Lines Matching defs:simdscalar
85 void vTranspose3x8(simd4scalar (&vDst)[8], const simdscalar &vSrc0, const simdscalar &vSrc1, const simdscalar &vSrc2)
87 simdscalar r0r2 = _simd_unpacklo_ps(vSrc0, vSrc2); //x0z0x1z1 x4z4x5z5
88 simdscalar r1rx = _simd_unpacklo_ps(vSrc1, _simd_setzero_ps()); //y0w0y1w1 y4w4y5w5
89 simdscalar r02r1xlolo = _simd_unpacklo_ps(r0r2, r1rx); //x0y0z0w0 x4y4z4w4
90 simdscalar r02r1xlohi = _simd_unpackhi_ps(r0r2, r1rx); //x1y1z1w1 x5y5z5w5
94 simdscalar r02r1xhilo = _simd_unpacklo_ps(r0r2, r1rx); //x2y2z2w2 x6y6z6w6
95 simdscalar r02r1xhihi = _simd_unpackhi_ps(r0r2, r1rx); //x3y3z3w3 x7y7z7w7
109 void vTranspose4x8(simd4scalar (&vDst)[8], const simdscalar &vSrc0, const simdscalar &vSrc1, const simdscalar &vSrc2, const simdscalar &vSrc3)
111 simdscalar r0r2 = _simd_unpacklo_ps(vSrc0, vSrc2); //x0z0x1z1 x4z4x5z5
112 simdscalar r1rx = _simd_unpacklo_ps(vSrc1, vSrc3); //y0w0y1w1 y4w4y5w5
113 simdscalar r02r1xlolo = _simd_unpacklo_ps(r0r2, r1rx); //x0y0z0w0 x4y4z4w4
114 simdscalar r02r1xlohi = _simd_unpackhi_ps(r0r2, r1rx); //x1y1z1w1 x5y5z5w5
118 simdscalar r02r1xhilo = _simd_unpacklo_ps(r0r2, r1rx); //x2y2z2w2 x6y6z6w6
119 simdscalar r02r1xhihi = _simd_unpackhi_ps(r0r2, r1rx); //x3y3z3w3 x7y7z7w7
156 void vTranspose8x8(simdscalar (&vDst)[8], const simdscalar &vMask0, const simdscalar &vMask1, const simdscalar &vMask2, const simdscalar &vMask3, const simdscalar &vMask4, const simdscalar &vMask5, const simdscalar &vMask6, const simdscalar &vMask7)
158 simdscalar __t0 = _simd_unpacklo_ps(vMask0, vMask1);
159 simdscalar __t1 = _simd_unpackhi_ps(vMask0, vMask1);
160 simdscalar __t2 = _simd_unpacklo_ps(vMask2, vMask3);
161 simdscalar __t3 = _simd_unpackhi_ps(vMask2, vMask3);
162 simdscalar __t4 = _simd_unpacklo_ps(vMask4, vMask5);
163 simdscalar __t5 = _simd_unpackhi_ps(vMask4, vMask5);
164 simdscalar __t6 = _simd_unpacklo_ps(vMask6, vMask7);
165 simdscalar __t7 = _simd_unpackhi_ps(vMask6, vMask7);
166 simdscalar __tt0 = _simd_shuffle_ps(__t0,__t2,_MM_SHUFFLE(1,0,1,0));
167 simdscalar __tt1 = _simd_shuffle_ps(__t0,__t2,_MM_SHUFFLE(3,2,3,2));
168 simdscalar __tt2 = _simd_shuffle_ps(__t1,__t3,_MM_SHUFFLE(1,0,1,0));
169 simdscalar __tt3 = _simd_shuffle_ps(__t1,__t3,_MM_SHUFFLE(3,2,3,2));
170 simdscalar __tt4 = _simd_shuffle_ps(__t4,__t6,_MM_SHUFFLE(1,0,1,0));
171 simdscalar __tt5 = _simd_shuffle_ps(__t4,__t6,_MM_SHUFFLE(3,2,3,2));
172 simdscalar __tt6 = _simd_shuffle_ps(__t5,__t7,_MM_SHUFFLE(1,0,1,0));
173 simdscalar __tt7 = _simd_shuffle_ps(__t5,__t7,_MM_SHUFFLE(3,2,3,2));
185 void vTranspose8x8(simdscalar (&vDst)[8], const simdscalari &vMask0, const simdscalari &vMask1, const simdscalari &vMask2, const simdscalari &vMask3, const simdscalari &vMask4, const simdscalari &vMask5, const simdscalari &vMask6, const simdscalari &vMask7)
347 simdscalar src0 = _simd_load_ps((const float*)pSrc);
348 simdscalar src1 = _simd_load_ps((const float*)pSrc + 8);
349 simdscalar src2 = _simd_load_ps((const float*)pSrc + 16);
350 simdscalar src3 = _simd_load_ps((const float*)pSrc + 24);
399 simdscalar src0 = _simd_load_ps((const float*)pSrc);
400 simdscalar src1 = _simd_load_ps((const float*)pSrc + 8);
401 simdscalar src2 = _simd_load_ps((const float*)pSrc + 16);
643 simdscalar src = _simd_load_ps((const float*)pSrc);