| 1 | ;****************************************************************************** |
| 2 | ;* FLAC DSP SIMD optimizations |
| 3 | ;* |
| 4 | ;* Copyright (C) 2014 Loren Merritt |
| 5 | ;* |
| 6 | ;* This file is part of FFmpeg. |
| 7 | ;* |
| 8 | ;* FFmpeg is free software; you can redistribute it and/or |
| 9 | ;* modify it under the terms of the GNU Lesser General Public |
| 10 | ;* License as published by the Free Software Foundation; either |
| 11 | ;* version 2.1 of the License, or (at your option) any later version. |
| 12 | ;* |
| 13 | ;* FFmpeg is distributed in the hope that it will be useful, |
| 14 | ;* but WITHOUT ANY WARRANTY; without even the implied warranty of |
| 15 | ;* MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU |
| 16 | ;* Lesser General Public License for more details. |
| 17 | ;* |
| 18 | ;* You should have received a copy of the GNU Lesser General Public |
| 19 | ;* License along with FFmpeg; if not, write to the Free Software |
| 20 | ;* Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA |
| 21 | ;****************************************************************************** |
| 22 | |
| 23 | %include "libavutil/x86/x86util.asm" |
| 24 | |
| 25 | SECTION .text |
| 26 | |
| 27 | %macro LPC_32 1 |
| 28 | INIT_XMM %1 |
| 29 | cglobal flac_lpc_32, 5,6,5, decoded, coeffs, pred_order, qlevel, len, j |
| 30 | sub lend, pred_orderd |
| 31 | jle .ret |
| 32 | lea decodedq, [decodedq+pred_orderq*4-8] |
| 33 | lea coeffsq, [coeffsq+pred_orderq*4] |
| 34 | neg pred_orderq |
| 35 | movd m4, qlevelm |
| 36 | ALIGN 16 |
| 37 | .loop_sample: |
| 38 | movd m0, [decodedq+pred_orderq*4+8] |
| 39 | add decodedq, 8 |
| 40 | movd m1, [coeffsq+pred_orderq*4] |
| 41 | pxor m2, m2 |
| 42 | pxor m3, m3 |
| 43 | lea jq, [pred_orderq+1] |
| 44 | test jq, jq |
| 45 | jz .end_order |
| 46 | .loop_order: |
| 47 | PMACSDQL m2, m0, m1, m2, m0 |
| 48 | movd m0, [decodedq+jq*4] |
| 49 | PMACSDQL m3, m1, m0, m3, m1 |
| 50 | movd m1, [coeffsq+jq*4] |
| 51 | inc jq |
| 52 | jl .loop_order |
| 53 | .end_order: |
| 54 | PMACSDQL m2, m0, m1, m2, m0 |
| 55 | psrlq m2, m4 |
| 56 | movd m0, [decodedq] |
| 57 | paddd m0, m2 |
| 58 | movd [decodedq], m0 |
| 59 | sub lend, 2 |
| 60 | jl .ret |
| 61 | PMACSDQL m3, m1, m0, m3, m1 |
| 62 | psrlq m3, m4 |
| 63 | movd m1, [decodedq+4] |
| 64 | paddd m1, m3 |
| 65 | movd [decodedq+4], m1 |
| 66 | jg .loop_sample |
| 67 | .ret: |
| 68 | REP_RET |
| 69 | %endmacro |
| 70 | |
| 71 | %if HAVE_XOP_EXTERNAL |
| 72 | LPC_32 xop |
| 73 | %endif |
| 74 | LPC_32 sse4 |