PM: An operating system coordinated high performance communication library

Tezuka, Hiroshi; Hori, Atsushi; Ishikawa, Yutaka; Sato, Mitsuhisa

doi:10.1007/bfb0031642

Cited by 93 publications

(30 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…PM library for Myrinet PC clusters [20] allows very low latency and high speed data transfer, based on which we can implement efficient parallel processing on the PC cluster.…”

Section: Real-time Dynamic 3d Object Shape Reconstruction Systemmentioning

confidence: 99%

Real-Time Dynamic 3-D Object Shape Reconstruction and High-Fidelity Texture Mapping for 3-D Video

Matsuyama

Takai

et al. 2004

IEEE Trans. Circuits Syst. Video Technol.

123

View full text Add to dashboard Cite

Abstract-3D video is a real 3D movie recording the object's full 3D shape, motion, and precise surface texture. This paper first proposes a parallel pipeline processing method for reconstructing dynamic 3D object shape from multi-view video images, by which a temporal series of full 3D voxel representations of the object behavior can be obtained in real-time. To realize the real-time processing, we first introduce a plane-based volume intersection algorithm: represent an observable 3D space by a group of parallel plane slices, back-project observed multi-view object silhouettes onto each slice, and apply 2D silhouette intersection on each slice. Then, we propose a method to parallelize this algorithm using a PC cluster, where we employ 5 stage pipeline processing in each PC as well as slice-by-slice parallel silhouette intersection. Several results of the quantitative performance evaluation are given to demonstrate the effectiveness of the proposed methods. In the latter half of the paper, we present an algorithm of generating video texture on the reconstructed dynamic 3D object surface. We first describe a naive viewindependent rendering method and show its problems. Then, we improve the method by introducing image-based rendering techniques. Experimental results demonstrate the effectiveness of the improved method in generating high fidelity object images from arbitrary viewpoints.

show abstract

“…PM library for Myrinet PC clusters [20] allows very low latency and high speed data transfer, based on which we can implement efficient parallel processing on the PC cluster.…”

Section: Real-time Dynamic 3d Object Shape Reconstruction Systemmentioning

confidence: 99%

Real-Time Dynamic 3-D Object Shape Reconstruction and High-Fidelity Texture Mapping for 3-D Video

Matsuyama

Takai

et al. 2004

IEEE Trans. Circuits Syst. Video Technol.

123

View full text Add to dashboard Cite

show abstract

“…Otherwise, a lower performance library using the TCP/IP protocol, such as MPICH/p4 or LAM, must be used because almost all networks support the TCP/IP protocol. PM for Myrinet achieves 15 micro second round trip time for a four byte user message and more than 100 MByte/sec bandwidth using a Pentium Pro 200MHz system [6]. The PM communication facility has been ported to an Essential Communications' Gigabit Ethernet card which also has an on-board processor [8].…”

Section: Introductionmentioning

confidence: 99%

PM2: High Performance Communication Middleware for Heterogeneous Network Environments

Takahashi¹,

Sumimoto²,

Hori³

et al. 2000

ACM/IEEE SC 2000 Conference (SC'00)

View full text Add to dashboard Cite

This paper introduces a high performance communication middle layer, called PM2, for heterogeneous network environments. PM2 currently supports Myrinet, Ethernet, and SMP. Binary code written in PM2 or written in a communication library, such as MPICH-SCore on top of PM2, may run on any combination of those networks without re-compilation. According to a set of NAS parallel benchmark results, MPICH-SCore performance is better than dedicated communication libraries such as MPICH-BIP/SMP and MPICH-GM when running some benchmark programs.

show abstract

“…PM library for Myrinet PC clusters [6] allows very low latency and high speed data transfer, based on which we can implement efficient parallel processing on the PC cluster. Figure 1.…”

Section: System Organizationmentioning

confidence: 99%