Soichi Shigeta
University of Electro-Communications
Network
Latest external collaboration on country level. Dive into details by clicking on the dots.
Publication
Featured researches published by Soichi Shigeta.
ieee international conference on high performance computing data and analytics | 2004
Ben A. Abderazek; M. Arsenji; Soichi Shigeta; Tsutomu Yoshinaga; Masahiro Sowa
This work proposes a novel produced order parallel queue processor architecture. To store intermediate results, the proposed system uses a FIFO queue registers instead of random access registers. Datum is inserted in the queue in produced order scheme and can be reused. We show that this feature has a profound implication in the areas of parallel execution, programs compactness, hardware simplicity and high execution speed. Our preliminary performance evaluations have shown a significant performance improvement (e.g., 10% to 26% decrease in program size and 6% to 46% decrease in execution time over a range of benchmark programs) when compared with the earlier proposed architecture.
international symposium on parallel and distributed processing and applications | 2003
Ben A. Abderazek; Soichi Shigeta; Tsutomu Yoshinaga; Masahiro Sowa
We propose in this paper a processor architecture that supports multi instructions set through run time functional assignment algorithm (RUNFA). The above processor, which is named Functional Assignment Register Microprocessor (FaRM-rq) supports queue and register based instruction set architecture and functions into different modes: (1) R-mode (FRM) - when switched for register based instructions support, and (2) Q-mode (FQM) - when switched for Queue based instructions support. The entities share a common data path and may operate independently though not in parallel. In FRM mode, the machines shared storage unit (SSU) behaves as a conventional register file. However, in FQM mode, the system organizes the SSU access as a first-in-first-out latches, thus accesses concentrate around a small window and the addressing of registers is implicit trough the Queue head and tail pointers. First, we present the novel aspects of the FaRM-rq1 architecture. Then, we give the novel FQM fundamentals and the principles underlying the architecture.
parallel and distributed computing systems (isca) | 2002
Masahiro Sowa; Ben A. Abderazek; Soichi Shigeta; Kirilka Nikolova; Tsutomu Yoshinaga
ITC-CSCC :International Technical Conference on Circuits Systems, Computers and Communications | 2003
Li Qiang Wang; Ben A. Abderazek; Soichi Shigeta; Tsutomu Yoshinaga; Masahiro Sowa
Distributed Computing | 2004
Arsenij Markovskij; Masahiro Sowa; Ben A. Abderazek; Soichi Shigeta; Tsutomu Yoshinaga
Archive | 2004
Ben A. Abderazek; M. Arsenji; Soichi Shigeta; Tsutomu Yoshinaga; Masahiro Sowa
ITC-CSCC :International Technical Conference on Circuits Systems, Computers and Communications | 2004
Hirotoshi Sasaki; Yoshitomo Okumura; Ben A. Abderazek; Soichi Shigeta; Tsutomu Yoshinaga; Masahiro Sowa
IPSJ SIG Notes | 2003
A Abderazek Ben; Soichi Shigeta; Tsutomu Yoshinaga; Masahiro Sowa
情報科学技術フォーラム一般講演論文集 | 2002
Cong Zhang; Soichi Shigeta; Abdallah Ben Abderazek; Masahiro Sowa
Computer Systems: Science & Engineering | 2001
Soichi Shigeta; Kentaro Shimizu; Masahiro Sowa