fix(windows): vendor audiopus_sys + patch libopus for clang-cl SIMD

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>

vendor/audiopus_sys/opus/silk/NLSF_decode.c

@@ -0,0 +1,93 @@
+/***********************************************************************
+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.
+***********************************************************************/
+
+#ifdef HAVE_CONFIG_H
+#include "config.h"
+#endif
+
+#include "main.h"
+
+/* Predictive dequantizer for NLSF residuals */
+static OPUS_INLINE void silk_NLSF_residual_dequant(          /* O    Returns RD value in Q30                     */
+          opus_int16         x_Q10[],                        /* O    Output [ order ]                            */
+    const opus_int8          indices[],                      /* I    Quantization indices [ order ]              */
+    const opus_uint8         pred_coef_Q8[],                 /* I    Backward predictor coefs [ order ]          */
+    const opus_int           quant_step_size_Q16,            /* I    Quantization step size                      */
+    const opus_int16         order                           /* I    Number of input values                      */
+)
+{
+    opus_int     i, out_Q10, pred_Q10;
+
+    out_Q10 = 0;
+    for( i = order-1; i >= 0; i-- ) {
+        pred_Q10 = silk_RSHIFT( silk_SMULBB( out_Q10, (opus_int16)pred_coef_Q8[ i ] ), 8 );
+        out_Q10  = silk_LSHIFT( indices[ i ], 10 );
+        if( out_Q10 > 0 ) {
+            out_Q10 = silk_SUB16( out_Q10, SILK_FIX_CONST( NLSF_QUANT_LEVEL_ADJ, 10 ) );
+        } else if( out_Q10 < 0 ) {
+            out_Q10 = silk_ADD16( out_Q10, SILK_FIX_CONST( NLSF_QUANT_LEVEL_ADJ, 10 ) );
+        }
+        out_Q10  = silk_SMLAWB( pred_Q10, (opus_int32)out_Q10, quant_step_size_Q16 );
+        x_Q10[ i ] = out_Q10;
+    }
+}
+
+
+/***********************/
+/* NLSF vector decoder */
+/***********************/
+void silk_NLSF_decode(
+          opus_int16            *pNLSF_Q15,                     /* O    Quantized NLSF vector [ LPC_ORDER ]         */
+          opus_int8             *NLSFIndices,                   /* I    Codebook path vector [ LPC_ORDER + 1 ]      */
+    const silk_NLSF_CB_struct   *psNLSF_CB                      /* I    Codebook object                             */
+)
+{
+    opus_int         i;
+    opus_uint8       pred_Q8[  MAX_LPC_ORDER ];
+    opus_int16       ec_ix[    MAX_LPC_ORDER ];
+    opus_int16       res_Q10[  MAX_LPC_ORDER ];
+    opus_int32       NLSF_Q15_tmp;
+    const opus_uint8 *pCB_element;
+    const opus_int16 *pCB_Wght_Q9;
+
+    /* Unpack entropy table indices and predictor for current CB1 index */
+    silk_NLSF_unpack( ec_ix, pred_Q8, psNLSF_CB, NLSFIndices[ 0 ] );
+
+    /* Predictive residual dequantizer */
+    silk_NLSF_residual_dequant( res_Q10, &NLSFIndices[ 1 ], pred_Q8, psNLSF_CB->quantStepSize_Q16, psNLSF_CB->order );
+
+    /* Apply inverse square-rooted weights to first stage and add to output */
+    pCB_element = &psNLSF_CB->CB1_NLSF_Q8[ NLSFIndices[ 0 ] * psNLSF_CB->order ];
+    pCB_Wght_Q9 = &psNLSF_CB->CB1_Wght_Q9[ NLSFIndices[ 0 ] * psNLSF_CB->order ];
+    for( i = 0; i < psNLSF_CB->order; i++ ) {
+        NLSF_Q15_tmp = silk_ADD_LSHIFT32( silk_DIV32_16( silk_LSHIFT( (opus_int32)res_Q10[ i ], 14 ), pCB_Wght_Q9[ i ] ), (opus_int16)pCB_element[ i ], 7 );
+        pNLSF_Q15[ i ] = (opus_int16)silk_LIMIT( NLSF_Q15_tmp, 0, 32767 );
+    }
+
+    /* NLSF stabilization */
+    silk_NLSF_stabilize( pNLSF_Q15, psNLSF_CB->deltaMin_Q15, psNLSF_CB->order );
+}