From 11da511c784eca003deb90c23570f0873954e0de Mon Sep 17 00:00:00 2001
From: Duncan Wilkie <antigravityd@gmail.com>
Date: Sat, 18 Nov 2023 06:11:09 -0600
Subject: Initial commit.

---
 gmp-6.3.0/mpn/pa32/hppa1_1/pa7100/rshift.asm | 92 ++++++++++++++++++++++++++++
 1 file changed, 92 insertions(+)
 create mode 100644 gmp-6.3.0/mpn/pa32/hppa1_1/pa7100/rshift.asm

(limited to 'gmp-6.3.0/mpn/pa32/hppa1_1/pa7100/rshift.asm')

diff --git a/gmp-6.3.0/mpn/pa32/hppa1_1/pa7100/rshift.asm b/gmp-6.3.0/mpn/pa32/hppa1_1/pa7100/rshift.asm
new file mode 100644
index 0000000..f7896fc
--- /dev/null
+++ b/gmp-6.3.0/mpn/pa32/hppa1_1/pa7100/rshift.asm
@@ -0,0 +1,92 @@
+dnl  HP-PA  mpn_rshift -- Shift a number right.
+dnl  Optimized for the PA7100, where is runs at 3.25 cycles/limb.
+
+dnl  Copyright 1992, 1994, 2000-2003 Free Software Foundation, Inc.
+
+dnl  This file is part of the GNU MP Library.
+dnl
+dnl  The GNU MP Library is free software; you can redistribute it and/or modify
+dnl  it under the terms of either:
+dnl
+dnl    * the GNU Lesser General Public License as published by the Free
+dnl      Software Foundation; either version 3 of the License, or (at your
+dnl      option) any later version.
+dnl
+dnl  or
+dnl
+dnl    * the GNU General Public License as published by the Free Software
+dnl      Foundation; either version 2 of the License, or (at your option) any
+dnl      later version.
+dnl
+dnl  or both in parallel, as here.
+dnl
+dnl  The GNU MP Library is distributed in the hope that it will be useful, but
+dnl  WITHOUT ANY WARRANTY; without even the implied warranty of MERCHANTABILITY
+dnl  or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License
+dnl  for more details.
+dnl
+dnl  You should have received copies of the GNU General Public License and the
+dnl  GNU Lesser General Public License along with the GNU MP Library.  If not,
+dnl  see https://www.gnu.org/licenses/.
+
+include(`../config.m4')
+
+C INPUT PARAMETERS
+C res_ptr	r26
+C s_ptr		r25
+C size		r24
+C cnt		r23
+
+ASM_START()
+PROLOGUE(mpn_rshift)
+	ldws,ma		4(0,%r25),%r22
+	mtsar		%r23
+	addib,=		-1,%r24,L(0004)
+	vshd		%r22,%r0,%r28		C compute carry out limb
+	ldws,ma		4(0,%r25),%r29
+	addib,<=	-5,%r24,L(rest)
+	vshd		%r29,%r22,%r20
+
+LDEF(loop)
+	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(loop)
+	vshd		%r29,%r22,%r20
+
+LDEF(rest)
+	addib,=		4,%r24,L(end1)
+	nop
+
+LDEF(eloop)
+	ldws,ma		4(0,%r25),%r22
+	stws,ma		%r20,4(0,%r26)
+	addib,<=	-1,%r24,L(end2)
+	vshd		%r22,%r29,%r20
+	ldws,ma		4(0,%r25),%r29
+	stws,ma		%r20,4(0,%r26)
+	addib,>		-1,%r24,L(eloop)
+	vshd		%r29,%r22,%r20
+
+LDEF(end1)
+	stws,ma		%r20,4(0,%r26)
+	vshd		%r0,%r29,%r20
+	bv		0(%r2)
+	stw		%r20,0(0,%r26)
+
+LDEF(end2)
+	stws,ma		%r20,4(0,%r26)
+
+LDEF(0004)
+	vshd		%r0,%r22,%r20
+	bv		0(%r2)
+	stw		%r20,0(0,%r26)
+EPILOGUE()
-- 
cgit v1.2.3