Project/Area Number |
07558039
|
Research Category |
Grant-in-Aid for Scientific Research (A)
|
Allocation Type | Single-year Grants |
Section | 展開研究 |
Research Field |
計算機科学
|
Research Institution | KYOTO UNIVERSITY |
Principal Investigator |
TAMARU Keikichi KYOTO UNIVERSITY,Department of Electronics & Communication, Professor, 工学研究科, 教授 (10127102)
|
Co-Investigator(Kenkyū-buntansha) |
YOSHIDA Toyohiko Mitsubishi Electric Corporation, Manager, システムLSI開発研究所, 主事
KOBAYASHI Kazutoshi KYOTO UNIVERSITY,Department of Electronics & Communication, Kyoto University, Re, 工学研究科, 助手 (70252476)
VASILY Moshnyaga KYOTO UNIVERSITY,Department of Electronics & Communication, Kyoto University, In, 工学研究科, 講師 (40243050)
ONODERA Hidetoshi KYOTO UNIVERSITY,Department of Electronics & Communication, Kyoto University, As, 工学研究科, 助教授 (80160927)
|
Project Period (FY) |
1995 – 1997
|
Project Status |
Completed (Fiscal Year 1997)
|
Budget Amount *help |
¥9,300,000 (Direct Cost: ¥9,300,000)
Fiscal Year 1997: ¥600,000 (Direct Cost: ¥600,000)
Fiscal Year 1996: ¥3,800,000 (Direct Cost: ¥3,800,000)
Fiscal Year 1995: ¥4,900,000 (Direct Cost: ¥4,900,000)
|
Keywords | Functional Memory / CAM / Vector Quantization / Parallel Processing / VLSI / Low Bit-rate / Image Compression / 超並列処理 / 光通信 |
Research Abstract |
(a)Development of a Functional Memory for Addition We develop a functional memory specialized for addtion. Its memory cell consists of a DRAM,which area is about 10 times smaller than that of an SRAM.A PE consists of two words and a bit-scrial ALU.We have designed and fabricated LSIs to evaluate is functionality and performance. (b)Low Bit-rate Image Compression Using a Functional Memory Here, we develop a functional memory specialized for vector quantization. It is called "FMPP-VQ", which stands for Functional Memory Type Parallel Processor for Vector Quantization. We have designed and fabricated two LSIs. One is an LSI for evaluation which consists of four PEs. The other has 64 PEs. It can be applied for low bit-rate image compression. We have developed an algorithm to send a QCIF (176*144) video sequence at 10 frames per second via a 29.2kbps line.
|