Add aarch64 (arm64) mpi assembly

* mpi/aarch64/mpi-asm-defs.h: New.
* mpi/aarch64/mpih-add1.S: New.
* mpi/aarch64/mpih-mul1.S: New.
* mpi/aarch64/mpih-mul2.S: New.
* mpi/aarch64/mpih-mul3.S: New.
* mpi/aarch64/mpih-sub1.S: New.
* mpi/config.links [host=aarch64-*-*]: Add configguration for aarch64
assembly.
* mpi/longlong.h [__aarch64__] (add_ssaaaa, sub_ddmmss, umul_ppmm)
(count_leading_zeros): New.
--

Add preliminary aarch64 assembly implementations for mpi.

Signed-off-by: Jussi Kivilinna <jussi.kivilinna@iki.fi>

1 files changed, 71 insertions, 0 deletions

diff --git a/mpi/aarch64/mpih-add1.S b/mpi/aarch64/mpih-add1.S
new file mode 100644
index 00000000..9f7e2e69
--- /dev/null
+++ b/mpi/aarch64/mpih-add1.S
@@ -0,0 +1,71 @@
+/* ARM64 add_n -- Add two limb vectors of the same length > 0 and store
+ *                sum in a third limb vector.
+ *
+ *      Copyright © 2013 Jussi Kivilinna <jussi.kivilinna@iki.fi>
+ *
+ * This file is part of Libgcrypt.
+ *
+ * Libgcrypt is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU Lesser General Public License as
+ * published by the Free Software Foundation; either version 2.1 of
+ * the License, or (at your option) any later version.
+ *
+ * Libgcrypt 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 Lesser General Public License for more details.
+ *
+ * You should have received a copy of the GNU Lesser General Public
+ * License along with this program; if not, see <http://www.gnu.org/licenses/>.
+ *
+ */
+
+#include "sysdep.h"
+#include "asm-syntax.h"
+
+/*******************
+ *  mpi_limb_t
+ *  _gcry_mpih_add_n( mpi_ptr_t res_ptr,	x0
+ *		   mpi_ptr_t s1_ptr,		x1
+ *		   mpi_ptr_t s2_ptr,		x2
+ *		   mpi_size_t size)		x3
+ */
+
+.text
+
+.globl _gcry_mpih_add_n
+.type  _gcry_mpih_add_n,%function
+_gcry_mpih_add_n:
+	and	x5, x3, #3;
+	adds	xzr, xzr, xzr; /* clear carry flag */
+
+	cbz	x5, .Large_loop;
+
+.Loop:
+	ldr	x4, [x1], #8;
+	sub	x3, x3, #1;
+	ldr	x11, [x2], #8;
+	and	x5, x3, #3;
+	adcs	x4, x4, x11;
+	str	x4, [x0], #8;
+	cbz	x3, .Lend;
+	cbnz	x5, .Loop;
+
+.Large_loop:
+	ldp	x4, x6, [x1], #16;
+	ldp	x5, x7, [x2], #16;
+	ldp	x8, x10, [x1], #16;
+	ldp	x9, x11, [x2], #16;
+	sub	x3, x3, #4;
+	adcs	x4, x4, x5;
+	adcs	x6, x6, x7;
+	adcs	x8, x8, x9;
+	adcs	x10, x10, x11;
+	stp	x4, x6, [x0], #16;
+	stp	x8, x10, [x0], #16;
+	cbnz	x3, .Large_loop;
+
+.Lend:
+	adc	x0, xzr, xzr;
+	ret;
+.size _gcry_mpih_add_n,.-_gcry_mpih_add_n;