added assembler stuff for hppa

2 files changed, 160 insertions, 0 deletions

diff --git a/mpi/pa7100/distfiles b/mpi/pa7100/distfiles
new file mode 100644
index 00000000..d468fa20
--- /dev/null
+++ b/mpi/pa7100/distfiles
@@ -0,0 +1,2 @@
+mpih-shift.S
+
diff --git a/mpi/pa7100/mpih-shift.S b/mpi/pa7100/mpih-shift.S
new file mode 100644
index 00000000..daff03f3
--- /dev/null
+++ b/mpi/pa7100/mpih-shift.S
@@ -0,0 +1,158 @@
+/* hppa   rshift, lshift
+ *	  optimized for the PA7100, where is runs at 3.25 cycles/limb
+ *	Copyright (C) 1992, 1994 Free Software Foundation, Inc.
+ *	Copyright (c) 1997 by Werner Koch (dd9jn)
+ *
+ * This file is part of G10.
+ *
+ * G10 is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ *
+ * G10 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 General Public License for more details.
+ *
+ * You should have received a copy of the GNU General Public License
+ * along with this program; if not, write to the Free Software
+ * Foundation, Inc., 59 Temple Place - Suite 330, Boston, MA 02111-1307, USA
+ *
+ * Note: This code is heavily based on the GNU MP Library.
+ *	 Actually it's the same code with only minor changes in the
+ *	 way the data is stored; this is to support the abstraction
+ *	 of an optional secure memory allocation which may be used
+ *	 to avoid revealing of sensitive data due to paging etc.
+ *	 The GNU MP Library itself is published under the LGPL;
+ *	 however I decided to publish this code under the plain GPL.
+ */
+
+
+
+/*******************
+ * mpi_limb_t
+ * mpihelp_lshift( mpi_ptr_t wp,	(gr26)
+ *		   mpi_ptr_t up,	(gr25)
+ *		   mpi_size_t usize,	(gr24)
+ *		   unsigned cnt)	(gr23)
+ */
+
+	.code
+	.export 	mpihelp_lshift
+mpihelp_lshift
+	.proc
+	.callinfo	frame=64,no_calls
+	.entry
+
+	sh2add		%r24,%r25,%r25
+	sh2add		%r24,%r26,%r26
+	ldws,mb 	-4(0,%r25),%r22
+	subi		32,%r23,%r1
+	mtsar		%r1
+	addib,= 	-1,%r24,L$0004
+	vshd		%r0,%r22,%r28		; compute carry out limb
+	ldws,mb 	-4(0,%r25),%r29
+	addib,<=	-5,%r24,L$rest
+	vshd		%r22,%r29,%r20
+
+L$loop	ldws,mb 	-4(0,%r25),%r22
+	stws,mb 	%r20,-4(0,%r26)
+	vshd		%r29,%r22,%r20
+	ldws,mb 	-4(0,%r25),%r29
+	stws,mb 	%r20,-4(0,%r26)
+	vshd		%r22,%r29,%r20
+	ldws,mb 	-4(0,%r25),%r22
+	stws,mb 	%r20,-4(0,%r26)
+	vshd		%r29,%r22,%r20
+	ldws,mb 	-4(0,%r25),%r29
+	stws,mb 	%r20,-4(0,%r26)
+	addib,> 	-4,%r24,L$loop
+	vshd		%r22,%r29,%r20
+
+L$rest	addib,= 	4,%r24,L$end1
+	nop
+L$eloop ldws,mb 	-4(0,%r25),%r22
+	stws,mb 	%r20,-4(0,%r26)
+	addib,<=	-1,%r24,L$end2
+	vshd		%r29,%r22,%r20
+	ldws,mb 	-4(0,%r25),%r29
+	stws,mb 	%r20,-4(0,%r26)
+	addib,> 	-1,%r24,L$eloop
+	vshd		%r22,%r29,%r20
+
+L$end1	stws,mb 	%r20,-4(0,%r26)
+	vshd		%r29,%r0,%r20
+	bv		0(%r2)
+	stw		%r20,-4(0,%r26)
+L$end2	stws,mb 	%r20,-4(0,%r26)
+L$0004	vshd		%r22,%r0,%r20
+	bv		0(%r2)
+	stw		%r20,-4(0,%r26)
+
+	.exit
+	.procend
+
+
+
+/*******************
+ * mpi_limb_t
+ * mpihelp_rshift( mpi_ptr_t wp,       (gr26)
+ *		   mpi_ptr_t up,       (gr25)
+ *		   mpi_size_t usize,   (gr24)
+ *		   unsigned cnt)       (gr23)
+ */
+
+	.code
+	.export 	mpihelp_rshift
+mpihelp_rshift
+	.proc
+	.callinfo	frame=64,no_calls
+	.entry
+
+	ldws,ma 	4(0,%r25),%r22
+	mtsar		%r23
+	addib,= 	-1,%r24,L$r004
+	vshd		%r22,%r0,%r28		; compute carry out limb
+	ldws,ma 	4(0,%r25),%r29
+	addib,<=	-5,%r24,L$rrest
+	vshd		%r29,%r22,%r20
+
+L$roop	ldws,ma 	4(0,%r25),%r22
+	stws,ma 	%r20,4(0,%r26)
+	vshd		%r22,%r29,%r20
+	ldws,ma 	4(0,%r25),%r29
+	stws,ma 	%r20,4(0,%r26)
+	vshd		%r29,%r22,%r20
+	ldws,ma 	4(0,%r25),%r22
+	stws,ma 	%r20,4(0,%r26)
+	vshd		%r22,%r29,%r20
+	ldws,ma 	4(0,%r25),%r29
+	stws,ma 	%r20,4(0,%r26)
+	addib,> 	-4,%r24,L$roop
+	vshd		%r29,%r22,%r20
+
+L$rrest addib,= 	4,%r24,L$rend1
+	nop
+L$eroop ldws,ma 	4(0,%r25),%r22
+	stws,ma 	%r20,4(0,%r26)
+	addib,<=	-1,%r24,L$rend2
+	vshd		%r22,%r29,%r20
+	ldws,ma 	4(0,%r25),%r29
+	stws,ma 	%r20,4(0,%r26)
+	addib,> 	-1,%r24,L$eroop
+	vshd		%r29,%r22,%r20
+
+L$rend1  stws,ma	 %r20,4(0,%r26)
+	vshd		%r0,%r29,%r20
+	bv		0(%r2)
+	stw		%r20,0(0,%r26)
+L$rend2  stws,ma	 %r20,4(0,%r26)
+L$r004	vshd		%r0,%r22,%r20
+	bv		0(%r2)
+	stw		%r20,0(0,%r26)
+
+	.exit
+	.procend
+
+