[FFmpeg-devel] [PATCH 1/7] proresdec2: port and fix for cached reader

[Christophe Gisquet <christophe.gisquet@gmail.com>]

Summary of changes
- move back to regular, non-macro, get_bits API
- reduce the lookup to switch the coding method
- shorter reads wherever possible, in particular for the end of bitstream
  (16 bits instead of 32, as per the above)

There are cases that really need longer lengths (larger EG codes) of up
to 27 bits.

Win64: 6.10 -> 4.87 (~20% speedup)

Reference for an hypothetical 32bits version of the cached reader:
Win32: 11.4 -> 9.8  (14%, because iDCT is not SIMDed)
---
 libavcodec/proresdec2.c | 53 ++++++++++++++++++-----------------------
 1 file changed, 23 insertions(+), 30 deletions(-)

diff --git a/libavcodec/proresdec2.c b/libavcodec/proresdec2.c
index 9297860946..6e243cfc17 100644
--- a/libavcodec/proresdec2.c
+++ b/libavcodec/proresdec2.c
@@ -24,9 +24,7 @@
  * Known FOURCCs: 'apch' (HQ), 'apcn' (SD), 'apcs' (LT), 'apco' (Proxy), 'ap4h' (4444), 'ap4x' (4444 XQ)
  */
 
-//#define DEBUG
-
-#define LONG_BITSTREAM_READER
+#define CACHED_BITSTREAM_READER 1
 
 #include "config_components.h"
 
@@ -422,35 +420,37 @@ static int decode_picture_header(AVCodecContext *avctx, const uint8_t *buf, cons
     return pic_data_size;
 }
 
-#define DECODE_CODEWORD(val, codebook, SKIP)                            \
+/* bitstream_read may fail on 32bits ARCHS for >24 bits, so use long version there */
+#if 0 //BITSTREAM_BITS == 32
+# define READ_BITS get_bits_long
+#else
+# define READ_BITS get_bits
+#endif
+
+#define DECODE_CODEWORD(val, codebook)                                  \
     do {                                                                \
         unsigned int rice_order, exp_order, switch_bits;                \
         unsigned int q, buf, bits;                                      \
                                                                         \
-        UPDATE_CACHE(re, gb);                                           \
-        buf = GET_CACHE(re, gb);                                        \
+        buf = show_bits(gb, 14);                                        \
                                                                         \
         /* number of bits to switch between rice and exp golomb */      \
         switch_bits =  codebook & 3;                                    \
         rice_order  =  codebook >> 5;                                   \
         exp_order   = (codebook >> 2) & 7;                              \
                                                                         \
-        q = 31 - av_log2(buf);                                          \
+        q = 13 - av_log2(buf);                                          \
                                                                         \
         if (q > switch_bits) { /* exp golomb */                         \
             bits = exp_order - switch_bits + (q<<1);                    \
-            if (bits > FFMIN(MIN_CACHE_BITS, 31))                       \
-                return AVERROR_INVALIDDATA;                             \
-            val = SHOW_UBITS(re, gb, bits) - (1 << exp_order) +         \
+            val = READ_BITS(gb, bits) - (1 << exp_order) +              \
                 ((switch_bits + 1) << rice_order);                      \
-            SKIP(re, gb, bits);                                         \
         } else if (rice_order) {                                        \
-            SKIP_BITS(re, gb, q+1);                                     \
-            val = (q << rice_order) + SHOW_UBITS(re, gb, rice_order);   \
-            SKIP(re, gb, rice_order);                                   \
+            skip_remaining(gb, q+1);                                    \
+            val = (q << rice_order) + get_bits(gb, rice_order);         \
         } else {                                                        \
             val = q;                                                    \
-            SKIP(re, gb, q+1);                                          \
+            skip_remaining(gb, q+1);                                    \
         }                                                               \
     } while (0)
 
@@ -466,9 +466,7 @@ static av_always_inline int decode_dc_coeffs(GetBitContext *gb, int16_t *out,
     int16_t prev_dc;
     int code, i, sign;
 
-    OPEN_READER(re, gb);
-
-    DECODE_CODEWORD(code, FIRST_DC_CB, LAST_SKIP_BITS);
+    DECODE_CODEWORD(code, FIRST_DC_CB);
     prev_dc = TOSIGNED(code);
     out[0] = prev_dc;
 
@@ -477,13 +475,12 @@ static av_always_inline int decode_dc_coeffs(GetBitContext *gb, int16_t *out,
     code = 5;
     sign = 0;
     for (i = 1; i < blocks_per_slice; i++, out += 64) {
-        DECODE_CODEWORD(code, dc_codebook[FFMIN(code, 6U)], LAST_SKIP_BITS);
+        DECODE_CODEWORD(code, dc_codebook[FFMIN(code, 6U)]);
         if(code) sign ^= -(code & 1);
         else     sign  = 0;
         prev_dc += (((code + 1) >> 1) ^ sign) - sign;
         out[0] = prev_dc;
     }
-    CLOSE_READER(re, gb);
     return 0;
 }
 
@@ -497,11 +494,9 @@ static av_always_inline int decode_ac_coeffs(AVCodecContext *avctx, GetBitContex
     const ProresContext *ctx = avctx->priv_data;
     int block_mask, sign;
     unsigned pos, run, level;
-    int max_coeffs, i, bits_left;
+    int max_coeffs, i, bits_rem;
     int log2_block_count = av_log2(blocks_per_slice);
 
-    OPEN_READER(re, gb);
-    UPDATE_CACHE(re, gb);                                           \
     run   = 4;
     level = 2;
 
@@ -509,28 +504,26 @@ static av_always_inline int decode_ac_coeffs(AVCodecContext *avctx, GetBitContex
     block_mask = blocks_per_slice - 1;
 
     for (pos = block_mask;;) {
-        bits_left = gb->size_in_bits - re_index;
-        if (!bits_left || (bits_left < 32 && !SHOW_UBITS(re, gb, bits_left)))
+        bits_rem = get_bits_left(gb);
+        if (!bits_rem || (bits_rem < 16 && !show_bits(gb, bits_rem)))
             break;
 
-        DECODE_CODEWORD(run, run_to_cb[FFMIN(run,  15)], LAST_SKIP_BITS);
+        DECODE_CODEWORD(run, run_to_cb[FFMIN(run,  15)]);
         pos += run + 1;
         if (pos >= max_coeffs) {
             av_log(avctx, AV_LOG_ERROR, "ac tex damaged %d, %d\n", pos, max_coeffs);
             return AVERROR_INVALIDDATA;
         }
 
-        DECODE_CODEWORD(level, lev_to_cb[FFMIN(level, 9)], SKIP_BITS);
+        DECODE_CODEWORD(level, lev_to_cb[FFMIN(level, 9)]);
         level += 1;
 
         i = pos >> log2_block_count;
 
-        sign = SHOW_SBITS(re, gb, 1);
-        SKIP_BITS(re, gb, 1);
+        sign = -get_bits1(gb);
         out[((pos & block_mask) << 6) + ctx->scan[i]] = ((level ^ sign) - sign);
     }
 
-    CLOSE_READER(re, gb);
     return 0;
 }
 
-- 
2.42.0

_______________________________________________
ffmpeg-devel mailing list
ffmpeg-devel@ffmpeg.org
https://ffmpeg.org/mailman/listinfo/ffmpeg-devel

To unsubscribe, visit link above, or email
ffmpeg-devel-request@ffmpeg.org with subject "unsubscribe".