[FFmpeg-devel] [RFC/PATCH] bitpacked_dec: Optimization for bitpacked_dec decoder performance

[Devin Heitmueller]

Rework the code a bit to speed up the 10-bit bitpacked decoding
routine.  This is probably about as fast as I can get it without
switching to assembly language.

Demonstratable with:

./ffmpeg -f lavfi -i "smptehdbars=size=3840x2160" -c bitpacked -f image2 -frames:v 1 source.yuv
./ffmpeg -f bitpacked -pix_fmt yuv422p10le -s 3840x2160 -c:v bitpacked -i source.yuv -pix_fmt yuv422p10le out.yuv

On my development system, it went from 80ms for a 2160p frame
down to 20ms (i.e. a 4X speedup).  Good enough for now, I hope...

Signed-off-by: Devin Heitmueller <dheitmueller at ltnglobal.com>
---
 libavcodec/bitpacked_dec.c | 17 +++++++----------
 1 file changed, 7 insertions(+), 10 deletions(-)

diff --git a/libavcodec/bitpacked_dec.c b/libavcodec/bitpacked_dec.c
index a1ffef1..96aba27 100644
--- a/libavcodec/bitpacked_dec.c
+++ b/libavcodec/bitpacked_dec.c
@@ -28,7 +28,6 @@
 
 #include "avcodec.h"
 #include "codec_internal.h"
-#include "get_bits.h"
 #include "libavutil/imgutils.h"
 #include "thread.h"
 
@@ -65,7 +64,7 @@ static int bitpacked_decode_yuv422p10(AVCodecContext *avctx, AVFrame *frame,
 {
     uint64_t frame_size = (uint64_t)avctx->width * (uint64_t)avctx->height * 20;
     uint64_t packet_size = (uint64_t)avpkt->size * 8;
-    GetBitContext bc;
+    uint8_t *src;
     uint16_t *y, *u, *v;
     int ret, i, j;
 
@@ -79,20 +78,18 @@ static int bitpacked_decode_yuv422p10(AVCodecContext *avctx, AVFrame *frame,
     if (avctx->width % 2)
         return AVERROR_PATCHWELCOME;
 
-    ret = init_get_bits(&bc, avpkt->data, avctx->width * avctx->height * 20);
-    if (ret)
-        return ret;
-
+    src = avpkt->data;
     for (i = 0; i < avctx->height; i++) {
         y = (uint16_t*)(frame->data[0] + i * frame->linesize[0]);
         u = (uint16_t*)(frame->data[1] + i * frame->linesize[1]);
         v = (uint16_t*)(frame->data[2] + i * frame->linesize[2]);
 
         for (j = 0; j < avctx->width; j += 2) {
-            *u++ = get_bits(&bc, 10);
-            *y++ = get_bits(&bc, 10);
-            *v++ = get_bits(&bc, 10);
-            *y++ = get_bits(&bc, 10);
+            *u++ = (src[0] << 2) | (src[1] >> 6);
+            *y++ = ((src[1] << 4) | (src[2] >> 4)) & 0x3ff;
+            *v++ = ((src[2] << 6) | (src[3] >> 2)) & 0x3ff;
+            *y++ = ((src[3] << 8) | (src[4]))      & 0x3ff;
+            src += 5;
         }
     }
 
-- 
1.8.3.1