100     movq      xmm7, qword ptr [eax + edi]  in TransposeWx8_SSSE3()
101     punpcklbw xmm6, xmm7  in TransposeWx8_SSSE3()
103     movdqa    xmm7, xmm6  in TransposeWx8_SSSE3()
104     palignr   xmm7, xmm7, 8  in TransposeWx8_SSSE3()
113     punpcklwd xmm5, xmm7  in TransposeWx8_SSSE3()
115     movdqa    xmm7, xmm5  in TransposeWx8_SSSE3()
117     palignr   xmm7, xmm7, 8  in TransposeWx8_SSSE3()
136     punpckldq xmm3, xmm7  in TransposeWx8_SSSE3()
140     movdqa    xmm7, xmm3  in TransposeWx8_SSSE3()
141     palignr   xmm7, xmm7, 8  in TransposeWx8_SSSE3()
143     movq      qword ptr [edx + esi], xmm7  in TransposeWx8_SSSE3()
184     movdqa    xmm7, xmm0  // use xmm7 as temp register.  in TransposeUVWx8_SSE2()
186     punpckhbw xmm7, xmm1  in TransposeUVWx8_SSE2()
187     movdqa    xmm1, xmm7  in TransposeUVWx8_SSE2()
191     movdqa    xmm7, xmm2  in TransposeUVWx8_SSE2()
193     punpckhbw xmm7, xmm3  in TransposeUVWx8_SSE2()
194     movdqa    xmm3, xmm7  in TransposeUVWx8_SSE2()
198     movdqa    xmm7, xmm4  in TransposeUVWx8_SSE2()
200     punpckhbw xmm7, xmm5  in TransposeUVWx8_SSE2()
201     movdqa    xmm5, xmm7  in TransposeUVWx8_SSE2()
203     movdqa    xmm7, [eax + edi]  in TransposeUVWx8_SSE2()
208     punpcklbw xmm6, xmm7  in TransposeUVWx8_SSE2()
209     punpckhbw xmm5, xmm7  in TransposeUVWx8_SSE2()
210     movdqa    xmm7, xmm5  in TransposeUVWx8_SSE2()
229     punpcklwd xmm5, xmm7  in TransposeUVWx8_SSE2()
230     punpckhwd xmm6, xmm7  in TransposeUVWx8_SSE2()
231     movdqa    xmm7, xmm6  in TransposeUVWx8_SSE2()
264     punpckldq xmm3, xmm7  in TransposeUVWx8_SSE2()
267     punpckhdq xmm0, xmm7  in TransposeUVWx8_SSE2()