> + for (int y = 0; y < height; y++) {
> + const uint8_t *src1 = src1_data[0] + y * src1_linesize[0];
> + const uint8_t *src2 = src2_data[0] + (y + pos_y) *
> src2_linesize[0] + pos_x * src2_step[0];
> + uint8_t *dest = dest_data[0] + (y + pos_y) *
> dest_linesize[0] + pos_x * sizeof(uint32_t);
> + for (int x = 0; x < width; x++) {
> + int src1_alpha = src1[0];
> + int src2_alpha = src2[0];
> +
> + if (src1_alpha == 255) {
> + memcpy(dest, src1, sizeof(uint32_t));
> + } else if (src1_alpha + src2_alpha == 0) {
> + memset(dest, 0, sizeof(uint32_t));
> + } else {
> + int tmp_alpha = src2_alpha - ROUNDED_DIV(src1_alpha
> * src2_alpha, 255);
> + int blend_alpha = src1_alpha + tmp_alpha;
> +
> + dest[0] = blend_alpha;
> + dest[1] = ROUNDED_DIV(src1[1] * src1_alpha + src2[1]
> * tmp_alpha, blend_alpha);
> + dest[2] = ROUNDED_DIV(src1[2] * src1_alpha + src2[2]
> * tmp_alpha, blend_alpha);
> + dest[3] = ROUNDED_DIV(src1[3] * src1_alpha + src2[3]
> * tmp_alpha, blend_alpha);
> + }
Is branching and a bunch of function calls (which I hope get optimized
out) really faster than just always doing the blending?
It mgiht also be worthwhile to check 8 bytes at a time against
UINT64_MAX and 0. That doesn't need to hold up this patch though. Same
with the YUVA version.
> +static int blend_frame_into_canvas(WebPContext *s)
> +{
> + AVFrame *canvas = s->canvas_frame.f;
> + AVFrame *frame = s->frame;
> + int width, height;
> + int pos_x, pos_y;
> +
> + if ((s->anmf_flags & ANMF_BLENDING_METHOD) ==
> ANMF_BLENDING_METHOD_OVERWRITE
> + || frame->format == AV_PIX_FMT_YUV420P) {
> + // do not blend, overwrite
> +
> + if (canvas->format == AV_PIX_FMT_ARGB) {
> + width = s->width;
> + height = s->height;
> + pos_x = s->pos_x;
> + pos_y = s->pos_y;
> +
> + for (int y = 0; y < height; y++) {
> + const uint32_t *src = (uint32_t *) (frame->data[0] +
> y * frame->linesize[0]);
> + uint32_t *dst = (uint32_t *) (canvas->data[0] + (y +
> pos_y) * canvas->linesize[0]) + pos_x;
> + memcpy(dst, src, width * sizeof(uint32_t));
> + }
This could be reduced to a single memcpy() when linesizes are equal.
Same for the other memcpy()s
> +static int dispose_prev_frame_in_canvas(WebPContext *s)
> +{
> + AVFrame *canvas = s->canvas_frame.f;
> + int width, height;
> + int pos_x, pos_y;
> +
> + if ((s->prev_anmf_flags & ANMF_DISPOSAL_METHOD) ==
> ANMF_DISPOSAL_METHOD_BACKGROUND) {
> + // dispose to background
> +
> + if (canvas->format == AV_PIX_FMT_ARGB) {
> + width = s->prev_width;
> + height = s->prev_height;
> + pos_x = s->prev_pos_x;
> + pos_y = s->prev_pos_y;
> +
> + for (int y = 0; y < height; y++) {
> + uint32_t *dst = (uint32_t *) (canvas->data[0] + (y +
> pos_y) * canvas->linesize[0]) + pos_x;
> + memset(dst, 0, width * sizeof(uint32_t));
> + }
This can be turned into a single memset(), and similarly below
/Tomas
_______________________________________________
ffmpeg-devel mailing list
ffmpeg-devel@ffmpeg.org
https://ffmpeg.org/mailman/listinfo/ffmpeg-devel
To unsubscribe, visit link above, or email
ffmpeg-devel-requ...@ffmpeg.org with subject "unsubscribe".
