ASR_BASE
Change-Id: Icf3719cc0afe3eeb3edc7fa80a2eb5199ca9dda1
diff --git a/marvell/linux/arch/c6x/lib/mpyll.S b/marvell/linux/arch/c6x/lib/mpyll.S
new file mode 100644
index 0000000..d07c13e
--- /dev/null
+++ b/marvell/linux/arch/c6x/lib/mpyll.S
@@ -0,0 +1,37 @@
+;; SPDX-License-Identifier: GPL-2.0-or-later
+;; Copyright (C) 2010 Texas Instruments Incorporated
+;; Contributed by Mark Salter <msalter@redhat.com>.
+;;
+
+#include <linux/linkage.h>
+
+ ;; uint64_t __c6xabi_mpyll(uint64_t x, uint64_t y)
+ ;;
+ ;; 64x64 multiply
+ ;; First compute partial results using 32-bit parts of x and y:
+ ;;
+ ;; b63 b32 b31 b0
+ ;; -----------------------------
+ ;; | 1 | 0 |
+ ;; -----------------------------
+ ;;
+ ;; P0 = X0*Y0
+ ;; P1 = X0*Y1 + X1*Y0
+ ;; P2 = X1*Y1
+ ;;
+ ;; result = (P2 << 64) + (P1 << 32) + P0
+ ;;
+ ;; Since the result is also 64-bit, we can skip the P2 term.
+
+ .text
+ENTRY(__c6xabi_mpyll)
+ mpy32u .m1x A4,B4,A1:A0 ; X0*Y0
+ b .s2 B3
+ || mpy32u .m2x B5,A4,B1:B0 ; X0*Y1 (don't need upper 32-bits)
+ || mpy32u .m1x A5,B4,A3:A2 ; X1*Y0 (don't need upper 32-bits)
+ nop
+ nop
+ mv .s1 A0,A4
+ add .l1x A2,B0,A5
+ add .s1 A1,A5,A5
+ENDPROC(__c6xabi_mpyll)