mirror/openssl
2
0
Fork 0
mirror of https://github.com/openssl/openssl.git synced 2024-11-21 01:15:20 +08:00
Code Issues Packages Projects Releases Wiki Activity

+20% performance improvement of P4-specific RC4_CHAR loop.

Browse Source
This commit is contained in:
Andy Polyakov 2005-05-15 22:43:00 +00:00
parent 81a86fcf17
commit 804515425a
1 changed files with 6 additions and 5 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

11
crypto/rc4/asm/rc4-586.pl
View File

@ -200,22 +200,23 @@ sub RC4
&lea ($ty,&DWP(0,$in,$ty));
&mov (&swtmp(2),$ty);
&movz ($tx,&BP(0,$d,$x));
# strangely enough unrolled loop performs over 20% slower...
&set_label("RC4_CHAR_loop");
&movz ($tx,&BP(0,$d,$x));
&add (&LB($y),&LB($tx));
&movz ($ty,&BP(0,$d,$y));
&movb (&BP(0,$d,$y),&LB($tx));
&movb (&BP(0,$d,$x),&LB($ty));
&add (&LB($ty),&LB($tx));
&movz ($ty,&BP(0,$d,$ty));
&add (&LB($x),1);
&xorb (&LB($ty),&BP(0,$in));
&movb (&BP(0,$out),&LB($ty));
&inc (&LB($x));
&inc ($in);
&inc ($out);
&lea ($in,&BP(1,$in));
&movz ($tx,&BP(0,$d,$x));
&cmp ($in,&swtmp(2));
&movb (&BP(0,$out),&LB($ty));
&lea ($out,&BP(1,$out));
&jb (&label("RC4_CHAR_loop"));
&set_label("finished");