Effectiveness of a High Speed Context Switching Method Using Register Bank (Special Section on VLSI Design and CAD Algorithms)
スポンサーリンク
概要
- 論文の詳細を見る
This paper proposes a method to reduce the context switching time using a register bank to store contexts of working tasks. Hardware cost and performance were measured by modeling the register bank and controller in VHDL. Following results were obtained : (1) The controller can be implemented with a much smaller amount of hardware cost compared to that of the register bank, which is realized by SRAM module. (2) Context switching time can be reduced to less than 50% compared to that by software implemantation. (3) Combination of the proposed architecture with our previous work (RTOS implemented in HW) gives us much higher performance of a hard real-time system.
- 1998-12-25
著者
-
ITO Jin-ichi
the Department of Informatics and Mathematical Science, Graduate School of Engineering Science, Osak
-
NAKANO Takumi
the Department of Information and Computer Engineering, Toyota National College of Technbology
-
TAKEUCHI Yoshinori
the Department of Informatics and Mathematical Science, Graduate School of Engineering Science, Osak
-
IMAI Masaharu
the Department of Informatics and Mathematical Science, Graduate School of Engineering Science, Osak
-
Imai Masaharu
The Department Of Informatics And Mathematical Science Graduate School Of Engineering Science Osaka
-
Ito Jin-ichi
The Department Of Informatics And Mathematical Science Graduate School Of Engineering Science Osaka
-
Nakano Takumi
The Department Of Information And Computer Engineering Toyota National College Of Technbology
-
Imai Masaharu
The Department Of Informatics And Mathematical Science Graduate School Of Engineering Science Osaka
-
Takeuchi Yoshinori
The Department Of Informatics And Mathematical Science Graduate School Of Engineering Science Osaka
関連論文
- Effectiveness of a High Speed Context Switching Method Using Register Bank (Special Section on VLSI Design and CAD Algorithms)
- Synthesizable HDL Generation for Pipelined Processors from a Micro-Operation Description (Special Section of Selected Papers from the 12th Workshop on Circuit and Systems in Karuizawa)
- An Optimization Algorithm for High Performance ASIP Design with Considering the RAM and ROM Sizes (Special Section on VLSI Design and CAD Algorithms)
- Segmentation of Depth-of-Field Images Based on the Response of ICA Filters
- Incorporating Contextual Information into Bag-of-Visual-Words Framework for Effective Object Categorization