| Require: Matrix S ( matrix, ) |
| Ensure: Matrix S ‘( matrix, ) |
| 1: for i from 0 to N, i+= BLOCK_TRANSPOSE do |
| 2: if i+BLOCK_TRANSPOSE > N |
| 3: let i-= BLOCK_TRANSPOSE-NBLOCK_TRANSPOSE; |
| 4: for j from 0 to L, j+=BLOCK_TRANSPOSE do |
| 5: if j+BLOCK_TRANSPOSE > L |
| 6: let j-= BLOCK_TRANSPOSE-LBLOCK_TRANSPOSE; |
| 7: vec1_l=NEON_Vector_Load(S+iL+j); |
| 8: vec1_h=NEON_Vector_Load(S+iL+j+8); |
| 9: vec2_l=NEON_Vector_Load(S+(i+8)L+j); |
| 10: vec2_h=NEON_Vector_Load(S+(i+8)L+j+8); |
| 11: t2 = NEON_Vector_Interleave(vec1_l, vec2_l); |
| 12: t3 = NEON_Vector_Interleave(vec1_h, vec2_h); |
| 13: vec1_l = NEON_Vector_Load(S + (i + 2) LWE_L + j); |
| 14: vec1_h = NEON_Vector_Load (S + (i + 2) LWE_L + j + 8); |
| 15: vec2_l = NEON_Vector_Load (S + (i + 10) LWE_L + j); |
| 16: vec2_h = NEON_Vector_Load (S + (i + 10) LWE_L + j + 8); |
| 17: t4 = NEON_Vector_Interleave(vec1_l, vec2_l); |
| 18: t5 = NEON_Vector_Interleave(vec1_h, vec2_h); |
| 19: vec1_l = NEON_Vector_Load (S + (i + 3) LWE_L + j); |
| 20: vec1_h = NEON_Vector_Load (S + (i + 3) LWE_L + j + 8); |
| 21: vec2_l = NEON_Vector_Load (S + (i + 11) LWE_L + j); |
| 22: vec2_h = NEON_Vector_Load (S + (i + 11) LWE_L + j + 8); |
| 23: t6 = NEON_Vector_Interleave(vec1_l, vec2_l); |
| 24: t7 = NEON_Vector_Interleave(vec1_h, vec2_h); |
| 25: m0 = NEON_Vector_Interleave(t0.val[], t4.val[]); |
| 26: m1 = NEON_Vector_Interleave(t0.val[], t4.val[]); |
| 27: m2 = NEON_Vector_Interleave(t1.val[], t5.val[]); |
| 28: m3 = NEON_Vector_Interleave(t1.val[], t5.val[]);// |
| 29: m4 = NEON_Vector_Interleave(t2.val[], t6.val[]); |
| 30: m5 = NEON_Vector_Interleave(t2.val[], t6.val[]); |
| 31: m6 = NEON_Vector_Interleave(t3.val[], t7.val[]); |
| 32: m7 = NEON_Vector_Interleave(t3.val[], t7.val[]); |
| 33: t0 = NEON_Vector_Interleave(m0.val[], m4.val[]); |
| 34: t1 = NEON_Vector_Interleave(m0.val[], m4.val[]); |
| 35: t2 = NEON_Vector_Interleave(m1.val[], m5.val[]); |
| 36: t3 = NEON_Vector_Interleave(m1.val[], m5.val[]); |
| 37: t4 = NEON_Vector_Interleave(m2.val[], m6.val[]); |
| 38: t5 = NEON_Vector_Interleave(m2.val[], m6.val[]); |
| 39: t6 = NEON_Vector_Interleave(m3.val[], m7.val[]); |
| 40: t7 = NEON_Vector_Interleave(m3.val[], m7.val[]); |
| 41: NEON_Vector_Store (S’ + j LWE_N + i, t0.val[]); |
| 42: NEON_Vector_Store (S’ + j LWE_N + i + 8, t0.val[]); |
| 43: NEON_Vector_Store (S’ + (j + 1) LWE_N + i, t1.val[]); |
| 44: NEON_Vector_Store (S’ + (j + 1) LWE_N + i + 8, t1.val[]); |
| 45: NEON_Vector_Store (S’ + (j + 2) LWE_N + i, t2.val[]); |
| 46: NEON_Vector_Store (S’ + (j + 2) LWE_N + i + 8, t2.val[]); |
| 47: NEON_Vector_Store (S’ + (j + 3) LWE_N + i, t3.val[]); |
| 48: NEON_Vector_Store (S’ + (j + 3) LWE_N + i + 8, t3.val[]); |
| 49: NEON_Vector_Store (S’ + (j + 4) LWE_N + i, t4.val[]); |
| 50: NEON_Vector_Store (S’ + (j + 4) LWE_N + i + 8, t4.val[]); |
| 51: NEON_Vector_Store (S’ + (j + 5) LWE_N + i, t5.val[]); |
| 52: NEON_Vector_Store (S’ + (j + 5) LWE_N + i + 8, t5.val[]); |
| 53: NEON_Vector_Store (S’ + (j + 6) LWE_N + i, t6.val[]); |
| 54: NEON_Vector_Store (S’ + (j + 6) LWE_N + i + 8, t6.val[]); |
| 55: NEON_Vector_Store (S’ + (j + 7) LWE_N + i, t7.val[]); |
| 56: NEON_Vector_Store (S’ + (j + 7) LWE_N + i + 8, t7.val[]); |
| 57: Return S’ |
