Original port to early 2.6 kernel using TI COFF toolchain. Brought up to date by Mark Salter <msalter@redhat.com> Signed-off-by: Aurelien Jacquiot <a-jacquiot@ti.com> Signed-off-by: Mark Salter <msalter@redhat.com> Acked-by: Arnd Bergmann <arnd@arndb.de>
		
			
				
	
	
		
			49 lines
		
	
	
	
		
			1.5 KiB
			
		
	
	
	
		
			ArmAsm
		
	
	
	
	
	
			
		
		
	
	
			49 lines
		
	
	
	
		
			1.5 KiB
			
		
	
	
	
		
			ArmAsm
		
	
	
	
	
	
;;  Copyright (C) 2010 Texas Instruments Incorporated
 | 
						|
;;  Contributed by Mark Salter <msalter@redhat.com>.
 | 
						|
;;
 | 
						|
;; 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.
 | 
						|
 | 
						|
#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)
 |