linux_dsm_epyc7002/arch/c6x/lib/mpyll.S
Thomas Gleixner 1a59d1b8e0 treewide: Replace GPLv2 boilerplate/reference with SPDX - rule 156
Based on 1 normalized pattern(s):

  this program is free software you can redistribute it and or modify
  it under the terms of the gnu general public license as published by
  the free software foundation either version 2 of the license or at
  your option any later version this program 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 general public license for more details you
  should have received a copy of the gnu general public license along
  with this program if not write to the free software foundation inc
  59 temple place suite 330 boston ma 02111 1307 usa

extracted by the scancode license scanner the SPDX license identifier

  GPL-2.0-or-later

has been chosen to replace the boilerplate/reference in 1334 file(s).

Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Reviewed-by: Allison Randal <allison@lohutok.net>
Reviewed-by: Richard Fontana <rfontana@redhat.com>
Cc: linux-spdx@vger.kernel.org
Link: https://lkml.kernel.org/r/20190527070033.113240726@linutronix.de
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
2019-05-30 11:26:35 -07:00

38 lines
918 B
ArmAsm

;; 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)