Bug-fix in CBC encrypt tail processing and commentary section update.

# forms are granted according to the OpenSSL license.

# ====================================================================

#

# Version 3.0.

# Version 3.1.

#

# You might fail to appreciate this module performance from the first

# try. If compared to "vanilla" linux-ia32-icc target, i.e. considered

# Instruction Level Parallelism, and it indeed resulted in up to 15%

# better performance on most recent µ-archs...

#

# Current ECB performance numbers for 128-bit key in cycles per byte

# [measure commonly used by AES benchmarkers] are:

# Current ECB performance numbers for 128-bit key in CPU cycles per

# processed byte [measure commonly used by AES benchmarkers] are:

#

#		small footprint		fully unrolled

# P4[-3]	23[24]			22[23]

# AMD K8	19			18

# PIII		26(*)			23

# PIII		26			23

# Pentium	63(*)			52

#

# (*)	Performance difference between small footprint code and fully

#	unrolled in more commonly used CBC mode is not as big, 7% for

#	PIII and 15% for Pentium, which I consider tolerable.

#	unrolled in more commonly used CBC mode is not as big, 4% for

#	for Pentium. PIII's ~13% difference [in both cases in 3rd

#	version] is considered tolerable...

#

# Third version adds AES_cbc_encrypt implementation, which resulted in

# up to 40% performance imrovement of CBC benchmark results [on most

# recent -archs]. CBC performance is virtually as good as ECB now and

# sometimes even better, because function prologues and epilogues are

# up to 40% performance imrovement of CBC benchmark results. 40% was

# observed on P4 core, where "overall" imrovement coefficient, i.e. if

# compared to PIC generated by GCC and in CBC mode, was observed to be

# as large as 4x:-) CBC performance is virtually identical to ECB now

# and on some platforms even better, e.g. 56 "small" cycles/byte on

# senior Pentium, because certain function prologues and epilogues are

# effectively taken out of the loop...

push(@INC,"perlasm","../../perlasm");

$small_footprint=1;	# $small_footprint=1 code is ~5% slower [on

			# recent µ-archs], but ~5 times smaller!

			# I favor compact code, because it minimizes

			# cache contention...

			# I favor compact code to minimize cache

			# contention and in hope to "collect" 5% back

			# in real-life applications...

$vertical_spin=0;	# shift "verticaly" defaults to 0, because of

			# its proof-of-concept status...

	&push	($key eq "edi" ? $key : "");	# push ivp

	&pushf	();

	&mov	($key,&wparam(1));		# load out

	&xor	($s0,$s0);

	&mov	(&DWP(0,$key),$s0);		# zero output

	&mov	(&DWP(4,$key),$s0);

	&mov	(&DWP(8,$key),$s0);

	&mov	(&DWP(12,$key),$s0);

	&mov	($s1,16);

	&sub	($s1,$s2);

	&cmp	($key,$acc);			# compare with inp

	&je	(&label("enc_in_place"));

	&data_word(0x90A4F3FC);	# cld; rep movsb; nop	# copy input

	&jmp	(&label("enc_skip_in_place"));

    &set_label("enc_in_place");

	&lea	($key,&DWP(0,$key,$s2));

    &set_label("enc_skip_in_place");

	&mov	($s2,$s1);

	&xor	($s0,$s0);

	&data_word(0x90AAF3FC);	# cld; rep stosb; nop	# zero tail

	&popf	();

	&pop	($key);				# pop ivp

	&pushf	();

	&data_word(0x90A4F3FC);	# cld; rep movsb; nop	# restore tail

	&popf	();

    &align	(4);

    &set_label("dec_out");

    &stack_pop(5);

&function_end("AES_cbc_encrypt");