/*
* Copyright © 2013 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, sublicense,
* 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 NONINFRINGEMENT. IN NO EVENT SHALL
* THE AUTHORS OR COPYRIGHT HOLDERS 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.
*
* Authors:
* Wang Zhenyu <zhenyu.z.wang@intel.com>
* Keith Packard <keithp@keithp.com>
* Zhao Yakui <yakui.zhao@intel.com>
*/
/* Sample the src surface in planar format */
include(`exa_wm.g4i')
/* Ivybridge uses GRFs in SEND instruction */
define(`src_msg_gen8', `g65')
define(`src_msg_ind_gen8',`65')
/* UV flag */
define(`uv_flag', `g6.0<0,1,0>UW')
/* prepare sampler read back gX register, which would be written back to output */
/* use simd16 sampler, param 0 is u, param 1 is v. */
/* 'payload' loading, assuming tex coord start from g4 */
cmp.e.f0.0 (1) null uv_flag 0x1UW {align1};
(f0.0) jmpi INTERLEAVED_UV;
cmp.e.f0.0 (1) null uv_flag 0x2UW {align1};
(f0.0) jmpi CONSTANT_UV;
/* load r */
mov (1) g0.8<1>UD 0x0000e000UD { align1 mask_disable };
mov (8) src_msg_gen8<1>UD g0<8,8,1>UD { align1 mask_disable };
/* emit sampler 'send' cmd */
/* sample U (Cr) */
send (16) src_msg_ind_gen8 /* msg reg index */
src_sample_g<1>UW /* readback */
null
sampler (3,2,F) /* sampler message description, (binding_table,sampler_index,datatype)
/* here(src->dst) we should use src_sampler and src_surface */
mlen 5 rlen 2 { align1 }; /* required message len 5, readback len 8 */
/* sample V (Cb) */
mov (1) g0.8<1>UD 0x0000e000UD { align1 mask_disable };
mov (8) src_msg_gen8<1>UD g0<8,8,1>UD { align1 mask_disable };
send (16) src_msg_ind_gen8 /* msg reg index */
src_sample_b<1>UW /* readback */
null
sampler (5,4,F) /* sampler message description, (binding_table,sampler_index,datatype)
/* here(src->dst) we should use src_sampler and src_surface */
mlen 5 rlen 2 { align1 }; /* required message len 5, readback len 8 */
jmpi SAMPLE_Y;
CONSTANT_UV:
mov (16) src_sample_g<1>f 0.5f { compr align1 mask_disable };
mov (16) src_sample_b<1>f 0.5f { compr align1 mask_disable };
jmpi SAMPLE_Y;
INTERLEAVED_UV:
mov (1) g0.8<1>UD 0x0000c000UD { align1 mask_disable };
mov (8) src_msg_gen8<1>UD g0<8,8,1>UD { align1 mask_disable };
/* sample UV (CrCb) */
send (16) src_msg_ind_gen8 /* msg reg index */
src_sample_g<1>UW /* readback */
null
sampler (3,2,F) /* sampler message description, (binding_table,sampler_index,datatype)
/* here(src->dst) we should use src_sampler and src_surface */
mlen 5 rlen 4 { align1 }; /* required message len 5, readback len 8 */
SAMPLE_Y:
mov (1) g0.8<1>UD 0x0000e000UD { align1 mask_disable };
mov (8) src_msg_gen8<1>UD g0<8,8,1>UD { align1 mask_disable };
/* sample Y */
send (16) src_msg_ind_gen8 /* msg reg index */
src_sample_r<1>UW /* readback */
null
sampler (1,0,F) /* sampler message description, (binding_table,sampler_index,datatype)
/* here(src->dst) we should use src_sampler and src_surface */
mlen 5 rlen 2 { align1 }; /* required message len 5, readback len 8 */