Announcement for Downloading full text filePlease respect the Copyright Act.
All digital full text dissertation and theses from this website are authorized the copyright owners. These copyrighted full-text dissertation and theses can be only used for academic, research and non-commercial purposes. Users of this website can search, read, and print for personal usage. In respect of the Copyright Act of the Republic of China, please do not reproduce, distribute, change, or edit the content of these dissertations and theses without any permission. Please do not create any work based upon a pre-existing work by reproduction, Adaptation, Distribution or other means.
URN etd-0826104-174426 Statistics This thesis had been viewed 2864 times. Download 1129 times. Author Chi-Huam Shieh Author's Email Address No Public. Department Computer Science and Enginerring Year 2003 Semester 2 Degree Master Type of Document Master's Thesis Language English Page Count 50 Title Automatic Detection and Generation of Self-Timed Pipeline Keyword VHDL Translation System-on-a-chipIntellectual Properties Self-Timed System Pipelining Pipeline Activity Diagram Activity Diagram Pipeline Pipelining Self-Timed System System-on-a-chipIntellectual Properties Translation VHDL Abstract Behavior synthesis is becoming the major design methodology for System-on-a-chip (SOC) design with IP (Intellectual Property) reuse to solve the productivity gap problem. Pipeline mechanism can be applied to the behavior models to improve performance. This thesis presents a new methodology to automatically detect and generate self-timed pipeline mechanism from high-level language descriptions.
Self-timed pipeline modules (i.e. StagePipeline, DecoderPipelineModule and DoubleRegx32) are designed. Then pipeline detection and generation algorithm automatically inserts self-timed pipeline modules to behavior models to improve performance.
Simple Java processor is designed and used to test our methodology. The experimental results show that a non-pipeline Java processor can be automatically partition into three stages and the pipelined Java processor is 1.99 times faster than the non-pipeline version with only 2.8% more hardware logic.
Advisor Committee Fu-Chiung Cheng - advisor
none - co-chair
none - co-chair
Files Date of Defense 2004-07-22 Date of Submission 2004-08-26