Lines Matching defs:__m256
150 void vTranspose3x8(__m128 (&vDst)[8], const __m256 &vSrc0, const __m256 &vSrc1, const __m256 &vSrc2)
152 __m256 r0r2 = _mm256_unpacklo_ps(vSrc0, vSrc2); //x0z0x1z1 x4z4x5z5
153 __m256 r1rx = _mm256_unpacklo_ps(vSrc1, _mm256_undefined_ps()); //y0w0y1w1 y4w4y5w5
154 __m256 r02r1xlolo = _mm256_unpacklo_ps(r0r2, r1rx); //x0y0z0w0 x4y4z4w4
155 __m256 r02r1xlohi = _mm256_unpackhi_ps(r0r2, r1rx); //x1y1z1w1 x5y5z5w5
159 __m256 r02r1xhilo = _mm256_unpacklo_ps(r0r2, r1rx); //x2y2z2w2 x6y6z6w6
160 __m256 r02r1xhihi = _mm256_unpackhi_ps(r0r2, r1rx); //x3y3z3w3 x7y7z7w7
174 void vTranspose4x8(__m128 (&vDst)[8], const __m256 &vSrc0, const __m256 &vSrc1, const __m256 &vSrc2, const __m256 &vSrc3)
176 __m256 r0r2 = _mm256_unpacklo_ps(vSrc0, vSrc2); //x0z0x1z1 x4z4x5z5
177 __m256 r1rx = _mm256_unpacklo_ps(vSrc1, vSrc3); //y0w0y1w1 y4w4y5w5
178 __m256 r02r1xlolo = _mm256_unpacklo_ps(r0r2, r1rx); //x0y0z0w0 x4y4z4w4
179 __m256 r02r1xlohi = _mm256_unpackhi_ps(r0r2, r1rx); //x1y1z1w1 x5y5z5w5
183 __m256 r02r1xhilo = _mm256_unpacklo_ps(r0r2, r1rx); //x2y2z2w2 x6y6z6w6
184 __m256 r02r1xhihi = _mm256_unpackhi_ps(r0r2, r1rx); //x3y3z3w3 x7y7z7w7
221 void vTranspose8x8(__m256 (&vDst)[8], const __m256 &vMask0, const __m256 &vMask1, const __m256 &vMask2, const __m256 &vMask3, const __m256 &vMask4, const __m256 &vMask5, const __m256 &vMask6, const __m256 &vMask7)
223 __m256 __t0 = _mm256_unpacklo_ps(vMask0, vMask1);
224 __m256 __t1 = _mm256_unpackhi_ps(vMask0, vMask1);
225 __m256 __t2 = _mm256_unpacklo_ps(vMask2, vMask3);
226 __m256 __t3 = _mm256_unpackhi_ps(vMask2, vMask3);
227 __m256 __t4 = _mm256_unpacklo_ps(vMask4, vMask5);
228 __m256 __t5 = _mm256_unpackhi_ps(vMask4, vMask5);
229 __m256 __t6 = _mm256_unpacklo_ps(vMask6, vMask7);
230 __m256 __t7 = _mm256_unpackhi_ps(vMask6, vMask7);
231 __m256 __tt0 = _mm256_shuffle_ps(__t0,__t2,_MM_SHUFFLE(1,0,1,0));
232 __m256 __tt1 = _mm256_shuffle_ps(__t0,__t2,_MM_SHUFFLE(3,2,3,2));
233 __m256 __tt2 = _mm256_shuffle_ps(__t1,__t3,_MM_SHUFFLE(1,0,1,0));
234 __m256 __tt3 = _mm256_shuffle_ps(__t1,__t3,_MM_SHUFFLE(3,2,3,2));
235 __m256 __tt4 = _mm256_shuffle_ps(__t4,__t6,_MM_SHUFFLE(1,0,1,0));
236 __m256 __tt5 = _mm256_shuffle_ps(__t4,__t6,_MM_SHUFFLE(3,2,3,2));
237 __m256 __tt6 = _mm256_shuffle_ps(__t5,__t7,_MM_SHUFFLE(1,0,1,0));
238 __m256 __tt7 = _mm256_shuffle_ps(__t5,__t7,_MM_SHUFFLE(3,2,3,2));
250 void vTranspose8x8(__m256 (&vDst)[8], const __m256i &vMask0, const __m256i &vMask1, const __m256i &vMask2, const __m256i &vMask3, const __m256i &vMask4, const __m256i &vMask5, const __m256i &vMask6, const __m256i &vMask7)
