avcodec/roqvideoenc: Avoid allocating buffers separately

This is possible because their size is known at compile-time; so they
can be put directly into the context and don't need to be allocated for
every frame.

Reviewed-by: Paul B Mahol <onemda@gmail.com>
Signed-off-by: Andreas Rheinhardt <andreas.rheinhardt@gmail.com>

1 files changed, 68 insertions, 78 deletions

diff --git a/libavcodec/roqvideoenc.c b/libavcodec/roqvideoenc.c
index d65c740d5f..1ab0de0abb 100644
--- a/libavcodec/roqvideoenc.c
+++ b/libavcodec/roqvideoenc.c
@@ -78,6 +78,36 @@
 /* The cast is useful when multiplying it by INT_MAX */
 #define ROQ_LAMBDA_SCALE ((uint64_t) FF_LAMBDA_SCALE)
 
+typedef struct RoqCodebooks {
+    int numCB4;
+    int numCB2;
+    int usedCB2[MAX_CBS_2x2];
+    int usedCB4[MAX_CBS_4x4];
+    uint8_t unpacked_cb2[MAX_CBS_2x2*2*2*3];
+    uint8_t unpacked_cb4[MAX_CBS_4x4*4*4*3];
+    uint8_t unpacked_cb4_enlarged[MAX_CBS_4x4*8*8*3];
+} RoqCodebooks;
+
+/**
+ * Temporary vars
+ */
+typedef struct RoqTempData
+{
+    int f2i4[MAX_CBS_4x4];
+    int i2f4[MAX_CBS_4x4];
+    int f2i2[MAX_CBS_2x2];
+    int i2f2[MAX_CBS_2x2];
+
+    int mainChunkSize;
+
+    int numCB4;
+    int numCB2;
+
+    RoqCodebooks codebooks;
+
+    int used_option[4];
+} RoqTempData;
+
 typedef struct SubcelEvaluation {
     int eval_dist[4];
     int best_bit_use;
@@ -115,7 +145,9 @@ typedef struct RoqEncContext {
 
     const AVFrame *frame_to_enc;
     uint8_t *out_buf;
-    struct RoqTempData *tmpData;
+    RoqTempData tmp_data;
+    roq_cell results4[4 * MAX_CBS_4x4];
+    int tmp_codebook_buf[FFMAX(24 * MAX_CBS_4x4, 6 * MAX_CBS_2x2)];
 
     CelEvaluation *cel_evals;
     int *closest_cb;
@@ -233,36 +265,6 @@ static inline int squared_diff_macroblock(uint8_t a[], uint8_t b[], int size)
     return sdiff;
 }
 
-typedef struct RoqCodebooks {
-    int numCB4;
-    int numCB2;
-    int usedCB2[MAX_CBS_2x2];
-    int usedCB4[MAX_CBS_4x4];
-    uint8_t unpacked_cb2[MAX_CBS_2x2*2*2*3];
-    uint8_t unpacked_cb4[MAX_CBS_4x4*4*4*3];
-    uint8_t unpacked_cb4_enlarged[MAX_CBS_4x4*8*8*3];
-} RoqCodebooks;
-
-/**
- * Temporary vars
- */
-typedef struct RoqTempData
-{
-    int f2i4[MAX_CBS_4x4];
-    int i2f4[MAX_CBS_4x4];
-    int f2i2[MAX_CBS_2x2];
-    int i2f2[MAX_CBS_2x2];
-
-    int mainChunkSize;
-
-    int numCB4;
-    int numCB2;
-
-    RoqCodebooks codebooks;
-
-    int used_option[4];
-} RoqTempdata;
-
 /**
  * Initialize cel evaluators and set their source coordinates
  */
@@ -424,9 +426,10 @@ static void motion_search(RoqEncContext *enc, int blocksize)
  * Get distortion for all options available to a subcel
  */
 static void gather_data_for_subcel(SubcelEvaluation *subcel, int x,
-                                   int y, RoqEncContext *enc, RoqTempdata *tempData)
+                                   int y, RoqEncContext *enc)
 {
     RoqContext *const roq = &enc->common;
+    RoqTempData *const tempData = &enc->tmp_data;
     uint8_t mb4[4*4*3];
     uint8_t mb2[2*2*3];
     int cluster_index;
@@ -488,10 +491,10 @@ static void gather_data_for_subcel(SubcelEvaluation *subcel, int x,
 /**
  * Get distortion for all options available to a cel
  */
-static void gather_data_for_cel(CelEvaluation *cel, RoqEncContext *enc,
-                                RoqTempdata *tempData)
+static void gather_data_for_cel(CelEvaluation *cel, RoqEncContext *enc)
 {
     RoqContext *const roq = &enc->common;
+    RoqTempData *const tempData = &enc->tmp_data;
     uint8_t mb8[8*8*3];
     int index = cel->sourceY * roq->width / 64 + cel->sourceX/8;
     int i, j, best_dist, divide_bit_use;
@@ -523,10 +526,10 @@ static void gather_data_for_cel(CelEvaluation *cel, RoqEncContext *enc,
         index_mb(mb8, tempData->codebooks.unpacked_cb4_enlarged,
                  tempData->codebooks.numCB4, &cel->cbEntry, 8);
 
-    gather_data_for_subcel(cel->subCels + 0, cel->sourceX+0, cel->sourceY+0, enc, tempData);
-    gather_data_for_subcel(cel->subCels + 1, cel->sourceX+4, cel->sourceY+0, enc, tempData);
-    gather_data_for_subcel(cel->subCels + 2, cel->sourceX+0, cel->sourceY+4, enc, tempData);
-    gather_data_for_subcel(cel->subCels + 3, cel->sourceX+4, cel->sourceY+4, enc, tempData);
+    gather_data_for_subcel(cel->subCels + 0, cel->sourceX+0, cel->sourceY+0, enc);
+    gather_data_for_subcel(cel->subCels + 1, cel->sourceX+4, cel->sourceY+0, enc);
+    gather_data_for_subcel(cel->subCels + 2, cel->sourceX+0, cel->sourceY+4, enc);
+    gather_data_for_subcel(cel->subCels + 3, cel->sourceX+4, cel->sourceY+4, enc);
 
     cel->eval_dist[RoQ_ID_CCC] = 0;
     divide_bit_use = 0;
@@ -563,9 +566,10 @@ static void gather_data_for_cel(CelEvaluation *cel, RoqEncContext *enc,
         }
 }
 
-static void remap_codebooks(RoqEncContext *enc, RoqTempdata *tempData)
+static void remap_codebooks(RoqEncContext *enc)
 {
     RoqContext *const roq = &enc->common;
+    RoqTempData *const tempData = &enc->tmp_data;
     int i, j, idx=0;
 
     /* Make remaps for the final codebook usage */
@@ -596,9 +600,10 @@ static void remap_codebooks(RoqEncContext *enc, RoqTempdata *tempData)
 /**
  * Write codebook chunk
  */
-static void write_codebooks(RoqEncContext *enc, RoqTempdata *tempData)
+static void write_codebooks(RoqEncContext *enc)
 {
     RoqContext *const roq = &enc->common;
+    RoqTempData *const tempData = &enc->tmp_data;
     int i, j;
     uint8_t **outp= &enc->out_buf;
 
@@ -652,10 +657,10 @@ static void write_typecode(CodingSpool *s, uint8_t type)
 }
 
 static void reconstruct_and_encode_image(RoqEncContext *enc,
-                                         RoqTempdata *tempData,
                                          int w, int h, int numBlocks)
 {
     RoqContext *const roq = &enc->common;
+    RoqTempData *const tempData = &enc->tmp_data;
     int i, j, k;
     int x, y;
     int subX, subY;
@@ -815,20 +820,17 @@ static int generate_codebook(RoqEncContext *enc,
     int i, j, k, ret = 0;
     int c_size = size*size/4;
     int *buf;
-    int *codebook = av_malloc_array(6*c_size, cbsize*sizeof(int));
+    int *codebook = enc->tmp_codebook_buf;
     int *closest_cb = enc->closest_cb;
 
-    if (!codebook)
-        return AVERROR(ENOMEM);
-
     ret = avpriv_init_elbg(points, 6 * c_size, inputCount, codebook,
                        cbsize, 1, closest_cb, &enc->randctx);
     if (ret < 0)
-        goto out;
+        return ret;
     ret = avpriv_do_elbg(points, 6 * c_size, inputCount, codebook,
                      cbsize, 1, closest_cb, &enc->randctx);
     if (ret < 0)
-        goto out;
+        return ret;
 
     buf = codebook;
     for (i=0; i<cbsize; i++)
@@ -840,40 +842,32 @@ static int generate_codebook(RoqEncContext *enc,
             results->v =    (*buf++ + CHROMA_BIAS/2)/CHROMA_BIAS;
             results++;
         }
-out:
-    av_free(codebook);
-    return ret;
+    return 0;
 }
 
-static int generate_new_codebooks(RoqEncContext *enc, RoqTempdata *tempData)
+static int generate_new_codebooks(RoqEncContext *enc)
 {
     int i, j, ret = 0;
-    RoqCodebooks *codebooks = &tempData->codebooks;
+    RoqCodebooks *codebooks = &enc->tmp_data.codebooks;
     RoqContext *const roq = &enc->common;
     int max = roq->width * roq->height / 16;
     uint8_t mb2[3*4];
-    roq_cell *results4 = av_malloc(sizeof(roq_cell)*MAX_CBS_4x4*4);
     int *points = enc->points;
 
-    if (!results4) {
-        ret = AVERROR(ENOMEM);
-        goto out;
-    }
-
     /* Subsample YUV data */
     create_clusters(enc->frame_to_enc, roq->width, roq->height, points);
 
-    /* Create 4x4 codebooks */
-    if ((ret = generate_codebook(enc, points, max,
-                                 results4, 4, (enc->quake3_compat ? MAX_CBS_4x4-1 : MAX_CBS_4x4))) < 0)
-        goto out;
-
     codebooks->numCB4 = (enc->quake3_compat ? MAX_CBS_4x4-1 : MAX_CBS_4x4);
 
+    /* Create 4x4 codebooks */
+    if ((ret = generate_codebook(enc, points, max, enc->results4,
+                                 4, codebooks->numCB4)) < 0)
+        return ret;
+
     /* Create 2x2 codebooks */
     if ((ret = generate_codebook(enc, points, max * 4,
                                  roq->cb2x2, 2, MAX_CBS_2x2)) < 0)
-        goto out;
+        return ret;
 
     codebooks->numCB2 = MAX_CBS_2x2;
 
@@ -884,7 +878,7 @@ static int generate_new_codebooks(RoqEncContext *enc, RoqTempdata *tempData)
     /* Index all 4x4 entries to the 2x2 entries, unpack, and enlarge */
     for (i=0; i<codebooks->numCB4; i++) {
         for (j=0; j<4; j++) {
-            unpack_roq_cell(&results4[4*i + j], mb2);
+            unpack_roq_cell(&enc->results4[4*i + j], mb2);
             index_mb(mb2, codebooks->unpacked_cb2, codebooks->numCB2,
                      &roq->cb4x4[i].idx[j], 2);
         }
@@ -893,20 +887,19 @@ static int generate_new_codebooks(RoqEncContext *enc, RoqTempdata *tempData)
         enlarge_roq_mb4(codebooks->unpacked_cb4 + i*4*4*3,
                         codebooks->unpacked_cb4_enlarged + i*8*8*3);
     }
-out:
-    av_free(results4);
-    return ret;
+
+    return 0;
 }
 
 static int roq_encode_video(RoqEncContext *enc)
 {
-    RoqTempdata *tempData = enc->tmpData;
+    RoqTempData *const tempData = &enc->tmp_data;
     RoqContext *const roq = &enc->common;
     int ret;
 
     memset(tempData, 0, sizeof(*tempData));
 
-    ret = generate_new_codebooks(enc, tempData);
+    ret = generate_new_codebooks(enc);
     if (ret < 0)
         return ret;
 
@@ -917,7 +910,7 @@ static int roq_encode_video(RoqEncContext *enc)
 
  retry_encode:
     for (int i = 0; i < roq->width * roq->height / 64; i++)
-        gather_data_for_cel(enc->cel_evals + i, enc, tempData);
+        gather_data_for_cel(enc->cel_evals + i, enc);
 
     /* Quake 3 can't handle chunks bigger than 65535 bytes */
     if (tempData->mainChunkSize/8 > 65535 && enc->quake3_compat) {
@@ -940,11 +933,11 @@ static int roq_encode_video(RoqEncContext *enc)
         goto retry_encode;
     }
 
-    remap_codebooks(enc, tempData);
+    remap_codebooks(enc);
 
-    write_codebooks(enc, tempData);
+    write_codebooks(enc);
 
-    reconstruct_and_encode_image(enc, tempData, roq->width, roq->height,
+    reconstruct_and_encode_image(enc, roq->width, roq->height,
                                  roq->width * roq->height / 64);
 
     /* Rotate frame history */
@@ -964,7 +957,6 @@ static av_cold int roq_encode_end(AVCodecContext *avctx)
     av_frame_free(&enc->common.current_frame);
     av_frame_free(&enc->common.last_frame);
 
-    av_freep(&enc->tmpData);
     av_freep(&enc->cel_evals);
     av_freep(&enc->closest_cb);
     av_freep(&enc->this_motion4);
@@ -1009,8 +1001,6 @@ static av_cold int roq_encode_init(AVCodecContext *avctx)
     if (!roq->last_frame || !roq->current_frame)
         return AVERROR(ENOMEM);
 
-    enc->tmpData      = av_malloc(sizeof(RoqTempdata));
-
     enc->this_motion4 =
         av_mallocz_array(roq->width * roq->height / 16, sizeof(motion_vect));
 
@@ -1028,7 +1018,7 @@ static av_cold int roq_encode_init(AVCodecContext *avctx)
     enc->closest_cb   =
         av_malloc_array(roq->width * roq->height, 3 * sizeof(int));
 
-    if (!enc->tmpData || !enc->this_motion4 || !enc->last_motion4 ||
+    if (!enc->this_motion4 || !enc->last_motion4 ||
         !enc->this_motion8 || !enc->last_motion8 || !enc->closest_cb)
         return AVERROR(ENOMEM);