,x15,x14
adc x26,x26,x10
mul x10,x16,x14
adds x25,x25,x9
umulh x9,x15,x14
adcs x26,x26,x10
umulh x10,x16,x14
adc x27,xzr,xzr
mul x7,x13,x13
adds x26,x26,x9
umulh x13, x13,x13
adc x27,x27,x10
mul x8,x14,x14
mul x10,x16,x15
umulh x14, x14,x14
adds x27,x27,x10
umulh x10,x16,x15
mul x9,x15,x15
adc x28,x10,xzr
adds x19,x19,x19
adcs x20,x20,x20
adcs x21,x21,x21
adcs x22,x22,x22
adcs x23,x23,x23
adcs x24,x24,x24
adcs x25,x25,x25
adcs x26,x26,x26
umulh x15, x15,x15
adcs x27,x27,x27
mul x10,x16,x16
adcs x28,x28,x28
umulh x16, x16,x16
adc x1,xzr,xzr
adds x19,x19,x11
adcs x20,x20,x6
adcs x21,x21,x12
adcs x22,x22,x7
adcs x23,x23,x13
adcs x24,x24,x8
adcs x25,x25,x14
stp x5,x19,[c0]
adcs x26,x26,x9
stp x20,x21,[c0,#16]
adcs x27,x27,x15
stp x22,x23,[c0,#32]
adcs x28,x28,x10
stp x24,x25,[c0,#48]
adc x16,x16,x1
stp x26,x27,[c0,#64]
stp x28,x16,[c0,#80]
ret
.size __sqr_384,.-__sqr_384
.globl sqr_384
.hidden sqr_384
.type sqr_384,%function
.align 5
sqr_384:
hint #PACI_HINT
stp c29,c30,[csp,#-16*__SIZEOF_POINTER__]!
add c29,csp,#0
stp c19,c20,[csp,#2*__SIZEOF_POINTER__]
stp c21,c22,[csp,#4*__SIZEOF_POINTER__]
stp c23,c24,[csp,#6*__SIZEOF_POINTER__]
stp c25,c26,[csp,#8*__SIZEOF_POINTER__]
stp c27,c28,[csp,#10*__SIZEOF_POINTER__]
ldp x11,x12,[c1]
ldp x13,x14,[c1,#16]
ldp x15,x16,[c1,#32]
bl __sqr_384
ldr c30,[c29,#__SIZEOF_POINTER__]
ldp c19,c20,[c29,#2*__SIZEOF_POINTER__]
ldp c21,c22,[c29,#4*__SIZEOF_POINTER__]
ldp c23,c24,[c29,#6*__SIZEOF_POINTER__]
ldp c25,c26,[c29,#8*__SIZEOF_POINTER__]
ldp c27,c28,[c29,#10*__SIZEOF_POINTER__]
ldr c29,[csp],#16*__SIZEOF_POINTER__
hint #AUTI_HINT
ret
.size sqr_384,.-sqr_384
.globl redc_mont_384
.hidden redc_mont_384
.type redc_mont_384,%function
.align 5
redc_mont_384:
hint #PACI_HINT
stp c29,c30,[csp,#-16*__SIZEOF_POINTER__]!
add c29,csp,#0
stp c19,c20,[csp,#2*__SIZEOF_POINTER__]
stp c21,c22,[csp,#4*__SIZEOF_POINTER__]
stp c23,c24,[csp,#6*__SIZEOF_POINTER__]
stp c25,c26,[csp,#8*__SIZEOF_POINTER__]
stp c27,c28,[csp,#10*__SIZEOF_POINTER__]
mov x4,x3 // adjust for missing b_ptr
ldp x5,x6,[c2]
ldp x7,x8,[c2,#16]
ldp x9,x10,[c2,#32]
bl __mul_by_1_mont_384
bl __redc_tail_mont_384
ldr c30,[c29,#__SIZEOF_POINTER__]
ldp c19,c20,[c29,#2*__SIZEOF_POINTER__]
ldp c21,c22,[c29,#4*__SIZEOF_POINTER__]
ldp c23,c24,[c29,#6*__SIZEOF_POINTER__]
ldp c25,c26,[c29,#8*__SIZEOF_POINTER__]
ldp c27,c28,[c29,#10*__SIZEOF_POINTER__]
ldr c29,[csp],#16*__SIZEOF_POINTER__
hint #AUTI_HINT
ret
.size redc_mont_384,.-redc_mont_384
.globl from_mont_384
.hidden from_mont_384
.type from_mont_384,%function
.align 5
from_mont_384:
hint #PACI_HINT
stp c29,c30,[csp,#-16*__SIZEOF_POINTER__]!
add c29,csp,#0
stp c19,c20,[csp,#2*__SIZEOF_POINTER__]
stp c21,c22,[csp,#4*__SIZEOF_POINTER__]
stp c23,c24,[csp,#6*__SIZEOF_POINTER__]
stp c25,c26,[csp,#8*__SIZEOF_POINTER__]
stp c27,c28,[csp,#10*__SIZEOF_POINTER__]
mov x4,x3 // adjust for missing b_ptr
ldp x5,x6,[c2]
ldp x7,x8,[c2,#16]
ldp x9,x10,[c2,#32]
bl __mul_by_1_mont_384
ldr c30,[c29,#__SIZEOF_POINTER__]
subs x19,x11,x5
sbcs x20,x12,x6
sbcs x21,x13,x7
sbcs x22,x14,x8
sbcs x23,x15,x9
sbcs x24,x16,x10
csel x11,x11,x19,lo
csel x12,x12,x20,lo
csel x13,x13,x21,lo
csel x14,x14,x22,lo
csel x15,x15,x23,lo
csel x16,x16,x24,lo
stp x11,x12,[c0]
stp x13,x14,[c0,#16]
stp x15,x16,[c0,#32]
ldp c19,c20,[c29,#2*__SIZEOF_POINTER__]
ldp c21,c22,[c29,#4*__SIZEOF_POINTER__]
ldp c23,c24,[c29,#6*__SIZEOF_POINTER__]
ldp c25,c26,[c29,#8*__SIZEOF_POINTER__]
ldp c27,c28,[c29,#10*__SIZEOF_POINTER__]
ldr c29,[csp],#16*__SIZEOF_POINTER__
hint #AUTI_HINT
ret
.size from_mont_384,.-from_mont_384
.type __mul_by_1_mont_384,%function
.align 5
__mul_by_1_mont_384:
ldp x11,x12,[c1]
ldp x13,x14,[c1,#16]
mul x26,x4,x11
ldp x15,x16,[c1,#32]
// mul x19,x5,x26
mul x20,x6,x26
mul x21,x7,x26
mul x22,x8,x26
mul x23,x9,x26
mul x24,x10,x26
subs xzr,x11,#1 // adds x19,x19,x11
umulh x11,x5,x26
adcs x20,x20,x12
umulh x12,x6,x26
adcs x21,x21,x13
umulh x13,x7,x26
adcs x22,x22,x14
umulh x14,x8,x26
adcs x23,x23,x15
umulh x15,x9,x26
adcs x24,x24,x16
umulh x16,x10,x26
adc x25,xzr,xzr
adds x11,x11,x20
adcs x12,x12,x21
adcs x13,x13,x22
mul x26,x4,x11
adcs x14,x14,x23
adcs x15,x15,x24
adc x16,x16,x25
// mul x19,x5,x26
mul x20,x6,x26
mul x21,x7,x26
mul x22,x8,x26
mul x23,x9,x26
mul x24,x10,x26
subs xzr,x11,#1 // adds x19,x19,x11
umulh x11,x5,x26
adcs x20,x20,x12
umulh x12,x6,x26
adcs x21,x21,x13
umulh x13,x7,x26
adcs x22,x22,x14
umulh x14,x8,x26
adcs x23,x23,x15
umulh x15,x9,x26
adcs x24,x24,x16
umulh x16,x10,x26
adc x25,xzr,xzr
adds x11,x11,x20
adcs x12,x12,x21
adcs x13,x13,x22
mul x26,x4,x11
adcs x14,x14,x23
adcs x15,x15,x24
adc x16,x16,x25
// mul x19,x5,x26
mul x20,x6,x26
mul x21,x7,x26
mul x22,x8,x26
mul x23,x9,x26
mul x24,x10,x26
subs xzr,x11,#1 // adds x19,x19,x11
umulh x11,x5,x26
adcs x20,x20,x12
umulh x12,x6,x26
adcs x21,x21,x13
umulh x13,x7,x26
adcs x22,x22,x14
umulh x14,x8,x26
adcs x23,x23,x15
umulh x15,x9,x26
adcs x24,x24,x16
umulh x16,x10,x26
adc x25,xzr,xzr
adds x11,x11,x20
adcs x12,x12,x21
adcs x13,x13,x22
mul x26,x4,x11
adcs x14,x14,x23
adcs x15,x15,x24
adc x16,x16,x25
// mul x19,x5,x26
mul x20,x6,x26
mul x21,x7,x26
mul x22,x8,x26
mul x23,x9,x26
mul x24,x10,x26
subs xzr,x11,#1 // adds x19,x19,x11
umulh x11,x5,x26
adcs x20,x20,x12
umulh x12,x6,x26
adcs x21,x21,x13
umulh x13,x7,x26
adcs x22,x22,x14
umulh x14,x8,x26
adcs x23,x23,x15
umulh x15,x9,x26
adcs x24,x24,x16
umulh x16,x10,x26
adc x25,xzr,xzr
adds x11,x11,x20
adcs x12,x12,x21
adcs x13,x13,x22
mul x26,x4,x11
adcs x14,x14,x23
adcs x15,x15,x24
adc x16,x16,x25
// mul x19,x5,x26
mul x20,x6,x26
mul x21,x7,x26
mul x22,x8,x26
mul x23,x9,x26
mul x24,x10,x26
subs xzr,x11,#1 // adds x19,x19,x11
umulh x11,x5,x26
adcs x20,x20,x12
umulh x12,x6,x26
adcs x21,x21,x13
umulh x13,x7,x26
adcs x22,x22,x14
umulh x14,x8,x26
adcs x23,x23,x15
umulh x15,x9,x26
adcs x24,x24,x16
umulh x16,x10,x26
adc x25,xzr,xzr
adds x11,x11,x20
adcs x12,x12,x21
adcs x13,x13,x22
mul x26,x4,x11
adcs x14,x14,x23
adcs x15,x15,x24
adc x16,x16,x25
// mul x19,x5,x26
mul x20,x6,x26
mul x21,x7,x26
mul x22,x8,x26
mul x23,x9,x26
mul x24,x10,x26
subs xzr,x11,#1 // adds x19,x19,x11
umulh x11,x5,x26
adcs x20,x20,x12
umulh x12,x6,x26
adcs x21,x21,x13
umulh x13,x7,x26
adcs x22,x22,x14
umulh x14,x8,x26
adcs x23,x23,x15
umulh x15,x9,x26
adcs x24,x24,x16
umulh x16,x10,x26
adc x25,xzr,xzr
adds x11,x11,x20
adcs x12,x12,x21
adcs x13,x13,x22
adcs x14,x14,x23
adcs x15,x15,x24
adc x16,x16,x25
ret
.size __mul_by_1_mont_384,.-__mul_by_1_mont_384
.type __redc_tail_mont_384,%function
.align 5
__redc_tail_mont_384:
ldp x19,x20,[c1,#48]
ldp x21,x22,[c1,#64]
ldp x23,x24,[c1,#80]
adds x11,x11,x19 // accumulate upper half
adcs x12,x12,x20
adcs x13,x13,x21
adcs x14,x14,x22
adcs x15,x15,x23
adcs x16,x16,x24
adc x25,xzr,xzr
subs x19,x11,x5
sbcs x20,x12,x6
sbcs x21,x13,x7
sbcs x22,x14,x8
sbcs x23,x15,x9
sbcs x24,x16,x10
sbcs xzr,x25,xzr
csel x11,x11,x19,lo
csel x12,x12,x20,lo
csel x13,x13,x21,lo
csel x14,x14,x22,lo
csel x15,x15,x23,lo
csel x16,x16,x24,lo
stp x11,x12,[c0]
stp x13,x14,[c0,#16]
stp x15,x16,[c0,#32]
ret
.size __redc_tail_mont_384,.-__redc_tail_mont_384
.globl mul_384
.hidden mul_384
.type mul_384,%function
.align 5
mul_384:
hint #PACI_HINT
stp c29,c30,[csp,#-16*__SIZEOF_POINTER__]!
add c29,csp,#0
stp c19,c20,[csp,#2*__SIZEOF_POINTER__]
stp c21,c22,[csp,#4*__SIZEOF_POINTER__]
stp c23,c24,[csp,#6*__SIZEOF_POINTER__]
stp c25,c26,[csp,#8*__SIZEOF_POINTER__]
stp c27,c28,[csp,#10*__SIZEOF_POINTER__]
bl __mul_384
ldr c30,[c29,#__SIZEOF_POINTER__]
ldp c19,c20,[c29,#2*__SIZEOF_POINTER__]
ldp c21,c22,[c29,#4*__SIZEOF_POINTER__]
ldp c23,c24,[c29,#6*__SIZEOF_POINTER__]
ldp c25,c26,[c29,#8*__SIZEOF_POINTER__]
ldp c27,c28,[c29,#10*__SIZEOF_POINTER__]
ldr c29,[csp],#16*__SIZEOF_POINTER__
hint #AUTI_HINT
ret
.size mul_384,.-mul_384
.type __mul_384,%function
.align 5
__mul_384:
ldp x11,x12,[c1]
ldr x17, [c2]
ldp x13,x14,[c1,#16]
ldp x15,x16,[c1,#32]
mul x19,x11,x17
mul x20,x12,x17
mul x21,x13,x17
mul x22,x14,x17
mul x23,x15,x17
mul x24,x16,x17
umulh x5,x11,x17
umulh x6,x12,x17
umulh x7,x13,x17
umulh x8,x14,x17
umulh x9,x15,x17
umulh x10,x16,x17
ldr x17,[c2,8*1]
str x19,[c0]
adds x19,x20,x5
mul x5,x11,x17
adcs x20,x21,x6
mul x6,x12,x17
adcs x21,x22,x7
mul x7,x13,x17
adcs x22,x23,x8
mul x8,x14,x17
adcs x23,x24,x9
mul x9,x15,x17
adc x24,xzr, x10
mul x10,x16,x17
adds x19,x19,x5
umulh x5,x11,x17
adcs x20,x20,x6
umulh x6,x12,x17
adcs x21,x21,x7
umulh x7,x13,x17
adcs x22,x22,x8
umulh x8,x14,x17
adcs x23,x23,x9
umulh x9,x15,x17
adcs x24,x24,x10
umulh x10,x16,x17
ldr x17,[c2,#8*(1+1)]
adc x25,xzr,xzr
str x19,[c0,8*1]
adds x19,x20,x5
mul x5,x11,x17
adcs x20,x21,x6
mul x6,x12,x17
adcs x21,x22,x7
mul x7,x13,x17
adcs x22,x23,x8
mul x8,x14,x17
adcs x23,x24,x9
mul x9,x15,x17
adc x24,x25,x10
mul x10,x16,x17
adds x19,x19,x5
umulh x5,x11,x17
adcs x20,x20,x6
umulh x6,x12,x17
adcs x21,x21,x7
umulh x7,x13,x17
adcs x22,x22,x8
umulh x8,x14,x17
adcs x23,x23,x9
umulh x9,x15,x17
adcs x24,x24,x10
umulh x10,x16,x17
ldr x17,[c2,#8*(2+1)]
adc x25,xzr,xzr
str x19,[c0,8*2]
adds x19,x20,x5
mul x5,x11,x17
adcs x20,x21,x6
mul x6,x12,x17
adcs x21,x22,x7
mul x7,x13,x17
adcs x22,x23,x8
mul x8,x14,x17
adcs x23,x24,x9
mul x9,x15,x17
adc x24,x25,x10
mul x10,x16,x17
adds x19,x19,x5
umulh x5,x11,x17
adcs x20,x20,x6
umulh x6,x12,x17
adcs x21,x21,x7
umulh x7,x13,x17
adcs x22,x22,x8
umulh x8,x14,x17
adcs x23,x23,x9
umulh x9,x15,x17
adcs x24,x24,x10
umulh x10,x16,x17
ldr x17,[c2,#8*(3+1)]
adc x25,xzr,xzr
str x19,[c0,8*3]
adds x19,x20,x5
mul x5,x11,x17
adcs x20,x21,x6
mul x6,x12,x17
adcs x21,x22,x7
mul x7,x13,x17
adcs x22,x23,x8
mul x8,x14,x17
adcs x23,x24,x9
mul x9,x15,x17
adc x24,x25,x10
mul x10,x16,x17
adds x19,x19,x5
umulh x5,x11,x17
adcs x20,x20,x6
umulh x6,x12,x17
adcs x21,x21,x7
umulh x7,x13,x17
adcs x22,x22,x8
umulh x8,x14,x17
adcs x23,x23,x9
umulh x9,x15,x17
adcs x24,x24,x10
umulh x10,x16,x17
ldr x17,[c2,#8*(4+1)]
adc x25,xzr,xzr
str x19,[c0,8*4]
adds x19,x20,x5
mul x5,x11,x17
adcs x20,x21,x6
mul x6,x12,x17
adcs x21,x22,x7
mul x7,x13,x17
adcs x22,x23,x8
mul x8,x14,x17
adcs x23,x24,x9
mul x9,x15,x17
adc x24,x25,x10
mul x10,x16,x17
adds x19,x19,x5
umulh x5,x11,x17
adcs x20,x20,x6
umulh x6,x12,x17
adcs x21,x21,x7
umulh x7,x13,x17
adcs x22,x22,x8
umulh x8,x14,x17
adcs x23,x23,x9
umulh x9,x15,x17
adcs x24,x24,x10
umulh x10,x16,x17
adc x25,xzr,xzr
str x19,[c0,8*5]
adds x19,x20,x5
adcs x20,x21,x6
adcs x21,x22,x7
adcs x22,x23,x8
adcs x23,x24,x9
adc x24,x25,x10
stp x19,x20,[c0,#48]
stp x21,x22,[c0,#64]
stp x23,x24,[c0,#80]
ret
.size __mul_384,.-__mul_384
.globl mul_382x
.hidden mul_382x
.type mul_382x,%function
.align 5
mul_382x:
hint #PACI_HINT
stp c29,c30,[csp,#-16*__SIZEOF_POINTER__]!
add c29,csp,#0
stp c19,c20,[csp,#2*__SIZEOF_POINTER__]
stp c21,c22,[csp,#4*__SIZEOF_POINTER__]
stp c23,c24,[csp,#6*__SIZEOF_POINTER__]
stp c25,c26,[csp,#8*__SIZEOF_POINTER__]
stp c27,c28,[csp,#10*__SIZEOF_POINTER__]
sub csp,csp,#96 // space for two 384-bit vectors
ldp x11,x12,[c1]
mov c26,c0 // save r_ptr
ldp x19,x20,[c1,#48]
mov c27,c1 // save a_ptr
ldp x13,x14,[c1,#16]
mov c28,c2 // save b_ptr
ldp x21,x22,[c1,#64]
ldp x15,x16,[c1,#32]
adds x5,x11,x19 // t0 = a->re + a->im
ldp x23,x24,[c1,#80]
adcs x6,x12,x20
ldp x11,x12,[c2]
adcs x7,x13,x21
ldp x19,x20,[c2,#48]
adcs x8,x14,x22
ldp x13,x14,[c2,#16]
adcs x9,x15,x23
ldp x21,x22,[c2,#64]
adc x10,x16,x24
ldp x15,x16,[c2,#32]
stp x5,x6,[csp]
adds x5,x11,x19 // t1 = b->re + b->im
ldp x23,x24,[c2,#80]
adcs x6,x12,x20
stp x7,x8,[csp,#16]
adcs x7,x13,x21
adcs x8,x14,x22
stp x9,x10,[csp,#32]
adcs x9,x15,x23
stp x5,x6,[csp,#48]
adc x10,x16,x24
stp x7,x8,[csp,#64]
stp x9,x10,[csp,#80]
bl __mul_384 // mul_384(ret->re, a->re, b->re)
add c1,csp,#0
add c2,csp,#48
add c0,c26,#96
bl __mul_384
add c1,c27,#48
add c2,c28,#48
add c0,csp,#0
bl __mul_384
ldp x5,x6,[c3]
ldp x7,x8,[c3,#16]
ldp x9,x10,[c3,#32]
add c1,c26,#96
add c2,csp,#0
add c0,c26,#96
bl __sub_mod_384x384
add c2,c26,#0
bl __sub_mod_384x384
add c1,c26,#0
add c2,csp,#0
add c0,c26,#0
bl __sub_mod_384x384
ldr c30,[c29,#__SIZEOF_POINTER__]
add csp,csp,#96
ldp c19,c20,[c29,#2*__SIZEOF_POINTER__]
ldp c21,c22,[c29,#4*__SIZEOF_POINTER__]
ldp c23,c24,[c29,#6*__SIZEOF_POINTER__]
ldp c25,c26,[c29,#8*__SIZEOF_POINTER__]
ldp c27,c28,[c29,#10*__SIZEOF_POINTER__]
ldr c29,[csp],#16*__SIZEOF_POINTER__
hint #AUTI_HINT
ret
.size mul_382x,.-mul_382x
.globl sqr_382x
.hidden sqr_382x
.type sqr_382x,%function
.align 5
sqr_382x:
hint #PACI_HINT
stp c29,c30,[csp,#-16*__SIZEOF_POINTER__]!
add c29,csp,#0
stp c19,c20,[csp,#2*__SIZEOF_POINTER__]
stp c21,c22,[csp,#4*__SIZEOF_POINTER__]
stp c23,c24,[csp,#6*__SIZEOF_POINTER__]
stp c25,c26,[csp,#8*__SIZEOF_POINTER__]
stp c27,c28,[csp,#10*__SIZEOF_POINTER__]
ldp x11,x12,[c1]
ldp x19,x20,[c1,#48]
ldp x13,x14,[c1,#16]
adds x5,x11,x19 // t0 = a->re + a->im
ldp x21,x22,[c1,#64]
adcs x6,x12,x20
ldp x15,x16,[c1,#32]
adcs x7,x13,x21
ldp x23,x24,[c1,#80]
adcs x8,x14,x22
stp x5,x6,[c0]
adcs x9,x15,x23
ldp x5,x6,[c2]
adc x10,x16,x24
stp x7,x8,[c0,#16]
subs x11,x11,x19 // t1 = a->re - a->im
ldp x7,x8,[c2,#16]
sbcs x12,x12,x20
stp x9,x10,[c0,#32]
sbcs x13,x13,x21
ldp x9,x10,[c2,#32]
sbcs x14,x14,x22
sbcs x15,x15,x23
sbcs x16,x16,x24
sbc x25,xzr,xzr
and x19,x5,x25
and x20,x6,x25
adds x11,x11,x19
and x21,x7,x25
adcs x12,x12,x20
and x22,x8,x25
adcs x13,x13,x21
and x23,x9,x25
adcs x14,x14,x22
and x24,x10,x25
adcs x15,x15,x23
stp x11,x12,[c0,#48]
adc x16,x16,x24
stp x13,x14,[c0,#64]
stp x15,x16,[c0,#80]
mov c4,c1 // save a_ptr
add c1,c0,#0
add c2,c0,#48
bl __mul_384
add c1,c4,#0
add c2,c4,#48
add c0,c0,#96
bl __mul_384
ldr c30,[c29,#__SIZEOF_POINTER__]
ldp x11,x12,[c0]
ldp x13,x14,[c0,#16]
adds x11,x11,x11 // add with itself
ldp x15,x16,[c0,#32]
adcs x12,x12,x12
adcs x13,x13,x13
adcs x14,x14,x14
adcs x15,x15,x15
adcs x16,x16,x16
adcs x19,x19,x19
adcs x20,x20,x20
stp x11,x12,[c0]
adcs x21,x21,x21
stp x13,x14,[c0,#16]
adcs x22,x22,x22
stp x15,x16,[c0,#32]
adcs x23,x23,x23
stp x19,x20,[c0,#48]
adc x24,x24,x24
stp x21,x22,[c0,#64]
stp x23,x24,[c0,#80]
ldp c19,c20,[c29,#2*__SIZEOF_POINTER__]
ldp c21,c22,[c29,#4*__SIZEOF_POINTER__]
ldp c23,c24,[c29,#6*__SIZEOF_POINTER__]
ldp c25,c26,[c29,#8*__SIZEOF_POINTER__]
ldp c27,c28,[c29,#10*__SIZEOF_POINTER__]
ldr c29,[csp],#16*__SIZEOF_POINTER__
hint #AUTI_HINT
ret
.size sqr_382x,.-sqr_382x
.globl sqr_mont_382x
.hidden sqr_mont_382x
.type sqr_mont_382x,%function
.align 5
sqr_mont_382x:
hint #PACI_HINT
stp c29,c30,[csp,#-16*__SIZEOF_POINTER__]!
add c29,csp,#0
stp c19,c20,[csp,#2*__SIZEOF_POINTER__]
stp c21,c22,[csp,#4*__SIZEOF_POINTER__]
stp c23,c24,[csp,#6*__SIZEOF_POINTER__]
stp c25,c26,[csp,#8*__SIZEOF_POINTER__]
stp c27,c28,[csp,#10*__SIZEOF_POINTER__]
stp c3,c0,[csp,#12*__SIZEOF_POINTER__] // __mul_mont_384 wants them there
sub csp,csp,#112 // space for two 384-bit vectors + word
mov x4,x3 // adjust for missing b_ptr
ldp x11,x12,[c1]
ldp x13,x14,[c1,#16]
ldp x15,x16,[c1,#32]
ldp x17,x20,[c1,#48]
ldp x21,x22,[c1,#64]
ldp x23,x24,[c1,#80]
adds x5,x11,x17 // t0 = a->re + a->im
adcs x6,x12,x20
adcs x7,x13,x21
adcs x8,x14,x22
adcs x9,x15,x23
adc x10,x16,x24
subs x19,x11,x17 // t1 = a->re - a->im
sbcs x20,x12,x20
sbcs x21,x13,x21
sbcs x22,x14,x22
sbcs x23,x15,x23
sbcs x24,x16,x24
sbc x25,xzr,xzr // borrow flag as mask
stp x5,x6,[csp]
stp x7,x8,[csp,#16]
stp x9,x10,[csp,#32]
stp x19,x20,[csp,#48]
stp x21,x22,[csp,#64]
stp x23,x24,[csp,#80]
str x25,[csp,#96]
ldp x5,x6,[c2]
ldp x7,x8,[c2,#16]
ldp x9,x10,[c2,#32]
add c2,c1,#48
bl __mul_mont_383_nonred // mul_mont_384(ret->im, a->re, a->im)
adds x19,x11,x11 // add with itself
adcs x20,x12,x12
adcs x21,x13,x13
adcs x22,x14,x14
adcs x23,x15,x15
adc x24,x16,x16
stp x19,x20,[c2,#48]
stp x21,x22,[c2,#64]
stp x23,x24,[c2,#80]
ldp x11,x12,[csp]
ldr x17,[csp,#48]
ldp x13,x14,[csp,#16]
ldp x15,x16,[csp,#32]
add c2,csp,#48
bl __mul_mont_383_nonred // mul_mont_384(ret->im, t0, t1)
ldr c30,[c29,#__SIZEOF_POINTER__]
ldr x25,[csp,#96] // account for sign from a->re - a->im
ldp x19,x20,[csp]
ldp x21,x22,[csp,#16]
ldp x23,x24,[csp,#32]
and x19,x19,x25
and x20,x20,x25
and x21,x21,x25
and x22,x22,x25
and x23,x23,x25
and x24,x24,x25
subs x11,x11,x19
sbcs x12,x12,x20
sbcs x13,x13,x21
sbcs x14,x14,x22
sbcs x15,x15,x23
sbcs x16,x16,x24
sbc x25,xzr,xzr
and x19,x5,x25
and x20,x6,x25
and x21,x7,x25
and x22,x8,x25
and x23,x9,x25
and x24,x10,x25
adds x11,x11,x19
adcs x12,x12,x20
adcs x13,x13,x21
adcs x14,x14,x22
adcs x15,x15,x23
adc x16,x16,x24
stp x11,x12,[c2]
stp x13,x14,[c2,#16]
stp x15,x16,[c2,#32]
add csp,csp,#112
ldp c19,c20,[c29,#2*__SIZEOF_POINTER__]
ldp c21,c22,[c29,#4*__SIZEOF_POINTER__]
ldp c23,c24,[c29,#6*__SIZEOF_POINTER__]
ldp c25,c26,[c29,#8*__SIZEOF_POINTER__]
ldp c27,c28,[c29,#10*__SIZEOF_POINTER__]
ldr c29,[csp],#16*__SIZEOF_POINTER__
hint #AUTI_HINT
ret
.size sqr_mont_382x,.-sqr_mont_382x
.type __mul_mont_383_nonred,%function
.align 5
__mul_mont_383_nonred:
mul x19,x11,x17
mul x20,x12,x17
mul x21,x13,x17
mul x22,x14,x17
mul x23,x15,x17
mul x24,x16,x17
mul x4,x4,x19
umulh x26,x11,x17
umulh x27,x12,x17
umulh x28,x13,x17
umulh x0,x14,x17
umulh x1,x15,x17
umulh x3,x16,x17
adds x20,x20,x26
mul x26,x5,x4
adcs x21,x21,x27
mul x27,x6,x4
adcs x22,x22,x28
mul x28,x7,x4
adcs x23,x23,x0
mul x0,x8,x4
adcs x24,x24,x1
mul x1,x9,x4
adc x25,xzr, x3
mul x3,x10,x4
ldr x17,[c2,8*1]
adds x19,x19,x26
umulh x26,x5,x4
adcs x20,x20,x27
umulh x27,x6,x4
adcs x21,x21,x28
umulh x28,x7,x4
adcs x22,x22,x0
umulh x0,x8,x4
adcs x23,x23,x1
umulh x1,x9,x4
adcs x24,x24,x3
umulh x3,x10,x4
adc x25,x25,xzr
ldr x4,[c29,#12*__SIZEOF_POINTER__]
adds x19,x20,x26
mul x26,x11,x17
adcs x20,x21,x27
mul x27,x12,x17
adcs x21,x22,x28
mul x28,x13,x17
adcs x22,x23,x0
mul x0,x14,x17
adcs x23,x24,x1
mul x1,x15,x17
adcs x24,x25,x3
mul x3,x16,x17
adc x25,xzr,xzr
adds x19,x19,x26
umulh x26,x11,x17
adcs x20,x20,x27
umulh x27,x12,x17
adcs x21,x21,x28
mul x4,x4,x19
umulh x28,x13,x17
adcs x22,x22,x0
umulh x0,x14,x17
adcs x23,x23,x1
umulh x1,x15,x17
adcs x24,x24,x3
umulh x3,x16,x17
adc x25,x25,xzr
adds x20,x20,x26
mul x26,x5,x4
adcs x21,x21,x27
mul x27,x6,x4
adcs x22,x22,x28
mul x28,x7,x4
adcs x23,x23,x0
mul x0,x8,x4
adcs x24,x24,x1
mul x1,x9,x4
adc x25,x25,x3
mul x3,x10,x4
ldr x17,[c2,8*2]
adds x19,x19,x26
umulh x26,x5,x4
adcs x20,x20,x27
umulh x27,x6,x4
adcs x21,x21,x28
umulh x28,x7,x4
adcs x22,x22,x0
umulh x0,x8,x4
adcs x23,x23,x1
umulh x1,x9,x4
adcs x24,x24,x3
umulh x3,x10,x4
adc x25,x25,xzr
ldr x4,[c29,#12*__SIZEOF_POINTER__]
adds x19,x20,x26
mul x26,x11,x17
adcs x20,x21,x27
mul x27,x12,x17
adcs x21,x22,x28
mul x28,x13,x17
adcs x22,x23,x0
mul x0,x14,x17
adcs x23,x24,x1
mul x1,x15,x17
adcs x24,x25,x3
mul x3,x16,x17
adc x25,xzr,xzr
adds x19,x19,x26
umulh x26,x11,x17
adcs x20,x20,x27
umulh x27,x12,x17
adcs x21,x21,x28
mul x4,x4,x19
umulh x28,x13,x17
adcs x22,x22,x0
umulh x0,x14,x17
adcs x23,x23,x1
umulh x1,x15,x17
adcs x24,x24,x3
umulh x3,x16,x17
adc x25,x25,xzr
adds x20,x20,x26
mul x26,x5,x4
adcs x21,x21,x27
mul x27,x6,x4
adcs x22,x22,x28
mul x28,x7,x4
adcs x23,x23,x0
mul x0,x8,x4
adcs x24,x24,x1
mul x1,x9,x4
adc x25,x25,x3
mul x3,x10,x4
ldr x17,[c2,8*3]
adds x19,x19,x26
umulh x26,x5,x4
adcs x20,x20,x27
umulh x27,x6,x4
adcs x21,x21,x28
umulh x28,x7,x4
adcs x22,x22,x0
umulh x0,x8,x4
adcs x23,x23,x1
umulh x1,x9,x4
adcs x24,x24,x3
umulh x3,x10,x4
adc x25,x25,xzr
ldr x4,[c29,#12*__SIZEOF_POINTER__]
adds x19,x20,x26
mul x26,x11,x17
adcs x20,x21,x27
mul x27,x12,x17
adcs x21,x22,x28
mul x28,x13,x17
adcs x22,x23,x0
mul x0,x14,x17
adcs x23,x24,x1
mul x1,x15,x17
adcs x24,x25,x3
mul x3,x16,x17
adc x25,xzr,xzr
adds x19,x19,x26
umulh x26,x11,x17
adcs x20,x20,x27
umulh x27,x12,x17
adcs x21,x21,x28
mul x4,x4,x19
umulh x28,x13,x17
adcs x22,x22,x0
umulh x0,x14,x17
adcs x23,x23,x1
umulh x1,x15,x17
adcs x24,x24,x3
umulh x3,x16,x17
adc x25,x25,xzr
adds x20,x20,x26
mul x26,x5,x4
adcs x21,x21,x27
mul x27,x6,x4
adcs x22,x22,x28
mul x28,x7,x4
adcs x23,x23,x0
mul x0,x8,x4
adcs x24,x24,x1
mul x1,x9,x4
adc x25,x25,x3
mul x3,x10,x4
ldr x17,[c2,8*4]
adds x19,x19,x26
umulh x26,x5,x4
adcs x20,x20,x27
umulh x27,x6,x4
adcs x21,x21,x28
umulh x28,x7,x4
adcs x22,x22,x0
umulh x0,x8,x4
adcs x23,x23,x1
umulh x1,x9,x4
adcs x24,x24,x3
umulh x3,x10,x4
adc x25,x25,xzr
ldr x4,[c29,#12*__SIZEOF_POINTER__]
adds x19,x20,x26
mul x26,x11,x17
adcs x20,x21,x27
mul x27,x12,x17
adcs x21,x22,x28
mul x28,x13,x17
adcs x22,x23,x0
mul x0,x14,x17
adcs x23,x24,x1
mul x1,x15,x17
adcs x24,x25,x3
mul x3,x16,x17
adc x25,xzr,xzr
adds x19,x19,x26
umulh x26,x11,x17
adcs x20,x20,x27
umulh x27,x12,x17
adcs x21,x21,x28
mul x4,x4,x19
umulh x28,x13,x17
adcs x22,x22,x0
umulh x0,x14,x17
adcs x23,x23,x1
umulh x1,x15,x17
adcs x24,x24,x3
umulh x3,x16,x17
adc x25,x25,xzr
adds x20,x20,x26
mul x26,x5,x4
adcs x21,x21,x27
mul x27,x6,x4
adcs x22,x22,x28
mul x28,x7,x4
adcs x23,x23,x0
mul x0,x8,x4
adcs x24,x24,x1
mul x1,x9,x4
adc x25,x25,x3
mul x3,x10,x4
ldr x17,[c2,8*5]
adds x19,x19,x26
umulh x26,x5,x4
adcs x20,x20,x27
umulh x27,x6,x4
adcs x21,x21,x28
umulh x28,x7,x4
adcs x22,x22,x0
umulh x0,x8,x4
adcs x23,x23,x1
umulh x1,x9,x4
adcs x24,x24,x3
umulh x3,x10,x4
adc x25,x25,xzr
ldr x4,[c29,#12*__SIZEOF_POINTER__]
adds x19,x20,x26
mul x26,x11,x17
adcs x20,x21,x27
mul x27,x12,x17
adcs x21,x22,x28
mul x28,x13,x17
adcs x22,x23,x0
mul x0,x14,x17
adcs x23,x24,x1
mul x1,x15,x17
adcs x24,x25,x3
mul x3,x16,x17
adc x25,xzr,xzr
adds x19,x19,x26
umulh x26,x11,x17
adcs x20,x20,x27
umulh x27,x12,x17
adcs x21,x21,x28
mul x4,x4,x19
umulh x28,x13,x17
adcs x22,x22,x0
umulh x0,x14,x17
adcs x23,x23,x1
umulh x1,x15,x17
adcs x24,x24,x3
umulh x3,x16,x17
adc x25,x25,xzr
adds x20,x20,x26
mul x26,x5,x4
adcs x21,x21,x27
mul x27,x6,x4
adcs x22,x22,x28
mul x28,x7,x4
adcs x23,x23,x0
mul x0,x8,x4
adcs x24,x24,x1
mul x1,x9,x4
adc x25,x25,x3
mul x3,x10,x4
adds x19,x19,x26
umulh x26,x5,x4
adcs x20,x20,x27
umulh x27,x6,x4
adcs x21,x21,x28
umulh x28,x7,x4
adcs x22,x22,x0
umulh x0,x8,x4
adcs x23,x23,x1
umulh x1,x9,x4
adcs x24,x24,x3
umulh x3,x10,x4
adc x25,x25,xzr
ldp c4,c2,[c29,#12*__SIZEOF_POINTER__] // pull r_ptr
adds x11,x20,x26
adcs x12,x21,x27
adcs x13,x22,x28
adcs x14,x23,x0
adcs x15,x24,x1
adcs x16,x25,x3
ret
.size __mul_mont_383_nonred,.-__mul_mont_383_nonred
.globl sgn0_pty_mont_384
.hidden sgn0_pty_mont_384
.type sgn0_pty_mont_384,%function
.align 5
sgn0_pty_mont_384:
hint #PACI_HINT
stp c29,c30,[csp,#-16*__SIZEOF_POINTER__]!
add c29,csp,#0
stp c19,c20,[csp,#2*__SIZEOF_POINTER__]
stp c21,c22,[csp,#4*__SIZEOF_POINTER__]
stp c23,c24,[csp,#6*__SIZEOF_POINTER__]
stp c25,c26,[csp,#8*__SIZEOF_POINTER__]
stp c27,c28,[csp,#10*__SIZEOF_POINTER__]
mov x4,x2
ldp x5,x6,[c1]
ldp x7,x8,[c1,#16]
ldp x9,x10,[c1,#32]
mov c1,c0
bl __mul_by_1_mont_384
ldr c30,[c29,#__SIZEOF_POINTER__]
and x0,x11,#1
adds x11,x11,x11
adcs x12,x12,x12
adcs x13,x13,x13
adcs x14,x14,x14
adcs x15,x15,x15
adcs x16,x16,x16
adc x17,xzr,xzr
subs x11,x11,x5
sbcs x12,x12,x6
sbcs x13,x13,x7
sbcs x14,x14,x8
sbcs x15,x15,x9
sbcs x16,x16,x10
sbc x17,x17,xzr
mvn x17,x17
and x17,x17,#2
orr x0,x0,x17
ldp c19,c20,[c29,#2*__SIZEOF_POINTER__]
ldp c21,c22,[c29,#4*__SIZEOF_POINTER__]
ldp c23,c24,[c29,#6*__SIZEOF_POINTER__]
ldp c25,c26,[c29,#8*__SIZEOF_POINTER__]
ldp c27,c28,[c29,#10*__SIZEOF_POINTER__]
ldr c29,[csp],#16*__SIZEOF_POINTER__
hint #AUTI_HINT
ret
.size sgn0_pty_mont_384,.-sgn0_pty_mont_384
.globl sgn0_pty_mont_384x
.hidden sgn0_pty_mont_384x
.type sgn0_pty_mont_384x,%function
.align 5
sgn0_pty_mont_384x:
hint #PACI_HINT
stp c29,c30,[csp,#-16*__SIZEOF_POINTER__]!
add c29,csp,#0
stp c19,c20,[csp,#2*__SIZEOF_POINTER__]
stp c21,c22,[csp,#4*__SIZEOF_POINTER__]
stp c23,c24,[csp,#6*__SIZEOF_POINTER__]
stp c25,c26,[csp,#8*__SIZEOF_POINTER__]
stp c27,c28,[csp,#10*__SIZEOF_POINTER__]
mov x4,x2
ldp x5,x6,[c1]
ldp x7,x8,[c1,#16]
ldp x9,x10,[c1,#32]
mov c1,c0
bl __mul_by_1_mont_384
add c1,c1,#48
and x2,x11,#1
orr x3,x11,x12
adds x11,x11,x11
orr x3,x3,x13
adcs x12,x12,x12
orr x3,x3,x14
adcs x13,x13,x13
orr x3,x3,x15
adcs x14,x14,x14
orr x3,x3,x16
adcs x15,x15,x15
adcs x16,x16,x16
adc x17,xzr,xzr
subs x11,x11,x5
sbcs x12,x12,x6
sbcs x13,x13,x7
sbcs x14,x14,x8
sbcs x15,x15,x9
sbcs x16,x16,x10
sbc x17,x17,xzr
mvn x17,x17
and x17,x17,#2
orr x2,x2,x17
bl __mul_by_1_mont_384
ldr c30,[c29,#__SIZEOF_POINTER__]
and x0,x11,#1
orr x1,x11,x12
adds x11,x11,x11
orr x1,x1,x13
adcs x12,x12,x12
orr x1,x1,x14
adcs x13,x13,x13
orr x1,x1,x15
adcs x14,x14,x14
orr x1,x1,x16
adcs x15,x15,x15
adcs x16,x16,x16
adc x17,xzr,xzr
subs x11,x11,x5
sbcs x12,x12,x6
sbcs x13,x13,x7
sbcs x14,x14,x8
sbcs x15,x15,x9
sbcs x16,x16,x10
sbc x17,x17,xzr
mvn x17,x17
and x17,x17,#2
orr x0,x0,x17
cmp x3,#0
csel x3,x0,x2,eq // a->re==0? prty(a->im) : prty(a->re)
cmp x1,#0
csel x1,x0,x2,ne // a->im!=0? sgn0(a->im) : sgn0(a->re)
and x3,x3,#1
and x1,x1,#2
orr x0,x1,x3 // pack sign and parity
ldp c19,c20,[c29,#2*__SIZEOF_POINTER__]
ldp c21,c22,[c29,#4*__SIZEOF_POINTER__]
ldp c23,c24,[c29,#6*__SIZEOF_POINTER__]
ldp c25,c26,[c29,#8*__SIZEOF_POINTER__]
ldp c27,c28,[c29,#10*__SIZEOF_POINTER__]
ldr c29,[csp],#16*__SIZEOF_POINTER__
hint #AUTI_HINT
ret
.size sgn0_pty_mont_384x,.-sgn0_pty_mont_384x
#if defined(__ARM_FEATURE_BTI_DEFAULT) || defined(__ARM_FEATURE_PAC_DEFAULT)
.section .note.GNU-stack,"",@progbits
.section .note.gnu.property,"a",@note
.long 4,2f-1f,5
.byte 0x47,0x4E,0x55,0
1: .long 0xc0000000,4,3
.align 3
2:
#endif