X-Git-Url: http://git.megacz.com/?a=blobdiff_plain;f=ghc%2Frts%2Fgmp%2Fmpn%2Fa29k%2Faddmul_1.s;fp=ghc%2Frts%2Fgmp%2Fmpn%2Fa29k%2Faddmul_1.s;h=8c0ec96ce5d47b1c6b968f414caa92a430ac7f82;hb=a343265d8f6bf27a84bb16f68f9242b346dc5095;hp=0000000000000000000000000000000000000000;hpb=fb716c88cdef841c5c6c3881f1d63637450b219d;p=ghc-hetmet.git

diff --git a/ghc/rts/gmp/mpn/a29k/addmul_1.s b/ghc/rts/gmp/mpn/a29k/addmul_1.s
new file mode 100644
index 0000000..8c0ec96
--- /dev/null
+++ b/ghc/rts/gmp/mpn/a29k/addmul_1.s
@@ -0,0 +1,113 @@
+; 29000 __mpn_addmul_1 -- Multiply a limb vector with a single limb and
+; add the product to a second limb vector.
+
+; Copyright (C) 1992, 1994 Free Software Foundation, Inc.
+
+; This file is part of the GNU MP Library.
+
+; The GNU MP Library is free software; you can redistribute it and/or modify
+; it under the terms of the GNU Library General Public License as published by
+; the Free Software Foundation; either version 2 of the License, or (at your
+; option) any later version.
+
+; The GNU MP Library is distributed in the hope that it will be useful, but
+; WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY
+; or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU Library General Public
+; License for more details.
+
+; You should have received a copy of the GNU Library General Public License
+; along with the GNU MP Library; see the file COPYING.LIB.  If not, write to
+; the Free Software Foundation, Inc., 59 Temple Place - Suite 330, Boston,
+; MA 02111-1307, USA.
+
+
+; INPUT PARAMETERS
+; res_ptr	lr2
+; s1_ptr	lr3
+; size		lr4
+; s2_limb	lr5
+
+	.cputype 29050
+	.sect .lit,lit
+	.text
+	.align	4
+	.global	___mpn_addmul_1
+	.word	0x60000
+___mpn_addmul_1:
+	sub	lr4,lr4,8
+	jmpt	lr4,Ltail
+	 const	gr120,0			; init cylimb reg
+
+	srl	gr117,lr4,3		; divide by 8
+	sub	gr117,gr117,1		; count for jmpfdec
+
+Loop:	mtsrim	cr,(8-1)
+	loadm	0,0,gr96,lr3
+	add	lr3,lr3,32
+
+	multiplu gr104,gr96,lr5
+	multmu	 gr96,gr96,lr5
+	multiplu gr105,gr97,lr5
+	multmu	 gr97,gr97,lr5
+	multiplu gr106,gr98,lr5
+	multmu	 gr98,gr98,lr5
+	multiplu gr107,gr99,lr5
+	multmu	 gr99,gr99,lr5
+	multiplu gr108,gr100,lr5
+	multmu	 gr100,gr100,lr5
+	multiplu gr109,gr101,lr5
+	multmu	 gr101,gr101,lr5
+	multiplu gr110,gr102,lr5
+	multmu	 gr102,gr102,lr5
+	multiplu gr111,gr103,lr5
+	multmu	 gr103,gr103,lr5
+
+	add	gr104,gr104,gr120
+	addc	gr105,gr105,gr96
+	addc	gr106,gr106,gr97
+	addc	gr107,gr107,gr98
+	addc	gr108,gr108,gr99
+	addc	gr109,gr109,gr100
+	addc	gr110,gr110,gr101
+	addc	gr111,gr111,gr102
+	addc	gr120,gr103,0
+
+	mtsrim	cr,(8-1)
+	loadm	0,0,gr96,lr2
+
+	add	gr104,gr96,gr104
+	addc	gr105,gr97,gr105
+	addc	gr106,gr98,gr106
+	addc	gr107,gr99,gr107
+	addc	gr108,gr100,gr108
+	addc	gr109,gr101,gr109
+	addc	gr110,gr102,gr110
+	addc	gr111,gr103,gr111
+	addc	gr120,gr120,0
+
+	mtsrim	cr,(8-1)
+	storem	0,0,gr104,lr2
+	jmpfdec	gr117,Loop
+	 add	lr2,lr2,32
+
+Ltail:	and	lr4,lr4,(8-1)
+	sub	gr118,lr4,1		; count for CR
+	jmpt	gr118,Lend
+	 sub	lr4,lr4,2
+	sub	lr2,lr2,4		; offset res_ptr by one limb
+
+Loop2:	load	0,0,gr116,lr3
+	add	lr3,lr3,4
+	multiplu gr117,gr116,lr5
+	multmu	gr118,gr116,lr5
+	add	lr2,lr2,4
+	load	0,0,gr119,lr2
+	add	gr117,gr117,gr120
+	addc	gr118,gr118,0
+	add	gr117,gr117,gr119
+	store	0,0,gr117,lr2
+	jmpfdec	lr4,Loop2
+	 addc	gr120,gr118,0
+
+Lend:	jmpi	lr0
+	 or	gr96,gr120,0		; copy