• Journal of Information Processing Systems
• /
• v.13 no.1
• /
• pp.95-103
• /
• 2017

The PCI Express is a widely used system bus technology that connects the processor and the peripheral I/O devices. The PCI Express is nowadays regarded as a de facto standard in system area interconnection network. It has good characteristics in terms of high-speed, low power. In addition, PCI Express is becoming popular interconnection network technology as like Gigabit Ethernet, InfiniBand, and Myrinet which are extensively used in high-performance computing. In this paper, we designed and implemented a evaluation platform for interconnect network using PCI Express between two computing nodes. We make use of the non-transparent bridge (NTB) technology of PCI Express in order to isolate between the two subsystems. We constructed a testbed system and evaluated the performance on the testbed.

• 제어로봇시스템학회:학술대회논문집
• /
• 1987.10b
• /
• pp.389-393
• /
• 1987

This paper describes the configuration of serial interconnection BUS, BitBUS, for Energy Management Systems, and it provides low cost, high performance approach in distributed data acquisition and control applications.

• Journal of the Korea Convergence Society
• /
• v.8 no.8
• /
• pp.9-15
• /
• 2017

With the development of semiconductor integration technology, central processing units and storage devices have been miniaturized and performance has been rapidly developed, interconnection network technology is becoming a more important factor in terms of the performance of high performance computing system. In this paper, we analyze the trend of interconnection network technology used in high performance computing. Interconnect technology, which is the most widely used in the Supercomputer Top 500(2017. 06.), is an Infiniband. Recently, Ethernet is the second highest share after InfiniBand due to the emergence of 40/100Gbps Gigabit Ethernet technology. Gigabit Ethernet, where latency performance is lower than InfiniBand, is preferred in cost-effective medium-sized data centers. In addition, top-end HPC systems that demand high performance are devoting themselves from Ethernet and InfiniBand technologies and are attempting to maximize system performance by introducing their own interconnect networks. In the future, high-performance interconnects are expected to utilize silicon-based optical communication technology to exchange data with light.

• Journal of Power Electronics
• /
• v.9 no.4
• /
• pp.544-552
• /
• 2009

This paper presents a novel spring pressure contact interconnect technique for medium power integrated power electronics modules (IPEMs). The key technology of this interconnection is a spring which is made from Be-Cu alloy. By means of the string pressure contact, sufficient press-contact force and good electrical interconnection can be achieved. Another important advantage is that the spring exhibits excellent performance in enduring thermo-mechanical stress. In terms of manufacture procedure, it is also comparatively simple. A 4 kW half-bridge power inverter module is fabricated to demonstrate the performance of the proposed pressure contact technique. Electrical, thermal and mechanical test results of the packaged device are reported. The results of both the simulation and experiment have proven that a good performance can be achieved by the proposed pressure contact technique for the medium power IPEMs.

• Journal of Welding and Joining
• /
• v.32 no.3
• /
• pp.19-26
• /
• 2014

Through Silicon Via (TSV) technology is the shortest interconnection technology which is compared with conventional wire bonding interconnection technology. Recently, this technology has been also noticed for the miniaturization of electronic devices, multi-functional and high performance. The short interconnection length of TSV achieve can implement a high density and power efficiency. Among the TSV technology, TSV filling process is important technology because the cost of TSV technology is depended on the filling process time and reliability. Various filling methods have been developed like as Cu electroplating method, molten solder insert method and Ti/W deposition method. In this paper, various TSV filling methods were introduced and each filling materials were discussed.

• The KIPS Transactions:PartA
• /
• v.11A no.1
• /
• pp.49-56
• /
• 2004

The performance of the multiprocessor systems is limited by the several factors. The system performance is affected by the processor speed, memory delay, and interconnection network bandwidth/latency. By the evolution of semiconductor technology, off the shelf microprocessor speed breaks beyond GHz, and the processors can be scalable up to multiprocessor system by connecting through the interconnection networks. In this situation, the system performances are bound by the latencies and the bandwidth of the interconnection networks. SCI, Myrinet, and Gigabit Ethernet are widely adopted as a high-speed interconnection network links for the high performance cluster systems. Performance improvement of the interconnection network can be achieved by the bandwidth extension and the latency minimization. Speed up of the operation clock speed is a simple way to accomplish the bandwidth and latency betterment, while its physical distance makes the difficulties to attain the high frequency clock. Hence the system performance and scalability suffered from the interconnection network limitation. Duplicating the link of the interconnection network is one of the solutions to resolve the bottleneck of the scalable systems. Dual-ring SCI link structure is an example of the interconnection network improvement. In this paper, I propose a network topology and a transaction path algorism, which optimize the latency and the efficiency under the duplicated links. By the simulation results, the proposed structure shows 1.05 to 1.11 times better latency, and exhibits 1.42 to 2.1 times faster execution compared to the dual ring systems.

• The Transactions of the Korea Information Processing Society
• /
• v.4 no.9
• /
• pp.2259-2268
• /
• 1997

Multistage interconnection networks(MINs) provide a high-bandwidth communication between processors and/or memory modules in a cost-effective way. In this paper, we propose a class of multipath MINs, called the Augmented Modified Delta(AMD) network, and analyze its performance and reliability. The salient features of the AMD network include fault-tolerant capability, modular structure, and high performance, which are essential for real-time parallel/distributed processing environments. The class of the AMD network retains well-known characteristics of the Kappa network, but it's design procedure is more systematic. Like Delta networks, all the AMD networks are topologically equivalent with each other.

• Journal of Information Processing Systems
• /
• v.18 no.1
• /
• pp.159-172
• /
• 2022

The role of the interconnect network, which connects computing nodes to each other, is important in high-performance computing (HPC) systems. In recent years, the peripheral component interconnect express (PCIe) has become a promising interface as an interconnection network for high-performance and cost-effective HPC systems having the features of non-transparent bridge (NTB) technologies. OpenSHMEM is a programming model for distributed shared memory that supports a partitioned global address space (PGAS). Currently, little work has been done to develop the OpenSHMEM library for PCIe-interconnected HPC systems. This paper introduces a prototype implementation of the OpenSHMEM library through a switchless interconnect network using PCIe NTB to provide a PGAS programming model. In particular, multi-interrupt, multi-thread-based data transfer over the OpenSHMEM shared memory model is applied at the implementation level to reduce the latency and increase the throughput of the switchless ring network system. The implemented OpenSHMEM programming model over the PCIe NTB switchless interconnection network provides a feasible, cost-effective HPC system with a PGAS programming model.

• Journal of the Microelectronics and Packaging Society
• /
• v.6 no.4
• /
• pp.61-71
• /
• 1999

The recent trend toward higher frequencies, miniaturization and lower-cost in wireless communication equipment is demanding high density packaging technologies such flip chip interconnection and multichip module(MCM) as a substitute of conventional plastic package. With analyzing the recently reported research results of the RF flip chip, this paper presents the technical issues and advantages of RF flip chip and suggest the flip chip technologies suitable for the development stage. At first, most of RF flip chips are designed in a coplanar waveguide line instead of microstrip in order to achieve better electrical performance and to avoid the interaction with a substrate. Secondly, eliminating wafer back-side grinding, via formation, and back-side metallization enables the manufacturing cost to be reduced. Finally, the electrical performance of flip chip bonding is much better than that of plastic package and the flip chip interconnection is more suitable for Transmit/Receiver modules at higher frequency. However, the characterization of CPW designed RF flip chip must be thoroughly studied and the Au stud bump bonding shall be suggested at the earlier stage of RF flip chip development.

• Proceedings of the International Microelectronics And Packaging Society Conference
• /
• 2001.04a
• /
• pp.35-43
• /
• 2001

Flip chip assembly on organic substrates using ACAs have received much attentions due to many advantages such as easier processing, good electrical performance, lower cost, and low temperature processing compatible with organic substrates. ACAs are generally composed of epoxy polymer resin and small amount of conductive fillers (less than 10 wt.%). As a result, ACAs have almost the same CTE values as an epoxy material itself which are higher than conventional underfill materials which contains lots of fillers. Therefore, it is necessary to lower the CTE value of ACAs to obtain more reliable flip chip assembly on organic substrates using ACAs. To modify the ACA composite materials with some amount of conductive fillers, non-conductive fillers were incorporated into ACAs. In this paper, we investigated the effect of fillers on the thermo-mechanical properties of modified ACA composite materials and the reliability of flip chip assembly on organic substrates using modified ACA composite materials. Contact resistance changes were measured during reliability tests such as thermal cycling, high humidity and temperature, and high temperature at dry condition. It was observed that reliability results were significantly affected by CTEs of ACA materials especially at the thermal cycling test. Results showed that flip chip assembly using modified ACA composites with lower CTEs and higher modulus by loading non-conducting fillers exhibited better contact resistance behavior than conventional ACAs without non-conducting fillers. Microwave model and high-frequency measurement of the ACF flip-chip interconnection was investigated using a microwave network analysis. ACF flip chip interconnection has only below 0.1nH, and very stable up to 13 GHz. Over the 13 GHz, there was significant loss because of epoxy capacitance of ACF. However, the addition of $SiO_2filler$ to the ACF lowered the dielectric constant of the ACF materials resulting in an increase of resonance frequency up to 15 GHz. Our results indicate that the electrical performance of ACF combined with electroless Wi/Au bump interconnection is comparable to that of solder joint.