94     f32x4_t     vecTmp0, vecTmp1;  in _arm_radix4_butterfly_f32_mve()  local
154                 vecTmp0 = vecSum0 + vecSum1;  in _arm_radix4_butterfly_f32_mve()
155                 vst1q(inA, vecTmp0);  in _arm_radix4_butterfly_f32_mve()
161                 vecTmp0 = vecSum0 - vecSum1;  in _arm_radix4_butterfly_f32_mve()
167                 vecTmp1 = MVE_CMPLX_MULT_FLT_Conj_AxB(vecW, vecTmp0);  in _arm_radix4_butterfly_f32_mve()
174                 vecTmp0 = MVE_CMPLX_SUB_A_ixB(vecDiff0, vecDiff1);  in _arm_radix4_butterfly_f32_mve()
180                 vecTmp1 = MVE_CMPLX_MULT_FLT_Conj_AxB(vecW, vecTmp0);  in _arm_radix4_butterfly_f32_mve()
187                 vecTmp0 = MVE_CMPLX_ADD_A_ixB(vecDiff0, vecDiff1);  in _arm_radix4_butterfly_f32_mve()
193                 vecTmp1 = MVE_CMPLX_MULT_FLT_Conj_AxB(vecW, vecTmp0);  in _arm_radix4_butterfly_f32_mve()
236         vecTmp0 = vecSum0 + vecSum1;  in _arm_radix4_butterfly_f32_mve()
237         vstrwq_scatter_base_f32(vecScGathAddr, -64, vecTmp0);  in _arm_radix4_butterfly_f32_mve()
239         vecTmp0 = vecSum0 - vecSum1;  in _arm_radix4_butterfly_f32_mve()
240         vstrwq_scatter_base_f32(vecScGathAddr, -64 + 8, vecTmp0);  in _arm_radix4_butterfly_f32_mve()
242         vecTmp0 = MVE_CMPLX_SUB_A_ixB(vecDiff0, vecDiff1);  in _arm_radix4_butterfly_f32_mve()
243         vstrwq_scatter_base_f32(vecScGathAddr, -64 + 16, vecTmp0);  in _arm_radix4_butterfly_f32_mve()
245         vecTmp0 = MVE_CMPLX_ADD_A_ixB(vecDiff0, vecDiff1);  in _arm_radix4_butterfly_f32_mve()
246         vstrwq_scatter_base_f32(vecScGathAddr, -64 + 24, vecTmp0);  in _arm_radix4_butterfly_f32_mve()
302     f32x4_t vecTmp0, vecTmp1;  in _arm_radix4_butterfly_inverse_f32_mve()  local
362                 vecTmp0 = vecSum0 + vecSum1;  in _arm_radix4_butterfly_inverse_f32_mve()
363                 vst1q(inA, vecTmp0);  in _arm_radix4_butterfly_inverse_f32_mve()
368                 vecTmp0 = vecSum0 - vecSum1;  in _arm_radix4_butterfly_inverse_f32_mve()
374                 vecTmp1 = MVE_CMPLX_MULT_FLT_AxB(vecW, vecTmp0);  in _arm_radix4_butterfly_inverse_f32_mve()
381                 vecTmp0 = MVE_CMPLX_ADD_A_ixB(vecDiff0, vecDiff1);  in _arm_radix4_butterfly_inverse_f32_mve()
387                 vecTmp1 = MVE_CMPLX_MULT_FLT_AxB(vecW, vecTmp0);  in _arm_radix4_butterfly_inverse_f32_mve()
394                 vecTmp0 = MVE_CMPLX_SUB_A_ixB(vecDiff0, vecDiff1);  in _arm_radix4_butterfly_inverse_f32_mve()
400                 vecTmp1 = MVE_CMPLX_MULT_FLT_AxB(vecW, vecTmp0);  in _arm_radix4_butterfly_inverse_f32_mve()
444         vecTmp0 = vecSum0 + vecSum1;  in _arm_radix4_butterfly_inverse_f32_mve()
445         vecTmp0 = vecTmp0 * onebyfftLen;  in _arm_radix4_butterfly_inverse_f32_mve()
446         vstrwq_scatter_base_f32(vecScGathAddr, -64, vecTmp0);  in _arm_radix4_butterfly_inverse_f32_mve()
448         vecTmp0 = vecSum0 - vecSum1;  in _arm_radix4_butterfly_inverse_f32_mve()
449         vecTmp0 = vecTmp0 * onebyfftLen;  in _arm_radix4_butterfly_inverse_f32_mve()
450         vstrwq_scatter_base_f32(vecScGathAddr, -64 + 8, vecTmp0);  in _arm_radix4_butterfly_inverse_f32_mve()
452         vecTmp0 = MVE_CMPLX_ADD_A_ixB(vecDiff0, vecDiff1);  in _arm_radix4_butterfly_inverse_f32_mve()
453         vecTmp0 = vecTmp0 * onebyfftLen;  in _arm_radix4_butterfly_inverse_f32_mve()
454         vstrwq_scatter_base_f32(vecScGathAddr, -64 + 16, vecTmp0);  in _arm_radix4_butterfly_inverse_f32_mve()
456         vecTmp0 = MVE_CMPLX_SUB_A_ixB(vecDiff0, vecDiff1);  in _arm_radix4_butterfly_inverse_f32_mve()
457         vecTmp0 = vecTmp0 * onebyfftLen;  in _arm_radix4_butterfly_inverse_f32_mve()
458         vstrwq_scatter_base_f32(vecScGathAddr, -64 + 24, vecTmp0);  in _arm_radix4_butterfly_inverse_f32_mve()