===================================================================
RCS file: /home/cvs/OpenXM_contrib/gmp/mpn/x86/pentium/Attic/mul_1.asm,v
retrieving revision 1.1.1.1
retrieving revision 1.1.1.2
diff -u -p -r1.1.1.1 -r1.1.1.2
--- OpenXM_contrib/gmp/mpn/x86/pentium/Attic/mul_1.asm	2000/09/09 14:12:44	1.1.1.1
+++ OpenXM_contrib/gmp/mpn/x86/pentium/Attic/mul_1.asm	2003/08/25 16:06:30	1.1.1.2
@@ -1,8 +1,6 @@
 dnl  Intel Pentium mpn_mul_1 -- mpn by limb multiplication.
-dnl
-dnl  P5: 13.0 cycles/limb
 
-dnl  Copyright (C) 1992, 1994, 1996, 1999, 2000 Free Software Foundation,
+dnl  Copyright 1992, 1994, 1996, 1999, 2000, 2002 Free Software Foundation,
 dnl  Inc.
 dnl 
 dnl  This file is part of the GNU MP Library.
@@ -22,58 +20,149 @@ dnl  License along with the GNU MP Library; see the fi
 dnl  not, write to the Free Software Foundation, Inc., 59 Temple Place -
 dnl  Suite 330, Boston, MA 02111-1307, USA. */
 
-
 include(`../config.m4')
 
 
+C P5: 12.0 cycles/limb
+
+
 C mp_limb_t mpn_mul_1 (mp_ptr dst, mp_srcptr src, mp_size_t size,
 C                      mp_limb_t multiplier);
+C mp_limb_t mpn_mul_1c (mp_ptr dst, mp_srcptr src, mp_size_t size,
+C                       mp_limb_t multiplier, mp_limb_t carry);
+C
 
+defframe(PARAM_CARRY,     20)
 defframe(PARAM_MULTIPLIER,16)
 defframe(PARAM_SIZE,      12)
 defframe(PARAM_SRC,       8)
 defframe(PARAM_DST,       4)
 
-	.text
+	TEXT
 	ALIGN(8)
+PROLOGUE(mpn_mul_1c)
+deflit(`FRAME',0)
+
+	movl	PARAM_CARRY, %ecx
+	pushl	%esi		FRAME_pushl()
+
+	jmp	L(start_1c)
+
+EPILOGUE()
+
+
+	ALIGN(8)
 PROLOGUE(mpn_mul_1)
+deflit(`FRAME',0)
 
-	pushl	%edi
-	pushl	%esi
-	pushl	%ebx
-	pushl	%ebp
-deflit(`FRAME',16)
+	xorl	%ecx, %ecx
+	pushl	%esi		FRAME_pushl()
 
-	movl	PARAM_DST, %edi
+L(start_1c):
 	movl	PARAM_SRC, %esi
-	movl	PARAM_SIZE, %ecx
-	movl	PARAM_MULTIPLIER, %ebp
+	movl	PARAM_SIZE, %eax
 
-	leal	(%edi,%ecx,4), %edi
-	leal	(%esi,%ecx,4), %esi
-	negl	%ecx
-	xorl	%ebx, %ebx
-	ALIGN(8)
+	shrl	%eax
+	jnz	L(two_or_more)
 
-L(oop):	adcl	$0, %ebx
-	movl	(%esi,%ecx,4), %eax
 
-	mull	%ebp
+	C one limb only
 
-	addl	%eax, %ebx
+	movl	(%esi), %eax
 
-	movl	%ebx, (%edi,%ecx,4)
-	incl	%ecx
+	mull	PARAM_MULTIPLIER
 
-	movl	%edx, %ebx
-	jnz	L(oop)
+	addl	%eax, %ecx
+	movl	PARAM_DST, %eax
 
-	adcl	$0, %ebx
-	movl	%ebx, %eax
+	adcl	$0, %edx
+	popl	%esi
+
+	movl	%ecx, (%eax)
+	movl	%edx, %eax
+
+	ret
+
+
+L(two_or_more):
+	C eax	size/2
+	C ebx
+	C ecx	carry
+	C edx
+	C esi	src
+	C edi
+	C ebp
+
+	pushl	%edi		FRAME_pushl()
+	pushl	%ebx		FRAME_pushl()
+
+	movl	PARAM_DST, %edi
+	leal	-1(%eax), %ebx		C size/2-1
+
+	notl	%ebx			C -size, preserve carry
+
+	leal	(%esi,%eax,8), %esi	C src end
+	leal	(%edi,%eax,8), %edi	C dst end
+
+	pushl	%ebp		FRAME_pushl()
+	jnc	L(top)
+
+
+	C size was odd, process one limb separately
+
+	movl	(%esi,%ebx,8), %eax
+	addl	$4, %esi
+
+	mull	PARAM_MULTIPLIER
+
+	addl	%ecx, %eax
+	movl	%edx, %ecx
+
+	movl	%eax, (%edi,%ebx,8)
+	leal	4(%edi), %edi
+
+
+L(top):
+	C eax
+	C ebx	counter, negative
+	C ecx	carry
+	C edx
+	C esi	src end
+	C edi	dst end
+	C ebp
+
+	adcl	$0, %ecx
+	movl	(%esi,%ebx,8), %eax
+
+	mull	PARAM_MULTIPLIER
+
+	movl	%edx, %ebp
+	addl	%eax, %ecx
+
+	adcl	$0, %ebp
+	movl	4(%esi,%ebx,8), %eax
+
+	mull	PARAM_MULTIPLIER
+
+	movl	%ecx, (%edi,%ebx,8)
+	addl	%ebp, %eax
+
+	movl	%eax, 4(%edi,%ebx,8)
+	incl	%ebx
+
+	movl	%edx, %ecx
+	jnz	L(top)
+
+
+	adcl	$0, %ecx
 	popl	%ebp
+
+	movl	%ecx, %eax
 	popl	%ebx
-	popl	%esi
+
 	popl	%edi
+	popl	%esi
+
 	ret
 
 EPILOGUE()