[FFmpeg-devel] [PATCH] avfilter/colormatrix:add slice threading
Yayoi
yayoi.ukai at gmail.com
Tue Mar 10 00:33:39 CET 2015
---
fixed the issue and cleaned up the code a bit
---
libavfilter/vf_colormatrix.c | 146 +++++++++++++++++++++++++++----------------
1 file changed, 92 insertions(+), 54 deletions(-)
diff --git a/libavfilter/vf_colormatrix.c b/libavfilter/vf_colormatrix.c
index daba16e..d0839cc 100644
--- a/libavfilter/vf_colormatrix.c
+++ b/libavfilter/vf_colormatrix.c
@@ -73,6 +73,17 @@ typedef struct {
int hsub, vsub;
} ColorMatrixContext;
+typedef struct ThreadData {
+ AVFrame *dst;
+ const AVFrame *src;
+ int c2;
+ int c3;
+ int c4;
+ int c5;
+ int c6;
+ int c7;
+} ThreadData;
+
#define OFFSET(x) offsetof(ColorMatrixContext, x)
#define FLAGS AV_OPT_FLAG_VIDEO_PARAM|AV_OPT_FLAG_FILTERING_PARAM
@@ -179,24 +190,28 @@ static av_cold int init(AVFilterContext *ctx)
return 0;
}
-static void process_frame_uyvy422(ColorMatrixContext *color,
- AVFrame *dst, AVFrame *src)
+static int process_slice_uyvy422(AVFilterContext *ctx, void *arg, int jobnr, int nb_jobs)
{
- const unsigned char *srcp = src->data[0];
- const int src_pitch = src->linesize[0];
+ const ThreadData *td = arg;
+ const AVFrame *src = td->src;
+ AVFrame *dst = td->dst;
const int height = src->height;
const int width = src->width*2;
- unsigned char *dstp = dst->data[0];
+ const int src_pitch = src->linesize[0];
const int dst_pitch = dst->linesize[0];
- const int c2 = color->yuv_convert[color->mode][0][1];
- const int c3 = color->yuv_convert[color->mode][0][2];
- const int c4 = color->yuv_convert[color->mode][1][1];
- const int c5 = color->yuv_convert[color->mode][1][2];
- const int c6 = color->yuv_convert[color->mode][2][1];
- const int c7 = color->yuv_convert[color->mode][2][2];
+ const int slice_start = (height * jobnr ) / nb_jobs;
+ const int slice_end = (height * (jobnr+1)) / nb_jobs;
+ const unsigned char *srcp = src->data[0] + slice_start * src_pitch;
+ unsigned char *dstp = dst->data[0] + slice_start * dst_pitch;
+ const int c2 = td->c2;
+ const int c3 = td->c3;
+ const int c4 = td->c4;
+ const int c5 = td->c5;
+ const int c6 = td->c6;
+ const int c7 = td->c7;
int x, y;
- for (y = 0; y < height; y++) {
+ for (y = slice_start; y < slice_end; y++) {
for (x = 0; x < width; x += 4) {
const int u = srcp[x + 0] - 128;
const int v = srcp[x + 2] - 128;
@@ -209,32 +224,36 @@ static void process_frame_uyvy422(ColorMatrixContext *color,
srcp += src_pitch;
dstp += dst_pitch;
}
+ return 0;
}
-static void process_frame_yuv422p(ColorMatrixContext *color,
- AVFrame *dst, AVFrame *src)
+static int process_slice_yuv422p(AVFilterContext *ctx, void *arg, int jobnr, int nb_jobs)
{
- const unsigned char *srcpU = src->data[1];
- const unsigned char *srcpV = src->data[2];
- const unsigned char *srcpY = src->data[0];
- const int src_pitchY = src->linesize[0];
- const int src_pitchUV = src->linesize[1];
+ const ThreadData *td = arg;
+ const AVFrame *src = td->src;
+ AVFrame *dst = td->dst;
const int height = src->height;
const int width = src->width;
- unsigned char *dstpU = dst->data[1];
- unsigned char *dstpV = dst->data[2];
- unsigned char *dstpY = dst->data[0];
+ const int slice_start = (height * jobnr ) / nb_jobs;
+ const int slice_end = (height * (jobnr+1)) / nb_jobs;
+ const int src_pitchY = src->linesize[0];
+ const int src_pitchUV = src->linesize[1];
+ const unsigned char *srcpU = src->data[1] + slice_start * src_pitchUV;
+ const unsigned char *srcpV = src->data[2] + slice_start * src_pitchUV;
+ const unsigned char *srcpY = src->data[0] + slice_start * src_pitchY;
const int dst_pitchY = dst->linesize[0];
const int dst_pitchUV = dst->linesize[1];
- const int c2 = color->yuv_convert[color->mode][0][1];
- const int c3 = color->yuv_convert[color->mode][0][2];
- const int c4 = color->yuv_convert[color->mode][1][1];
- const int c5 = color->yuv_convert[color->mode][1][2];
- const int c6 = color->yuv_convert[color->mode][2][1];
- const int c7 = color->yuv_convert[color->mode][2][2];
+ unsigned char *dstpU = dst->data[1] + slice_start * dst_pitchUV;
+ unsigned char *dstpV = dst->data[2] + slice_start * dst_pitchUV;
+ unsigned char *dstpY = dst->data[0] + slice_start * dst_pitchY;
+ const int c2 = td->c2;
+ const int c3 = td->c3;
+ const int c4 = td->c4;
+ const int c5 = td->c5;
+ const int c6 = td->c6;
+ const int c7 = td->c7;
int x, y;
-
- for (y = 0; y < height; y++) {
+ for (y = slice_start; y < slice_end; y++) {
for (x = 0; x < width; x += 2) {
const int u = srcpU[x >> 1] - 128;
const int v = srcpV[x >> 1] - 128;
@@ -251,34 +270,38 @@ static void process_frame_yuv422p(ColorMatrixContext *color,
dstpU += dst_pitchUV;
dstpV += dst_pitchUV;
}
+ return 0;
}
-static void process_frame_yuv420p(ColorMatrixContext *color,
- AVFrame *dst, AVFrame *src)
+static int process_slice_yuv420p(AVFilterContext *ctx, void *arg, int jobnr, int nb_jobs)
{
- const unsigned char *srcpU = src->data[1];
- const unsigned char *srcpV = src->data[2];
- const unsigned char *srcpY = src->data[0];
- const unsigned char *srcpN = src->data[0] + src->linesize[0];
- const int src_pitchY = src->linesize[0];
- const int src_pitchUV = src->linesize[1];
+ const ThreadData *td = arg;
+ const AVFrame *src = td->src;
+ AVFrame *dst = td->dst;
const int height = src->height;
const int width = src->width;
- unsigned char *dstpU = dst->data[1];
- unsigned char *dstpV = dst->data[2];
- unsigned char *dstpY = dst->data[0];
- unsigned char *dstpN = dst->data[0] + dst->linesize[0];
+ const int slice_start = (height * jobnr ) / nb_jobs;
+ const int slice_end = (height * (jobnr+1)) / nb_jobs;
+ const int src_pitchY = src->linesize[0];
+ const int src_pitchUV = src->linesize[1];
const int dst_pitchY = dst->linesize[0];
const int dst_pitchUV = dst->linesize[1];
- const int c2 = color->yuv_convert[color->mode][0][1];
- const int c3 = color->yuv_convert[color->mode][0][2];
- const int c4 = color->yuv_convert[color->mode][1][1];
- const int c5 = color->yuv_convert[color->mode][1][2];
- const int c6 = color->yuv_convert[color->mode][2][1];
- const int c7 = color->yuv_convert[color->mode][2][2];
+ const unsigned char *srcpY = src->data[0] + src_pitchY * slice_start;
+ const unsigned char *srcpU = src->data[1] + src_pitchUV * (slice_start >> 1);
+ const unsigned char *srcpV = src->data[2] + src_pitchUV * (slice_start >> 1);
+ const unsigned char *srcpN = src->data[0] + src_pitchY * (slice_start + 1);
+ unsigned char *dstpU = dst->data[1] + dst_pitchUV * (slice_start >> 1);
+ unsigned char *dstpV = dst->data[2] + dst_pitchUV * (slice_start >> 1);
+ unsigned char *dstpY = dst->data[0] + dst_pitchY * slice_start;
+ unsigned char *dstpN = dst->data[0] + dst_pitchY * (slice_start + 1);
+ const int c2 = td->c2;
+ const int c3 = td->c3;
+ const int c4 = td->c4;
+ const int c5 = td->c5;
+ const int c6 = td->c6;
+ const int c7 = td->c7;
int x, y;
-
- for (y = 0; y < height; y += 2) {
+ for (y = slice_start; y < slice_end; y += 2) {
for (x = 0; x < width; x += 2) {
const int u = srcpU[x >> 1] - 128;
const int v = srcpV[x >> 1] - 128;
@@ -299,6 +322,7 @@ static void process_frame_yuv420p(ColorMatrixContext *color,
dstpU += dst_pitchUV;
dstpV += dst_pitchUV;
}
+ return 0;
}
static int config_input(AVFilterLink *inlink)
@@ -372,12 +396,26 @@ static int filter_frame(AVFilterLink *link, AVFrame *in)
calc_coefficients(ctx);
+ ThreadData td = {
+ .src = in,
+ .dst = out,
+ .c2 = color->yuv_convert[color->mode][0][1],
+ .c3 = color->yuv_convert[color->mode][0][2],
+ .c4 = color->yuv_convert[color->mode][1][1],
+ .c5 = color->yuv_convert[color->mode][1][2],
+ .c6 = color->yuv_convert[color->mode][2][1],
+ .c7 = color->yuv_convert[color->mode][2][2],
+ };
+
if (in->format == AV_PIX_FMT_YUV422P)
- process_frame_yuv422p(color, out, in);
+ ctx->internal->execute(ctx, process_slice_yuv422p, &td, NULL,
+ FFMIN(in->height, ctx->graph->nb_threads));
else if (in->format == AV_PIX_FMT_YUV420P)
- process_frame_yuv420p(color, out, in);
+ ctx->internal->execute(ctx, process_slice_yuv420p, &td, NULL,
+ FFMIN(in->height, ctx->graph->nb_threads));
else
- process_frame_uyvy422(color, out, in);
+ ctx->internal->execute(ctx, process_slice_uyvy422, &td, NULL,
+ FFMIN(in->height, ctx->graph->nb_threads));
av_frame_free(&in);
return ff_filter_frame(outlink, out);
@@ -410,5 +448,5 @@ AVFilter ff_vf_colormatrix = {
.inputs = colormatrix_inputs,
.outputs = colormatrix_outputs,
.priv_class = &colormatrix_class,
- .flags = AVFILTER_FLAG_SUPPORT_TIMELINE_GENERIC,
+ .flags = AVFILTER_FLAG_SUPPORT_TIMELINE_GENERIC | AVFILTER_FLAG_SLICE_THREADS,
};
--
1.8.3.4 (Apple Git-47)
More information about the ffmpeg-devel
mailing list