1 files changed, 102 insertions, 0 deletions
diff --git a/sysdeps/mips/mips64/submul_1.S b/sysdeps/mips/mips64/submul_1.S
new file mode 100644
index 0000000000..bf24123bde
--- /dev/null
+++ b/sysdeps/mips/mips64/submul_1.S
@@ -0,0 +1,102 @@
+/* MIPS3 __mpn_submul_1 -- Multiply a limb vector with a single limb and
+ * subtract the product from a second limb vector.
+ *
+ * Copyright (C) 1992-2014 Free Software Foundation, Inc.
+ *
+ * This file is part of the GNU MP Library.
+ *
+ * The GNU MP Library 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.
+ *
+ * The GNU MP Library 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 the GNU MP Library.  If not, see
+ * <http://www.gnu.org/licenses/>.
+ */
+
+#include <sysdep.h>
+#include <sys/asm.h>
+
+/* INPUT PARAMETERS
+ * res_ptr	$4
+ * s1_ptr	$5
+ * size		$6
+ * s2_limb	$7
+ */
+
+#ifdef __PIC__
+	.option pic2
+#endif
+ENTRY (__mpn_submul_1)
+#ifdef __PIC__
+	SETUP_GP /* ??? unused */
+#endif
+	.set    noreorder
+	.set    nomacro
+
+ # warm up phase 0
+	ld	$8,0($5)
+
+ # warm up phase 1
+	daddiu	$5,$5,8
+	dmultu	$8,$7
+
+	daddiu	$6,$6,-1
+	beq	$6,$0,L(LC0)
+	move	$2,$0		# zero cy2
+
+	daddiu	$6,$6,-1
+	beq	$6,$0,L(LC1)
+	ld	$8,0($5)	# load new s1 limb as early as possible
+
+L(Loop):	ld	$10,0($4)
+	mflo	$3
+	mfhi	$9
+	daddiu	$5,$5,8
+	daddu	$3,$3,$2	# add old carry limb to low product limb
+	dmultu	$8,$7
+	ld	$8,0($5)	# load new s1 limb as early as possible
+	daddiu	$6,$6,-1	# decrement loop counter
+	sltu	$2,$3,$2	# carry from previous addition -> $2
+	dsubu	$3,$10,$3
+	sgtu	$10,$3,$10
+	daddu	$2,$2,$10
+	sd	$3,0($4)
+	daddiu	$4,$4,8
+	bne	$6,$0,L(Loop)
+	daddu	$2,$9,$2	# add high product limb and carry from addition
+
+ # cool down phase 1
+L(LC1):	ld	$10,0($4)
+	mflo	$3
+	mfhi	$9
+	daddu	$3,$3,$2
+	sltu	$2,$3,$2
+	dmultu	$8,$7
+	dsubu	$3,$10,$3
+	sgtu	$10,$3,$10
+	daddu	$2,$2,$10
+	sd	$3,0($4)
+	daddiu	$4,$4,8
+	daddu	$2,$9,$2	# add high product limb and carry from addition
+
+ # cool down phase 0
+L(LC0):	ld	$10,0($4)
+	mflo	$3
+	mfhi	$9
+	daddu	$3,$3,$2
+	sltu	$2,$3,$2
+	dsubu	$3,$10,$3
+	sgtu	$10,$3,$10
+	daddu	$2,$2,$10
+	sd	$3,0($4)
+	j	$31
+	daddu	$2,$9,$2	# add high product limb and carry from addition
+
+END (__mpn_submul_1)