float sum;
/* copy to avoid wrap */
- memcpy(in + 512, in, 32 * sizeof(*in));
+ __asm__ volatile(
+ "movaps 0(%0), %%xmm0 \n\t" \
+ "movaps 16(%0), %%xmm1 \n\t" \
+ "movaps 32(%0), %%xmm2 \n\t" \
+ "movaps 48(%0), %%xmm3 \n\t" \
+ "movaps %%xmm0, 0(%1) \n\t" \
+ "movaps %%xmm1, 16(%1) \n\t" \
+ "movaps %%xmm2, 32(%1) \n\t" \
+ "movaps %%xmm3, 48(%1) \n\t" \
+ "movaps 64(%0), %%xmm0 \n\t" \
+ "movaps 80(%0), %%xmm1 \n\t" \
+ "movaps 96(%0), %%xmm2 \n\t" \
+ "movaps 112(%0), %%xmm3 \n\t" \
+ "movaps %%xmm0, 64(%1) \n\t" \
+ "movaps %%xmm1, 80(%1) \n\t" \
+ "movaps %%xmm2, 96(%1) \n\t" \
+ "movaps %%xmm3, 112(%1) \n\t"
+ ::"r"(in), "r"(in+512)
+ :"memory"
+ );
apply_window(in + 16, win , win + 512, suma, sumc, 16);
apply_window(in + 32, win + 48, win + 640, sumb, sumd, 16);
} \
}
+#if HAVE_YASM
+#if HAVE_SSE
DECL_IMDCT_BLOCKS(sse,sse)
DECL_IMDCT_BLOCKS(sse2,sse)
DECL_IMDCT_BLOCKS(sse3,sse)
DECL_IMDCT_BLOCKS(ssse3,sse)
+#endif
+#if HAVE_AVX
DECL_IMDCT_BLOCKS(avx,avx)
+#endif
+#endif
void ff_mpadsp_init_mmx(MPADSPContext *s)
{
s->apply_window_float = apply_window_mp3;
}
#if HAVE_YASM
- if (mm_flags & AV_CPU_FLAG_AVX && HAVE_AVX) {
+ if (0) {
+#if HAVE_AVX
+ } else if (mm_flags & AV_CPU_FLAG_AVX && HAVE_AVX) {
s->imdct36_blocks_float = imdct36_blocks_avx;
+#endif
#if HAVE_SSE
} else if (mm_flags & AV_CPU_FLAG_SSSE3) {
s->imdct36_blocks_float = imdct36_blocks_ssse3;