0683dde5d3
cargo-xwin drives the Windows MSVC cross-compile via clang-cl, under which CMake sets MSVC=1 — causing libopus 1.3.1's `if(NOT MSVC)` guards to skip the per-file `-msse4.1` / `-mssse3` COMPILE_FLAGS that its x86 SIMD source files need. Clang-cl (unlike real cl.exe) still honors Clang's target-feature system, so those files then fail to compile with "always_inline function '_mm_cvtepi16_epi32' requires target feature 'sse4.1'" errors across silk/NSQ_sse4_1.c, NSQ_del_dec_sse4_1.c, and VQ_WMat_EC_sse4_1.c. Earlier attempts to fix this downstream (cargo-xwin toolchain file, override.cmake CMAKE_C_COMPILE_OBJECT <FLAGS> replace, CFLAGS env vars) all failed because cargo-xwin rewrites override.cmake from scratch on every `cargo xwin build` invocation and cmake-rs's -DCMAKE_C_FLAGS= assembly happens before toolchain FORCE sets propagate. Fixing it upstream at the source: vendor audiopus_sys 0.2.2 into vendor/audiopus_sys, patch its bundled opus/CMakeLists.txt to introduce an MSVC_CL var (true only when CMAKE_C_COMPILER_ID == "MSVC", i.e. real cl.exe), and flip the eight `if(NOT MSVC)` SIMD guards to `if(NOT MSVC_CL)`. Clang-cl then gets the GCC-style per-file flags and the SSE4.1 sources build cleanly. Also flip the `if(MSVC)` global /arch block at line 445 to `if(MSVC_CL)` so only cl.exe applies /arch:AVX and clang-cl relies purely on per-file flags (no global/per-file mixing). Wire via [patch.crates-io] in the workspace root Cargo.toml; the patch is resolved relative to the workspace root as `vendor/audiopus_sys`. Upstream context: xiph/opus#256, xiph/opus PR #257 (both stale). Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>
122 lines
6.7 KiB
C
122 lines
6.7 KiB
C
/***********************************************************************
|
|
Copyright (c) 2006-2011, Skype Limited. All rights reserved.
|
|
Redistribution and use in source and binary forms, with or without
|
|
modification, are permitted provided that the following conditions
|
|
are met:
|
|
- Redistributions of source code must retain the above copyright notice,
|
|
this list of conditions and the following disclaimer.
|
|
- Redistributions in binary form must reproduce the above copyright
|
|
notice, this list of conditions and the following disclaimer in the
|
|
documentation and/or other materials provided with the distribution.
|
|
- Neither the name of Internet Society, IETF or IETF Trust, nor the
|
|
names of specific contributors, may be used to endorse or promote
|
|
products derived from this software without specific prior written
|
|
permission.
|
|
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
|
|
AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
|
|
IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
|
|
ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE
|
|
LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR
|
|
CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF
|
|
SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS
|
|
INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN
|
|
CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE)
|
|
ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE
|
|
POSSIBILITY OF SUCH DAMAGE.
|
|
***********************************************************************/
|
|
|
|
/* *
|
|
* silk_biquad_alt.c *
|
|
* *
|
|
* Second order ARMA filter *
|
|
* Can handle slowly varying filter coefficients *
|
|
* */
|
|
|
|
#ifdef HAVE_CONFIG_H
|
|
#include "config.h"
|
|
#endif
|
|
|
|
#include "SigProc_FIX.h"
|
|
|
|
/* Second order ARMA filter, alternative implementation */
|
|
void silk_biquad_alt_stride1(
|
|
const opus_int16 *in, /* I input signal */
|
|
const opus_int32 *B_Q28, /* I MA coefficients [3] */
|
|
const opus_int32 *A_Q28, /* I AR coefficients [2] */
|
|
opus_int32 *S, /* I/O State vector [2] */
|
|
opus_int16 *out, /* O output signal */
|
|
const opus_int32 len /* I signal length (must be even) */
|
|
)
|
|
{
|
|
/* DIRECT FORM II TRANSPOSED (uses 2 element state vector) */
|
|
opus_int k;
|
|
opus_int32 inval, A0_U_Q28, A0_L_Q28, A1_U_Q28, A1_L_Q28, out32_Q14;
|
|
|
|
/* Negate A_Q28 values and split in two parts */
|
|
A0_L_Q28 = ( -A_Q28[ 0 ] ) & 0x00003FFF; /* lower part */
|
|
A0_U_Q28 = silk_RSHIFT( -A_Q28[ 0 ], 14 ); /* upper part */
|
|
A1_L_Q28 = ( -A_Q28[ 1 ] ) & 0x00003FFF; /* lower part */
|
|
A1_U_Q28 = silk_RSHIFT( -A_Q28[ 1 ], 14 ); /* upper part */
|
|
|
|
for( k = 0; k < len; k++ ) {
|
|
/* S[ 0 ], S[ 1 ]: Q12 */
|
|
inval = in[ k ];
|
|
out32_Q14 = silk_LSHIFT( silk_SMLAWB( S[ 0 ], B_Q28[ 0 ], inval ), 2 );
|
|
|
|
S[ 0 ] = S[1] + silk_RSHIFT_ROUND( silk_SMULWB( out32_Q14, A0_L_Q28 ), 14 );
|
|
S[ 0 ] = silk_SMLAWB( S[ 0 ], out32_Q14, A0_U_Q28 );
|
|
S[ 0 ] = silk_SMLAWB( S[ 0 ], B_Q28[ 1 ], inval);
|
|
|
|
S[ 1 ] = silk_RSHIFT_ROUND( silk_SMULWB( out32_Q14, A1_L_Q28 ), 14 );
|
|
S[ 1 ] = silk_SMLAWB( S[ 1 ], out32_Q14, A1_U_Q28 );
|
|
S[ 1 ] = silk_SMLAWB( S[ 1 ], B_Q28[ 2 ], inval );
|
|
|
|
/* Scale back to Q0 and saturate */
|
|
out[ k ] = (opus_int16)silk_SAT16( silk_RSHIFT( out32_Q14 + (1<<14) - 1, 14 ) );
|
|
}
|
|
}
|
|
|
|
void silk_biquad_alt_stride2_c(
|
|
const opus_int16 *in, /* I input signal */
|
|
const opus_int32 *B_Q28, /* I MA coefficients [3] */
|
|
const opus_int32 *A_Q28, /* I AR coefficients [2] */
|
|
opus_int32 *S, /* I/O State vector [4] */
|
|
opus_int16 *out, /* O output signal */
|
|
const opus_int32 len /* I signal length (must be even) */
|
|
)
|
|
{
|
|
/* DIRECT FORM II TRANSPOSED (uses 2 element state vector) */
|
|
opus_int k;
|
|
opus_int32 A0_U_Q28, A0_L_Q28, A1_U_Q28, A1_L_Q28, out32_Q14[ 2 ];
|
|
|
|
/* Negate A_Q28 values and split in two parts */
|
|
A0_L_Q28 = ( -A_Q28[ 0 ] ) & 0x00003FFF; /* lower part */
|
|
A0_U_Q28 = silk_RSHIFT( -A_Q28[ 0 ], 14 ); /* upper part */
|
|
A1_L_Q28 = ( -A_Q28[ 1 ] ) & 0x00003FFF; /* lower part */
|
|
A1_U_Q28 = silk_RSHIFT( -A_Q28[ 1 ], 14 ); /* upper part */
|
|
|
|
for( k = 0; k < len; k++ ) {
|
|
/* S[ 0 ], S[ 1 ], S[ 2 ], S[ 3 ]: Q12 */
|
|
out32_Q14[ 0 ] = silk_LSHIFT( silk_SMLAWB( S[ 0 ], B_Q28[ 0 ], in[ 2 * k + 0 ] ), 2 );
|
|
out32_Q14[ 1 ] = silk_LSHIFT( silk_SMLAWB( S[ 2 ], B_Q28[ 0 ], in[ 2 * k + 1 ] ), 2 );
|
|
|
|
S[ 0 ] = S[ 1 ] + silk_RSHIFT_ROUND( silk_SMULWB( out32_Q14[ 0 ], A0_L_Q28 ), 14 );
|
|
S[ 2 ] = S[ 3 ] + silk_RSHIFT_ROUND( silk_SMULWB( out32_Q14[ 1 ], A0_L_Q28 ), 14 );
|
|
S[ 0 ] = silk_SMLAWB( S[ 0 ], out32_Q14[ 0 ], A0_U_Q28 );
|
|
S[ 2 ] = silk_SMLAWB( S[ 2 ], out32_Q14[ 1 ], A0_U_Q28 );
|
|
S[ 0 ] = silk_SMLAWB( S[ 0 ], B_Q28[ 1 ], in[ 2 * k + 0 ] );
|
|
S[ 2 ] = silk_SMLAWB( S[ 2 ], B_Q28[ 1 ], in[ 2 * k + 1 ] );
|
|
|
|
S[ 1 ] = silk_RSHIFT_ROUND( silk_SMULWB( out32_Q14[ 0 ], A1_L_Q28 ), 14 );
|
|
S[ 3 ] = silk_RSHIFT_ROUND( silk_SMULWB( out32_Q14[ 1 ], A1_L_Q28 ), 14 );
|
|
S[ 1 ] = silk_SMLAWB( S[ 1 ], out32_Q14[ 0 ], A1_U_Q28 );
|
|
S[ 3 ] = silk_SMLAWB( S[ 3 ], out32_Q14[ 1 ], A1_U_Q28 );
|
|
S[ 1 ] = silk_SMLAWB( S[ 1 ], B_Q28[ 2 ], in[ 2 * k + 0 ] );
|
|
S[ 3 ] = silk_SMLAWB( S[ 3 ], B_Q28[ 2 ], in[ 2 * k + 1 ] );
|
|
|
|
/* Scale back to Q0 and saturate */
|
|
out[ 2 * k + 0 ] = (opus_int16)silk_SAT16( silk_RSHIFT( out32_Q14[ 0 ] + (1<<14) - 1, 14 ) );
|
|
out[ 2 * k + 1 ] = (opus_int16)silk_SAT16( silk_RSHIFT( out32_Q14[ 1 ] + (1<<14) - 1, 14 ) );
|
|
}
|
|
}
|