aacenc: add SIMD optimizations for abs_pow34 and quantization

Performance improvements:

quant_bands:
with:     681 decicycles in quant_bands, 8388453 runs,    155 skips
without: 1190 decicycles in quant_bands, 8388386 runs,    222 skips
Around 42% for the function

Twoloop coder:

abs_pow34:
with/without: 7.82s/8.17s
Around 4% for the entire encoder

Both:
with/without: 7.15s/8.17s
Around 12% for the entire encoder

Fast coder:

abs_pow34:
with/without: 3.40s/3.77s
Around 10% for the entire encoder

Both:
with/without: 3.02s/3.77s
Around 20% faster for the entire encoder

Signed-off-by: Rostislav Pehlivanov <atomnuker@gmail.com>
Tested-by: Michael Niedermayer <michael@niedermayer.cc>
Reviewed-by: James Almer <jamrial@gmail.com>

1 files changed, 6 insertions, 0 deletions

diff --git a/libavcodec/aacenc.h b/libavcodec/aacenc.h
index 1ace00d2e0..38a9734994 100644
--- a/libavcodec/aacenc.h
+++ b/libavcodec/aacenc.h
@@ -127,11 +127,17 @@ typedef struct AACEncContext {
     uint16_t quantize_band_cost_cache_generation;
     AACQuantizeBandCostCacheEntry quantize_band_cost_cache[256][128]; ///< memoization area for quantize_band_cost
 
+    void (*abs_pow34)(float *out, const float *in, const int size);
+    void (*quant_bands)(int *out, const float *in, const float *scaled,
+                        int size, int is_signed, int maxval, const float Q34,
+                        const float rounding);
+
     struct {
         float *samples;
     } buffer;
 } AACEncContext;
 
+void ff_aac_dsp_init_x86(AACEncContext *s);
 void ff_aac_coder_init_mips(AACEncContext *c);
 void ff_quantize_band_cost_cache_init(struct AACEncContext *s);