- "casp %[t0], %H[t0], %[wdata], %H[wdata], [%[loc]]\n"
- "casp %[t1], %H[t1], %[wdata], %H[wdata], [%[loc]]\n"
- "casp %[t2], %H[t2], %[wdata], %H[wdata], [%[loc]]\n"
- "casp %[t3], %H[t3], %[wdata], %H[wdata], [%[loc]]\n"
- "casp %[t4], %H[t4], %[wdata], %H[wdata], [%[loc]]\n"
- "casp %[t5], %H[t5], %[wdata], %H[wdata], [%[loc]]\n"
- "casp %[t6], %H[t6], %[wdata], %H[wdata], [%[loc]]\n"
- "casp %[t7], %H[t7], %[wdata], %H[wdata], [%[loc]]\n"
- "casp %[t8], %H[t8], %[wdata], %H[wdata], [%[loc]]\n"
- "casp %[t9], %H[t9], %[wdata], %H[wdata], [%[loc]]\n"
- "casp %[t10], %H[t10], %[wdata], %H[wdata], [%[loc]]\n"
- "casp %[t11], %H[t11], %[wdata], %H[wdata], [%[loc]]\n"
- "fmov d16, %[t0]\n"
- "fmov v16.D[1], %H[t0]\n"
- "casp %[t0], %H[t0], %[wdata], %H[wdata], [%[loc]]\n"
- "fmov d17, %[t1]\n"
- "fmov v17.D[1], %H[t1]\n"
- "casp %[t1], %H[t1], %[wdata], %H[wdata], [%[loc]]\n"
- "fmov d18, %[t2]\n"
- "fmov v18.D[1], %H[t2]\n"
- "casp %[t2], %H[t2], %[wdata], %H[wdata], [%[loc]]\n"
- "fmov d19, %[t3]\n"
- "fmov v19.D[1], %H[t3]\n"
- "casp %[t3], %H[t3], %[wdata], %H[wdata], [%[loc]]\n"
+ "casp x0, x1, %[wdata64], %[wdata128], [%[loc]]\n"
+ "casp x2, x3, %[wdata64], %[wdata128], [%[loc]]\n"
+ "casp x4, x5, %[wdata64], %[wdata128], [%[loc]]\n"
+ "casp x6, x7, %[wdata64], %[wdata128], [%[loc]]\n"
+ "casp x8, x9, %[wdata64], %[wdata128], [%[loc]]\n"
+ "casp x10, x11, %[wdata64], %[wdata128], [%[loc]]\n"
+ "casp x12, x13, %[wdata64], %[wdata128], [%[loc]]\n"
+ "casp x14, x15, %[wdata64], %[wdata128], [%[loc]]\n"
+ "casp x16, x17, %[wdata64], %[wdata128], [%[loc]]\n"
+ "casp x18, x19, %[wdata64], %[wdata128], [%[loc]]\n"
+ "casp x20, x21, %[wdata64], %[wdata128], [%[loc]]\n"
+ "casp x22, x23, %[wdata64], %[wdata128], [%[loc]]\n"
+ "fmov d16, x0\n"
+ "fmov v16.D[1], x1\n"
+ "casp x0, x1, %[wdata64], %[wdata128], [%[loc]]\n"
+ "fmov d17, x2\n"
+ "fmov v17.D[1], x3\n"
+ "casp x2, x3, %[wdata64], %[wdata128], [%[loc]]\n"
+ "fmov d18, x4\n"
+ "fmov v18.D[1], x5\n"
+ "casp x4, x5, %[wdata64], %[wdata128], [%[loc]]\n"
+ "fmov d19, x6\n"
+ "fmov v19.D[1], x7\n"
+ "casp x6, x7, %[wdata64], %[wdata128], [%[loc]]\n"