Pentium optimizations for DES (BIG)

[i.am.not.a.number at best.com]

here is Mikkelson's macro, with a few cycles shaved.
on my machine there is a small but measurable improvement.


DesRound	macro RoundNo,reg1,reg2

		mov	eax,		DWORD PTR (RoundNo*8) [ebp]
		xor	ebx,		ebx

		mov	edx,		DWORD PTR (RoundNo*8+4) [ebp]

		xor	eax,		reg1
		xor	edx,		reg1

		and	eax,		0fcfcfcfch
		mov	bl,		al
		and	edx,		0cfcfcfcfh
		mov	cl,		ah
		ror	edx,		4
		xor	reg2,		DWORD PTR _des_SPtrans[ebx]
		mov	bl,		dl

		xor	reg2,		DWORD PTR _des_SPtrans[0200h+ecx]
		mov	cl,			dh
		shr	eax,		16

		xor	reg2,		DWORD PTR _des_SPtrans[0100h+ebx]

		mov	bl,		ah
		shr	edx,		16

		xor	reg2,		DWORD PTR _des_SPtrans[0300h+ecx]

		mov	cl,		dh
		and	eax,		0FFh
		and	edx,		0FFh

		xor	reg2,		DWORD PTR _des_SPtrans[0600h+ebx];ebx
		mov				ebx,DWORD PTR _des_SPtrans[0700h+ecx]
		xor	reg2,		ebx
		mov				ebx,DWORD PTR _des_SPtrans[0400h+eax]
		xor	reg2,		ebx
		mov				ebx,DWORD PTR _des_SPtrans[0500h+edx]
		xor	reg2,		ebx

		endm

At 10:19 AM 1/14/97 -6, Peter Trei wrote:
>I hope you'll look at Svend Olaf Mikkleson's
>latest DES round replacement for libdes. He
>seems to have gotten the round down to 18
>clock cycles. I have not yet had a chance
>to try it myself.
>
>see: http://inet.uni-c.dk/~svolaf/des.htm
>
>Peter Trei
>trei at process.com
>
>Peter Trei
>Senior Software Engineer
>Purveyor Development Team                                
>Process Software Corporation
>http://www.process.com
>trei at process.com
>
>