ref: 8d940a664e14952f3541b6587e367064d9f321bd
parent: 164a229644a60c368a35edb5993251efcc907a98
author: Timothy B. Terriberry <[email protected]>
date: Sun Oct 19 10:41:38 EDT 2008
Change end-of-stream handling in the range coder. Instead of trying to maximize the number of trailing zeros (minimize the number of bits encoded), we try to maximize the number of trailing bits that can contain arbitrary data. Note that this requires ec_enc_tell() and ec_dec_tell() to reserve an extra bit, since depending on the exact final codeword, as little as half the final range might be available for storing arbitrary data. This is the first step needed to start packing literal bits outside the range coder (for speed and robustness purposes).
--- a/libcelt/mfrngdec.c
+++ b/libcelt/mfrngdec.c
@@ -69,60 +69,13 @@
one or two code words in the interval.
For details see \cite{SM98}.- This coder also handles the end of the stream in a slightly more graceful
- fashion than most arithmetic or range coders.
- Once the final symbol has been encoded, the coder selects the code word with
- the shortest number of bits that still falls within the final interval.
- This method is not novel.
- Here, by the length of the code word, we refer to the number of bits until
- its final 1.
- Any trailing zeros may be discarded, since the encoder, once it runs out of
- input, will pad its buffer with zeros.
+ End of stream is handled by writing out the smallest number of bits that
+ ensures that the stream will be correctly decoded regardless of the value of
+ any subsequent bits.
+ ec_dec_tell() can be used to determine how many bits were needed to decode
+ all the symbols thus far; other data can be packed in the remaining bits of
+ the input buffer.
- But this means that no encoded stream would ever have any zero bytes at the
- end.
- Since there are some coded representations we cannot produce, it implies that
- there is still some redundancy in the stream.
- In this case, we can pick a special byte value, RSV1, and should the stream
- end in a sequence of zeros, followed by the RSV1 byte, we can code the
- zeros, and discard the RSV1 byte.
- The decoder, knowing that the encoder would never produce a sequence of zeros
- at the end, would then know to add in the RSV1 byte if it observed it.
-
- Now, the encoder would never produce a stream that ended in a sequence of
- zeros followed by a RSV1 byte.
- So, if the stream ends in a non-empty sequence of zeros, followed by any
- positive number of RSV1 bytes, the last RSV1 byte is discarded.
- The decoder, if it encounters a stream that ends in non-empty sequence of
- zeros followed by any non-negative number of RSV1 bytes, adds an additional
- RSV1 byte to the stream.
- With this strategy, every possible sequence of input bytes is transformed to
- one that could actually be produced by the encoder.
-
- The only question is what non-zero value to use for RSV1.
- We select 0x80, since it has the nice property of producing the shortest
- possible byte streams when using our strategy for selecting a number within
- the final interval to encode.
- Clearly if the shortest possible code word that falls within the interval has
- its last one bit as the most significant bit of the final byte, and the
- previous bytes were a non-empty sequence of zeros followed by a non-negative
- number of 0x80 bytes, then the last byte would be discarded.
- If the shortest code word is not so formed, then no other code word in the
- interval would result in any more bytes being discarded.
- Any longer code word would have an additional one bit somewhere, and so would
- require at a minimum that that byte would be coded.
- If the shortest code word has a 1 before the final one that is preventing the
- stream from ending in a non-empty sequence of zeros followed by a
- non-negative number of 0x80's, then there is no code word of the same length
- which contains that bit as a zero.
- If there were, then we could simply leave that bit a 1, and drop all the bits
- after it without leaving the interval, thus producing a shorter code word.
-
- In this case, RSV1 can only drop 1 bit off the final stream.
- Other choices could lead to savings of up to 8 bits for particular streams,
- but this would produce the odd situation that a stream with more non-zero
- bits is actually encoded in fewer bytes.
-
@PHDTHESIS{Pas76,author="Richard Clark Pasco",
title="Source coding algorithms for fast data compression",
@@ -257,13 +210,10 @@
long nbits;
nbits=(ec_byte_bytes(_this->buf)-(EC_CODE_BITS+EC_SYM_BITS-1)/EC_SYM_BITS)*
EC_SYM_BITS;
- /*To handle the non-integral number of bits still left in the encoder state,
+ /*To handle the non-integral number of bits still left in the decoder state,
we compute the number of bits of low that must be encoded to ensure that
- the value is inside the range for any possible subsequent bits.
- Note that this is subtly different than the actual value we would end the
- stream with, which tries to make as many of the trailing bits zeros as
- possible.*/
- nbits+=EC_CODE_BITS;
+ the value is inside the range for any possible subsequent bits.*/
+ nbits+=EC_CODE_BITS+1;
nbits<<=_b;
l=EC_ILOG(_this->rng);
r=_this->rng>>l-16;
@@ -276,40 +226,3 @@
}
return nbits-l;
}
-
-#if 0
-int ec_dec_done(ec_dec *_this){- unsigned low;
- int ret;
- /*Check to make sure we've used all the input bytes.
- This ensures that no more ones would ever be inserted into the decoder.*/
- if(_this->buf->ptr-ec_byte_get_buffer(_this->buf)<=
- ec_byte_bytes(_this->buf)){- return 0;
- }
- /*We compute the smallest finitely odd fraction that fits inside the current
- range, and write that to the stream.
- This is guaranteed to yield the smallest possible encoding.*/
- /*TODO: Fix this line, as it is wrong.
- It doesn't seem worth being able to make this check to do an extra
- subtraction for every symbol decoded.*/
- low=/*What we want: _this->top-_this->rng; What we have:*/_this->dif
- if(low){- unsigned end;
- end=EC_CODE_TOP;
- /*Ensure that the next free end is in the range.*/
- if(end-low>=_this->rng){- unsigned msk;
- msk=EC_CODE_TOP-1;
- do{- msk>>=1;
- end=low+msk&~msk|msk+1;
- }
- while(end-low>=_this->rng);
- }
- /*The remaining input should have been the next free end.*/
- return end-low!=_this->dif;
- }
- return 1;
-}
-#endif
--- a/libcelt/mfrngenc.c
+++ b/libcelt/mfrngenc.c
@@ -169,11 +169,8 @@
nbits=(ec_byte_bytes(_this->buf)+(_this->rem>=0)+_this->ext)*EC_SYM_BITS;
/*To handle the non-integral number of bits still left in the encoder state,
we compute the number of bits of low that must be encoded to ensure that
- the value is inside the range for any possible subsequent bits.
- Note that this is subtly different than the actual value we would end the
- stream with, which tries to make as many of the trailing bits zeros as
- possible.*/
- nbits+=EC_CODE_BITS;
+ the value is inside the range for any possible subsequent bits.*/
+ nbits+=EC_CODE_BITS+1;
nbits<<=_b;
l=EC_ILOG(_this->rng);
r=_this->rng>>l-16;
@@ -188,30 +185,26 @@
}
void ec_enc_done(ec_enc *_this){- /*We compute the integer in the current interval that has the largest number
- of trailing zeros, and write that to the stream.
- This is guaranteed to yield the smallest possible encoding.*/
- if(_this->low){- ec_uint32 end;
- end=EC_CODE_TOP;
- /*Ensure that the end value is in the range.*/
- if(end-_this->low>=_this->rng){- ec_uint32 msk;
- msk=EC_CODE_TOP-1;
- do{- msk>>=1;
- end=_this->low+msk&~msk|msk+1;
- }
- while(end-_this->low>=_this->rng);
- }
- /*The remaining output is the next free end.*/
- while(end){- ec_enc_carry_out(_this,end>>EC_CODE_SHIFT);
- end=end<<EC_SYM_BITS&EC_CODE_TOP-1;
- }
+ ec_uint32 end;
+ ec_uint32 msk;
+ int l;
+ /*We output the minimum number of bits that ensures that the symbols encoded
+ thus far will be decoded correctly regardless of the bits that follow.*/
+ l=EC_CODE_BITS-EC_ILOG(_this->rng);
+ msk=EC_CODE_TOP-1>>l;
+ end=_this->low+msk&~msk;
+ if((end|msk)>=_this->low+_this->rng){+ l++;
+ msk>>=1;
+ end=_this->low+msk&~msk;
}
+ while(l>0){+ ec_enc_carry_out(_this,(int)(end>>EC_CODE_SHIFT));
+ end=end<<EC_SYM_BITS&EC_CODE_TOP-1;
+ l-=EC_SYM_BITS;
+ }
/*If we have a buffered byte flush it into the output buffer.*/
- if(_this->rem>0||_this->ext>0){+ if(_this->rem>=0||_this->ext>0){ec_enc_carry_out(_this,0);
_this->rem=-1;
}
--- a/libcelt/rangedec.c
+++ b/libcelt/rangedec.c
@@ -61,6 +61,12 @@
encoding for efficiency actually re-discovers many of the principles
behind range encoding, and presents a good theoretical analysis of them.
+ End of stream is handled by writing out the smallest number of bits that
+ ensures that the stream will be correctly decoded regardless of the value of
+ any subsequent bits.
+ ec_dec_tell() can be used to determine how many bits were needed to decode
+ all the symbols thus far; other data can be packed in the remaining bits of
+ the input buffer.
@PHDTHESIS{Pas76,author="Richard Clark Pasco",
title="Source coding algorithms for fast data compression",
@@ -168,13 +174,10 @@
long nbits;
nbits=(ec_byte_bytes(_this->buf)-(EC_CODE_BITS+EC_SYM_BITS-1)/EC_SYM_BITS)*
EC_SYM_BITS;
- /*To handle the non-integral number of bits still left in the encoder state,
+ /*To handle the non-integral number of bits still left in the decoder state,
we compute the number of bits of low that must be encoded to ensure that
- the value is inside the range for any possible subsequent bits.
- Note that this is subtly different than the actual value we would end the
- stream with, which tries to make as many of the trailing bits zeros as
- possible.*/
- nbits+=EC_CODE_BITS;
+ the value is inside the range for any possible subsequent bits.*/
+ nbits+=EC_CODE_BITS+1;
nbits<<=_b;
l=EC_ILOG(_this->rng);
r=_this->rng>>l-16;
@@ -187,40 +190,3 @@
}
return nbits-l;
}
-
-#if 0
-int ec_dec_done(ec_dec *_this){- unsigned low;
- int ret;
- /*Check to make sure we've used all the input bytes.
- This ensures that no more ones would ever be inserted into the decoder.*/
- if(_this->buf->ptr-ec_byte_get_buffer(_this->buf)<=
- ec_byte_bytes(_this->buf)){- return 0;
- }
- /*We compute the smallest finitely odd fraction that fits inside the current
- range, and write that to the stream.
- This is guaranteed to yield the smallest possible encoding.*/
- /*TODO: Fix this line, as it is wrong.
- It doesn't seem worth being able to make this check to do an extra
- subtraction for every symbol decoded.*/
- low=/*What we want: _this->top-_this->rng; What we have:*/_this->dif
- if(low){- unsigned end;
- end=EC_CODE_TOP;
- /*Ensure that the next free end is in the range.*/
- if(end-low>=_this->rng){- unsigned msk;
- msk=EC_CODE_TOP-1;
- do{- msk>>=1;
- end=(low+msk)&~msk|msk+1;
- }
- while(end-low>=_this->rng);
- }
- /*The remaining input should have been the next free end.*/
- return end-low!=_this->dif;
- }
- return 1;
-}
-#endif
--- a/libcelt/rangeenc.c
+++ b/libcelt/rangeenc.c
@@ -143,11 +143,8 @@
nbits=(ec_byte_bytes(_this->buf)+(_this->rem>=0)+_this->ext)*EC_SYM_BITS;
/*To handle the non-integral number of bits still left in the encoder state,
we compute the number of bits of low that must be encoded to ensure that
- the value is inside the range for any possible subsequent bits.
- Note that this is subtly different than the actual value we would end the
- stream with, which tries to make as many of the trailing bits zeros as
- possible.*/
- nbits+=EC_CODE_BITS;
+ the value is inside the range for any possible subsequent bits.*/
+ nbits+=EC_CODE_BITS+1;
nbits<<=_b;
l=EC_ILOG(_this->rng);
r=_this->rng>>l-16;
@@ -162,30 +159,26 @@
}
void ec_enc_done(ec_enc *_this){- /*We compute the integer in the current interval that has the largest number
- of trailing zeros, and write that to the stream.
- This is guaranteed to yield the smallest possible encoding.*/
- if(_this->low){- ec_uint32 end;
- end=EC_CODE_TOP;
- /*Ensure that the end value is in the range.*/
- if(end-_this->low>=_this->rng){- ec_uint32 msk;
- msk=EC_CODE_TOP-1;
- do{- msk>>=1;
- end=_this->low+msk&~msk|msk+1;
- }
- while(end-_this->low>=_this->rng);
- }
- /*The remaining output is the next free end.*/
- while(end){- ec_enc_carry_out(_this,end>>EC_CODE_SHIFT);
- end=end<<EC_SYM_BITS&EC_CODE_TOP-1;
- }
+ ec_uint32 msk;
+ ec_uint32 end;
+ int l;
+ /*We output the minimum number of bits that ensures that the symbols encoded
+ thus far will be decoded correctly regardless of the bits that follow.*/
+ l=EC_CODE_BITS-EC_ILOG(_this->rng);
+ msk=EC_CODE_TOP-1>>l;
+ end=_this->low+msk&~msk;
+ if((end|msk)>=_this->low+_this->rng){+ l++;
+ msk>>=1;
+ end=_this->low+msk&~msk;
}
+ while(l>0){+ ec_enc_carry_out(_this,(int)(end>>EC_CODE_SHIFT));
+ end=end<<EC_SYM_BITS&EC_CODE_TOP-1;
+ l-=EC_SYM_BITS;
+ }
/*If we have a buffered byte flush it into the output buffer.*/
- if(_this->rem>0||_this->ext>0){+ if(_this->rem>=0||_this->ext>0){ec_enc_carry_out(_this,0);
_this->rem=-1;
}