/***********************************************************************
Copyright (c) 2006-2012, Skype Limited. All rights reserved. 
Redistribution and use in source and binary forms, with or without 
modification, (subject to the limitations in the disclaimer below) 
are permitted provided that the following conditions are met:
- Redistributions of source code must retain the above copyright notice,
this list of conditions and the following disclaimer.
- Redistributions in binary form must reproduce the above copyright 
notice, this list of conditions and the following disclaimer in the 
documentation and/or other materials provided with the distribution.
- Neither the name of Skype Limited, nor the names of specific 
contributors, may be used to endorse or promote products derived from 
this software without specific prior written permission.
NO EXPRESS OR IMPLIED LICENSES TO ANY PARTY'S PATENT RIGHTS ARE GRANTED 
BY THIS LICENSE. THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND 
CONTRIBUTORS ''AS IS'' AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING,
BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND 
FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE 
COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, 
INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT
NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF 
USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON 
ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT 
(INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE 
OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
***********************************************************************/

#if __arm__
#include "SKP_Silk_AsmPreproc.h"

#if ( EMBEDDED_ARM >= 6 )

	VARDEF val_N, r4
	VARDEF val_K, r5
	VARDEF val_order, r6
	VARDEF val_in_Q15, _r7
	VARDEF val_cb_Q15, r8
	VARDEF val_wtmp_Q6, sb
	VARDEF val_sum_error, sl
	VARDEF val_diff, ip
	VARDEF val_tmp, lr

	VARDEF val_in_Q15_tmp, ip
	VARDEF val_wtmp_Q6_tmp, lr

	VARDEF ptr_wtmp, _r7
	VARDEF val0_wtmp, sb
	VARDEF val1_wtmp, r5
	VARDEF val2_wtmp, r8

	VARDEF ptr_err_Q20, r0
	VARDEF ptr_in_Q15, r1
	VARDEF ptr_w_Q6, r2
	VARDEF ptr_pCB_Q15, r3

.set	sp_wtmp, 0 
.set	sp_err_Q20, 32 
.set	sp_in_Q15, 36 
.set	sp_w_Q6, 40 
.set	sp_pCB_Q15, 44 
.globl	SYM(SKP_Silk_NLSF_VQ_sum_error_FIX)
SYM(SKP_Silk_NLSF_VQ_sum_error_FIX):
	stmdb	sp!,  {r4-r10, fp, ip, lr}
	add		fp, sp, #36
	sub		sp, sp, #48
.set	ptr_N, 88 
.set	ptr_K, 92 
.set	ptr_LPC_order, 96 

	str	r0, [sp, #sp_err_Q20]
	str	r1, [sp, #sp_in_Q15]
	str	r2, [sp, #sp_w_Q6]
	str	r3, [sp, #sp_pCB_Q15]
	ldr	val_N, [sp, #ptr_N]

	ldr	val_order, [sp, #ptr_LPC_order]
	ldr	val1_wtmp, [r2], #4
	ldr	val2_wtmp, [r2], #4
	sub	val_order, val_order, #2
	add	ptr_wtmp, sp, #sp_wtmp
L(3)
	pkhbt	val0_wtmp, val1_wtmp, val2_wtmp, lsl #16
	subs	val_order, val_order, #2
	ldr	val1_wtmp, [r2], #4
	ldr	val2_wtmp, [r2], #4
	str	val0_wtmp, [ptr_wtmp], #4
	bgt	LR(3, b)
	pkhbt	val0_wtmp, val1_wtmp, val2_wtmp, lsl #16
	str	val0_wtmp, [ptr_wtmp], #4

	ands	val_tmp, ptr_pCB_Q15, #3
	bgt	LR(4, f)
/*OUTTER_LOOP*/
L(2)
	ldr	ptr_pCB_Q15, [sp, #sp_pCB_Q15]
	ldr	val_K, [sp, #ptr_K]
/*MIDDLE_LOOP*/  
L(1)
	ldr	ptr_in_Q15, [sp, #sp_in_Q15]
	add	ptr_w_Q6, sp, #sp_wtmp
	ldr	val_order, [sp, #ptr_LPC_order]
	mov	val_sum_error, #0
/*INNER_LOOP*/
L(0)
	ldmia	ptr_in_Q15!, {val_in_Q15, val_in_Q15_tmp}
	ldr	val_wtmp_Q6, [ptr_w_Q6], #4
	ldr	val_cb_Q15, [ptr_pCB_Q15], #4
	subs	val_order, val_order, #2
	pkhbt	val_in_Q15, val_in_Q15, val_in_Q15_tmp, lsl #16
	ssub16	val_diff, val_in_Q15, val_cb_Q15
	smulbb	val_tmp, val_diff, val_diff
	smultt	val_diff, val_diff, val_diff
	smlawb	val_sum_error, val_tmp, val_wtmp_Q6, val_sum_error
	smlawt	val_sum_error, val_diff, val_wtmp_Q6, val_sum_error
	bgt	LR(0, b)
	subs	val_K, val_K, #1
	str	val_sum_error, [ptr_err_Q20], #4
	bgt	LR(1, b)
	subs	val_N, val_N, #1
	str	ptr_in_Q15, [sp, #sp_in_Q15]
	bgt	LR(2, b)

	add		sp, sp, #48
	ldmia	sp!,  {r4-r10, fp, ip, pc}

L(4)
	ldr	ptr_pCB_Q15, [sp, #sp_pCB_Q15]
	ldr	val_K, [sp, #ptr_K]
/*MIDDLE_LOOP*/  
L(1)
	ldr	ptr_in_Q15, [sp, #sp_in_Q15]
	add	ptr_w_Q6, sp, #sp_wtmp
	ldr	val_order, [sp, #ptr_LPC_order]
	mov	val_sum_error, #0
/*INNER_LOOP*/
L(0)
	ldmia	ptr_in_Q15!, {val_in_Q15, val_in_Q15_tmp}
	ldr	val_wtmp_Q6, [ptr_w_Q6], #4
	ldrh	val_cb_Q15, [ptr_pCB_Q15], #2
	ldrh	val_tmp, [ptr_pCB_Q15], #2
	subs	val_order, val_order, #2
	pkhbt	val_in_Q15, val_in_Q15, val_in_Q15_tmp, lsl #16
	pkhbt	val_cb_Q15, val_cb_Q15, val_tmp, lsl #16
	ssub16	val_diff, val_in_Q15, val_cb_Q15
	smulbb	val_tmp, val_diff, val_diff
	smultt	val_diff, val_diff, val_diff
	smlawb	val_sum_error, val_tmp, val_wtmp_Q6, val_sum_error
	smlawt	val_sum_error, val_diff, val_wtmp_Q6, val_sum_error
	bgt	LR(0, b)
	subs	val_K, val_K, #1
	str	val_sum_error, [ptr_err_Q20], #4
	bgt	LR(1, b)
	subs	val_N, val_N, #1
	str	ptr_in_Q15, [sp, #sp_in_Q15]
	bgt	LR(4, b)

	add		sp, sp, #48
	ldmia	sp!,  {r4-r10, fp, ip, pc}
	END
#endif
#endif