From 70eb77b34e9f08cd5e431921a2792f31e4b5265c Mon Sep 17 00:00:00 2001 From: Rostislav Pehlivanov Date: Sat, 29 Jul 2017 21:27:01 +0100 Subject: mdct15: add inverse transform postrotation SIMD 2.5ms frames: Before (c): 2638 decicycles in postrotate, 2097040 runs, 112 skips After (sse3): 1467 decicycles in postrotate, 2097083 runs, 69 skips After (avx2): 1244 decicycles in postrotate, 2097085 runs, 67 skips 5ms frames: Before (c): 4987 decicycles in postrotate, 1048371 runs, 205 skips After (sse3): 2644 decicycles in postrotate, 1048509 runs, 67 skips After (avx2): 2031 decicycles in postrotate, 1048523 runs, 53 skips 10ms frames: Before (c): 9153 decicycles in postrotate, 523575 runs, 713 skips After (sse3): 5110 decicycles in postrotate, 523726 runs, 562 skips After (avx2): 3738 decicycles in postrotate, 524223 runs, 65 skips 20ms frames: Before (c): 17857 decicycles in postrotate, 261866 runs, 278 skips After (sse3): 10041 decicycles in postrotate, 261746 runs, 398 skips After (avx2): 7050 decicycles in postrotate, 262116 runs, 28 skips Improves total decoding performance for real world content by 9% with avx2. Signed-off-by: Rostislav Pehlivanov --- libavcodec/mdct15.h | 3 +++ 1 file changed, 3 insertions(+) (limited to 'libavcodec/mdct15.h') diff --git a/libavcodec/mdct15.h b/libavcodec/mdct15.h index 1c2149d436..42e60f3e10 100644 --- a/libavcodec/mdct15.h +++ b/libavcodec/mdct15.h @@ -42,6 +42,9 @@ typedef struct MDCT15Context { /* 15-point FFT */ void (*fft15)(FFTComplex *out, FFTComplex *in, FFTComplex *exptab, ptrdiff_t stride); + /* PFA postrotate and exptab */ + void (*postreindex)(FFTComplex *out, FFTComplex *in, FFTComplex *exp, int *lut, ptrdiff_t len8); + /* Calculate a full 2N -> N MDCT */ void (*mdct)(struct MDCT15Context *s, float *dst, const float *src, ptrdiff_t stride); -- cgit v1.2.3