1 files changed, 77 insertions, 0 deletions
diff --git a/mpi/arm/mpih-sub1.S b/mpi/arm/mpih-sub1.S
new file mode 100644
index 00000000..a573efff
--- /dev/null
+++ b/mpi/arm/mpih-sub1.S
@@ -0,0 +1,77 @@
+/* ARM sub_n -- Subtract 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/>.
+ *
+ * Note: This code is heavily based on the GNU MP Library (version 4.2.1).
+ */
+
+#include "sysdep.h"
+#include "asm-syntax.h"
+
+.syntax unified
+.arm
+
+/*******************
+ *  mpi_limb_t
+ *  _gcry_mpih_sub_n( mpi_ptr_t res_ptr,	%r0
+ *		   mpi_ptr_t s1_ptr,		%r1
+ *		   mpi_ptr_t s2_ptr,		%r2
+ *		   mpi_size_t size)		%r3
+ */
+
+.text
+
+.globl _gcry_mpih_sub_n
+.type  _gcry_mpih_sub_n,%function
+_gcry_mpih_sub_n:
+	push	{%r4, %r5, %r6, %r7, %r8, %r9, %r10, %lr};
+	cmp	%r0, #0; /* prepare carry flag for sub */
+
+	tst	%r3, #3;
+	beq	.Large_loop;
+
+.Loop:
+	ldr	%r4, [%r1], #4;
+	sub	%r3, #1;
+	ldr	%lr, [%r2], #4;
+	sbcs	%r4, %lr;
+	tst	%r3, #3;
+	str	%r4, [%r0], #4;
+	bne	.Loop;
+
+	teq	%r3, #0;
+	beq	.Lend;
+
+.Large_loop:
+	ldm	%r1!, {%r4, %r6, %r8, %r10};
+	sub	%r3, #4;
+	ldm	%r2!, {%r5, %r7, %r9, %lr};
+	sbcs	%r4, %r5;
+	sbcs	%r6, %r7;
+	sbcs	%r8, %r9;
+	sbcs	%r10, %lr;
+	teq	%r3, #0;
+	stm	%r0!, {%r4, %r6, %r8, %r10};
+	bne	.Large_loop;
+
+.Lend:
+	sbc	%r0, %r3, #0;
+	neg	%r0, %r0;
+	pop	{%r4, %r5, %r6, %r7, %r8, %r9, %r10, %pc};
+.size _gcry_mpih_sub_n,.-_gcry_mpih_sub_n;