69 #define MATRIX_DIM4 4  macro
302     float32_t       *pInA1 = pInA0 + CMPLX_DIM * MATRIX_DIM4;  in arm_mat_cmplx_mult_f32_4x4_mve()
303     float32_t       *pInA2 = pInA1 + CMPLX_DIM * MATRIX_DIM4;  in arm_mat_cmplx_mult_f32_4x4_mve()
304     float32_t       *pInA3 = pInA2 + CMPLX_DIM * MATRIX_DIM4;  in arm_mat_cmplx_mult_f32_4x4_mve()
309         MATRIX_DIM4 * CMPLX_DIM, MATRIX_DIM4 * CMPLX_DIM + 1  in arm_mat_cmplx_mult_f32_4x4_mve()
311 …static const uint32_t offsetB1[4] = { 2 * MATRIX_DIM4 * CMPLX_DIM, 2 * MATRIX_DIM4 * CMPLX_DIM + 1,  in arm_mat_cmplx_mult_f32_4x4_mve()
312         3 * MATRIX_DIM4 * CMPLX_DIM, 3 * MATRIX_DIM4 * CMPLX_DIM + 1  in arm_mat_cmplx_mult_f32_4x4_mve()
356     pOut[0 * CMPLX_DIM * MATRIX_DIM4 + 0] = acc0[0] + acc0[2];  in arm_mat_cmplx_mult_f32_4x4_mve()
357     pOut[0 * CMPLX_DIM * MATRIX_DIM4 + 1] = acc0[1] + acc0[3];  in arm_mat_cmplx_mult_f32_4x4_mve()
358     pOut[1 * CMPLX_DIM * MATRIX_DIM4 + 0] = acc1[0] + acc1[2];  in arm_mat_cmplx_mult_f32_4x4_mve()
359     pOut[1 * CMPLX_DIM * MATRIX_DIM4 + 1] = acc1[1] + acc1[3];  in arm_mat_cmplx_mult_f32_4x4_mve()
360     pOut[2 * CMPLX_DIM * MATRIX_DIM4 + 0] = acc2[0] + acc2[2];  in arm_mat_cmplx_mult_f32_4x4_mve()
361     pOut[2 * CMPLX_DIM * MATRIX_DIM4 + 1] = acc2[1] + acc2[3];  in arm_mat_cmplx_mult_f32_4x4_mve()
362     pOut[3 * CMPLX_DIM * MATRIX_DIM4 + 0] = acc3[0] + acc3[2];  in arm_mat_cmplx_mult_f32_4x4_mve()
363     pOut[3 * CMPLX_DIM * MATRIX_DIM4 + 1] = acc3[1] + acc3[3];  in arm_mat_cmplx_mult_f32_4x4_mve()
407     pOut[0 * CMPLX_DIM * MATRIX_DIM4 + 0] = acc0[0] + acc0[2];  in arm_mat_cmplx_mult_f32_4x4_mve()
408     pOut[0 * CMPLX_DIM * MATRIX_DIM4 + 1] = acc0[1] + acc0[3];  in arm_mat_cmplx_mult_f32_4x4_mve()
409     pOut[1 * CMPLX_DIM * MATRIX_DIM4 + 0] = acc1[0] + acc1[2];  in arm_mat_cmplx_mult_f32_4x4_mve()
410     pOut[1 * CMPLX_DIM * MATRIX_DIM4 + 1] = acc1[1] + acc1[3];  in arm_mat_cmplx_mult_f32_4x4_mve()
411     pOut[2 * CMPLX_DIM * MATRIX_DIM4 + 0] = acc2[0] + acc2[2];  in arm_mat_cmplx_mult_f32_4x4_mve()
412     pOut[2 * CMPLX_DIM * MATRIX_DIM4 + 1] = acc2[1] + acc2[3];  in arm_mat_cmplx_mult_f32_4x4_mve()
413     pOut[3 * CMPLX_DIM * MATRIX_DIM4 + 0] = acc3[0] + acc3[2];  in arm_mat_cmplx_mult_f32_4x4_mve()
414     pOut[3 * CMPLX_DIM * MATRIX_DIM4 + 1] = acc3[1] + acc3[3];  in arm_mat_cmplx_mult_f32_4x4_mve()
458     pOut[0 * CMPLX_DIM * MATRIX_DIM4 + 0] = acc0[0] + acc0[2];  in arm_mat_cmplx_mult_f32_4x4_mve()
459     pOut[0 * CMPLX_DIM * MATRIX_DIM4 + 1] = acc0[1] + acc0[3];  in arm_mat_cmplx_mult_f32_4x4_mve()
460     pOut[1 * CMPLX_DIM * MATRIX_DIM4 + 0] = acc1[0] + acc1[2];  in arm_mat_cmplx_mult_f32_4x4_mve()
461     pOut[1 * CMPLX_DIM * MATRIX_DIM4 + 1] = acc1[1] + acc1[3];  in arm_mat_cmplx_mult_f32_4x4_mve()
462     pOut[2 * CMPLX_DIM * MATRIX_DIM4 + 0] = acc2[0] + acc2[2];  in arm_mat_cmplx_mult_f32_4x4_mve()
463     pOut[2 * CMPLX_DIM * MATRIX_DIM4 + 1] = acc2[1] + acc2[3];  in arm_mat_cmplx_mult_f32_4x4_mve()
464     pOut[3 * CMPLX_DIM * MATRIX_DIM4 + 0] = acc3[0] + acc3[2];  in arm_mat_cmplx_mult_f32_4x4_mve()
465     pOut[3 * CMPLX_DIM * MATRIX_DIM4 + 1] = acc3[1] + acc3[3];  in arm_mat_cmplx_mult_f32_4x4_mve()
509     pOut[0 * CMPLX_DIM * MATRIX_DIM4 + 0] = acc0[0] + acc0[2];  in arm_mat_cmplx_mult_f32_4x4_mve()
510     pOut[0 * CMPLX_DIM * MATRIX_DIM4 + 1] = acc0[1] + acc0[3];  in arm_mat_cmplx_mult_f32_4x4_mve()
511     pOut[1 * CMPLX_DIM * MATRIX_DIM4 + 0] = acc1[0] + acc1[2];  in arm_mat_cmplx_mult_f32_4x4_mve()
512     pOut[1 * CMPLX_DIM * MATRIX_DIM4 + 1] = acc1[1] + acc1[3];  in arm_mat_cmplx_mult_f32_4x4_mve()
513     pOut[2 * CMPLX_DIM * MATRIX_DIM4 + 0] = acc2[0] + acc2[2];  in arm_mat_cmplx_mult_f32_4x4_mve()
514     pOut[2 * CMPLX_DIM * MATRIX_DIM4 + 1] = acc2[1] + acc2[3];  in arm_mat_cmplx_mult_f32_4x4_mve()
515     pOut[3 * CMPLX_DIM * MATRIX_DIM4 + 0] = acc3[0] + acc3[2];  in arm_mat_cmplx_mult_f32_4x4_mve()
516     pOut[3 * CMPLX_DIM * MATRIX_DIM4 + 1] = acc3[1] + acc3[3];  in arm_mat_cmplx_mult_f32_4x4_mve()