diff options
| author | Peter Meerwald <pmeerw@pmeerw.net> | 2015-02-15 12:21:25 +0100 |
|---|---|---|
| committer | Martin Storsjö <martin@martin.st> | 2015-02-15 22:47:21 +0200 |
| commit | 702458538d4e52809bcef460d39baabf061b16b5 (patch) | |
| tree | d258db5fb5af6982f278a199547782aa36161e35 /libavcodec/arm/g722dsp_neon.S | |
| parent | 73ae0a9d12857852222363f9a7c14d07058ebfd3 (diff) | |
g722: Add ARM NEON implementation for g722_apply_qmf()
Signed-off-by: Peter Meerwald <pmeerw@pmeerw.net>
Signed-off-by: Martin Storsjö <martin@martin.st>
Diffstat (limited to 'libavcodec/arm/g722dsp_neon.S')
| -rw-r--r-- | libavcodec/arm/g722dsp_neon.S | 69 |
1 files changed, 69 insertions, 0 deletions
diff --git a/libavcodec/arm/g722dsp_neon.S b/libavcodec/arm/g722dsp_neon.S new file mode 100644 index 0000000000..5fa3c279e9 --- /dev/null +++ b/libavcodec/arm/g722dsp_neon.S @@ -0,0 +1,69 @@ +/* + * ARM NEON optimised DSP functions for G722 coding + * Copyright (c) 2015 Peter Meerwald <pmeerw@pmeerw.net> + * + * This file is part of Libav. + * + * Libav is free software; you can redistribute it and/or + * modify it under the terms of the GNU Lesser General Public + * License as published by the Free Software Foundation; either + * version 2.1 of the License, or (at your option) any later version. + * + * Libav is distributed in the hope that it will be useful, + * but WITHOUT ANY WARRANTY; without even the implied warranty of + * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU + * Lesser General Public License for more details. + * + * You should have received a copy of the GNU Lesser General Public + * License along with Libav; if not, write to the Free Software + * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA + */ + +#include "libavutil/arm/asm.S" + +function ff_g722_apply_qmf_neon, export=1, align=4 + movrel r3, qmf_coeffs + vld1.s16 {d2,d3,d4}, [r0]! /* load prev_samples */ + vld1.s16 {d16,d17,d18}, [r3,:64]! /* load qmf_coeffs */ + vmull.s16 q0, d2, d16 + vmlal.s16 q0, d3, d17 + vmlal.s16 q0, d4, d18 + + vld1.s16 {d5,d6,d7}, [r0]! /* load prev_samples */ + vld1.s16 {d19,d20,d21}, [r3,:64]! /* load qmf_coeffs */ + vmlal.s16 q0, d5, d19 + vmlal.s16 q0, d6, d20 + vmlal.s16 q0, d7, d21 + + vadd.s32 d0, d1, d0 + vrev64.32 d0, d0 + vst1.s32 {d0}, [r1] + bx lr +endfunc + +const qmf_coeffs, align=4 + .hword 3 + .hword -11 + .hword -11 + .hword 53 + .hword 12 + .hword -156 + .hword 32 + .hword 362 + .hword -210 + .hword -805 + .hword 951 + .hword 3876 + .hword 3876 + .hword 951 + .hword -805 + .hword -210 + .hword 362 + .hword 32 + .hword -156 + .hword 12 + .hword 53 + .hword -11 + .hword -11 + .hword 3 +endconst |