avcodec/decode: Optimize lcevc away if disabled

Signed-off-by: Andreas Rheinhardt <andreas.rheinhardt@outlook.com>

.gitignore

@@ -36,6 +36,7 @@
 /ffprobe
 /config.asm
 /config.h
+/config_components.asm
 /config_components.h
 /coverage.info
 /lcov/

libavcodec/Makefile

@@ -47,7 +47,6 @@ OBJS = ac3_parser.o                                                     \
        get_buffer.o                                                     \
        imgconvert.o                                                     \
        jni.o                                                            \
-       lcevcdec.o                                                       \
        mathtables.o                                                     \
        mediacodec.o                                                     \
        mpeg12framerate.o                                                \
@@ -130,6 +129,7 @@ OBJS-$(CONFIG_IVIDSP)                  += ivi_dsp.o
 OBJS-$(CONFIG_JNI)                     += ffjni.o jni.o
 OBJS-$(CONFIG_JPEGTABLES)              += jpegtables.o
 OBJS-$(CONFIG_LCMS2)                   += fflcms2.o
+OBJS-$(CONFIG_LIBLCEVC_DEC)            += lcevcdec.o
 OBJS-$(CONFIG_LLAUDDSP)                += lossless_audiodsp.o
 OBJS-$(CONFIG_LLVIDDSP)                += lossless_videodsp.o
 OBJS-$(CONFIG_LLVIDENCDSP)             += lossless_videoencdsp.o

libavcodec/decode.c

@@ -94,10 +94,14 @@ typedef struct DecodeContext {
      */
     uint64_t side_data_pref_mask;
 
-    FFLCEVCContext *lcevc;
+#if CONFIG_LIBLCEVC_DEC
-    int lcevc_frame;
+    struct {
-    int width;
+        FFLCEVCContext *ctx;
-    int height;
+        int frame;
+        int width;
+        int height;
+    } lcevc;
+#endif
 } DecodeContext;
 
 static DecodeContext *decode_ctx(AVCodecInternal *avci)
@@ -1658,26 +1662,29 @@ int ff_attach_decode_data(AVFrame *frame)
 
 static void update_frame_props(AVCodecContext *avctx, AVFrame *frame)
 {
+#if CONFIG_LIBLCEVC_DEC
     AVCodecInternal    *avci = avctx->internal;
     DecodeContext        *dc = decode_ctx(avci);
 
-    dc->lcevc_frame = dc->lcevc && avctx->codec_type == AVMEDIA_TYPE_VIDEO &&
+    dc->lcevc.frame = dc->lcevc.ctx && avctx->codec_type == AVMEDIA_TYPE_VIDEO &&
                       av_frame_get_side_data(frame, AV_FRAME_DATA_LCEVC);
 
-    if (dc->lcevc_frame) {
+    if (dc->lcevc.frame) {
-        dc->width     = frame->width;
+        dc->lcevc.width  = frame->width;
-        dc->height    = frame->height;
+        dc->lcevc.height = frame->height;
         frame->width  = frame->width  * 2 / FFMAX(frame->sample_aspect_ratio.den, 1);
         frame->height = frame->height * 2 / FFMAX(frame->sample_aspect_ratio.num, 1);
     }
+#endif
 }
 
 static int attach_post_process_data(AVCodecContext *avctx, AVFrame *frame)
 {
+#if CONFIG_LIBLCEVC_DEC
     AVCodecInternal    *avci = avctx->internal;
     DecodeContext        *dc = decode_ctx(avci);
 
-    if (dc->lcevc_frame) {
+    if (dc->lcevc.frame) {
         FrameDecodeData *fdd = frame->private_ref;
         FFLCEVCFrame *frame_ctx;
         int ret;
@@ -1692,13 +1699,13 @@ static int attach_post_process_data(AVCodecContext *avctx, AVFrame *frame)
             return AVERROR(ENOMEM);
         }
 
-        frame_ctx->lcevc = av_refstruct_ref(dc->lcevc);
+        frame_ctx->lcevc = av_refstruct_ref(dc->lcevc.ctx);
         frame_ctx->frame->width  = frame->width;
         frame_ctx->frame->height = frame->height;
         frame_ctx->frame->format = frame->format;
 
-        frame->width  = dc->width;
+        frame->width  = dc->lcevc.width;
-        frame->height = dc->height;
+        frame->height = dc->lcevc.height;
 
         ret = avctx->get_buffer2(avctx, frame_ctx->frame, 0);
         if (ret < 0) {
@@ -1712,7 +1719,8 @@ static int attach_post_process_data(AVCodecContext *avctx, AVFrame *frame)
         fdd->post_process_opaque_free = ff_lcevc_unref;
         fdd->post_process = ff_lcevc_process;
     }
-    dc->lcevc_frame = 0;
+    dc->lcevc.frame = 0;
+#endif
 
     return 0;
 }
@@ -1960,7 +1968,7 @@ static av_cold void progress_frame_pool_free_entry_cb(AVRefStructOpaque opaque,
     av_frame_free(&progress->f);
 }
 
-int ff_decode_preinit(AVCodecContext *avctx)
+av_cold int ff_decode_preinit(AVCodecContext *avctx)
 {
     AVCodecInternal *avci = avctx->internal;
     DecodeContext     *dc = decode_ctx(avci);
@@ -2080,9 +2088,13 @@ int ff_decode_preinit(AVCodecContext *avctx)
         return ret;
 
     if (!(avctx->export_side_data & AV_CODEC_EXPORT_DATA_ENHANCEMENTS)) {
-        ret = ff_lcevc_alloc(&dc->lcevc);
+        if (avctx->codec_type == AVMEDIA_TYPE_VIDEO) {
-        if (ret < 0 && (avctx->err_recognition & AV_EF_EXPLODE))
+#if CONFIG_LIBLCEVC_DEC
-            return ret;
+            ret = ff_lcevc_alloc(&dc->lcevc.ctx);
+            if (ret < 0 && (avctx->err_recognition & AV_EF_EXPLODE))
+                return ret;
+#endif
+        }
     }
 
     return 0;
@@ -2292,7 +2304,7 @@ int ff_hwaccel_frame_priv_alloc(AVCodecContext *avctx, void **hwaccel_picture_pr
     return 0;
 }
 
-void ff_decode_flush_buffers(AVCodecContext *avctx)
+av_cold void ff_decode_flush_buffers(AVCodecContext *avctx)
 {
     AVCodecInternal *avci = avctx->internal;
     DecodeContext     *dc = decode_ctx(avci);
@@ -2310,27 +2322,31 @@ void ff_decode_flush_buffers(AVCodecContext *avctx)
     dc->draining_started   = 0;
 }
 
-AVCodecInternal *ff_decode_internal_alloc(void)
+av_cold AVCodecInternal *ff_decode_internal_alloc(void)
 {
     return av_mallocz(sizeof(DecodeContext));
 }
 
-void ff_decode_internal_sync(AVCodecContext *dst, const AVCodecContext *src)
+av_cold void ff_decode_internal_sync(AVCodecContext *dst, const AVCodecContext *src)
 {
     const DecodeContext *src_dc = decode_ctx(src->internal);
     DecodeContext *dst_dc = decode_ctx(dst->internal);
 
     dst_dc->initial_pict_type = src_dc->initial_pict_type;
     dst_dc->intra_only_flag   = src_dc->intra_only_flag;
-    av_refstruct_replace(&dst_dc->lcevc, src_dc->lcevc);
+#if CONFIG_LIBLCEVC_DEC
+    av_refstruct_replace(&dst_dc->lcevc.ctx, src_dc->lcevc.ctx);
+#endif
 }
 
-void ff_decode_internal_uninit(AVCodecContext *avctx)
+av_cold void ff_decode_internal_uninit(AVCodecContext *avctx)
 {
+#if CONFIG_LIBLCEVC_DEC
     AVCodecInternal *avci = avctx->internal;
     DecodeContext *dc = decode_ctx(avci);
 
-    av_refstruct_unref(&dc->lcevc);
+    av_refstruct_unref(&dc->lcevc.ctx);
+#endif
 }
 
 static int attach_displaymatrix(AVCodecContext *avctx, AVFrame *frame, int orientation)

libavcodec/lcevcdec.c

@@ -16,8 +16,6 @@
  * Foundation, Inc., 51 Franklin Street, Fifth Floor, Boston, MA 02110-1301 USA
  */
 
-#include "config_components.h"
-
 #include "libavutil/avassert.h"
 #include "libavutil/frame.h"
 #include "libavutil/imgutils.h"
@@ -28,7 +26,6 @@
 #include "decode.h"
 #include "lcevcdec.h"
 
-#if CONFIG_LIBLCEVC_DEC
 static LCEVC_ColorFormat map_format(int format)
 {
     switch (format) {
@@ -249,11 +246,9 @@ static void lcevc_free(AVRefStructOpaque unused, void *obj)
         LCEVC_DestroyDecoder(lcevc->decoder);
     memset(lcevc, 0, sizeof(*lcevc));
 }
-#endif
 
 static int lcevc_init(FFLCEVCContext *lcevc, void *logctx)
 {
-#if CONFIG_LIBLCEVC_DEC
     LCEVC_AccelContextHandle dummy = { 0 };
     const int32_t event = LCEVC_Log;
 
@@ -272,7 +267,6 @@ static int lcevc_init(FFLCEVCContext *lcevc, void *logctx)
         return AVERROR_EXTERNAL;
     }
 
-#endif
     lcevc->initialized = 1;
 
     return 0;
@@ -291,7 +285,6 @@ int ff_lcevc_process(void *logctx, AVFrame *frame)
             return ret;
     }
 
-#if CONFIG_LIBLCEVC_DEC
     av_assert0(frame_ctx->frame);
 
 
@@ -304,7 +297,6 @@ int ff_lcevc_process(void *logctx, AVFrame *frame)
         return ret;
 
     av_frame_remove_side_data(frame, AV_FRAME_DATA_LCEVC);
-#endif
 
     return 0;
 }
@@ -312,11 +304,9 @@ int ff_lcevc_process(void *logctx, AVFrame *frame)
 int ff_lcevc_alloc(FFLCEVCContext **plcevc)
 {
     FFLCEVCContext *lcevc = NULL;
-#if CONFIG_LIBLCEVC_DEC
     lcevc = av_refstruct_alloc_ext(sizeof(*lcevc), 0, NULL, lcevc_free);
     if (!lcevc)
         return AVERROR(ENOMEM);
-#endif
     *plcevc = lcevc;
     return 0;
 }

libavcodec/pthread_frame.c

@@ -401,7 +401,6 @@ FF_ENABLE_DEPRECATION_WARNINGS
         dst->hwaccel_flags = src->hwaccel_flags;
 
         av_refstruct_replace(&dst->internal->pool, src->internal->pool);
-        ff_decode_internal_sync(dst, src);
     }
 
     if (for_user) {

libavcodec/x86/hpeldsp.asm

@@ -54,8 +54,8 @@ cglobal put_pixels8_x2, 4,5
     pavgb        m0, m2
     pavgb        m1, m3
 %else
-    PAVGB        m0, [r1]
+    pavgb        m0, [r1]
-    PAVGB        m1, [r1+r2]
+    pavgb        m1, [r1+r2]
 %endif
     mova       [r0], m0
     mova    [r0+r2], m1
@@ -69,8 +69,8 @@ cglobal put_pixels8_x2, 4,5
     pavgb        m0, m2
     pavgb        m1, m3
 %else
-    PAVGB        m0, [r1]
+    pavgb        m0, [r1]
-    PAVGB        m1, [r1+r2]
+    pavgb        m1, [r1+r2]
 %endif
     add          r1, r4
     mova       [r0], m0
@@ -103,8 +103,8 @@ cglobal put_no_rnd_pixels8_x2, 4,5
     add          r1, r4
     psubusb      m0, m6
     psubusb      m2, m6
-    PAVGB        m0, m1
+    pavgb        m0, m1
-    PAVGB        m2, m3
+    pavgb        m2, m3
     mova       [r0], m0
     mova    [r0+r2], m2
     mova         m0, [r1]
@@ -115,8 +115,8 @@ cglobal put_no_rnd_pixels8_x2, 4,5
     add          r1, r4
     psubusb      m0, m6
     psubusb      m2, m6
-    PAVGB        m0, m1
+    pavgb        m0, m1
-    PAVGB        m2, m3
+    pavgb        m2, m3
     mova       [r0], m0
     mova    [r0+r2], m2
     add          r0, r4
@@ -143,8 +143,8 @@ cglobal %1_no_rnd_pixels8_x2_exact, 4,5
     pxor         m2, m4
     pxor         m1, m4
     pxor         m3, m4
-    PAVGB        m0, m1
+    pavgb        m0, m1
-    PAVGB        m2, m3
+    pavgb        m2, m3
     pxor         m0, m4
     pxor         m2, m4
 %ifidn %1, avg
@@ -161,8 +161,8 @@ cglobal %1_no_rnd_pixels8_x2_exact, 4,5
     pxor         m1, m4
     pxor         m2, m4
     pxor         m3, m4
-    PAVGB        m0, m1
+    pavgb        m0, m1
-    PAVGB        m2, m3
+    pavgb        m2, m3
     pxor         m0, m4
     pxor         m2, m4
 %ifidn %1, avg
@@ -198,16 +198,16 @@ cglobal put_pixels8_y2, 4,5
     movu         m1, [r1+r2]
     movu         m2, [r1+r4]
     add          r1, r4
-    PAVGB        m0, m1
+    pavgb        m0, m1
-    PAVGB        m1, m2
+    pavgb        m1, m2
     mova    [r0+r2], m0
     mova    [r0+r4], m1
     movu         m1, [r1+r2]
     movu         m0, [r1+r4]
     add          r0, r4
     add          r1, r4
-    PAVGB        m2, m1
+    pavgb        m2, m1
-    PAVGB        m1, m0
+    pavgb        m1, m0
     mova    [r0+r2], m2
     mova    [r0+r4], m1
     add          r0, r4
@@ -235,8 +235,8 @@ cglobal put_no_rnd_pixels8_y2, 4,5
     mova         m2, [r1+r4]
     add          r1, r4
     psubusb      m1, m6
-    PAVGB        m0, m1
+    pavgb        m0, m1
-    PAVGB        m1, m2
+    pavgb        m1, m2
     mova    [r0+r2], m0
     mova    [r0+r4], m1
     mova         m1, [r1+r2]
@@ -244,8 +244,8 @@ cglobal put_no_rnd_pixels8_y2, 4,5
     add          r0, r4
     add          r1, r4
     psubusb      m1, m6
-    PAVGB        m2, m1
+    pavgb        m2, m1
-    PAVGB        m1, m0
+    pavgb        m1, m0
     mova    [r0+r2], m2
     mova    [r0+r4], m1
     add          r0, r4
@@ -271,8 +271,8 @@ cglobal %1_no_rnd_pixels8_y2_exact, 4,5
     movu         m2, [r1+r2]
     pxor         m1, m3
     pxor         m2, m3
-    PAVGB        m0, m1
+    pavgb        m0, m1
-    PAVGB        m1, m2
+    pavgb        m1, m2
     pxor         m0, m3
     pxor         m1, m3
 %ifidn %1, avg
@@ -285,8 +285,8 @@ cglobal %1_no_rnd_pixels8_y2_exact, 4,5
     movu         m0, [r1+r4]
     pxor         m1, m3
     pxor         m0, m3
-    PAVGB        m2, m1
+    pavgb        m2, m1
-    PAVGB        m1, m0
+    pavgb        m1, m0
     pxor         m2, m3
     pxor         m1, m3
 %ifidn %1, avg
@@ -325,11 +325,11 @@ cglobal avg_pixels8_x2, 4,5
     pavgb        m0, m1
     pavgb        m2, m3
 %else
-    PAVGB        m0, [r1+1], m3, m5
+    pavgb        m0, [r1+1]
-    PAVGB        m2, [r1+r2+1], m4, m5
+    pavgb        m2, [r1+r2+1]
 %endif
-    PAVGB        m0, [r0], m3, m5
+    pavgb        m0, [r0]
-    PAVGB        m2, [r0+r2], m4, m5
+    pavgb        m2, [r0+r2]
     add          r1, r4
     mova       [r0], m0
     mova    [r0+r2], m2
@@ -341,13 +341,13 @@ cglobal avg_pixels8_x2, 4,5
     pavgb        m0, m1
     pavgb        m2, m3
 %else
-    PAVGB        m0, [r1+1], m3, m5
+    pavgb        m0, [r1+1]
-    PAVGB        m2, [r1+r2+1], m4, m5
+    pavgb        m2, [r1+r2+1]
 %endif
     add          r0, r4
     add          r1, r4
-    PAVGB        m0, [r0], m3, m5
+    pavgb        m0, [r0]
-    PAVGB        m2, [r0+r2], m4, m5
+    pavgb        m2, [r0+r2]
     mova       [r0], m0
     mova    [r0+r2], m2
     add          r0, r4
@@ -377,20 +377,20 @@ cglobal avg_pixels8_y2, 4,5
     movu         m1, [r1+r2]
     movu         m2, [r1+r4]
     add          r1, r4
-    PAVGB        m0, m1
+    pavgb        m0, m1
-    PAVGB        m1, m2
+    pavgb        m1, m2
-    PAVGB        m0, [r0+r2]
+    pavgb        m0, [r0+r2]
-    PAVGB        m1, [r0+r4]
+    pavgb        m1, [r0+r4]
     mova    [r0+r2], m0
     mova    [r0+r4], m1
     movu         m1, [r1+r2]
     movu         m0, [r1+r4]
-    PAVGB        m2, m1
+    pavgb        m2, m1
-    PAVGB        m1, m0
+    pavgb        m1, m0
     add          r0, r4
     add          r1, r4
-    PAVGB        m2, [r0+r2]
+    pavgb        m2, [r0+r2]
-    PAVGB        m1, [r0+r4]
+    pavgb        m1, [r0+r4]
     mova    [r0+r2], m2
     mova    [r0+r4], m1
     add          r0, r4
@@ -423,12 +423,12 @@ cglobal %1%3_pixels8_xy2, 4,5,5
     punpcklbw   m0, m1
     pmaddubsw   m0, m4
 %ifidn %3, _no_rnd
-    paddusw     m2, m3
+    paddw       m2, m3
-    paddusw     m2, m0
+    paddw       m2, m0
     psrlw       m2, 2
 %else
-    paddusw     m2, m0
+    paddw       m2, m0
-    pmulhrsw    m2, [pw_8192]
+    pmulhrsw    m2, m3
 %endif
 %ifidn %1, avg
     movh        m1, [r0+r4]
@@ -445,12 +445,12 @@ cglobal %1%3_pixels8_xy2, 4,5,5
     punpcklbw   m2, m1
     pmaddubsw   m2, m4
 %ifidn %3, _no_rnd
-    paddusw     m0, m3
+    paddw       m0, m3
-    paddusw     m0, m2
+    paddw       m0, m2
     psrlw       m0, 2
 %else
-    paddusw     m0, m2
+    paddw       m0, m2
-    pmulhrsw    m0, [pw_8192]
+    pmulhrsw    m0, m3
 %endif
 %ifidn %1, avg
     movh        m1, [r0+r4]
@@ -485,8 +485,8 @@ cglobal %1%3_pixels16_xy2, 4,5,8
     punpcklbw   m4, m7
     punpckhbw   m1, m7
     punpckhbw   m5, m7
-    paddusw     m4, m0
+    paddw       m4, m0
-    paddusw     m5, m1
+    paddw       m5, m1
     xor         r4, r4
     add         r1, r2
 .loop:
@@ -498,18 +498,18 @@ cglobal %1%3_pixels16_xy2, 4,5,8
     punpcklbw   m2, m7
     punpckhbw   m1, m7
     punpckhbw   m3, m7
-    paddusw     m0, m2
+    paddw       m0, m2
-    paddusw     m1, m3
+    paddw       m1, m3
-    paddusw     m4, m6
+    paddw       m4, m6
-    paddusw     m5, m6
+    paddw       m5, m6
-    paddusw     m4, m0
+    paddw       m4, m0
-    paddusw     m5, m1
+    paddw       m5, m1
     psrlw       m4, 2
     psrlw       m5, 2
 %ifidn %1, avg
     mova        m3, [r0+r4]
     packuswb    m4, m5
-    PAVGB       m4, m3
+    pavgb       m4, m3
 %else
     packuswb    m4, m5
 %endif
@@ -524,18 +524,18 @@ cglobal %1%3_pixels16_xy2, 4,5,8
     punpcklbw   m4, m7
     punpckhbw   m3, m7
     punpckhbw   m5, m7
-    paddusw     m4, m2
+    paddw       m4, m2
-    paddusw     m5, m3
+    paddw       m5, m3
-    paddusw     m0, m6
+    paddw       m0, m6
-    paddusw     m1, m6
+    paddw       m1, m6
-    paddusw     m0, m4
+    paddw       m0, m4
-    paddusw     m1, m5
+    paddw       m1, m5
     psrlw       m0, 2
     psrlw       m1, 2
 %ifidn %1, avg
     mova        m3, [r0+r4]
     packuswb    m0, m1
-    PAVGB       m0, m3
+    pavgb       m0, m3
 %else
     packuswb    m0, m1
 %endif
@@ -567,8 +567,8 @@ cglobal %1_pixels16_xy2, 4,5,%2
     movu        m3, [r1+r4+1]
     pmaddubsw   m2, m5
     pmaddubsw   m3, m5
-    paddusw     m0, m2
+    paddw       m0, m2
-    paddusw     m1, m3
+    paddw       m1, m3
     pmulhrsw    m0, [pw_8192]
     pmulhrsw    m1, [pw_8192]
 %ifidn %1, avg
@@ -587,8 +587,8 @@ cglobal %1_pixels16_xy2, 4,5,%2
     movu        m1, [r1+r4+1]
     pmaddubsw   m0, m5
     pmaddubsw   m1, m5
-    paddusw     m2, m0
+    paddw       m2, m0
-    paddusw     m3, m1
+    paddw       m3, m1
     pmulhrsw    m2, [pw_8192]
     pmulhrsw    m3, [pw_8192]
 %ifidn %1, avg