Abstract: A technique for decoding an encoded data stream representing an original sequence of data bits is provided, wherein the encoded data stream comprises a plurality of codes, each code being dependent on a current data bit and a first predetermined number of preceding data bits in the original sequence. For each of a number of possible states of the first predetermined number of preceding data bits, a score is provided indicating the likelihood that the corresponding state represents the first predetermined number of preceding data bits. The scores are arranged in an initial ordering. Upon receipt of a code given each of the two possible values of the current data bit in the received code, two update values are determined for each state indicating the likelihood, based on the received code, that that state represents the first predetermined number of bits.

Abstract: Character codes 2 representing pictograph font characters 6 may be used to determine an address 8 within a variable length coded data stream 10 of pixel data for the whole font relevant to the character 6 concerned. This access is via a two level table lookup with the first table level Table 1 returning an initial offset HuffOff within the coded data stream, an average size AvSz of data for a character and a pointer TB2Off to a second table Table 2. The second table is then used to lookup an error value Err to correct an estimate of the address generated from the information in the first table using the error value Err and the position N within the second table Table 2 that led to the match. The pixel bitmaps 36 for pictograph characters 6 can be divided into smaller tiles 38 and each of these tiles given a code. The tile codes may then be Huffman coded to provide highly efficient compression of the pixel bitmap font data.

Abstract: Character codes 2 representing pictograph font characters 6 may be used to determine an address 8 within a variable length coded data stream 10 of pixel data for the whole font relevant to the character 6 concerned. This access is via a two level table lookup with the first table level Table 1 returning an initial offset HuffOff within the coded data stream, an average size AvSz of data for a character and a pointer TB2Off to a second table Table 2. The second table is then used to lookup an error value Err to correct an estimate of the address generated from the information in the first table using the error value Err and the position N within the second table Table 2 that led to the match. The pixel bitmaps 36 for pictograph characters 6 can be divided into smaller tiles 38 and each of these tiles given a code. The tile codes may then be Huffman coded to provide highly efficient compression of the pixel bitmap font data.

Abstract: A digital signal processing system comprising a central processing unit core 2, a memory 8 and a coprocessor 4 operates using coprocessor memory access instructions (e.g. LDC, STC). The addressing mode information within these coprocessor memory access instructions (P, U, W, Offset) not only controls the addressing mode used by the central processing unit core 2 but is also used by the coprocessor 4 to determine the number of data words in the transfer being specified such that the coprocessor 4 can terminate the transfer at the appropriate time. Knowledge in advance of the number of words in a transfer is also advantageous in some bus systems, such as those that can be used with synchronous DRAM. The Offset field within the instruction may be used to specify changes to be made in the value provided by the central processing unit core 2 upon execution of a particular instruction and also to specify the number of words in the transfer.