1 /****************************************************************************
2 * Copyright (C) 2014-2015 Intel Corporation. All Rights Reserved.
3 *
4 * Permission is hereby granted, free of charge, to any person obtaining a
5 * copy of this software and associated documentation files (the "Software"),
6 * to deal in the Software without restriction, including without limitation
7 * the rights to use, copy, modify, merge, publish, distribute, sublicense,
8 * and/or sell copies of the Software, and to permit persons to whom the
9 * Software is furnished to do so, subject to the following conditions:
10 *
11 * The above copyright notice and this permission notice (including the next
12 * paragraph) shall be included in all copies or substantial portions of the
13 * Software.
14 *
15 * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
16 * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
17 * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
18 * THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
19 * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
20 * FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
21 * IN THE SOFTWARE.
22 *
23 * @file state.h
24 *
25 * @brief Definitions for API state - complex function implementation.
26 *
27 ******************************************************************************/
28 #pragma once
29
30 #include "core/state.h"
31 #include "common/simdintrin.h"
32
33 template <typename MaskT>
expandThenBlend4(uint32_t * min,uint32_t * max)34 INLINE __m128i SWR_MULTISAMPLE_POS::expandThenBlend4(uint32_t* min, uint32_t* max)
35 {
36 __m128i vMin = _mm_set1_epi32(*min);
37 __m128i vMax = _mm_set1_epi32(*max);
38 return _simd_blend4_epi32<MaskT::value>(vMin, vMax);
39 }
40
PrecalcSampleData(int numSamples)41 INLINE void SWR_MULTISAMPLE_POS::PrecalcSampleData(int numSamples)
42 {
43 for (int i = 0; i < numSamples; i++)
44 {
45 _vXi[i] = _mm_set1_epi32(_xi[i]);
46 _vYi[i] = _mm_set1_epi32(_yi[i]);
47 _vX[i] = _simd_set1_ps(_x[i]);
48 _vY[i] = _simd_set1_ps(_y[i]);
49 }
50 // precalculate the raster tile BB for the rasterizer.
51 CalcTileSampleOffsets(numSamples);
52 }
53
CalcTileSampleOffsets(int numSamples)54 INLINE void SWR_MULTISAMPLE_POS::CalcTileSampleOffsets(int numSamples)
55 {
56 auto minXi = std::min_element(std::begin(_xi), &_xi[numSamples]);
57 auto maxXi = std::max_element(std::begin(_xi), &_xi[numSamples]);
58 using xMask = std::integral_constant<int, 0xA>;
59 // BR(max), BL(min), UR(max), UL(min)
60 tileSampleOffsetsX = expandThenBlend4<xMask>(minXi, maxXi);
61
62 auto minYi = std::min_element(std::begin(_yi), &_yi[numSamples]);
63 auto maxYi = std::max_element(std::begin(_yi), &_yi[numSamples]);
64 using yMask = std::integral_constant<int, 0xC>;
65 // BR(max), BL(min), UR(max), UL(min)
66 tileSampleOffsetsY = expandThenBlend4<yMask>(minYi, maxYi);
67 };
68