From b2c82b23b9fd9906a98b53af5ee8eadd08eb95d9 Mon Sep 17 00:00:00 2001 From: Devin Heitmueller Date: Fri, 5 May 2023 17:54:17 -0400 Subject: [PATCH] avcodec/bitpacked_dec: optimize bitpacked_decode_yuv422p10 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... Comments from Marton: Originally on my system better performance could be achieved by simply switching to the cached bitstream reader, but for Devin it was slower than his direct byte operations. I changed the order of writing output from u/y/v/y to u/v/y/y, and that made the code faster than the cached bitstream reader on my system as well. TIMER measurement of the decode loop on Ryzen 5 3600 with command line: ./ffmpeg -stream_loop 256 -threads 1 -f bitpacked -pix_fmt yuv422p10le -s 3840x2160 -c:v bitpacked -i source.yuv -pix_fmt yuv422p10le -f null none -loglevel error Before: 823204127 decicycles in YUV, 256 runs, 0 skips After: 315070524 decicycles in YUV, 256 runs, 0 skips Signed-off-by: Devin Heitmueller Signed-off-by: Marton Balint --- 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 c88f861993..54c008bd86 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); + *v++ = ((src[2] << 6) | (src[3] >> 2)) & 0x3ff; + *y++ = ((src[1] << 4) | (src[2] >> 4)) & 0x3ff; + *y++ = ((src[3] << 8) | (src[4])) & 0x3ff; + src += 5; } }