1
0
mirror of https://github.com/mpv-player/mpv synced 2024-12-18 21:06:00 +00:00
mpv/video/sws_utils.h

83 lines
2.6 KiB
C
Raw Normal View History

#ifndef MPLAYER_SWS_UTILS_H
#define MPLAYER_SWS_UTILS_H
#include <stdbool.h>
#include "mp_image.h"
struct mp_image;
struct mpv_global;
// libswscale currently requires 16 bytes alignment for row pointers and
// strides. Otherwise, it will print warnings and use slow codepaths.
// Guaranteed to be a power of 2 and > 1.
video: generally try to align image data on 64 bytes Generally, using x86 SIMD efficiently (or crash-free) requires aligning all data on boundaries of 16, 32, or 64 (depending on instruction set used). 64 bytes is needed or AVX-512, 32 for old AVX, 16 for SSE. Both FFmpeg and zimg usually require aligned data for this reason. FFmpeg is very unclear about alignment. Yes, it requires you to align data pointers and strides. No, it doesn't tell you how much, except sometimes (libavcodec has a legacy-looking avcodec_align_dimensions2() API function, that requires a heavy-weight AVCodecContext as argument). Sometimes, FFmpeg will take a shit on YOUR and ITS OWN alignment. For example, vf_crop will randomly reduce alignment of data pointers, depending on the crop parameters. On the other hand, some libavfilter filters or libavcodec encoders may randomly crash if they get the wrong alignment. I have no idea how this thing works at all. FFmpeg usually doesn't seem to signal alignment internal anywhere, and usually leaves it to av_malloc() etc. to allocate with proper alignment. libavutil/mem.c currently has a ALIGN define, which is set to 64 if FFmpeg is built with AVX-512 support, or as low as 16 if built without any AVX support. The really funny thing is that a normal FFmpeg build will e.g. align tiny string allocations to 64 bytes, even if the machine does not support AVX at all. For zimg use (in a later commit), we also want guaranteed alignment. Modern x86 should actually not be much slower at unaligned accesses, but that doesn't help. zimg's dumb intrinsic code apparently randomly chooses between aligned or unaligned accesses (depending on compiler, I guess), and on some CPUs these can even cause crashes. So just treat the requirement to align as a fact of life. All this means that we should probably make sure our own allocations are 64 bit aligned. This still doesn't guarantee alignment in all cases, but it's slightly better than before. This also makes me wonder whether we should always override libavcodec's buffer pool, just so we have a guaranteed alignment. Currently, we only do that if --vd-lavc-dr is used (and if that actually works). On the other hand, it always uses DR on my machine, so who cares.
2019-07-15 01:06:47 +00:00
#define SWS_MIN_BYTE_ALIGN MP_IMAGE_BYTE_ALIGN
extern const int mp_sws_fast_flags;
bool mp_sws_supported_format(int imgfmt);
int mp_image_swscale(struct mp_image *dst, struct mp_image *src,
int my_sws_flags);
int mp_image_sw_blur_scale(struct mp_image *dst, struct mp_image *src,
float gblur);
enum mp_sws_scaler {
MP_SWS_AUTO = 0, // use command line
MP_SWS_SWS,
MP_SWS_ZIMG,
};
struct mp_sws_context {
// Can be set for verbose error printing.
struct mp_log *log;
// User configuration. These can be changed freely, at any time.
// mp_sws_scale() will handle the changes transparently.
int flags;
bool allow_zimg; // use zimg if available (ignores filters and all)
bool force_reload;
// These are also implicitly set by mp_sws_scale(), and thus optional.
// Setting them before that call makes sense when using mp_sws_reinit().
struct mp_image_params src, dst;
// This is unfortunately a hack: bypass command line choice
enum mp_sws_scaler force_scaler;
// If zimg is used. Need to manually invalidate cache (set force_reload).
// Conflicts with enabling command line opts.
struct zimg_opts *zimg_opts;
// Changing these requires setting force_reload=true.
// By default, they are NULL.
// Freeing the mp_sws_context will deallocate these if set.
struct SwsFilter *src_filter, *dst_filter;
double params[2];
// Cached context (if any)
struct SwsContext *sws;
bool supports_csp;
// Private.
struct m_config_cache *opts_cache;
struct mp_sws_context *cached; // contains parameters for which sws is valid
struct mp_zimg_context *zimg;
bool zimg_ok;
struct mp_image *aligned_src, *aligned_dst;
};
struct mp_sws_context *mp_sws_alloc(void *talloc_ctx);
void mp_sws_enable_cmdline_opts(struct mp_sws_context *ctx, struct mpv_global *g);
int mp_sws_reinit(struct mp_sws_context *ctx);
int mp_sws_scale(struct mp_sws_context *ctx, struct mp_image *dst,
struct mp_image *src);
bool mp_sws_supports_formats(struct mp_sws_context *ctx,
int imgfmt_out, int imgfmt_in);
struct mp_image *mp_img_swap_to_native(struct mp_image *img);
#endif /* MP_SWS_UTILS_H */
// vim: ts=4 sw=4 et tw=80