Thomas Tsou | 0a3dc4c | 2013-11-09 02:29:55 -0500 | [diff] [blame] | 1 | /* |
| 2 | * NEON complex multiplication |
| 3 | * Copyright (C) 2012,2013 Thomas Tsou <tom@tsou.cc> |
| 4 | * |
| 5 | * This library is free software; you can redistribute it and/or |
| 6 | * modify it under the terms of the GNU Lesser General Public |
| 7 | * License as published by the Free Software Foundation; either |
| 8 | * version 2.1 of the License, or (at your option) any later version. |
| 9 | * |
| 10 | * This library is distributed in the hope that it will be useful, |
| 11 | * but WITHOUT ANY WARRANTY; without even the implied warranty of |
| 12 | * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU |
| 13 | * Lesser General Public License for more details. |
| 14 | * |
| 15 | * You should have received a copy of the GNU Lesser General Public |
| 16 | * License along with this library; if not, write to the Free Software |
| 17 | * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA |
| 18 | */ |
| 19 | |
| 20 | .syntax unified |
| 21 | .text |
| 22 | .align 2 |
| 23 | .global neon_cmplx_mul_4n |
| 24 | .type neon_cmplx_mul_4n, %function |
| 25 | neon_cmplx_mul_4n: |
| 26 | vpush {q4-q7} |
| 27 | .loop_mul: |
| 28 | vld2.32 {q0-q1}, [r1]! |
| 29 | vld2.32 {q2-q3}, [r2]! |
| 30 | vmul.f32 q4, q0, q2 |
| 31 | vmul.f32 q5, q1, q3 |
| 32 | vmul.f32 q6, q0, q3 |
| 33 | vmul.f32 q7, q2, q1 |
| 34 | vsub.f32 q8, q4, q5 |
| 35 | vadd.f32 q9, q6, q7 |
| 36 | vst2.32 {q8-q9}, [r0]! |
| 37 | subs r3, #1 |
| 38 | bne .loop_mul |
| 39 | vpop {q4-q7} |
| 40 | bx lr |
| 41 | .size neon_cmplx_mul_4n, .-neon_cmplx_mul_4n |
| 42 | .section .note.GNU-stack,"",%progbits |