1 /////////////////////////////////////////////////////////////////////////////////// 2 /// OpenGL Mathematics (glm.g-truc.net) 3 /// 4 /// Copyright (c) 2005 - 2014 G-Truc Creation (www.g-truc.net) 5 /// Permission is hereby granted, free of charge, to any person obtaining a copy 6 /// of this software and associated documentation files (the "Software"), to deal 7 /// in the Software without restriction, including without limitation the rights 8 /// to use, copy, modify, merge, publish, distribute, sublicense, and/or sell 9 /// copies of the Software, and to permit persons to whom the Software is 10 /// furnished to do so, subject to the following conditions: 11 /// 12 /// The above copyright notice and this permission notice shall be included in 13 /// all copies or substantial portions of the 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 THE 18 /// AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER 19 /// LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, 20 /// OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN 21 /// THE SOFTWARE. 22 /// 23 /// @ref core 24 /// @file glm/core/intrinsic_exponential.hpp 25 /// @date 2009-05-11 / 2011-06-15 26 /// @author Christophe Riccio 27 /////////////////////////////////////////////////////////////////////////////////// 28 29 #ifndef glm_detail_intrinsic_exponential 30 #define glm_detail_intrinsic_exponential 31 32 #include "setup.hpp" 33 34 #if(!(GLM_ARCH & GLM_ARCH_SSE2)) 35 # error "SSE2 instructions not supported or enabled" 36 #else 37 38 namespace glm{ 39 namespace detail 40 { 41 /* 42 GLM_FUNC_QUALIFIER __m128 sse_rsqrt_nr_ss(__m128 const x) 43 { 44 __m128 recip = _mm_rsqrt_ss( x ); // "estimate" opcode 45 const static __m128 three = { 3, 3, 3, 3 }; // aligned consts for fast load 46 const static __m128 half = { 0.5,0.5,0.5,0.5 }; 47 __m128 halfrecip = _mm_mul_ss( half, recip ); 48 __m128 threeminus_xrr = _mm_sub_ss( three, _mm_mul_ss( x, _mm_mul_ss ( recip, recip ) ) ); 49 return _mm_mul_ss( halfrecip, threeminus_xrr ); 50 } 51 52 GLM_FUNC_QUALIFIER __m128 sse_normalize_fast_ps( float * RESTRICT vOut, float * RESTRICT vIn ) 53 { 54 __m128 x = _mm_load_ss(&vIn[0]); 55 __m128 y = _mm_load_ss(&vIn[1]); 56 __m128 z = _mm_load_ss(&vIn[2]); 57 58 const __m128 l = // compute x*x + y*y + z*z 59 _mm_add_ss( 60 _mm_add_ss( _mm_mul_ss(x,x), 61 _mm_mul_ss(y,y) 62 ), 63 _mm_mul_ss( z, z ) 64 ); 65 66 67 const __m128 rsqt = _mm_rsqrt_nr_ss( l ); 68 _mm_store_ss( &vOut[0] , _mm_mul_ss( rsqt, x ) ); 69 _mm_store_ss( &vOut[1] , _mm_mul_ss( rsqt, y ) ); 70 _mm_store_ss( &vOut[2] , _mm_mul_ss( rsqt, z ) ); 71 72 return _mm_mul_ss( l , rsqt ); 73 } 74 */ 75 }//namespace detail 76 }//namespace glm 77 78 #endif//GLM_ARCH 79 #endif//glm_detail_intrinsic_exponential 80