aarch64: NEON float (i)MDCT

Approximately as fast as the ARM NEON version on Apple's A7.

1 files changed, 10 insertions, 0 deletions

diff --git a/libavcodec/aarch64/fft_init_aarch64.c b/libavcodec/aarch64/fft_init_aarch64.c
index caa5a0d90a..589e82d331 100644
--- a/libavcodec/aarch64/fft_init_aarch64.c
+++ b/libavcodec/aarch64/fft_init_aarch64.c
@@ -26,6 +26,10 @@
 void ff_fft_permute_neon(FFTContext *s, FFTComplex *z);
 void ff_fft_calc_neon(FFTContext *s, FFTComplex *z);
 
+void ff_imdct_calc_neon(FFTContext *s, FFTSample *output, const FFTSample *input);
+void ff_imdct_half_neon(FFTContext *s, FFTSample *output, const FFTSample *input);
+void ff_mdct_calc_neon(FFTContext *s, FFTSample *output, const FFTSample *input);
+
 av_cold void ff_fft_init_aarch64(FFTContext *s)
 {
     int cpu_flags = av_get_cpu_flags();
@@ -33,5 +37,11 @@ av_cold void ff_fft_init_aarch64(FFTContext *s)
     if (have_neon(cpu_flags)) {
         s->fft_permute  = ff_fft_permute_neon;
         s->fft_calc     = ff_fft_calc_neon;
+#if CONFIG_MDCT
+        s->imdct_calc   = ff_imdct_calc_neon;
+        s->imdct_half   = ff_imdct_half_neon;
+        s->mdct_calc    = ff_mdct_calc_neon;
+        s->mdct_permutation = FF_MDCT_PERM_INTERLEAVE;
+#endif
     }
 }