Another possibility that could be adapted to fit:

use warnings;
use strict;

my $text = "I am a GIRL, a Real GIRL. A test WITH Multiple conDITions 
+AND other tests.";

print map{"$_ "}
      map{$_ = lc($_) unless (($_ eq uc $_) and length $_ > 1 ); $_ }
      map{split ' ',$_}$text;
      
__END__
Prints: 
i am a GIRL, a real GIRL. a test WITH multiple conditions AND other te
+sts.
[download]

Converting between upper and lower case ASCII is just flipping a bit (fast). No regex is needed here. length() is also very fast. $_ eq uc $_ should be very fast. This map,map,map stuff is slow, but speeding that up is left to the reader.

Update: Here is one possibility of many:

use warnings;
use strict;

my $text = "I am a GIRL, a Real GIRL. A test WITH Multiple conDITions 
+AND other tests.";

print "".onlyAllcaps ($text);


sub onlyAllcaps
{
   my $input = shift;
   
   my @words = split ' ',$text;
   foreach my $word (@words)
   {
      $word = lc($word) unless (($word eq uc $word) and length $word> 
+1 )
   }

   my $output = join " ",@words,"\n";
   return $output;
}

__END__
Prints:
i am a GIRL, a real GIRL. a test WITH multiple conditions AND other te
+sts.
[download]