Network


Latest external collaboration on country level. Dive into details by clicking on the dots.

Hotspot


Dive into the research topics where Fumihiko Hayakawa is active.

Publication


Featured researches published by Fumihiko Hayakawa.


international solid-state circuits conference | 2005

A 51.2 GOPS 1.0 GB/s-DMA single-chip multi-processor integrating quadruple 8-way VLIW processors

Tetsuyoshi Shiota; Kenichi Kawasaki; Yukihito Kawabe; Wataru Shibamoto; Atsushi Sato; Tetsutaro Hashimoto; Fumihiko Hayakawa; Shin-ichirou Tago; Hiroshi Okano; Yasuki Nakamura; Hideo Miyake; Atsuhiro Suga; Hiromasa Takahashi

A 51.2-GOPS chip multi-processor integrates four 8-way VLIW embedded processors with 1.0 GB/s local-bus direct memory access. This IC completes MPEG2 MP@HL video-stream decoding at 68% of its processor capability without dedicated hardware. The 11.9 mm /spl times/ 10.3 mm chip is fabricated in a 90 nm 9M CMOS process and consumes 5 W at 533 MHz.


Proceedings. IEEE Asia-Pacific Conference on ASIC, | 2002

An 8-way VLIW embedded multimedia processor with advanced cache mechanism

Fumihiko Hayakawa; Hiroshi Okano; Atsuhiro Suga

An 8-way VLIW embedded multimedia processor is developed in 0.11 /spl mu/m 7-layer Cu/Al metal CMOS process technology. The processor achieved the peak performance of 2132 MIPS/2.1 GFLOPS/4.26 GOPS at 533 MHz. This processor equips 4-way integer and 4-way floating/media pipelines. Each media pipeline can execute a 4-parallel SIMD instruction, so 16-operations can be executed at a cycle. It also equips the data and instruction caches, and each of their size is 32 KB. The data cache has a non-aligned data access mechanism and an enhanced store operation mechanism, and a 9% performance improvement was verified. The instruction cache has a reconfigurable associativity mechanism, and achieved more than 12% of power consumption decrease. As a result, this processor achieved more than twice the performance over our previous processor. This processor enables MPEG2 MP@ML 2-stream decoding.


international symposium on computing and networking | 2014

ARM Based Platform SoC for Embedded Applications

Fumihiko Hayakawa; Atsuhiro Suga

In these days embedded system needs Open Source Software (OSS) and open framework like as Open GL/Open CL because of better developing efficiency. This paper shows you about high performance SoC architecture for embedded system. This SoC shows lower power consumption in stand-by case and better performance about some applications. To reuse these hardware and software platform, custom SoCs can be developed easily in short period.


Archive | 2002

Device and method for information processing

Hiroshi Okano; Fumihiko Hayakawa


Archive | 2003

Information processing device equipped with improved address queue register files for cache miss

Satoshi Imai; Fumihiko Hayakawa; Atsuhiro Suga


Archive | 2013

SYSTEM AND DATA LOADING METHOD

Koji Kurihara; Koichiro Yamashita; Takahisa Suzuki; Hiromasa Yamauchi; Fumihiko Hayakawa; Naoki Odate; Tetsuo Hiraki; Toshiya Otomo


Archive | 2013

SYSTEM AND SCHEDULING METHOD

Takahisa Suzuki; Koichiro Yamashita; Hiromasa Yamauchi; Koji Kurihara; Fumihiko Hayakawa; Naoki Odate; Tetsuo Hiraki; Toshiya Otomo


Archive | 2013

MULTICORE PROCESSOR SYSTEM AND POWER CONTROL METHOD

Takahisa Suzuki; Koichiro Yamashita; Hiromasa Yamauchi; Koji Kurihara; Fumihiko Hayakawa; Naoki Odate; Tetsuo Hiraki; Toshiya Otomo


Archive | 2015

MULTI-CORE PROCESSOR SYSTEM, MEMORY CONTROLLER CONTROL METHOD, AND COMPUTER PRODUCT

Koichiro Yamashita; Fumihiko Hayakawa


Archive | 2013

Task scheduling method and multi-core system

Tetsuo Hiraki; Hiromasa Yamauchi; Koichiro Yamashita; Fumihiko Hayakawa; Naoki Odate; Takahisa Suzuki; Koji Kurihara

Collaboration


Dive into the Fumihiko Hayakawa's collaboration.

Researchain Logo
Decentralizing Knowledge