Network


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

Hotspot


Dive into the research topics where Takumi Maruyama is active.

Publication


Featured researches published by Takumi Maruyama.


international symposium on microarchitecture | 2010

Sparc64 VIIIfx: A New-Generation Octocore Processor for Petascale Computing

Takumi Maruyama; Toshio Yoshida; Ryuji Kan; Iwao Yamazaki; Shuji Yamamura; Noriyuki Takahashi; Mikio Hondou; Hiroshi Okano

The Sparc64 VIIIfx eight-core processor, developed for use in petascale computing systems, runs at speeds of up to 2 GHz and achieves a peak performance of 128 gigaflops while consuming as little as 58 watts of power. Sparc64 VIIIfx realizes a six-fold improvement in performance per watt over previous generation Sparc64 processors.


ieee hot chips symposium | 2009

SPARC64™ VIIIfx: Fujitsu's new generation octo core processor for PETA scale computing

Takumi Maruyama

Presents a collection of slides covering the following topics: SPARC64™ VIIIfx; octo core processor; PETA scale computing; high performance computing-arithmetic computational extensions; register sets; SIMD; FP trigonometric functions; software controlled cache; and integrated multicore parallel architecture.


symposium on vlsi circuits | 2010

Fine grained power analysis and low-power techniques of a 128GFLOPS/58W SPARC64 ™ VIIIfx processor for peta-scale computing

Hiroshi Okano; Yukihito Kawabe; Ryuji Kan; Toshio Yoshida; Iwao Yamazaki; Hitoshi Sakurai; Mikio Hondou; Nobuyuki Matsui; Hideo Yamashita; Tatsumi Nakada; Takumi Maruyama; Takeo Asakawa

An 8-core SPARC64™ VIIIfx processor is fabricated in a 45nm CMOS process and achieves a peak performance of 128GFLOPS. Measured results show that the processor consumes only 58W of power when executing a maximum power program. Fine-grained power analysis was used to tune the micro-architecture for low power consumption, and circuit-level low-power techniques were developed. Water cooling and supply voltage adjustment contribute to power reduction at the system level.


ieee hot chips symposium | 2008

SPARC64™ VII Fujitsu's next generation quad-core processor

Takumi Maruyama

This article consists of a collection of slides from the authors conference presentation on the Fujitsu SPARC64™ VII quad-core processor.


ieee hot chips symposium | 2012

SPARC64™ X: Fujitsu's new generation 16 core processor for the next generation UNIX servers

Takumi Maruyama

This article consists of a collection of slides from the authors conference presentation on Fujituss SPARC64, the companys new generation 16 core processor for UNIX servers. Some of the specific topics discussed include: the system specifications and design concept of the product; software-on-chip capabilities; processor chip overview; u-Architecture and design capabilities; and performance evaluations.


international symposium on microarchitecture | 2010

SPARC64™ VIIIfx: Fujitsu’s New Generation Octo Core Processor for PETA Scale computing

Takumi Maruyama

The SPARC64 XII 12-core processor, developed for high-performance, mission-critical servers, runs at speeds of up to 4.35 GHz and achieves a peak performance of 417 GIPS and 835 Gflops. SPARC64 XII realizes a 2.3-2.9 times improvement in core performance over the previous-generation SPARC64 X+.


2017 IEEE Symposium in Low-Power and High-Speed Chips (COOL CHIPS) | 2017

SPARC64TM XII: Fujitsu's latest 12 core processor for mission critical servers

Takumi Maruyama

This paper describes the design, microarchitecture, and performance of the latest Fujitsu SPARC64 XII 12 core microprocessor which has been developed for high performance, mission critical servers. Dual instruction pipelines, 8-way SMT (Simultaneous Multi-Threading), a high CPU frequency of over 4 GHz, and a 12 core design have doubled the chip performance compared with the previous SPARC64 X+, while keeping its high single thread performance.


Archive | 1995

Processor structure and method for watchpoint of plural simultaneous unresolved branch evaluation

Gene W. Shen; Michael C. Shebanow; Hideki Osone; Takumi Maruyama


Archive | 1995

Method and apparatus for selecting the oldest queued instructions without data dependencies

Michael C. Shebanow; John Gmuender; Michael A. Simone; John Szeto; Takumi Maruyama; Deforest W Tovey


Archive | 1994

Multi-CPU system having fault monitoring facility

Takumi Maruyama; Kiyoshi Sugita; Mitsunobu Yoshida

Collaboration


Dive into the Takumi Maruyama's collaboration.

Researchain Logo
Decentralizing Knowledge