summaryrefslogtreecommitdiff
path: root/mpn/arm64
diff options
context:
space:
mode:
authorTorbjorn Granlund <tg@gmplib.org>2019-08-07 17:21:10 +0200
committerTorbjorn Granlund <tg@gmplib.org>2019-08-07 17:21:10 +0200
commit68c683469d88b831ca9d2b74309f79367fc1f13e (patch)
tree58db64a06aaf8c9497a6576671421d5b70ea9d2d /mpn/arm64
parentd5b51eb2a622666bf9ee96e78d3e2cff99e6cfc2 (diff)
downloadgmp-68c683469d88b831ca9d2b74309f79367fc1f13e.tar.gz
Provide many gcd_11.
Diffstat (limited to 'mpn/arm64')
-rw-r--r--mpn/arm64/gcd_11.asm70
1 files changed, 70 insertions, 0 deletions
diff --git a/mpn/arm64/gcd_11.asm b/mpn/arm64/gcd_11.asm
new file mode 100644
index 000000000..d8cc3e2cf
--- /dev/null
+++ b/mpn/arm64/gcd_11.asm
@@ -0,0 +1,70 @@
+dnl ARM v8a mpn_gcd_11.
+
+dnl Based on the K7 gcd_1.asm, by Kevin Ryde. Rehacked for ARM by Torbjorn
+dnl Granlund.
+
+dnl Copyright 2000-2002, 2005, 2009, 2011-2013 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')
+
+changecom(blah)
+
+C cycles/bit (approx)
+C Cortex-A35 ?
+C Cortex-A53 ?
+C Cortex-A55 ?
+C Cortex-A57 ?
+C Cortex-A72 ?
+C Cortex-A73 ?
+C Cortex-A75 ?
+C Cortex-A76 ?
+C Cortex-A77 ?
+C Numbers measured with: speed -CD -s16-64 -t48 mpn_gcd_1
+
+define(`u0', `x0')
+define(`v0', `x1')
+
+ASM_START()
+ TEXT
+ ALIGN(16)
+PROLOGUE(mpn_gcd_11)
+ subs x3, u0, v0 C 0
+ b.eq L(end) C
+
+ ALIGN(16)
+L(top): rbit x12, x3 C 1,5
+ clz x12, x12 C 2
+ csneg x3, x3, x3, cs C v = abs(u-v), even 1
+ csel u0, v0, u0, cs C u = min(u,v) 1
+ lsr v0, x3, x12 C 3
+ subs x3, u0, v0 C 4
+ b.ne L(top) C
+
+L(end): ret
+EPILOGUE()