[go: up one dir, main page]

US20050152609A1 - Video decoder - Google Patents

Video decoder Download PDF

Info

Publication number
US20050152609A1
US20050152609A1 US11/001,636 US163604A US2005152609A1 US 20050152609 A1 US20050152609 A1 US 20050152609A1 US 163604 A US163604 A US 163604A US 2005152609 A1 US2005152609 A1 US 2005152609A1
Authority
US
United States
Prior art keywords
data
image data
bit
processor
multiplexer
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Abandoned
Application number
US11/001,636
Inventor
Roy Wang
David Wang
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Via Technologies Inc
Original Assignee
Via Technologies Inc
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Via Technologies Inc filed Critical Via Technologies Inc
Priority to US11/001,636 priority Critical patent/US20050152609A1/en
Assigned to VIA TECHNOLOGIES, INC. reassignment VIA TECHNOLOGIES, INC. ASSIGNMENT OF ASSIGNORS INTEREST (SEE DOCUMENT FOR DETAILS). Assignors: WANG, DAVID, WANG, ROY
Publication of US20050152609A1 publication Critical patent/US20050152609A1/en
Priority to US12/976,012 priority patent/US20110091124A1/en
Abandoned legal-status Critical Current

Links

Images

Classifications

    • HELECTRICITY
    • H04ELECTRIC COMMUNICATION TECHNIQUE
    • H04NPICTORIAL COMMUNICATION, e.g. TELEVISION
    • H04N19/00Methods or arrangements for coding, decoding, compressing or decompressing digital video signals
    • H04N19/42Methods or arrangements for coding, decoding, compressing or decompressing digital video signals characterised by implementation details or hardware specially adapted for video compression or decompression, e.g. dedicated software implementation
    • H04N19/423Methods or arrangements for coding, decoding, compressing or decompressing digital video signals characterised by implementation details or hardware specially adapted for video compression or decompression, e.g. dedicated software implementation characterised by memory arrangements
    • H04N19/426Methods or arrangements for coding, decoding, compressing or decompressing digital video signals characterised by implementation details or hardware specially adapted for video compression or decompression, e.g. dedicated software implementation characterised by memory arrangements using memory downsizing methods
    • H04N19/427Display on the fly, e.g. simultaneous writing to and reading from decoding memory

Definitions

  • the present invention generally relates to a control device, system and method for data reading, and more particularly to a control device, system and method for multi-byte reading.
  • JPEG Joint Photographic Experts Groups
  • FIG. 1 it shows a system, which normally decodes something with a dual buffer within a system.
  • the image data is processed by a Huffman decoder (not shown) and an Inverse quantifier (not shown).
  • the IDCT Inverse Discrete Cosine Transform
  • the 32-bit processor 150 reads the first buffer's data by switching the multiplexer 140 .
  • the IDCT block 110 continuously processes the image data and outputs the data to be stored in the second buffer 130 .
  • the processor reads the first buffer's data. It means that a delay happens between the time that the processor is informed and the time of the actual reading. For example: based on the clock unit, the delay is about 6 to 7 system clocks. However, the delay in the prior art causes the processor to idle.
  • the processor reads the data of the first buffer based on an 8-bit unit for JPEG. It only can process 8 bits of data for JPEG even the processor with 32 bits can process 32 bits of data. As a result, the processor can not work efficiently.
  • a new and improved device, system and method is needed for multi-bit reading to solve the problems in the prior art such as: how to use the delay when the processor reads the data, how to provide the multi-bit data for reading and how to improve the efficiency of the processor.
  • the well-known multi-bit reading such as: the processing time is delayed and the system is idle, and the efficiency of the processor is questioned.
  • the object of the invention invention provides a device, system and method for multi-bit reading, which improves the above-mentioned disadvantage.
  • the object of the invention provides a device, system and method for processor reading.
  • For the processor reading and writing image data into registers is in the delay period of the processor reading clock.
  • the object of the invention also provides a device, system and method for improving the efficiency of the processor reading.
  • the processor By storing multi-byte image data, the processor reads the reading multi-byte data during a reading sequence. This is the way to fully utilize the data bus.
  • the object of the invention further provides a device, system and method for processing data of the different compressing format.
  • the invention can utilize JPEG and MPEG 2 format data.
  • the said objects of the invention provides a device, system and method for multi-byte reading. It provides a processor receiving multi-byte image data. By utilizing a portion of the memory units, after every memory unit sequentially receives the writing, the signals are enabled respectively, therefore, receiving and storing the multi-byte image data.
  • IDCT Inverse Discrete Cosine Transform
  • the processor simultaneously receives the output of these memory units.
  • the clock that's enabling all the memory units has less delay for the processor reading.
  • FIG. 1 is a schematic block diagram illustrating a normal decompressing image data system with a dual buffer according to the prior art
  • FIG. 2 is a schematic block diagram illustrating a decompressing image data system with a dual buffer according to the invention
  • FIGS. 3A and 3B are different schematic block diagrams illustrating one control circuit according to the invention.
  • FIG. 4 is a schematic flow chart illustrating decoding system.
  • the IDCT (Inverse Discrete Cosine Transform) unit 210 connects to a plurality of buffers (For example: the first buffer 220 and the second buffer 230 ) for receiving image data, writing data to buffers and transmitting a signal to the processor 250 .
  • a plurality of buffers connects to the control circuit 260 through the multiplexer 240 .
  • the control circuit 260 connects to the processor 250 .
  • the first buffer 220 and second buffer 230 are general memory devices, for example: Random Access Memory, RAM.
  • the processor 250 is a general processor with the 32-bit bus and the input/output function. However, it is not limited.
  • the processor 250 has a clock delay, which is induced by the physical characters of the hardware device. In one embodiment, the processor 250 has a 6 to 7 system clocks delay. The clock delay is not limited here, and the more clock delays with the processor 250 the more distinct merits the present invention has.
  • the control circuit 260 receives data from the first buffer 220 and the second buffer 230 , and provides image data to the processor 250 .
  • the processor 250 does not directly read the data of the buffers that is connected to the IDCT unit 210 . Which means that the first buffer 220 or the second buffer 230 could transmit the image data through the multiplexer 240 to the control circuit 260 when the processor 250 reads is in the “idle” state. Then, the processor 250 reads the data directly from the control circuit 260 , while actually processing the reading data. There, the processor 250 could read the data with a wide range for improving the efficiency of the processor. For example: the range of the data read can be increased from 1 byte to 2 bytes or to 4 bytes. It is noted that the time of transmitting the image data to the control circuit 260 must take less than time then the clock reading of the processor 250 .
  • the multiplexer 240 control the Image data that's transmitting from the first buffer 220 or the second buffer 230 to the control circuit 260 .
  • the multiplexer 240 provides a data path for the data of first buffer 220 transmitting to the control circuit 260 , when the stored data of the first buffer 220 is waiting for the processor 250 to read.
  • the IDCT unit 210 receives the processed image data and stores them in the second buffer 230 .
  • the multiplexer 240 provides a data path for the data of the second buffer 230 transmitting to the control circuit 260 ; At this time, the IDCT unit 210 receives the processed image data and stores them in the first buffer 220 .
  • the control circuit 260 includes the input selection unit and memory units.
  • the input selection unit in one embodiment, for instance: the multiplexer 240 , is used to receive a plurality of the input image data 22 a and 22 b and to output data 23 to memory unit(s).
  • the input image data 22 a comes from the first buffer
  • the input image data 22 b comes from the second buffer.
  • the control circuit of this invention is not limited in that the multiplexer as the input selection unit.
  • the control circuit is suitable for any designed logic circuit to replace the multiplexer.
  • the memory units for example: the registers 2602 , 2604 , 2606 and 2608 , respectively receives the writing enable signals 24 a, 24 b, 24 c and 24 d, that are corresponded and controlled by the control signal units 25 a to 25 d respectively. After receiving the corresponded writing enable signal, each memory unit respectively receives the data 23 from the multiplexer 240 and further outputs the necessary data 26 a, 26 b, 26 c, 26 d and 26 e to the corresponding processor, such as processor 250 . It is noted that the writing enable signals 24 a, 24 b, 24 c and 24 d, by corresponding clock times, sequentially writing enable the register 2602 , 2604 , 2606 and 2608 .
  • the control signal units 25 a to 25 d can be inside of the control unit 260 or outside of the control unit 260 .
  • the time of the enabling all registers is no more than the delay of the processor reading clock.
  • every writing enable signal enables a register for a clock and the embodiment for example is 4 accumulated clocks.
  • the enabling time, 4 clocks does not exceed the processor delay clock, 6 to 7 clocks.
  • it further includes a data bus of a plurality of byte data (not shown). The data bus is for receiving and transmitting the data of all the memory units (register 2602 , 2604 , 2606 and 2608 ).
  • the invention suits many kinds of compressed image data, such as: Motion Picture Experts Group 2, MPEG 2, and JPEG.
  • Different compressed image data has different bit numbers (especially for writing enable signal), for example: MPEG 2 has 9 bits data and JPEG has 8 bits data.
  • the invention can further include a multiplexer 2603 for selecting between different bit data and the multiplexer 2603 outputs a data 26 e (the multiplexer is not needed as the FIG. 3A , If the input is not different bit data).
  • the register 2602 and the register 2604 connected to the multiplexer 2603 have different pin numbers from each other.
  • the register 2602 and the multiplexer 240 connected with 9 pins and the register 2604 and the multiplexer 240 connected with 8 pins.
  • the register 2606 , the register 2608 and the multiplexer 240 connect with 8 pins, too.
  • the register 2602 has two different data outputs, one is 8 bits output, data 26 a, and the other one is the highest bit or lowest bit of the output.
  • the register 2604 has the output, one is 7 bits output, data 26 b, and the other one is the first bit of the output to the multiplexer 2603 .
  • the multiplexer 2603 select the data from the register 2602 and outputs the bit data, 26 e, and 8 bit data, 26 a.
  • the bit data, 26 e, and the 8 bit data combine a 9 bit data for doing motion compensation.
  • the multiplexer 2603 selects the data from the register 2604 and outputs a bit data, 26 e, and 7 bit data, 26 b.
  • the bit data, 26 e, and the 7 bit data combine an 8 bit data.
  • the multiplexer 2603 outputs different data 26 e by referring to the input format, and then the processor 250 controlled by the control circuit 260 , can select the data from the register 2602 or the register 2604 .
  • the other registers are not connected to the multiplexer 2603 , in the embodiment such as: register 2606 and 2608 , have 8 bits output data, respectively, such as 26 c and 26 d.
  • the received data of the processor is 32 bits and its equal to the bit numbers of the data bus.
  • the bit numbers of the output of the plurality of register is strongly close to the bit numbers of the data bus, so that the processor can read once for receiving the data that is equal to the bit numbers of the data bus.
  • the processor can read multi-byte image data, efficiently utilizing the bit numbers of the data bus and have maximum performance of the data bus.
  • 32 bits do not limit the control circuit of the invention. And it is not limited by the 4-clock system delay.
  • the only limitations are the following: the bit number of the data is no more than the bit number of the data bus of the processor, the processor can read the multi-byte data, and the total clock is not more than the reading delay of the processor. Any variation limited by the above limitations is included in the scope of the invention.
  • FIG. 4 shows a flow chart of an embodiment of the decoding system in the invention.
  • the typical image data goes through the Huffman decoder and the Inverse quantizer, the typical data are inputted to the IDCT unit.
  • the data goes through the IDCT unit and is written in a buffer and then at least one buffer full of data (step 410 ).
  • the IDCT unit informs the processor to read the data (step 420 ).
  • the processor has a “m” bit data bus and a delay “n” that is the time between the reading signal received and that of the execution started.
  • the data of the buffer write in registers in sequence (step 430 ).
  • the total time of the data writing in a plurality of registers is less than the time of the delay “n”.
  • the processor reads the data of the registers at the same time ( 440 ). Wherein the processor reads the data and has a bit number which is substantially equal (or not less than) to “m”.
  • control circuit of this invention applies to a decoding system with the dual buffer, the idle of reading image data and the writing in buffer of the IDCT unit do not depend on the acting of the processor.
  • the control circuit includes some registers.
  • the register can receive data when clocks delay in the processor. This reduces the idle time.
  • the total output bit of the register is close to the data bus, so as the processor can have the maximum performance of the data bus.

Landscapes

  • Engineering & Computer Science (AREA)
  • Multimedia (AREA)
  • Signal Processing (AREA)
  • Compression Or Coding Systems Of Tv Signals (AREA)
  • Complex Calculations (AREA)
  • Image Processing (AREA)
  • Compression Of Band Width Or Redundancy In Fax (AREA)
  • Closed-Circuit Television Systems (AREA)
  • Feedback Control In General (AREA)
  • Compression, Expansion, Code Conversion, And Decoders (AREA)

Abstract

A control device, system and method for multi-pixel reading provides a processor receiving multi-pixel, uses memory units wherein each memory unit sequentially receiving a writing enable signal, and then receiving and storing multi-pixel. Simultaneously, the processor having multi-data bus receives multi-pixel of the each memory unit output. The clock of the enabling all the memory units is less then the delay of the processor reading, so that reducing the spare time of the image decoding system and reducing the reading time of the reading image.

Description

    BACKGROUND OF THE INVENTION
  • 1. Field of the Invention
  • The present invention generally relates to a control device, system and method for data reading, and more particularly to a control device, system and method for multi-byte reading.
  • 2. Description of the Prior Art
  • JPEG, Joint Photographic Experts Groups, is basically a data processing method that normally includes a recovering (decoding) method. Referring to FIG. 1, it shows a system, which normally decodes something with a dual buffer within a system. The image data is processed by a Huffman decoder (not shown) and an Inverse quantifier (not shown). Then, the IDCT (Inverse Discrete Cosine Transform) block 110 processes the data and outputs it to be stored in the first buffer 120. When IDCT block 110 fills the first buffer 120 with data, a signal is sent to inform the 32-bit processor 150. And the 32-bit processor 150 reads the first buffer's data by switching the multiplexer 140. At this time, the IDCT block 110 continuously processes the image data and outputs the data to be stored in the second buffer 130.
  • Generally, it is an I/O (input and output) action that the processor reads the first buffer's data. It means that a delay happens between the time that the processor is informed and the time of the actual reading. For example: based on the clock unit, the delay is about 6 to 7 system clocks. However, the delay in the prior art causes the processor to idle. Next, the processor reads the data of the first buffer based on an 8-bit unit for JPEG. It only can process 8 bits of data for JPEG even the processor with 32 bits can process 32 bits of data. As a result, the processor can not work efficiently.
  • According to the previous mentioned disadvantage of the multi-bit reading, a new and improved device, system and method is needed for multi-bit reading to solve the problems in the prior art such as: how to use the delay when the processor reads the data, how to provide the multi-bit data for reading and how to improve the efficiency of the processor.
  • SUMMARY OF THE INVENTION
  • According to the defects of the prior art, the well-known multi-bit reading, such as: the processing time is delayed and the system is idle, and the efficiency of the processor is questioned. The object of the invention invention provides a device, system and method for multi-bit reading, which improves the above-mentioned disadvantage.
  • The object of the invention provides a device, system and method for processor reading. For the processor reading and writing image data into registers is in the delay period of the processor reading clock.
  • The object of the invention also provides a device, system and method for improving the efficiency of the processor reading. By storing multi-byte image data, the processor reads the reading multi-byte data during a reading sequence. This is the way to fully utilize the data bus.
  • The object of the invention further provides a device, system and method for processing data of the different compressing format. The invention can utilize JPEG and MPEG 2 format data.
  • Accordingly, the said objects of the invention provides a device, system and method for multi-byte reading. It provides a processor receiving multi-byte image data. By utilizing a portion of the memory units, after every memory unit sequentially receives the writing, the signals are enabled respectively, therefore, receiving and storing the multi-byte image data. When IDCT (Inverse Discrete Cosine Transform) unit informs the processor to read data, by the multi-byte bus of the processor, the processor simultaneously receives the output of these memory units. Herein, the clock that's enabling all the memory units has less delay for the processor reading.
  • BRIEF DESCRIPTION OF THE DRAWINGS
  • The foregoing aspects and many of the attendant advantages of this invention will become more readily appreciated as the same becomes better understood by reference to the following detailed description, when taken in conjunction with the accompanying drawings, wherein:
  • FIG. 1 is a schematic block diagram illustrating a normal decompressing image data system with a dual buffer according to the prior art;
  • FIG. 2 is a schematic block diagram illustrating a decompressing image data system with a dual buffer according to the invention;
  • FIGS. 3A and 3B are different schematic block diagrams illustrating one control circuit according to the invention; and
  • FIG. 4 is a schematic flow chart illustrating decoding system.
  • DESCRIPTION OF THE PREFERRED EMBODIMENTS
  • Some sample embodiments of the invention will now be described in greater detail. Nevertheless, it should be recognized that the present invention could be practiced in a wide range of procedures.
  • The present invention will be described in detail with reference to the accompanying drawings. It should be noted that the drawings are in greatly simplified form and in order to provide a clear illustration and understanding of the present invention.
  • Referring to FIG. 2, it is an embodiment of decompressing image data according to this invention. The IDCT (Inverse Discrete Cosine Transform) unit 210 connects to a plurality of buffers (For example: the first buffer 220 and the second buffer 230) for receiving image data, writing data to buffers and transmitting a signal to the processor 250. A plurality of buffers connects to the control circuit 260 through the multiplexer 240. And the control circuit 260 connects to the processor 250. In one embodiment, the first buffer 220 and second buffer 230 are general memory devices, for example: Random Access Memory, RAM. Next, the processor 250 is a general processor with the 32-bit bus and the input/output function. However, it is not limited. The more bits the processor has, the more merit the invention has. Between the time of preparing to send and receive the data and the time of actually receiving the data, the processor 250 has a clock delay, which is induced by the physical characters of the hardware device. In one embodiment, the processor 250 has a 6 to 7 system clocks delay. The clock delay is not limited here, and the more clock delays with the processor 250 the more distinct merits the present invention has.
  • The control circuit 260 receives data from the first buffer 220 and the second buffer 230, and provides image data to the processor 250. The processor 250 does not directly read the data of the buffers that is connected to the IDCT unit 210. Which means that the first buffer 220 or the second buffer 230 could transmit the image data through the multiplexer 240 to the control circuit 260 when the processor 250 reads is in the “idle” state. Then, the processor 250 reads the data directly from the control circuit 260, while actually processing the reading data. There, the processor 250 could read the data with a wide range for improving the efficiency of the processor. For example: the range of the data read can be increased from 1 byte to 2 bytes or to 4 bytes. It is noted that the time of transmitting the image data to the control circuit 260 must take less than time then the clock reading of the processor 250.
  • The multiplexer 240 control the Image data that's transmitting from the first buffer 220 or the second buffer 230 to the control circuit 260. The multiplexer 240 provides a data path for the data of first buffer 220 transmitting to the control circuit 260, when the stored data of the first buffer 220 is waiting for the processor 250 to read. At the same time, the IDCT unit 210 receives the processed image data and stores them in the second buffer 230. Similarly, when the data of the second buffer 230 is waiting for the processor 250 to read, the multiplexer 240 provides a data path for the data of the second buffer 230 transmitting to the control circuit 260; At this time, the IDCT unit 210 receives the processed image data and stores them in the first buffer 220.
  • Referring to FIG. 3A, it is an embodiment of the control circuit according to this invention. The control circuit 260 includes the input selection unit and memory units. The input selection unit in one embodiment, for instance: the multiplexer 240, is used to receive a plurality of the input image data 22 a and 22 b and to output data 23 to memory unit(s). Herein, the input image data 22 a comes from the first buffer, and the input image data 22 b comes from the second buffer. It is noted that the control circuit of this invention is not limited in that the multiplexer as the input selection unit. The control circuit is suitable for any designed logic circuit to replace the multiplexer. The memory units, for example: the registers 2602, 2604, 2606 and 2608, respectively receives the writing enable signals 24 a, 24 b, 24 c and 24 d, that are corresponded and controlled by the control signal units 25 a to 25 d respectively. After receiving the corresponded writing enable signal, each memory unit respectively receives the data 23 from the multiplexer 240 and further outputs the necessary data 26 a, 26 b, 26 c, 26 d and 26 e to the corresponding processor, such as processor 250. It is noted that the writing enable signals 24 a, 24 b, 24 c and 24 d, by corresponding clock times, sequentially writing enable the register 2602, 2604, 2606 and 2608. The control signal units 25 a to 25 d can be inside of the control unit 260 or outside of the control unit 260. In the embodiment, the time of the enabling all registers is no more than the delay of the processor reading clock. In the embodiment, every writing enable signal enables a register for a clock and the embodiment for example is 4 accumulated clocks. The enabling time, 4 clocks, does not exceed the processor delay clock, 6 to 7 clocks. In the embodiment, it further includes a data bus of a plurality of byte data (not shown). The data bus is for receiving and transmitting the data of all the memory units ( register 2602, 2604, 2606 and 2608).
  • Next, the invention suits many kinds of compressed image data, such as: Motion Picture Experts Group 2, MPEG 2, and JPEG. Different compressed image data has different bit numbers (especially for writing enable signal), for example: MPEG 2 has 9 bits data and JPEG has 8 bits data. Referring to FIG. 3B. The invention can further include a multiplexer 2603 for selecting between different bit data and the multiplexer 2603 outputs a data 26 e (the multiplexer is not needed as the FIG. 3A, If the input is not different bit data). The register 2602 and the register 2604 connected to the multiplexer 2603 have different pin numbers from each other. In one embodiment, the register 2602 and the multiplexer 240 connected with 9 pins and the register 2604 and the multiplexer 240 connected with 8 pins. In addition to, the register 2606, the register 2608 and the multiplexer 240 connect with 8 pins, too. Next, the register 2602 has two different data outputs, one is 8 bits output, data 26 a, and the other one is the highest bit or lowest bit of the output. And the register 2604 has the output, one is 7 bits output, data 26 b, and the other one is the first bit of the output to the multiplexer 2603. When the decoding system applies in data inputting of MPEG 2, the multiplexer 2603 select the data from the register 2602 and outputs the bit data, 26 e, and 8 bit data, 26 a. The bit data, 26 e, and the 8 bit data combine a 9 bit data for doing motion compensation. When the decoding system applies in data inputting of JPEG, the multiplexer 2603 selects the data from the register 2604 and outputs a bit data, 26 e, and 7 bit data, 26 b. The bit data, 26 e, and the 7 bit data combine an 8 bit data. In other words, the multiplexer 2603 outputs different data 26 e by referring to the input format, and then the processor 250 controlled by the control circuit 260, can select the data from the register 2602 or the register 2604. Herein, the other registers are not connected to the multiplexer 2603, in the embodiment such as: register 2606 and 2608, have 8 bits output data, respectively, such as 26 c and 26 d.
  • According to the previous said discussion, the received data of the processor is 32 bits and its equal to the bit numbers of the data bus. In the invention, the bit numbers of the output of the plurality of register is strongly close to the bit numbers of the data bus, so that the processor can read once for receiving the data that is equal to the bit numbers of the data bus. The processor can read multi-byte image data, efficiently utilizing the bit numbers of the data bus and have maximum performance of the data bus. One must explain that 32 bits do not limit the control circuit of the invention. And it is not limited by the 4-clock system delay. The only limitations are the following: the bit number of the data is no more than the bit number of the data bus of the processor, the processor can read the multi-byte data, and the total clock is not more than the reading delay of the processor. Any variation limited by the above limitations is included in the scope of the invention.
  • FIG. 4 shows a flow chart of an embodiment of the decoding system in the invention. After that the typical image data goes through the Huffman decoder and the Inverse quantizer, the typical data are inputted to the IDCT unit. The data goes through the IDCT unit and is written in a buffer and then at least one buffer full of data (step 410). When the buffer is full, the IDCT unit informs the processor to read the data (step 420). The processor has a “m” bit data bus and a delay “n” that is the time between the reading signal received and that of the execution started. At the time of sending the read signal, the data of the buffer write in registers in sequence (step 430). The total time of the data writing in a plurality of registers is less than the time of the delay “n”. The processor reads the data of the registers at the same time (440). Wherein the processor reads the data and has a bit number which is substantially equal (or not less than) to “m”.
  • Because the control circuit of this invention applies to a decoding system with the dual buffer, the idle of reading image data and the writing in buffer of the IDCT unit do not depend on the acting of the processor. Next, the control circuit includes some registers. The register can receive data when clocks delay in the processor. This reduces the idle time. The total output bit of the register is close to the data bus, so as the processor can have the maximum performance of the data bus.
  • Other embodiments of the invention will appear to those skilled in the art from consideration of the specification and practice of the invention disclosed herein. It is intended that the specification and examples to be considered as exemplary only, with a true scope and spirit of the invention being indicated by the following claims.

Claims (19)

1. A controlling device for outputting multi-byte image data, comprising:
a plurality of memory units, each said memory unit receiving and storing a plurality of bit image data, wherein said plurality of memory units simultaneously and correspondingly output said plurality of bit image data, and the sum of said plurality of said bit image data equal to a plurality of byte image data; and
a plurality of control signal units for generating a plurality of writing enable signals, said plurality of writing enable signals being corresponding to said plurality of memory units, respectively, wherein said plurality of writing enable signals control said plurality of memory units to be stored in said plurality of bit image data in sequence.
2. The controlling device according to claim 1, wherein a plurality of said memory units are a plurality of registers.
3. The controlling device according to claim 1, wherein the controlling device further comprises at least one multiplexer being connected with at least two said memory units.
4. The controlling device according to claim 3, wherein said plurality of bit image data from any said memory units connected to said multiplexer is chosen from the groups selected as follows: a first bit data and a second bit data, wherein said first bit data is not equal to said second bit data.
5. The controlling device according to claim 4, wherein said first bit data is not more than 1 bit data.
6. The controlling device according to claim 4, wherein the bit number of said bit image data received and stored in any said memory units connected to said multiplexer is not equal to the bit number of said bit image data received and stored in the others said memory units connected to said multiplexer.
7. The controlling device according to claim 4, wherein some said memory units connected to said multiplexer output said bit image data is integrated to build said plurality of byte image data.
8. The controlling device according to claim 4, wherein said multiplexer outputs one of said first bit data of one said memory unit connected to said multiplexer.
9. The controlling device according to claim 1, further comprising a data bus having a plurality of byte for transmitting a plurality of said byte image data.
10. A controlling system for outputting multi-byte image data, comprises:
an inverse discrete consine transform (IDCT) unit for processing a plurality of image data;
a plurality of buffers for receiving said plurality of image data processed by said inverse discrete consine transform (IDCT) unit;
a multiplexer connected to said plurality of buffers;
a control circuit connected to said multiplexer for utilizing said multiplexer to move said image data from said buffers to said control circuit; and
a processor, connected to said control circuit, for receiving said image data from said control circuit simultaneously.
11. The controlling system according to claim 10, further comprising a data bus for transmitting data from said control circuit to said processor, wherein the bit number of said data bus is not less than the total bit number of said buffers.
12. The controlling system according to claim 10, when said processor being idle, said buffers transmit said plurality of image data through said multiplexer to said control circuit, and when said processor reading, said processor reads a plurality of said image data from said control circuit directly.
13. The controlling system according to claim 10, wherein said multiplexer controls said image data transmitted between said buffers and said control circuit, and at the same time, only one said buffer transmits data to said control circuit and other said buffers receive said image data processed by said inverse discrete consine transform (IDCT) unit.
14. The controlling system according to claim 10, when any said buffer is full of data, said control circuit moves data of said filled buffer to said control circuit for enabling said buffer to receive data from said inverse discrete consine transform (IDCT) unit.
15. The controlling system according to claim 10, when said control circuit is full of data, said IDCT unit sends a signal to said processor for informing said processor to read said control circuit.
16. A method for outputting multi-byte image data, comprising:
receiving a plurality of writing enable signals in sequence, when receiving any one of said writing enable signal, receiving and storing at least one bit image data to at least one memory unit; and
outputting a plurality of said bit image data simultaneously.
17. The method according to claim 16, wherein said outputting simultaneously step uses a data bus of a plurality of byte outputting and uses a processor for reading a plurality of said bit image data.
18. The method according to claim 17, wherein said processor having delay, said delay is more than the duration of spending said receiving said writing enable signals step
19. The method according to claim 16, further comprising a plurality of buffers for receiving said bit image data, and when any said buffer full of data, sends writing enable signal in sequence for moving said bit image data from said buffers to a plurality of memory unit.
US11/001,636 2003-12-03 2004-12-02 Video decoder Abandoned US20050152609A1 (en)

Priority Applications (2)

Application Number Priority Date Filing Date Title
US11/001,636 US20050152609A1 (en) 2003-12-03 2004-12-02 Video decoder
US12/976,012 US20110091124A1 (en) 2003-12-03 2010-12-22 System for multi-byte reading

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
US52629403P 2003-12-03 2003-12-03
US11/001,636 US20050152609A1 (en) 2003-12-03 2004-12-02 Video decoder

Related Child Applications (1)

Application Number Title Priority Date Filing Date
US12/976,012 Division US20110091124A1 (en) 2003-12-03 2010-12-22 System for multi-byte reading

Publications (1)

Publication Number Publication Date
US20050152609A1 true US20050152609A1 (en) 2005-07-14

Family

ID=34375610

Family Applications (6)

Application Number Title Priority Date Filing Date
US10/986,095 Abandoned US20050125480A1 (en) 2003-12-03 2004-11-12 Method and apparatus for multiplying based on booth's algorithm
US10/992,814 Abandoned US20050125475A1 (en) 2003-12-03 2004-11-22 Circuit sharing of MPEG and JPEG on IDCT
US10/992,849 Abandoned US20050123046A1 (en) 2003-12-03 2004-11-22 Method and device for sharing MPEG frame buffers
US11/000,885 Active 2026-10-13 US7558431B2 (en) 2003-12-03 2004-12-02 Method and system for discrete cosine transforms/inverse discrete cosine transforms based on pipeline architecture
US11/001,636 Abandoned US20050152609A1 (en) 2003-12-03 2004-12-02 Video decoder
US12/976,012 Abandoned US20110091124A1 (en) 2003-12-03 2010-12-22 System for multi-byte reading

Family Applications Before (4)

Application Number Title Priority Date Filing Date
US10/986,095 Abandoned US20050125480A1 (en) 2003-12-03 2004-11-12 Method and apparatus for multiplying based on booth's algorithm
US10/992,814 Abandoned US20050125475A1 (en) 2003-12-03 2004-11-22 Circuit sharing of MPEG and JPEG on IDCT
US10/992,849 Abandoned US20050123046A1 (en) 2003-12-03 2004-11-22 Method and device for sharing MPEG frame buffers
US11/000,885 Active 2026-10-13 US7558431B2 (en) 2003-12-03 2004-12-02 Method and system for discrete cosine transforms/inverse discrete cosine transforms based on pipeline architecture

Family Applications After (1)

Application Number Title Priority Date Filing Date
US12/976,012 Abandoned US20110091124A1 (en) 2003-12-03 2010-12-22 System for multi-byte reading

Country Status (3)

Country Link
US (6) US20050125480A1 (en)
CN (7) CN100527071C (en)
TW (5) TWI289992B (en)

Cited By (1)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20100287622A1 (en) * 2009-05-07 2010-11-11 Tensilica, Inc. System and Method for Preventing Proper Execution of an Application Program in an Unauthorized Processor

Families Citing this family (20)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
TWI245548B (en) * 2004-10-20 2005-12-11 Inst Information Industry Method and device for video decoding
US8599841B1 (en) 2006-03-28 2013-12-03 Nvidia Corporation Multi-format bitstream decoding engine
US8593469B2 (en) 2006-03-29 2013-11-26 Nvidia Corporation Method and circuit for efficient caching of reference video data
TW200816787A (en) * 2006-09-25 2008-04-01 Sunplus Technology Co Ltd Method and system of image decoding and image recoding
CN101246468B (en) * 2007-02-13 2010-05-19 扬智科技股份有限公司 Modified discrete cosine inverse conversion method
CN101064515B (en) * 2007-04-18 2011-05-11 威盛电子股份有限公司 Methods to Improve Decoding Performance
US8477852B2 (en) * 2007-06-20 2013-07-02 Nvidia Corporation Uniform video decoding and display
CN100588254C (en) * 2007-06-28 2010-02-03 威盛电子股份有限公司 Inverse discrete cosine transform circuit
US8502709B2 (en) 2007-09-17 2013-08-06 Nvidia Corporation Decoding variable length codes in media applications
JP4988627B2 (en) * 2008-03-05 2012-08-01 ルネサスエレクトロニクス株式会社 Filter calculator and motion compensation device
US9110849B2 (en) 2009-04-15 2015-08-18 Qualcomm Incorporated Computing even-sized discrete cosine transforms
US9069713B2 (en) 2009-06-05 2015-06-30 Qualcomm Incorporated 4X4 transform for media coding
US9075757B2 (en) 2009-06-24 2015-07-07 Qualcomm Incorporated 16-point transform for media data coding
US9118898B2 (en) 2009-06-24 2015-08-25 Qualcomm Incorporated 8-point transform for media data coding
US9081733B2 (en) * 2009-06-24 2015-07-14 Qualcomm Incorporated 16-point transform for media data coding
US9824066B2 (en) 2011-01-10 2017-11-21 Qualcomm Incorporated 32-point transform for media data coding
WO2015086730A1 (en) 2013-12-13 2015-06-18 Sanofi Non-acylated exendin-4 peptide analogues
KR102459917B1 (en) * 2015-02-23 2022-10-27 삼성전자주식회사 Image signal processor and devices having the same
CN105868554B (en) * 2016-03-28 2018-03-27 朱洲森 A kind of relay drainage method based on big data complex calculation
KR102885930B1 (en) * 2020-12-02 2025-11-12 삼성전자주식회사 Integrated circuit for constant multiplication and device including the same

Family Cites Families (32)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP0469855B1 (en) * 1990-07-31 1999-12-01 Fujitsu Limited Image data processing method and apparatus
US7095783B1 (en) * 1992-06-30 2006-08-22 Discovision Associates Multistandard video decoder and decompression system for processing encoded bit streams including start codes and methods relating thereto
US5842033A (en) * 1992-06-30 1998-11-24 Discovision Associates Padding apparatus for passing an arbitrary number of bits through a buffer in a pipeline system
JPH0744586B2 (en) * 1993-02-26 1995-05-15 日本電気株式会社 Parallel data transfer circuit
JP3546437B2 (en) 1993-03-31 2004-07-28 ソニー株式会社 Adaptive video signal processing unit
US5636155A (en) * 1993-04-27 1997-06-03 Matsushita Electric Industrial Co., Ltd. Arithmetic processor and arithmetic method
US5452466A (en) * 1993-05-11 1995-09-19 Teknekron Communications Systems, Inc. Method and apparatus for preforming DCT and IDCT transforms on data signals with a preprocessor, a post-processor, and a controllable shuffle-exchange unit connected between the pre-processor and post-processor
JPH0793134A (en) * 1993-09-24 1995-04-07 Nec Corp Multiplier
US5509129A (en) * 1993-11-30 1996-04-16 Guttag; Karl M. Long instruction word controlling plural independent processor operations
JP2851804B2 (en) 1993-12-27 1999-01-27 松下電器産業株式会社 2D orthogonal transform device
JPH07200539A (en) * 1993-12-28 1995-08-04 Matsushita Electric Ind Co Ltd Two-dimensional DCT computing device
US5574863A (en) * 1994-10-25 1996-11-12 Hewlett-Packard Company System for using mirrored memory as a robust communication path between dual disk storage controllers
JPH08152994A (en) * 1994-11-29 1996-06-11 Mitsubishi Electric Corp Multiplier and digital filter
US5787029A (en) * 1994-12-19 1998-07-28 Crystal Semiconductor Corp. Ultra low power multiplier
JP3474663B2 (en) * 1995-02-24 2003-12-08 三菱電機株式会社 Multiplication circuit
KR100212268B1 (en) * 1995-12-13 1999-08-02 윤종용 Idct system using lee's algorithm
US5854757A (en) * 1996-05-07 1998-12-29 Lsi Logic Corporation Super-compact hardware architecture for IDCT computation
US6026217A (en) * 1996-06-21 2000-02-15 Digital Equipment Corporation Method and apparatus for eliminating the transpose buffer during a decomposed forward or inverse 2-dimensional discrete cosine transform through operand decomposition storage and retrieval
US6144771A (en) * 1996-06-28 2000-11-07 Competitive Technologies Of Pa, Inc. Method and apparatus for encoding and decoding images
JPH1079940A (en) * 1996-09-05 1998-03-24 Mitsubishi Electric Corp Image coding device
US6128340A (en) * 1997-03-14 2000-10-03 Sony Corporation Decoder system with 2.53 frame display buffer
US6137916A (en) * 1997-11-17 2000-10-24 Sony Electronics, Inc. Method and system for improved digital video data processing using 8-point discrete cosine transforms
TW364269B (en) 1998-01-02 1999-07-11 Winbond Electronic Corp Discreet cosine transform/inverse discreet cosine transform circuit
WO1999039303A1 (en) * 1998-02-02 1999-08-05 The Trustees Of The University Of Pennsylvania Method and system for computing 8x8 dct/idct and a vlsi implementation
JP2000125136A (en) * 1998-10-19 2000-04-28 Internatl Business Mach Corp <Ibm> Image data compression device and its method
US6507614B1 (en) * 1999-10-19 2003-01-14 Sony Corporation Efficient de-quantization in a digital video decoding process using a dynamic quantization matrix for parallel computations
US20030099293A1 (en) * 1999-12-15 2003-05-29 Shigeyuki Okada Image reproducing method, and image processing method, and image reproducing device, image processing device, and television receiver capable of using the methods
TW502532B (en) * 1999-12-24 2002-09-11 Sanyo Electric Co Digital still camera, memory control device therefor, apparatus and method for image processing
US6675185B1 (en) * 2000-06-07 2004-01-06 International Business Machines Corporation Hybrid domain processing of multi-dimensional transformed data
JP3639517B2 (en) * 2000-10-04 2005-04-20 三洋電機株式会社 Moving picture decoding apparatus and moving picture decoding method
US7599434B2 (en) * 2001-09-26 2009-10-06 Reynolds Jodie L System and method for compressing portions of a media signal using different codecs
US6888372B1 (en) * 2002-12-20 2005-05-03 Altera Corporation Programmable logic device with soft multiplier

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
US20100287622A1 (en) * 2009-05-07 2010-11-11 Tensilica, Inc. System and Method for Preventing Proper Execution of an Application Program in an Unauthorized Processor
US9117060B2 (en) * 2009-05-07 2015-08-25 Cadence Design Systems, Inc. System and method for preventing proper execution of an application program in an unauthorized processor

Also Published As

Publication number Publication date
CN1282368C (en) 2006-10-25
US7558431B2 (en) 2009-07-07
TW200520536A (en) 2005-06-16
TWI289992B (en) 2007-11-11
CN100527071C (en) 2009-08-12
CN1630373A (en) 2005-06-22
CN1591319A (en) 2005-03-09
TWI295787B (en) 2008-04-11
TWI227840B (en) 2005-02-11
US20050125475A1 (en) 2005-06-09
CN1617594A (en) 2005-05-18
CN1595994A (en) 2005-03-16
US20050123046A1 (en) 2005-06-09
TWI240560B (en) 2005-09-21
CN1305313C (en) 2007-03-14
TWI233267B (en) 2005-05-21
TW200520535A (en) 2005-06-16
TW200520399A (en) 2005-06-16
CN100531393C (en) 2009-08-19
CN100539699C (en) 2009-09-09
CN1555199A (en) 2004-12-15
US20050125469A1 (en) 2005-06-09
CN1598876A (en) 2005-03-23
CN101060631A (en) 2007-10-24
TW200519633A (en) 2005-06-16
US20110091124A1 (en) 2011-04-21
US20050125480A1 (en) 2005-06-09

Similar Documents

Publication Publication Date Title
US20110091124A1 (en) System for multi-byte reading
US6378030B1 (en) Method and apparatus for processing video data
US6799246B1 (en) Memory interface for reading/writing data from/to a memory
US6167475A (en) Data transfer method/engine for pipelining shared memory bus accesses
US5675331A (en) Decoding device for decoding a variety of code signals
US7734853B2 (en) Latency dependent data bus transmission
JPH06348492A (en) Data pipeline device and data encoding method
JP2005510981A (en) Multi-channel video transcoding system and method
KR100291532B1 (en) An information processing system comprising a reconfigurable processing stage
JPH08251586A (en) Run length decoder
US6285789B1 (en) Variable length code decoder for MPEG
US5513301A (en) Image compression and decompression apparatus with reduced frame memory
US5781135A (en) High speed variable length code decoder
US5754234A (en) Moving picture decoding system
US6820087B1 (en) Method and apparatus for initializing data structures to accelerate variable length decode
US6313766B1 (en) Method and apparatus for accelerating software decode of variable length encoded information
JPH07222164A (en) Digital video bitstream coder
US6621428B1 (en) Entropy codec for fast data compression and decompression
US20030185297A1 (en) Cascaded output for an encoder system using multiple encoders
US6233280B1 (en) Video decoder for high picture quality
US6785337B2 (en) MPEG picture processing apparatus and data transferring method using the apparatus
JP3330813B2 (en) Image compression device and image decompression device
US5822770A (en) Memory interfacing method and circuit of variable length decoder for accessing external memory when empty portion of internal memory exceeds a predetermined level
JPH05189360A (en) Data transfer and storage method
KR100292050B1 (en) Data variable device of variable length decoder

Legal Events

Date Code Title Description
AS Assignment

Owner name: VIA TECHNOLOGIES, INC., TAIWAN

Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNORS:WANG, ROY;WANG, DAVID;REEL/FRAME:016219/0584;SIGNING DATES FROM 20041126 TO 20041201

STCB Information on status: application discontinuation

Free format text: ABANDONED -- FAILURE TO RESPOND TO AN OFFICE ACTION