/*
 * Copyright © <2010>, Intel Corporation.
 *
 * Permission is hereby granted, free of charge, to any person obtaining a
 * copy of this software and associated documentation files (the
 * "Software"), to deal in the Software without restriction, including
 * without limitation the rights to use, copy, modify, merge, publish,
 * distribute, sub license, and/or sell copies of the Software, and to
 * permit persons to whom the Software is furnished to do so, subject to
 * the following conditions:
 *
 * The above copyright notice and this permission notice (including the
 * next paragraph) shall be included in all copies or substantial portions
 * of the Software.
 *
 * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS
 * OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF
 * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND NON-INFRINGEMENT.
 * IN NO EVENT SHALL PRECISION INSIGHT AND/OR ITS SUPPLIERS BE LIABLE FOR
 * ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN ACTION OF CONTRACT,
 * TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN CONNECTION WITH THE
 * SOFTWARE OR THE USE OR OTHER DEALINGS IN THE SOFTWARE.
 *
 * This file was originally licensed under the following license
 *
 *  Licensed under the Apache License, Version 2.0 (the "License");
 *  you may not use this file except in compliance with the License.
 *  You may obtain a copy of the License at
 *
 *      http://www.apache.org/licenses/LICENSE-2.0
 *
 *  Unless required by applicable law or agreed to in writing, software
 *  distributed under the License is distributed on an "AS IS" BASIS,
 *  WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
 *  See the License for the specific language governing permissions and
 *  limitations under the License.
 *
 */
//	Kernel name: RoundShift_C_4x4.asm
//
//	Do (...+32)>>6 to 4x4 (NV12 8x4) interpolated chrominance data
//


//#if !defined(__RoundShift_C_4x4__)		// Make sure this is only included once
//#define __RoundShift_C_4x4__


	// TODO: Optimize using instruction compression
	add (16)	acc0<1>:w					r[pRESULT,0]<16;16,1>:w			32:w
	add (16)	acc1<1>:w					r[pRESULT,nGRFWIB]<16;16,1>:w	32:w
	asr.sat (16) r[pRESULT,0]<2>:ub			acc0<16;16,1>:w					6:w
	asr.sat (16) r[pRESULT,nGRFWIB]<2>:ub	acc1<16;16,1>:w					6:w
	

//#endif	// !defined(__RoundShift_C_4x4__)