sub BODY_00_xx()

in crypto/sha512-armv8.pl [106:193]

• 78 lines of code
• 8 McCabe index (conditional complexity)

sub BODY_00_xx {
my ($i,$a,$b,$c,$d,$e,$f,$g,$h)=@_;
my $j=($i+1)&15;
my ($T0,$T1,$T2)=(@X[($i-8)&15],@X[($i-9)&15],@X[($i-10)&15]);
   $T0=@X[$i+3] if ($i<11);

$code.=<<___	if ($i<16);
#ifndef	__AARCH64EB__
	rev	@X[$i],@X[$i]			// $i
#endif
___
$code.=<<___	if ($i<13 && ($i&1));
	ldp	@X[$i+1],@X[$i+2],[$inp],#2*$SZ
___
$code.=<<___	if ($i==13);
	ldp	@X[14],@X[15],[$inp]
___
$code.=<<___	if ($i>=14);
	ldr	@X[($i-11)&15],[sp,#`$SZ*(($i-11)%4)`]
___
$code.=<<___	if ($i>0 && $i<16);
	add	$a,$a,$t1			// h+=Sigma0(a)
___
$code.=<<___	if ($i>=11);
	str	@X[($i-8)&15],[sp,#`$SZ*(($i-8)%4)`]
___
# While ARMv8 specifies merged rotate-n-logical operation such as
# 'eor x,y,z,ror#n', it was found to negatively affect performance
# on Apple A7. The reason seems to be that it requires even 'y' to
# be available earlier. This means that such merged instruction is
# not necessarily best choice on critical path... On the other hand
# Cortex-A5x handles merged instructions much better than disjoint
# rotate and logical... See (**) footnote above.
$code.=<<___	if ($i<15);
	ror	$t0,$e,#$Sigma1[0]
	add	$h,$h,$t2			// h+=K[i]
	eor	$T0,$e,$e,ror#`$Sigma1[2]-$Sigma1[1]`
	and	$t1,$f,$e
	bic	$t2,$g,$e
	add	$h,$h,@X[$i&15]			// h+=X[i]
	orr	$t1,$t1,$t2			// Ch(e,f,g)
	eor	$t2,$a,$b			// a^b, b^c in next round
	eor	$t0,$t0,$T0,ror#$Sigma1[1]	// Sigma1(e)
	ror	$T0,$a,#$Sigma0[0]
	add	$h,$h,$t1			// h+=Ch(e,f,g)
	eor	$t1,$a,$a,ror#`$Sigma0[2]-$Sigma0[1]`
	add	$h,$h,$t0			// h+=Sigma1(e)
	and	$t3,$t3,$t2			// (b^c)&=(a^b)
	add	$d,$d,$h			// d+=h
	eor	$t3,$t3,$b			// Maj(a,b,c)
	eor	$t1,$T0,$t1,ror#$Sigma0[1]	// Sigma0(a)
	add	$h,$h,$t3			// h+=Maj(a,b,c)
	ldr	$t3,[$Ktbl],#$SZ		// *K++, $t2 in next round
	//add	$h,$h,$t1			// h+=Sigma0(a)
___
$code.=<<___	if ($i>=15);
	ror	$t0,$e,#$Sigma1[0]
	add	$h,$h,$t2			// h+=K[i]
	ror	$T1,@X[($j+1)&15],#$sigma0[0]
	and	$t1,$f,$e
	ror	$T2,@X[($j+14)&15],#$sigma1[0]
	bic	$t2,$g,$e
	ror	$T0,$a,#$Sigma0[0]
	add	$h,$h,@X[$i&15]			// h+=X[i]
	eor	$t0,$t0,$e,ror#$Sigma1[1]
	eor	$T1,$T1,@X[($j+1)&15],ror#$sigma0[1]
	orr	$t1,$t1,$t2			// Ch(e,f,g)
	eor	$t2,$a,$b			// a^b, b^c in next round
	eor	$t0,$t0,$e,ror#$Sigma1[2]	// Sigma1(e)
	eor	$T0,$T0,$a,ror#$Sigma0[1]
	add	$h,$h,$t1			// h+=Ch(e,f,g)
	and	$t3,$t3,$t2			// (b^c)&=(a^b)
	eor	$T2,$T2,@X[($j+14)&15],ror#$sigma1[1]
	eor	$T1,$T1,@X[($j+1)&15],lsr#$sigma0[2]	// sigma0(X[i+1])
	add	$h,$h,$t0			// h+=Sigma1(e)
	eor	$t3,$t3,$b			// Maj(a,b,c)
	eor	$t1,$T0,$a,ror#$Sigma0[2]	// Sigma0(a)
	eor	$T2,$T2,@X[($j+14)&15],lsr#$sigma1[2]	// sigma1(X[i+14])
	add	@X[$j],@X[$j],@X[($j+9)&15]
	add	$d,$d,$h			// d+=h
	add	$h,$h,$t3			// h+=Maj(a,b,c)
	ldr	$t3,[$Ktbl],#$SZ		// *K++, $t2 in next round
	add	@X[$j],@X[$j],$T1
	add	$h,$h,$t1			// h+=Sigma0(a)
	add	@X[$j],@X[$j],$T2
___
	($t2,$t3)=($t3,$t2);
}