# P4 +85%(!) +45%
#
# As you can see Pentium came out as looser:-( Yet I reckoned that
-# improvement on P4 outweights the loss and incorporate this
+# improvement on P4 outweighs the loss and incorporate this
# re-tuned code to 0.9.7 and later.
# ----------------------------------------------------------------
-# <appro@fy.chalmers.se>
# August 2009.
#
$output=pop;
open STDOUT,">$output";
-&asm_init($ARGV[0],"sha1-586.pl",$ARGV[$#ARGV] eq "386");
+&asm_init($ARGV[0],$ARGV[$#ARGV] eq "386");
$xmm=$ymm=0;
for (@ARGV) { $xmm=1 if (/-DOPENSSL_IA32_SSE2/); }
`ml 2>&1` =~ /Version ([0-9]+)\./ &&
$1>=10); # first version supporting AVX
-$ymm=1 if ($xmm && !$ymm && `$ENV{CC} -v 2>&1` =~ /(^clang version|based on LLVM) ([3-9]\.[0-9]+)/ &&
+$ymm=1 if ($xmm && !$ymm && `$ENV{CC} -v 2>&1` =~ /((?:^clang|LLVM) version|based on LLVM) ([3-9]\.[0-9]+)/ &&
$2>=3.0); # first version supporting AVX
$shaext=$xmm; ### set to zero if compiling for 1.0.1
# being implemented in SSSE3). Once 8 quadruples or 32 elements are
# collected, it switches to routine proposed by Max Locktyukhin.
#
-# Calculations inevitably require temporary reqisters, and there are
+# Calculations inevitably require temporary registers, and there are
# no %xmm registers left to spare. For this reason part of the ring
# buffer, X[2..4] to be specific, is offloaded to 3 quadriples ring
# buffer on the stack. Keep in mind that X[2] is alias X[-6], X[3] -
&jmp (&label("loop"));
######################################################################
-# SSE instruction sequence is first broken to groups of indepentent
+# SSE instruction sequence is first broken to groups of independent
# instructions, independent in respect to their inputs and shifter
# (not all architectures have more than one). Then IALU instructions
# are "knitted in" between the SSE groups. Distance is maintained for
#
# Temporary registers usage. X[2] is volatile at the entry and at the
# end is restored from backtrace ring buffer. X[3] is expected to
-# contain current K_XX_XX constant and is used to caclulate X[-1]+K
+# contain current K_XX_XX constant and is used to calculate X[-1]+K
# from previous round, it becomes volatile the moment the value is
# saved to stack for transfer to IALU. X[4] becomes volatile whenever
# X[-4] is accumulated and offloaded to backtrace ring buffer, at the
# end it is loaded with next K_XX_XX [which becomes X[3] in next
# round]...
#
-sub Xupdate_ssse3_16_31() # recall that $Xi starts wtih 4
+sub Xupdate_ssse3_16_31() # recall that $Xi starts with 4
{ use integer;
my $body = shift;
my @insns = (&$body,&$body,&$body,&$body); # 40 instructions
&and (@T[0],@T[1]);
&jmp (&label("loop"));
-sub Xupdate_avx_16_31() # recall that $Xi starts wtih 4
+sub Xupdate_avx_16_31() # recall that $Xi starts with 4
{ use integer;
my $body = shift;
my @insns = (&$body,&$body,&$body,&$body); # 40 instructions