ETD

Archivio digitale delle tesi discusse presso l'Università di Pisa

Tesi etd-03202008-173135


Tipo di tesi
Tesi di laurea specialistica
Autore
BONINI, GIOVANNI
URN
etd-03202008-173135
Titolo
ASIP approach for high speed interface
Dipartimento
INGEGNERIA
Corso di studi
INGEGNERIA INFORMATICA
Relatori
Relatore Foglia, Pierfrancesco
Relatore Heijligers, Marc
Relatore Prof. Fanucci, Luca
Parole chiave
  • DisplayPort
  • HDMI
  • interface
  • ASIP
  • Target
Data inizio appello
07/05/2008
Consultabilità
Non consultabile
Data di rilascio
07/05/2048
Riassunto
1 Multimedia protocol
This paragraph describes multimedia protocols, a multimedia protocol is a procedure that can manage the multimedia data, and the word multimedia is a media that utilizes a combination of different content forms. The term can be used as a noun (a medium with multiple content forms) or as an adjective describing a medium as having multiple content forms. The term is used in contrast to media which only utilize traditional forms of printed or hand-produced text and still graphics. In general, multimedia includes a combination of text, audio, still images, animation, video, and interactivity content forms. Multimedia is usually recorded and played, displayed or accessed by information content processing devices, such as computerized and electronic devices, but can also be part of a live performance [1].
1.1 Digital Visual Interface
Digital Visual Interface (DVI) is a video interface standard designed to maximize the visual quality of digital display devices such as flat panel LCD computer displays and digital projectors. It was developed by an industry consortium, the Digital Display Working Group (DDWG). It is designed for carrying uncompressed digital video data to a display. It is partially compatible with the High-Definition Multimedia Interface (HDMI) standard in digital mode (DVI-D). The DVI does not support the data protection [2].
1.1.1 Technical characteristics
The DVI interface uses a digital protocol in which the desired illumination of pixels is transmitted as binary data. When the display is driven at its native resolution, it will read each number and apply that brightness to the appropriate pixel. In this way, each pixel in the output buffer of the source device corresponds directly to one pixel in the display device, whereas with an analog signal the appearance of each pixel may be affected by its adjacent pixels as well as by electrical noise and other forms of analog distortion.
1.2 High Definition Multimedia Interface
The High-Definition Multimedia Interface (HDMI) is a compact audio/video connector interface for transmitting uncompressed digital streams. It represents a digital alternative to consumer analog standards such as RF (coaxial cable), composite video, S-Video, SCART, component video and VGA [2].
1.2.1 Technical characteristics
HDMI connects digital audio/video sources such as a set-top box, a Blue-ray Disc player, a personal computer, a video game console, or an AV receiver to a compatible digital audio device and/or video monitor such as a digital television (DTV) [2].
1.3 DisplayPort
DisplayPort is a digital display interface standard put forth by the Video Electronics Standards Association (VESA). It defines a new license-free, royalty-free, digital audio/video interconnect, intended to be used primarily between a computer and its display monitor, or a computer and a home-theater system [4].
1.3.1 Technical characteristics
The data transmission protocol in DisplayPort is Micro-Packet based which is extensible in future to add features, whereas DVI/HDMI transmission protocol is Serial Data Stream at 10x pixel clock rate. However one of the biggest advantages that DisplayPort provides over DVI/HDMI is that DisplayPort is intended to consolidate both external (box-to-box) and internal (LCD panel) display connections.
1.4 Analogies and differences among the functionalities
This paragraph describes the analogies and the differences among the functionalities, there are not strong differences among the protocols about the functionalities field, rather there is a convergence to a common group of the functionalities, indeed the real differences are into the low implementation level but also in this field the protocols are converging on a compatibility solution. The motivations about these convergences are many but the principals are two:
1.5 Economic and technical analysis
This paragraph describes the economic and the technical analysis of the devices where there is a multimedia protocols, it means where there is a multimedia interface. In particular the paragraph is composed of two parts:
1.5.1 Economic analysis
This paragraph describes the economic situation of the multimedia devices, obviously in particular that devices using the multimedia protocols.
1.5.2 Technological analysis
This paragraph describes the technological analysis; this analysis does not show the technical details of the multimedia protocols, so it is not a low level analysis, but it a high level analysis. This setting-out is depending by the fact that the multimedia protocols have not big differences among them, indeed, as showed into the paragraph 1.4, the functionalities are more or less the same, so it is important to analyze not the how they implements the functionality, but the why they implements in that way the functionalities.
1.6 Identification of the problem
This paragraph defines the problem; in particular it gives an extraction of the solution concept.
2 Study phase and introduction of the Target tools
This chapter shows which is the solution to our problem identifying some common blocks among the multimedia protocols and it describes the general solution applied to these common blocks. In the chapter there also an introduction of the Target tools that is suggested as the tool for the implementation of the solution.
2.1 Identification of the common blocks
This paragraph shows the motivation of the choice of the common and the suitable blocks, indeed these blocks must be also suitable because they must show the solution, so we have chosen two blocks, which dialog respectively to the data source and to the data receiver.
2.2 Advantage and disadvantage of the total hardware or software solution
This paragraph describes more in detail the advantage and the disadvantage of the total hardware solution and of the total software solution.
2.2.1 The total hardware solution
The total hardware solution is the current solution adopted by the multimedia protocols, it means a total mapping of the protocol on hardware, and this type of solution is suitable to fix the first problem of an interface, which is the timing. Indeed these multimedia interfaces have a timing problem; this problem comes from the quantity of data that they should manage because one of the most important properties of multimedia protocols is the uncompressed transmission. The uncompressed transmission is the base point to support the progressive resolution; there are two type of resolution:
2.2.2 The total software solution
The total software solution means that all multimedia protocols are mapped on a software code, so it could be a solution about the re-programmability problem, indeed by the software code if quite easy to change the algorithm, inserting a evolution of the algorithm or a new functionality. This code is processed by a general processor that translated in several instructions the code statements, but a general processor has an instructions set very adaptable. It means that instructions set is composed by “general” instructions, so these instructions can support every algorithms, but they use many processor cycles. The following table shows an example.
2.3 ASIP: solution and tools
This paragraph uses the precedent study phases and it offers another study phase reaching to a solution of our problem, the paragraph gives also an introduction of the tools used to implement the solution.
2.3.1 The ASIP solution
This paragraph describes the ASIP solution, the ASIP is an acronym of Application Specific Instruction-Set Processor, indeed this solution offers a compromise between a hardware dedicated solution, which ensures the performance, and a general processor solution, which ensures the flexibility.
2.3.2 The ASIP tools
This paragraphs shows a brief introduction about the tools, which can make a ASIP solution, but in particular it shows the main step of the TARGET tools.
3 Design phase
Chapter three describes the design phase of the Conversion Block and the Deep Color Block.
3.1 Conversion Block
The main functionality of Conversion Block is to make a conversion from a color space to another one. Indeed it could be happen that the color space of a transmitter is different than a receiver, therefore the receiver must use this functionality for adapting to a correct color space.
3.1.1 Algorithm
The algorithm is the following:
3.1.2 Decomposition of algorithm
We have analyzed the algorithm but it is not completely correct because the parameter, belonging to matrix P, is calculated typically when X, Y, Z, X', Y', Z' belong in real range [0; 1] or [-0.5; +0.5].

3.1.3 Analysis of data
Before our implementation, it is important to understand our problem, in particular what are the ranges and how many types of input can we have.
3.2 Implementation of Conversion Block

This paragraph is divided in two parts:
3.2.1 General approach
The main problem that we should resolve is sharing of complexity between hardware and software.
3.2.2 Complete implementation

3.3 Deep Color Block
The main functionality of the Deep Color Block is to give a meaning to the data, in particular this block produces the data for Conversion Block, indeed it receives an input, in this input there are information and the Deep Color Block extracts the useful data for the Conversion Block. The constraint of this block is the particular formula that links the input frequency to the output frequency.
3.3.1 Analysis of algorithm
This paragraph describes the algorithm of the block, but to explain better the algorithm, it is necessary a brief introduction about the inputs and the outputs of the block.
3.3.2 Implementation of Deep Color Block
The paragraph shows all implementation aspects of all algorithms, but in particular about the algorithm with sorting and with only one data decoding. Being this block a data producer for the Conversion Block, we have realized many architectures for the same block, this point is necessary because the data management capacity and the frequency are a constraint for the Deep Color Block, so it is important to show different approaches.
3.4 General system
This paragraph describes the system composed of both precedent blocks; we have analyzed the advantage and the disadvantage about the implementation of this system. In particular the paragraph is organized in the following way:
3.4.1 System analysis
The system is composed of two parts:
3.4.2 Possible solutions
This paragraph shows the possible solution about the system analyzed into the precedent paragraph, we have design two possible solution.
4 Verification of the Flexibility
This chapter is a verification of the flexibility degree of our system, in the following paragraphs we describes the behavior of our processors. To understand this degree we show for each processor two points:
4.1 Modification and new functionality of the algorithm's conversion
This paragraph describes the modifications on the algorithm's conversion, the processor is able to support change about:
4.2 Modification and new functionality of the algorithm's Deep Color with sorting
This paragraph synthesizes the characteristics of the Deep Color Block, the processor can support the change of parameters however it is designed to make sorting algorithm, so it is especially dedicated to the typical sorting operations, it means:
Conclusion
Chapter describes the missing part in the report and the sensations on this type of solution.
Appendix A
The algorithm of Deep Color without generalization
File