• No results found

Synthesis of a parallel data stream processor from data flow process networks

N/A
N/A
Protected

Academic year: 2021

Share "Synthesis of a parallel data stream processor from data flow process networks"

Copied!
2
0
0

Bezig met laden.... (Bekijk nu de volledige tekst)

Hele tekst

(1)

Synthesis of a parallel data stream processor from data flow process networks

Zissulescu-Ianculescu, C.

Citation

Zissulescu-Ianculescu, C. (2008, November 13). Synthesis of a parallel data stream processor from data flow process networks. Retrieved from

https://hdl.handle.net/1887/13262

Version: Corrected Publisher’s Version

License: Licence agreement concerning inclusion of doctoral thesis in the Institutional Repository of the University of Leiden

Downloaded from: https://hdl.handle.net/1887/13262

Note: To cite this publication please use the final published version (if applicable).

(2)

Propositions (Stellingen) by Claudiu Zissulescu-Ianculescu, author of

Synthesis of a Parallel Data Stream Processor from Data Flow Process Networks 1. The Look-up table implementation of Read/Write control units is not opti-

mal for image processing algorithms such as Optical Flow algorithm. (This Dissertation, Chapter 3)

2. The upper bound capacity of a Compaan Data Flow Process Network com- munication channel can be determined using the Bounding Box technique.

(This Dissertation, Chapter 5)

3. The First In First Out (FIFO) channel capacity of a self-loop in a Compaan Data Flow Process Network can be precisely determined. (This Dissertation, Chapter 5)

4. The control of a Laura processor can be implemented with only look-up tables, adders, and selectors. (This Dissertation, Chapter 6)

5. The architecture generated by the Laura tool is suited for algorithms that make use of complex (non-trivial) Intellectual Property (IP) cores. (This Dissertation, Chapter 8)

6. In a Process Network, the First In First Out (FIFO) channel capacities dictate the execution schedule of the processes.

7. The Process Network model of computation is suited for the mapping of an application onto heterogeneous platforms.

8. In spite of Moore’s Law, communication remains the bottleneck of current architectures.

9. The less wildlife locations a country has, the more national parks it has.

10. If someone in a negotiation replies to your proposal by saying ”I will think about it”, then in many cases this means your proposal does not fit his plan- ning.

1

Referenties

GERELATEERDE DOCUMENTEN

Eventual completion with φ LTL (when φ has no state formulas) / CTL (when φ is CTL) Eventual completion LTL/CTL DATA-FLOW ERRORS Missing LTL/CTL Strongly redundant LTL/CTL

The log file is then mined and a Product Data Model (PDM) and eventually a workflow model can be created. The advantage of our approach is that,.. when needed to investigate a

In this paper, we illustrated some of the potential of process mining techniques applied to online assessment data where students in one of the tests were able to receive tailored

The knowledge which is needed has been described in Chapter 1.3.2 by the following two research questions: “What kind of business process modelling technique is suitable for

- How can the FB-BPM method be used for a systematic derivation of data models from process models in the context of designing a database supporting an EHR-system at a LTHN.. -

Given an affine nested loop program and its input-output equivalent C OMPAAN Data Flow Process Network specification, how can we implement that specification in an FPGA

I een proces verwerkt inkomende gegevens en creëert uitgaande gegevens. → transformatieproces: invoer wordt getransformeerd

The process part is represented using an extension of UML activity diagrams, while the product part is represented as a UML class dia- gram, utilizing the part-of construct to